技术领域Technical Field
本发明涉及医疗技术领域，具体涉及压力性损伤的预警方法、装置及计算机设备。The present invention relates to the field of medical technology, and in particular to a method, device and computer equipment for early warning of pressure injuries.
背景技术Background technique
术中压力性损伤，也被称为手术相关性压疮，在手术不良事件中占据了较大的比例，对医疗对象和医疗系统都有显著的负面影响。例如，压力性损伤会影响医疗对象的健康、增加医疗对象和医疗系统的治疗成本和延长医疗对象住院时间等。因此，如何在手术过程中对压力性损伤及时预警，是需要解决的问题。Intraoperative pressure injuries, also known as surgery-related pressure sores, account for a large proportion of surgical adverse events and have significant negative impacts on both medical subjects and the medical system. For example, pressure injuries can affect the health of medical subjects, increase the treatment costs of medical subjects and the medical system, and prolong the hospital stay of medical subjects. Therefore, how to promptly warn of pressure injuries during surgery is a problem that needs to be solved.
目前，通常是定时进行受压部位的检查按摩、轻微变化手术体位或者在受压部位增加软垫等。上述方案存在的问题是，实际手术过程中，医护对象长时间工作或承受巨大的工作压力导致注意力分散，可能忘记定时检查医疗对象的压力部位的皮肤或进行体位调整，从而无法及时预警压力性损伤。At present, it is usually necessary to regularly check and massage the pressure area, slightly change the surgical position, or add cushions to the pressure area. The problem with the above solutions is that during the actual operation, the medical staff work for a long time or are under great work pressure, which leads to distraction. They may forget to regularly check the skin of the medical staff's pressure area or adjust the body position, so that pressure injuries cannot be warned in time.
发明内容Summary of the invention
有鉴于此，本发明提供了一种压力性损伤的预警方法，以解决医护对象因忘记定时对医疗对象的压力部位进行检查，从而导致压力性损伤的问题。In view of this, the present invention provides an early warning method for pressure injury to solve the problem that the medical object forgets to regularly check the pressure parts of the medical object, thereby causing pressure injury.
第一方面，本发明提供了一种压力性损伤的预警方法，该方法包括：In a first aspect, the present invention provides a method for early warning of pressure injury, the method comprising:
对于任一医疗对象，获取医疗对象进行手术所需的多个气室单元；For any medical object, obtaining a plurality of air chamber units required for performing surgery on the medical object;
基于阈值确定模型，确定医疗对象的多组压力预警数据和多组温度预警数据，阈值确定模型基于多个样本医疗对象的所需气室单元的压力数据、温度数据和是否发生压力性损伤的关系训练得到；Based on a threshold determination model, multiple groups of pressure warning data and multiple groups of temperature warning data of the medical object are determined, and the threshold determination model is trained based on the relationship between the pressure data, temperature data and whether pressure injury occurs of the required air chamber unit of multiple sample medical objects;
基于多组压力预警数据和多组温度预警数据，调整多个气室单元，对压力性损伤进行预警。Based on multiple sets of pressure warning data and multiple sets of temperature warning data, multiple air chamber units are adjusted to provide early warning for pressure injuries.
本发明实施例提供的压力性损伤的预警方法，通过基于医疗对象的压力预警数据和温度预警数据，对医疗对象所用的气室单元进行调整，解决了医护对象对医疗对象的人工检查可能不及时，从而导致发生压力性损伤的问题，实现了对压力性损伤的及时预警，保障了医疗对象的健康，同时避免了整体气垫装置的调整，减少了对手术过程的干扰。The pressure injury warning method provided in the embodiment of the present invention adjusts the air chamber unit used for the medical object based on the pressure warning data and temperature warning data of the medical object, thereby solving the problem that the medical staff may not conduct timely manual inspection of the medical object, thereby causing pressure injuries, and achieves timely warning of pressure injuries, ensuring the health of the medical object. At the same time, it avoids the adjustment of the overall air cushion device and reduces interference with the surgical process.
在一种可选的实施方式中，每组压力预警数据包括压力预警阈值和压力时长阈值，每组温度预警数据包括温度预警阈值和温度时长阈值；基于多组压力预警数据和多组温度预警数据，调整多个气室单元，对压力性损伤进行预警，包括：In an optional implementation, each set of pressure warning data includes a pressure warning threshold and a pressure duration threshold, and each set of temperature warning data includes a temperature warning threshold and a temperature duration threshold; based on multiple sets of pressure warning data and multiple sets of temperature warning data, multiple air chamber units are adjusted to warn of pressure damage, including:
对于任一组压力预警数据，确定气室单元在压力预警数据对应的压力预警阈值下的第一持续时长；For any set of pressure warning data, determine a first duration of time that the air chamber unit is below the pressure warning threshold corresponding to the pressure warning data;
对于任一组温度预警数据，确定气室单元在温度预警数据对应的温度预警阈值下的第二持续时长；For any set of temperature warning data, determine a second duration of the air chamber unit being below the temperature warning threshold corresponding to the temperature warning data;
在第一持续时长不小于压力时长阈值的情况下，对气室单元进行放气操作，对压力性损伤进行预警；When the first duration is not less than the pressure duration threshold, the air chamber unit is deflated to issue an early warning for pressure injury;
在第二持续时长不小于温度时长阈值的情况下，对气室单元进行降温操作，对压力性损伤进行预警。When the second duration is not less than the temperature duration threshold, the air chamber unit is cooled down and a warning is issued for pressure damage.
本发明实施例提供的压力性损伤的预警方法，由于医疗对象在压力预警阈值或温度预警阈值下持续保持不动会导致压力性损伤的发生，因此通过确定气室单元在压力预警阈值下的第一持续时长和在温度预警阈值下的第二持续时长，能够基于时长对气室单元进行放气或降温操作，实现了对压力性损伤的有效预警，保障了医疗对象的健康。The early warning method for pressure injury provided in the embodiment of the present invention, since pressure injury may occur if the medical subject remains motionless for a long time at the pressure warning threshold or the temperature warning threshold, by determining the first duration of the air chamber unit at the pressure warning threshold and the second duration of the air chamber unit at the temperature warning threshold, the air chamber unit can be deflated or cooled based on the duration, thereby achieving effective early warning of pressure injury and protecting the health of the medical subject.
在一种可选的实施方式中，该阈值确定模型的训练过程包括：In an optional implementation, the training process of the threshold determination model includes:
获取多个样本医疗对象的体位数据、术前诊断信息和样本医疗结果，样本医疗结果表示样本医疗对象是否发生压力性损伤；Acquiring body position data, preoperative diagnosis information, and sample medical results of a plurality of sample medical subjects, wherein the sample medical results indicate whether pressure injuries occur in the sample medical subjects;
对于任一样本医疗对象，获取样本医疗对象在手术过程中所用的多个气室单元的样本压力数据和样本温度数据；For any sample medical object, obtaining sample pressure data and sample temperature data of a plurality of air chamber units used by the sample medical object during surgery;
对气室单元的样本压力数据进行离散化处理，得到多组样本压力预警数据，样本压力预警数据包括样本压力预警阈值和样本压力时长阈值；Discretize the sample pressure data of the air chamber unit to obtain multiple groups of sample pressure warning data, the sample pressure warning data including a sample pressure warning threshold and a sample pressure duration threshold;
对多个气室单元的样本温度数据进行离散化处理，得到多组样本温度预警数据，样本温度预警数据包括样本温度预警阈值和样本温度时长阈值；Discretize the sample temperature data of multiple air chamber units to obtain multiple groups of sample temperature warning data, the sample temperature warning data including a sample temperature warning threshold and a sample temperature duration threshold;
将样本医疗对象的体位数据、术前诊断信息和样本医疗结果作为输入，多组样本压力预警数据和多组样本温度预警数据作为标签，对阈值确定模型进行训练。The body position data, preoperative diagnosis information and sample medical results of sample medical subjects are used as input, and multiple groups of sample pressure warning data and multiple groups of sample temperature warning data are used as labels to train the threshold determination model.
本发明实施例提供的压力性损伤的预警方法，通过样本医疗对象的体位数据、术前诊断信息、样本压力预警数据和样本温度预警数据，对阈值确定模型进行训练，从而使得训练好的阈值确定模型能够确定不同医疗对象在不同体位下的压力预警数据和温度预警数据，有效避免了压力性损伤的发生。The pressure injury warning method provided in the embodiment of the present invention trains a threshold determination model through the body position data of sample medical subjects, preoperative diagnosis information, sample pressure warning data and sample temperature warning data, so that the trained threshold determination model can determine the pressure warning data and temperature warning data of different medical subjects in different body positions, thereby effectively avoiding the occurrence of pressure injuries.
在一种可选的实施方式中，该方法还包括：In an optional embodiment, the method further includes:
获取医疗对象预设范围内的多帧全景画面和医疗对象的气室压力数据，气室压力数据表示医疗对象在手术过程中使用的气室单元的压力数据；Acquire multiple frames of panoramic images within a preset range of the medical object and air chamber pressure data of the medical object, where the air chamber pressure data represents pressure data of an air chamber unit used by the medical object during surgery;
基于对象检测模型对第一帧全景画面进行识别，分别确定巡回护士对象、手术床和操作电脑，对象检测模型基于多张样本全景画面训练得到，用于识别画面中的对象和物体；The first frame of the panoramic picture is identified based on the object detection model, and the circulating nurse object, the operating table and the operating computer are determined respectively. The object detection model is trained based on multiple sample panoramic pictures and is used to identify the objects and objects in the picture;
基于巡回护士对象、手术床和医疗对象的气室压力数据，对医疗对象的手术过程进行监控。Based on the circulating nurse object, the operating table and the air chamber pressure data of the medical object, the surgical process of the medical object is monitored.
本发明实施例提供的压力性损伤的预警方法，由于巡回护士对象对医疗对象进行的医疗检查，对避免压力性损伤有帮助，因此通过对象检测模型对手术过程中的全景画面进行识别，确定巡回护士对象，从而能够对巡回护士对象和手术过程进行监控，避免了压力性损伤的发生。The early warning method for pressure injuries provided in the embodiment of the present invention is helpful in avoiding pressure injuries because the medical examination of medical objects by the circulating nurse objects is helpful in avoiding pressure injuries. Therefore, the panoramic picture of the surgical process is identified through the object detection model to determine the circulating nurse object, so that the circulating nurse object and the surgical process can be monitored to avoid the occurrence of pressure injuries.
在一种可选的实施方式中，该对象检测模型的训练过程包括：In an optional implementation, the training process of the object detection model includes:
获取多张样本全景画面；Get multiple sample panoramic images;
基于对象检测模型对多张样本全景画面进行识别，分别得到多个样本对象、样本手术床以及样本操作电脑的样本标注位置；Based on the object detection model, multiple sample panoramic images are identified to obtain sample annotation positions of multiple sample objects, sample operating tables, and sample operating computers;
基于多个样本对象、样本手术床以及样本操作电脑的样本标注位置与实际位置之间的差异，对对象检测模型进行训练。The object detection model is trained based on the differences between the sample annotated positions and the actual positions of multiple sample objects, sample operating tables, and sample operating computers.
本发明实施例提供的压力性损伤的预警方法，通过对象检测模型对样本全景画面的识别，能够得到样本对象、样本手术床和样本操作电脑的样本标注位置，从而能够基于样本标注位置和实际位置之间的差异对对象检测模型进行训练，使得对象检测模型能够准确识别出画面中的所有对象和物体，保障了监控巡回护士对象和手术过程的准确度。The early warning method for pressure injuries provided by the embodiment of the present invention can obtain the sample annotated positions of the sample object, sample operating table and sample operating computer through the recognition of the sample panoramic picture by the object detection model, so that the object detection model can be trained based on the difference between the sample annotated position and the actual position, so that the object detection model can accurately identify all objects and objects in the picture, thereby ensuring the accuracy of monitoring the circulating nurse objects and the surgical process.
在一种可选的实施方式中，基于对象检测模型对第一帧全景画面进行识别，分别确定巡回护士对象、手术床和操作电脑，包括：In an optional implementation, the first frame of the panoramic picture is identified based on the object detection model to respectively determine the circulating nurse object, the operating table, and the operating computer, including:
基于对象检测模型对第一帧全景画面进行识别，确定多个第一对象、手术床和操作电脑；Recognize the first panoramic frame based on the object detection model to determine a plurality of first objects, an operating table, and an operating computer;
确定操作电脑的第一中心坐标；Determine the first center coordinates of the operating computer;
分别确定多个第一对象对应的第二中心坐标；respectively determining second center coordinates corresponding to the plurality of first objects;
对于任一第一对象，确定第一对象的第二中心坐标和第一中心坐标之间的距离；For any first object, determining a distance between a second center coordinate and a first center coordinate of the first object;
将多个第一对象对应的距离中最小的距离对应的第一对象，确定为巡回护士对象。The first object corresponding to the smallest distance among the distances corresponding to the multiple first objects is determined as the circulating nurse object.
本发明实施例提供的压力性损伤的预警方法，由于手术过程中存在多个第一对象，因此通过第一对象和操作电脑之间的距离，确定巡回护士对象，保障了确定巡回护士对象的准确度。In the pressure injury early warning method provided by the embodiment of the present invention, since there are multiple first objects during the operation, the circulating nurse object is determined by the distance between the first object and the operating computer, thereby ensuring the accuracy of determining the circulating nurse object.
在一种可选的实施方式中，基于对象检测模型对第一帧全景画面进行识别，分别确定巡回护士对象、手术床和操作电脑之后，该方法还包括：In an optional implementation, after the first frame of the panoramic picture is identified based on the object detection model and the circulating nurse object, the operating table and the operating computer are respectively determined, the method further includes:
基于对象检测模型，对第一帧全景画面的下一帧全景画面进行识别，确定多个第二对象；Based on the object detection model, a next panoramic frame of the first panoramic frame is identified to determine a plurality of second objects;
对巡回护士对象进行特征提取，得到巡回护士对象的第一特征向量；Extract features of the circulating nurse object to obtain a first feature vector of the circulating nurse object;
分别对多个第二对象进行特征提取，得到多个第二对象对应的第二特征向量；Extracting features from the plurality of second objects respectively to obtain second feature vectors corresponding to the plurality of second objects;
对于任一第二特征向量，基于余弦相似度算法，确定第二特征向量与第一特征向量的相似值；For any second eigenvector, determining a similarity value between the second eigenvector and the first eigenvector based on a cosine similarity algorithm;
将相似值最大的第二特征向量对应的第二对象，确定为新的巡回护士对象。The second object corresponding to the second eigenvector with the largest similarity value is determined as a new circulating nurse object.
本发明实施例提供的压力性损伤的预警方法，由于巡回护士对象在手术过程中的位置是会发生移动的，因此通过下一帧全景画面中和巡回护士对象的特征向量最相似的第二对象，作为新的巡回护士对象，能够确保确定巡回护士对象的准确度。In the pressure injury warning method provided by the embodiment of the present invention, since the position of the circulating nurse object will move during the operation, the second object with the most similar feature vector to the circulating nurse object in the next frame of the panoramic picture is used as the new circulating nurse object, thereby ensuring the accuracy of determining the circulating nurse object.
在一种可选的实施方式中，基于巡回护士对象、手术床和医疗对象的气室压力数据，对医疗对象的手术过程进行监控，包括：In an optional embodiment, the surgical process of the medical subject is monitored based on the circulating nurse object, the operating table and the air chamber pressure data of the medical subject, including:
获取手术床的周边坐标，周边坐标包括手术床的左上角坐标、右上角坐标、左下角坐标和右下角坐标；Obtaining the peripheral coordinates of the operating table, the peripheral coordinates including the coordinates of the upper left corner, the upper right corner, the lower left corner, and the lower right corner of the operating table;
在预设时间段内，若巡回护士对象的坐标出现在周边坐标的第一预设范围内，确定巡回护士对象出现在手术床的第二预设范围内；Within a preset time period, if the coordinates of the circulating nurse object appear within a first preset range of the peripheral coordinates, determining that the circulating nurse object appears within a second preset range of the operating table;
在医疗对象的气室压力数据发生波动的情况下，获取气室压力数据的波动值；When the air chamber pressure data of the medical subject fluctuates, obtaining a fluctuation value of the air chamber pressure data;
在巡回护士对象出现在手术床的第二预设范围内，并且波动值大于预设波动阈值的情况下，确定巡回护士对象对医疗对象进行医疗检查，实现对医疗对象的手术过程的监控。When the circulating nurse object appears within the second preset range of the operating table and the fluctuation value is greater than the preset fluctuation threshold, it is determined that the circulating nurse object performs a medical examination on the medical object to monitor the surgical process of the medical object.
本发明实施例提供的压力性损伤的预警方法，通过确定巡回护士对象出现在医疗对象的手术床的周边范围，并且通过医疗对象的气室单元的压力波动，确定巡回护士对象对医疗对象的受压部位进行了检查，基于两方面对巡回护士对象的医疗检查进行监控，有效避免了压力性损伤的发生，保障了医疗对象的健康。The early warning method for pressure injuries provided in the embodiment of the present invention determines that the circulating nurse object appears in the peripheral range of the operating table of the medical object, and determines that the circulating nurse object has inspected the compressed parts of the medical object through the pressure fluctuation of the air chamber unit of the medical object. Based on these two aspects, the medical examination of the circulating nurse object is monitored, thereby effectively avoiding the occurrence of pressure injuries and ensuring the health of the medical object.
第二方面，本发明提供了一种压力性损伤的预警装置，该装置包括：In a second aspect, the present invention provides an early warning device for pressure injury, the device comprising:
获取模块，用于对于任一医疗对象，获取医疗对象进行手术所需的多个气室单元；An acquisition module, used for acquiring, for any medical object, a plurality of air chamber units required for the medical object to undergo surgery;
确定模块，用于基于阈值确定模型，确定医疗对象的多组压力预警数据和多组温度预警数据，阈值确定模型基于多个样本医疗对象的所需气室单元的压力数据、温度数据和是否发生压力性损伤的关系训练得到；A determination module, used to determine multiple groups of pressure warning data and multiple groups of temperature warning data of a medical object based on a threshold determination model, wherein the threshold determination model is trained based on the relationship between pressure data, temperature data and whether pressure injury occurs in a required air chamber unit of multiple sample medical objects;
预警模块，用于基于多组压力预警数据和多组温度预警数据，调整多个气室单元，对压力性损伤进行预警。The early warning module is used to adjust multiple air chamber units based on multiple groups of pressure early warning data and multiple groups of temperature early warning data to warn of pressure damage.
第三方面，本发明提供了一种计算机设备，包括：存储器和处理器，存储器和处理器之间互相通信连接，存储器中存储有计算机指令，处理器通过执行计算机指令，从而执行上述第一方面或其对应的任一实施方式的压力性损伤的预警方法。In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the pressure injury warning method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.
第四方面，本发明提供了一种计算机可读存储介质，该计算机可读存储介质上存储有计算机指令，计算机指令用于使计算机执行上述第一方面或其对应的任一实施方式的压力性损伤的预警方法。In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to cause a computer to execute the pressure injury warning method of the first aspect or any corresponding embodiment thereof.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
为了更清楚地说明本发明具体实施方式或现有技术中的技术方案，下面将对具体实施方式或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图是本发明的一些实施方式，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
图1是根据本发明实施例的压力性损伤的预警方法的流程图；FIG1 is a flow chart of a method for early warning of pressure injury according to an embodiment of the present invention;
图2是根据本发明实施例的另一压力性损伤的预警方法的流程图；FIG2 is a flow chart of another early warning method for pressure injury according to an embodiment of the present invention;
图3是根据本发明实施例的训练阈值确定模型的示意图；FIG3 is a schematic diagram of a training threshold determination model according to an embodiment of the present invention;
图4是根据本发明实施例的应用阈值确定模型的示意图；FIG4 is a schematic diagram of an application threshold determination model according to an embodiment of the present invention;
图5是根据本发明实施例的调整气室单元的流程示意图；FIG5 is a schematic diagram of a process for adjusting an air chamber unit according to an embodiment of the present invention;
图6是根据本发明实施例的样本标注位置的示意图；FIG6 is a schematic diagram of sample annotation positions according to an embodiment of the present invention;
图7是根据本发明实施例的对象检测模型进行对象或物体识别的示意图；7 is a schematic diagram of object or object recognition performed by an object detection model according to an embodiment of the present invention;
图8是根据本发明实施例的持续确定巡回护士对象的流程示意图；8 is a schematic diagram of a process of continuously determining circulating nurse objects according to an embodiment of the present invention;
图9是根据本发明实施例的手术床的周边坐标的示意图；FIG9 is a schematic diagram of peripheral coordinates of an operating table according to an embodiment of the present invention;
图10是根据本发明实施例的监控手术过程的示意图；FIG10 is a schematic diagram of a monitoring surgical procedure according to an embodiment of the present invention;
图11是根据本发明实施例的压力性损伤的预警方法的系统示意图；FIG11 is a system schematic diagram of a method for early warning of pressure injury according to an embodiment of the present invention;
图12是根据本发明实施例的压力性损伤的预警装置的结构框图；FIG12 is a structural block diagram of a warning device for pressure injury according to an embodiment of the present invention;
图13是本发明可选实施例提供的一种计算机设备的结构示意图。FIG. 13 is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention.
具体实施方式Detailed ways
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.
本发明实施例提供了一种压力性损伤的预警方法，解决了医护对象对医疗对象的人工检查可能不及时，从而导致发生压力性损伤的问题，实现了对压力性损伤的及时预警，保障了医疗对象的健康，同时避免了相关技术中对整体气垫装置的调整，减少了对手术过程的干扰。The embodiment of the present invention provides a method for early warning of pressure injuries, which solves the problem that medical staff may not conduct timely manual inspections of medical subjects, thereby causing pressure injuries. It achieves timely early warning of pressure injuries and protects the health of medical subjects. At the same time, it avoids the adjustment of the overall air cushion device in related technologies and reduces interference with the surgical process.
根据本发明实施例，提供了一种压力性损伤的预警方法实施例，需要说明的是，在附图的流程图示出的步骤可以在诸如一组计算机可执行指令的计算机系统中执行，并且，虽然在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤。According to an embodiment of the present invention, an embodiment of a method for early warning of pressure injuries is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.
在本实施例中提供了一种压力性损伤的预警方法，可用于上述的移动终端，如手术室内的操作电脑等，图1是根据本发明实施例的压力性损伤的预警方法的流程图，如图1所示，该流程包括如下步骤：In this embodiment, a method for early warning of pressure injury is provided, which can be used in the above-mentioned mobile terminal, such as an operating computer in an operating room. FIG. 1 is a flow chart of the method for early warning of pressure injury according to an embodiment of the present invention. As shown in FIG. 1 , the process includes the following steps:
步骤S101，对于任一医疗对象，获取医疗对象进行手术所需的多个气室单元。具体地，医疗对象进行手术时，会使用气体交换装置以预防压力性损伤，该气体交换装置有多个气室单元。但不同医疗对象的身高、体重等基础数据不同，手术类型和所对应的手术体位也是不同的，因此不同的医疗对象手术时所需的气室单元是不同的。需要说明的是，气室单元可由医护对象基于经验配置，也可从体位数据库中获取，或其他可以确定医疗对象所需气室单元的方法，本发明实施例对此不进行限制。其中，该体位数据库中存有多个体位对应的气室单元。可选的，以医疗对象的手术类型为胆囊切除术，手术体位为仰卧位为例，通过上述任一方法确定该医疗对象所需的气室单元，下表1为该医疗对象的气室单元配置数据。Step S101, for any medical object, obtain multiple air chamber units required for the medical object to perform surgery. Specifically, when the medical object undergoes surgery, a gas exchange device will be used to prevent pressure injuries, and the gas exchange device has multiple air chamber units. However, the basic data such as height and weight of different medical objects are different, and the type of surgery and the corresponding surgical position are also different. Therefore, the air chamber units required for different medical objects during surgery are different. It should be noted that the air chamber unit can be configured by the medical object based on experience, or it can be obtained from a body position database, or other methods that can determine the air chamber unit required by the medical object are not limited to this embodiment of the present invention. Among them, the body position database contains multiple air chamber units corresponding to body positions. Optionally, taking the medical object's surgical type as cholecystectomy and the surgical position as supine as an example, the air chamber unit required by the medical object is determined by any of the above methods, and the following Table 1 is the air chamber unit configuration data of the medical object.
表1医疗对象的气室单元配置数据示例Table 1 Example of air chamber unit configuration data for medical objects
其中，该气体交换装置中所有气室单元按照从上到下，从左到右的顺序进行编号，通过上述任一方法均可得到如表1所示的气室单元配置数据，然后基于该配置数据，启动需要工作的气室单元。需要说明的是，该气室单元还可通过其他方式进行编号，本发明实施例对此不进行限制。通过获取医疗对象所需的气室单元，避免了非压力点位气室单元无效工作，减少了对手术过程的影响。Among them, all the air chamber units in the gas exchange device are numbered in order from top to bottom and from left to right. The air chamber unit configuration data shown in Table 1 can be obtained by any of the above methods, and then the air chamber unit that needs to work is started based on the configuration data. It should be noted that the air chamber unit can also be numbered in other ways, and the embodiment of the present invention does not limit this. By obtaining the air chamber unit required by the medical object, the ineffective operation of the air chamber unit at the non-pressure point is avoided, and the impact on the surgical process is reduced.
步骤S102，基于阈值确定模型，确定医疗对象的多组压力预警数据和多组温度预警数据，阈值确定模型基于多个样本医疗对象的所需气室单元的压力数据、温度数据和是否发生压力性损伤的关系训练得到。具体地，不同医疗对象对压力性损伤的敏感程度不一样，因此，不同的医疗对象的压力预警数据和温度预警数据是不同的。同时，医疗对象在不同压力下保持不动直至发生压力性损伤的时长是不同的，在不同温度下保持不动直至发生压力性损伤的时长也是不同的。因此，通过阈值确定模型确定医疗对象的压力预警数据和温度预警数据，使得能够对发生压力性损伤的情况数据化，从而有效预警压力性损伤。Step S102, based on the threshold determination model, multiple groups of pressure warning data and multiple groups of temperature warning data of the medical object are determined. The threshold determination model is trained based on the relationship between the pressure data, temperature data and whether pressure injury occurs of the required air chamber unit of multiple sample medical objects. Specifically, different medical objects have different sensitivities to pressure injury. Therefore, the pressure warning data and temperature warning data of different medical objects are different. At the same time, the length of time that the medical object remains motionless under different pressures until the pressure injury occurs is different, and the length of time that the medical object remains motionless under different temperatures until the pressure injury occurs is also different. Therefore, the pressure warning data and temperature warning data of the medical object are determined by the threshold determination model, so that the situation of pressure injury can be digitized, thereby effectively warning of pressure injury.
步骤S103，基于多组压力预警数据和多组温度预警数据，调整多个气室单元，对压力性损伤进行预警。具体地，对于任一气室单元，在该气室单元满足压力预警数据或温度预警数据的触发条件时，对该气室单元进行调整，以避免医疗对象发生压力性损伤。需要说明的是，医疗对象仅使用气体交换装置的部分气室单元，并且不同气室单元的压力和温度是不同的，因此只对满足压力预警数据或温度预警数据的触发条件的气室单元进行调整。通过对气室单元进行自动调整，解决了医护对象的人工检查不及时导致发生压力性损伤的问题，实现了对压力性损伤的及时预警，保障了医疗对象的健康，同时避免了对全部气室单元进行调整，减少了对手术过程的干扰。Step S103, based on multiple sets of pressure warning data and multiple sets of temperature warning data, multiple air chamber units are adjusted to warn of pressure injuries. Specifically, for any air chamber unit, when the air chamber unit meets the triggering conditions of the pressure warning data or the temperature warning data, the air chamber unit is adjusted to avoid pressure injuries to the medical subject. It should be noted that the medical subject only uses part of the air chamber units of the gas exchange device, and the pressures and temperatures of different air chamber units are different. Therefore, only the air chamber units that meet the triggering conditions of the pressure warning data or the temperature warning data are adjusted. By automatically adjusting the air chamber units, the problem of pressure injuries caused by untimely manual inspection of medical subjects is solved, timely warning of pressure injuries is achieved, and the health of the medical subjects is protected. At the same time, the adjustment of all air chamber units is avoided, reducing interference with the surgical process.
本发明实施例提供了一种压力性损伤的预警方法，通过基于医疗对象的压力预警数据和温度预警数据，对医疗对象所用的气室单元进行调整，解决了医护对象对医疗对象的人工检查可能不及时，从而导致发生压力性损伤的问题，实现了对压力性损伤的及时预警，保障了医疗对象的健康，同时避免了整体气垫装置的调整，减少了对手术过程的干扰。An embodiment of the present invention provides a method for early warning of pressure injuries. By adjusting the air chamber unit used for the medical object based on the pressure warning data and temperature warning data of the medical object, the problem of pressure injuries caused by the medical staff's untimely manual inspection of the medical object is solved. Timely early warning of pressure injuries is achieved, the health of the medical object is protected, and the adjustment of the overall air cushion device is avoided, reducing interference with the surgical process.
在本实施例中提供了一种压力性损伤的预警方法，可用于上述的移动终端，如手术室内的操作电脑等，图2是根据本发明实施例的另一压力性损伤的预警方法的流程图，如图2所示，包括如下步骤：In this embodiment, a method for early warning of pressure injury is provided, which can be used in the above-mentioned mobile terminal, such as an operating computer in an operating room. FIG. 2 is a flow chart of another method for early warning of pressure injury according to an embodiment of the present invention. As shown in FIG. 2 , the method comprises the following steps:
步骤S201，对于任一医疗对象，获取医疗对象进行手术所需的多个气室单元。详细请参见图1所示实施例的步骤S101，在此不再赘述。Step S201: for any medical object, a plurality of air chamber units required for the medical object to undergo surgery are obtained. For details, please refer to step S101 of the embodiment shown in FIG1 , which will not be described in detail here.
步骤S202，基于阈值确定模型，确定医疗对象的多组压力预警数据和多组温度预警数据，阈值确定模型基于多个样本医疗对象的所需气室单元的压力数据、温度数据和是否发生压力性损伤的关系训练得到。详细请参见图1所示实施例的步骤S102，在此不再赘述。Step S202, based on the threshold determination model, multiple groups of pressure warning data and multiple groups of temperature warning data of the medical object are determined, and the threshold determination model is trained based on the relationship between the pressure data, temperature data and whether pressure injury occurs of the required air chamber unit of multiple sample medical objects. For details, please refer to step S102 of the embodiment shown in Figure 1, which will not be repeated here.
在一些可选的实施方式中，该阈值确定模型的训练过程包括以下步骤：In some optional implementations, the training process of the threshold determination model includes the following steps:
步骤a1，获取多个样本医疗对象的体位数据、术前诊断信息和样本医疗结果，样本医疗结果表示样本医疗对象是否发生压力性损伤。具体地，用于训练阈值确定模型的任一样本医疗对象的体位数据和术前诊断信息如下表2所示：Step a1, obtaining the body position data, preoperative diagnosis information and sample medical results of multiple sample medical subjects, where the sample medical results indicate whether the sample medical subjects have pressure injuries. Specifically, the body position data and preoperative diagnosis information of any sample medical subject used to train the threshold determination model are shown in Table 2 below:
表2样本医疗对象的体位数据和术前诊断信息示例Table 2 Examples of body position data and preoperative diagnosis information of sample medical subjects
其中，该样本医疗对象id与样本医疗对象一一对应，用于唯一标识样本医疗对象。由于不同医疗对象的体位数据、术前诊断信息和对压力性损伤的敏感度不一样，所以可以基于多个样本医疗对象和多方面数据对阈值确定模型进行训练，提高模型预测准确度。The sample medical object ID corresponds to the sample medical object one by one and is used to uniquely identify the sample medical object. Since different medical objects have different body position data, preoperative diagnostic information and sensitivity to pressure injuries, the threshold determination model can be trained based on multiple sample medical objects and multi-faceted data to improve the prediction accuracy of the model.
在一些可选的实施方式中，可以通过不良事件系统获取样本医疗对象的样本医疗结果，该不良事件系统为医院内部用于记录不良事件的系统，还可基于其他方法得到样本医疗结果，本发明实施例对此不进行限制。以样本医疗对象id为100000922为例，该样本医疗对象的样本医疗结果如下表3所示：In some optional implementations, the sample medical results of the sample medical subject can be obtained through an adverse event system, which is a system used to record adverse events within the hospital. The sample medical results can also be obtained based on other methods, which are not limited by the embodiments of the present invention. Taking the sample medical subject id as 100000922 as an example, the sample medical results of the sample medical subject are shown in Table 3 below:
表3样本医疗对象的样本医疗结果示例Table 3 Examples of sample medical outcomes for sample medical subjects
步骤a2，对于任一样本医疗对象，获取样本医疗对象在手术过程中所用的多个气室单元的样本压力数据和样本温度数据。可选的，基于气体交换装置中不同位置的压力传感器和温度传感器，对样本医疗对象的样本压力数据和样本温度数据进行采集。需要说明的是，为了减少对气体交换装置的外观的影响，本发明采用蓝牙无线方式进行数据传输并实时存入数据库中，还可采用其他方式获取数据，本发明实施例对此不进行限制。下表4为以编号为1的气室单元为例，获取样本压力数据和样本温度数据的数据结构。Step a2, for any sample medical object, obtain the sample pressure data and sample temperature data of multiple air chamber units used by the sample medical object during the operation. Optionally, based on the pressure sensors and temperature sensors at different positions in the gas exchange device, the sample pressure data and sample temperature data of the sample medical object are collected. It should be noted that in order to reduce the impact on the appearance of the gas exchange device, the present invention uses Bluetooth wireless method to transmit data and store it in real time in the database, and other methods can also be used to obtain data, which is not limited by the embodiments of the present invention. Table 4 below is a data structure for obtaining sample pressure data and sample temperature data, taking the air chamber unit numbered 1 as an example.
表4样本压力数据和样本温度数据的数据结构示例Table 4 Data structure examples of sample pressure data and sample temperature data
其中，以一分钟采集一次为例对样本压力数据和样本温度数据进行采集，还可三十秒采集一次、两分钟采集一次或三分钟采集一次，本发明实施例对此不进行限制。基于上表4所示的数据结构，得到如下表5所示的连续采集的分钟级数据示例。The sample pressure data and sample temperature data are collected once a minute as an example, and can also be collected once every thirty seconds, once every two minutes, or once every three minutes, which is not limited in the embodiment of the present invention. Based on the data structure shown in Table 4 above, an example of continuously collected minute-level data is obtained as shown in Table 5 below.
表5样本压力数据和样本温度数据的示例Table 5 Examples of sample pressure data and sample temperature data
步骤a3，对气室单元的样本压力数据进行离散化处理，得到多组样本压力预警数据，样本压力预警数据包括样本压力预警阈值和样本压力时长阈值。具体地，基于专家经验可知，当医疗对象的皮肤压力大于等于32mmHg时发生压力性损伤的概率较大，但对持续时长并无判断。因此，通过对样本压力数据进行离散化处理，按照气室单元编号进行分组，将压力值超过32mmHg的连续时长进行统计，能够得到多组样本压力预警阈值和与其对应的样本压力时长阈值。其中，皮肤压力32mmHg仅为参考临界压力值，还可根据其他方法对发生压力性损伤的临界压力值进行确定或指定其他任意参考临界压力值，本发明实施例对此不进行限制。Step a3, discretize the sample pressure data of the air chamber unit to obtain multiple groups of sample pressure warning data, and the sample pressure warning data include a sample pressure warning threshold and a sample pressure duration threshold. Specifically, based on expert experience, it is known that when the skin pressure of the medical subject is greater than or equal to 32 mmHg, the probability of pressure injury is relatively high, but there is no judgment on the duration. Therefore, by discretizing the sample pressure data, grouping them according to the air chamber unit number, and counting the continuous duration of the pressure value exceeding 32 mmHg, it is possible to obtain multiple groups of sample pressure warning thresholds and the corresponding sample pressure duration thresholds. Among them, the skin pressure of 32 mmHg is only a reference critical pressure value, and the critical pressure value for pressure injury can be determined or other arbitrary reference critical pressure values can be specified according to other methods, and the embodiments of the present invention are not limited to this.
步骤a4，对多个气室单元的样本温度数据进行离散化处理，得到多组样本温度预警数据，样本温度预警数据包括样本温度预警阈值和样本温度时长阈值。具体地，基于专家经验可知，当医疗对象的皮肤温度大于等于38摄氏度时发生压力性损伤的概率较大，但对持续时长并无判断。因此，通过对样本温度数据进行离散化处理，按照气室单元编号进行分组，将温度值超过38摄氏度的连续时长进行统计，能够得到多组样本温度预警阈值和与其对应的样本温度时长阈值。其中，皮肤温度38摄氏度仅为参考临界温度值，还可根据其他方法对发生压力性损伤的临界温度值进行确定或指定其他任意参考临界温度值，本发明实施例对此不进行限制。可选的，以编号为1的气室单元，样本医疗对象id为100000922为例，通过步骤a3和步骤a4得到的样本压力预警数据和样本温度预警数据如下表6所示：Step a4, discretize the sample temperature data of multiple air chamber units to obtain multiple groups of sample temperature warning data, the sample temperature warning data including sample temperature warning thresholds and sample temperature duration thresholds. Specifically, based on expert experience, it is known that when the skin temperature of the medical object is greater than or equal to 38 degrees Celsius, the probability of pressure injury is high, but there is no judgment on the duration. Therefore, by discretizing the sample temperature data, grouping them according to the air chamber unit number, and counting the continuous duration of the temperature value exceeding 38 degrees Celsius, multiple groups of sample temperature warning thresholds and corresponding sample temperature duration thresholds can be obtained. Among them, the skin temperature of 38 degrees Celsius is only a reference critical temperature value, and the critical temperature value for the occurrence of pressure injury can also be determined or other arbitrary reference critical temperature values can be specified according to other methods, and the embodiment of the present invention does not limit this. Optionally, taking the air chamber unit numbered 1 and the sample medical object id 100000922 as an example, the sample pressure warning data and sample temperature warning data obtained by steps a3 and a4 are shown in Table 6 below:
表6样本压力预警数据和样本温度预警数据示例Table 6 Examples of sample pressure warning data and sample temperature warning data
步骤a5，将样本医疗对象的体位数据、术前诊断信息和样本医疗结果作为输入，多组样本压力预警数据和多组样本温度预警数据作为标签，对阈值确定模型进行训练。具体地，本发明实施例以随机森林算法为例，对阈值确定模型进行训练。将样本医疗对象的体位数据、术前诊断信息和样本医疗结果作为随机森林算法的输入特征数据，将多组样本压力预警数据和多组样本温度预警数据作为随机森林算法的标签数据。其中，该标签数据用于指导阈值确定模型应该输出的预测结果，在本发明中该预测结果为样本压力预警数据和样本温度预警数据。图3是根据本发明实施例的训练阈值确定模型的示意图，如图3所示，样本医疗对象的体位数据包括身高信息、体重信息、性别信息、年龄信息、民族信息；该样本医疗结果指示是否发生压力性损伤；右侧标签数据以上述表6为例。基于随机森林算法进行模型拟合，对阈值确定模型进行训练，模型训练完成后形成一个模型文件。Step a5, taking the body position data, preoperative diagnosis information and sample medical results of the sample medical object as input, and multiple groups of sample pressure warning data and multiple groups of sample temperature warning data as labels, the threshold determination model is trained. Specifically, the embodiment of the present invention takes the random forest algorithm as an example to train the threshold determination model. The body position data, preoperative diagnosis information and sample medical results of the sample medical object are used as input feature data of the random forest algorithm, and multiple groups of sample pressure warning data and multiple groups of sample temperature warning data are used as label data of the random forest algorithm. Among them, the label data is used to guide the prediction result that the threshold determination model should output. In the present invention, the prediction result is the sample pressure warning data and the sample temperature warning data. Figure 3 is a schematic diagram of the training threshold determination model according to an embodiment of the present invention. As shown in Figure 3, the body position data of the sample medical object includes height information, weight information, gender information, age information, and ethnic information; the sample medical result indicates whether pressure injury occurs; the label data on the right side takes the above Table 6 as an example. Model fitting is performed based on the random forest algorithm, and the threshold determination model is trained. After the model training is completed, a model file is formed.
在一些可选的实施方式中，图4是根据本发明实施例的应用阈值确定模型的示意图，如图4所示，对于任一医疗对象，将该医疗对象的体位数据、术前诊断信息、医疗结果和阈值确定模型的模型文件作为随机森林算法的输入，得到压力预警数据和温度预警数据，图4中以上述表6中提供的字段为例。其中，该医疗结果默认为发生了压力性损伤，从而基于该阈值确定模型确定发生压力性损伤时的压力预警数据和温度预警数据。In some optional implementations, FIG4 is a schematic diagram of an application threshold determination model according to an embodiment of the present invention. As shown in FIG4, for any medical object, the body position data, preoperative diagnosis information, medical results and model file of the threshold determination model of the medical object are used as inputs of the random forest algorithm to obtain pressure warning data and temperature warning data. FIG4 takes the fields provided in the above Table 6 as an example. Among them, the medical result defaults to the occurrence of pressure injury, so the pressure warning data and temperature warning data when the pressure injury occurs are determined based on the threshold determination model.
步骤S203，基于多组压力预警数据和多组温度预警数据，调整多个气室单元，对压力性损伤进行预警。Step S203, based on the multiple sets of pressure warning data and the multiple sets of temperature warning data, multiple air chamber units are adjusted to issue a warning for pressure damage.
具体地，上述步骤S203包括：Specifically, the above step S203 includes:
步骤S2031，对于任一组压力预警数据，确定气室单元在压力预警数据对应的压力预警阈值下的第一持续时长。具体地，任一医疗对象对应多组压力预警数据，该压力预警数据包括多个压力预警阈值和与其对应的压力时长阈值。对于任一气室单元，确定该气室单元在任一压力预警阈值下的第一持续时长，从而能够根据在该压力预警阈值下的持续时间判断是否触发预警条件，使得能够有效预警压力性损伤。Step S2031, for any set of pressure warning data, determine the first duration of the air chamber unit under the pressure warning threshold corresponding to the pressure warning data. Specifically, any medical object corresponds to multiple sets of pressure warning data, and the pressure warning data includes multiple pressure warning thresholds and pressure duration thresholds corresponding thereto. For any air chamber unit, determine the first duration of the air chamber unit under any pressure warning threshold, so that it is possible to determine whether the warning condition is triggered according to the duration under the pressure warning threshold, so that pressure injury can be effectively warned.
步骤S2032，对于任一组温度预警数据，确定气室单元在温度预警数据对应的温度预警阈值下的第二持续时长。具体地，任一医疗对象对应多组温度预警数据，该温度预警数据包括多个温度预警阈值和与其对应的温度时长阈值。对于任一气室单元，确定该气室单元在任一温度预警阈值下的第二持续时长，从而能够根据在该温度预警阈值下的持续时间判断是否触发预警条件，使得能够有效预警压力性损伤。Step S2032, for any set of temperature warning data, determine the second duration of the air chamber unit under the temperature warning threshold corresponding to the temperature warning data. Specifically, any medical object corresponds to multiple sets of temperature warning data, and the temperature warning data includes multiple temperature warning thresholds and temperature duration thresholds corresponding thereto. For any air chamber unit, determine the second duration of the air chamber unit under any temperature warning threshold, so that it is possible to determine whether the warning condition is triggered according to the duration under the temperature warning threshold, so that pressure injury can be effectively warned.
步骤S2033，在第一持续时长不小于压力时长阈值的情况下，对气室单元进行放气操作，对压力性损伤进行预警。具体地，对于任一气室单元，向该气室单元配置多组压力预警数据、多组温度预警数据、压力期望值和温度期望值。当第一持续时长不小于压力时长阈值时，医疗对象的皮肤压力值较大，进而发生压力性损伤的概率较大。因此，第一持续时长不小于压力时长阈值的气室单元进行自动化放气直至此时压力值达到压力期望值，同时会语音播报警告信息，该警告信息用于提示医护人员对医疗对象的受压部位进行医疗检查。可选的，为了预留缓冲时间以保障医疗对象的健康，可以在第一持续时长不小于压力时长阈值减去一个单位粒度的情况下，执行上述调整。其中，该单位粒度可以为1分钟、5分钟或10分钟，本发明实施例对此不进行限制。通过对满足压力预警条件的气室单元进行自动化放气，解决了由于医护对象没有及时进行医疗检查从而导致医疗对象压力性损伤的问题，有效避免了压力性损伤的发生，保障了医疗对象的健康。Step S2033, when the first duration is not less than the pressure duration threshold, the air chamber unit is deflated to warn of pressure injury. Specifically, for any air chamber unit, multiple groups of pressure warning data, multiple groups of temperature warning data, pressure expectation values and temperature expectation values are configured for the air chamber unit. When the first duration is not less than the pressure duration threshold, the skin pressure value of the medical object is large, and the probability of pressure injury is high. Therefore, the air chamber unit whose first duration is not less than the pressure duration threshold is automatically deflated until the pressure value reaches the pressure expectation value at this time, and a voice broadcast warning message is broadcast at the same time, which is used to prompt medical staff to perform medical examinations on the compressed parts of the medical object. Optionally, in order to reserve buffer time to protect the health of the medical object, the above adjustment can be performed when the first duration is not less than the pressure duration threshold minus a unit granularity. Among them, the unit granularity can be 1 minute, 5 minutes or 10 minutes, and the embodiment of the present invention does not limit this. By automatically deflating the air chamber units that meet the pressure warning conditions, the problem of pressure injuries to medical subjects due to the medical subjects not undergoing timely medical examinations is solved, effectively avoiding the occurrence of pressure injuries and ensuring the health of the medical subjects.
步骤S2034，在第二持续时长不小于温度时长阈值的情况下，对气室单元进行降温操作，对压力性损伤进行预警。具体地，对于任一气室单元，向该气室单元配置多组压力预警数据、多组温度预警数据、压力期望值和温度期望值。当第二持续时长不小于温度时长阈值时，医疗对象的皮肤温度值较高，进而发生压力性损伤的概率较大。因此，第二持续时长不小于温度时长阈值的气室单元进行自动化降温直至此时温度值达到温度期望值，同时会语音播报警告信息。可选的，为了预留缓冲时间以保障医疗对象的健康，可以在第二持续时长不小于温度时长阈值减去一个单位粒度的情况下，执行上述调整操作。通过对满足温度预警条件的气室单元进行自动化降温，解决了由于医护对象没有及时进行医疗检查从而导致医疗对象压力性损伤的问题，有效避免了压力性损伤的发生，保障了医疗对象的健康。Step S2034, when the second duration is not less than the temperature duration threshold, the air chamber unit is cooled down to warn of pressure injury. Specifically, for any air chamber unit, multiple sets of pressure warning data, multiple sets of temperature warning data, pressure expected values and temperature expected values are configured for the air chamber unit. When the second duration is not less than the temperature duration threshold, the skin temperature value of the medical object is high, and the probability of pressure injury is high. Therefore, the air chamber unit whose second duration is not less than the temperature duration threshold is automatically cooled down until the temperature value reaches the temperature expected value at this time, and a warning message is broadcast by voice at the same time. Optionally, in order to reserve buffer time to protect the health of the medical object, the above adjustment operation can be performed when the second duration is not less than the temperature duration threshold minus one unit granularity. By automatically cooling down the air chamber unit that meets the temperature warning condition, the problem of pressure injury of the medical object caused by the medical object not undergoing medical examination in time is solved, the occurrence of pressure injury is effectively avoided, and the health of the medical object is protected.
在一些可选的实施方式中，以单位粒度为10分钟，压力期望值为30mmHg，温度期望值为36摄氏度和上述表5中提供的字段为例，对配置给气室单元的数据结构进行说明，如下表7所示：In some optional implementations, taking the unit granularity as 10 minutes, the expected pressure value as 30 mmHg, the expected temperature value as 36 degrees Celsius and the fields provided in the above Table 5 as an example, the data structure configured for the air chamber unit is described as shown in the following Table 7:
表7气室单元配置数据结构示例Table 7 Example of gas cell unit configuration data structure
需要说明的是，若在手术过程中，医疗对象所使用的所有气室单元，在预设时间内没有进行放气或降温操作，也即所有气室单元的在任一压力预警阈值下的第一持续时长均小于压力时长阈值并且在任一温度预警阈值下的第二持续时长均小于温度时长阈值，此时触发定时提醒机制，用于自动语音播报警告信息，提醒医护对象对医疗对象进行医疗检查。其中，该预设时间可以为1小时、2小时或3小时等，本发明实施例对此不进行限制。若在手术过程中，医疗对象所使用的任一气室单元，在预设时间内进行了放气或者降温操作，则认为对医疗对象进行过压力性损伤的缓解措施，此时重新开始计时。通过在压力和温度预警的基础上，设置定时提醒机制，降低了发生压力性损伤的概率，保障了医疗对象的健康。It should be noted that if during the operation, all the air chamber units used by the medical subject have not been deflated or cooled within the preset time, that is, the first duration of all the air chamber units under any pressure warning threshold is less than the pressure duration threshold and the second duration under any temperature warning threshold is less than the temperature duration threshold, then the timing reminder mechanism is triggered, which is used to automatically broadcast the warning information by voice to remind the medical subject to perform a medical examination on the medical subject. Among them, the preset time can be 1 hour, 2 hours or 3 hours, etc., and the embodiment of the present invention is not limited to this. If during the operation, any of the air chamber units used by the medical subject has been deflated or cooled within the preset time, it is considered that the medical subject has been subjected to mitigation measures for pressure injuries, and the timing is restarted at this time. By setting a timing reminder mechanism based on pressure and temperature warnings, the probability of pressure injuries is reduced and the health of the medical subject is guaranteed.
在一些可选的实施方式中，图5是根据本发明实施例的调整气室单元的流程示意图，如图5所示，对于任一医疗对象，通过上述步骤S202得到该医疗对象的多组压力预警阈值和与其对应的压力时长阈值，多组温度预警阈值和与其对应的温度时长阈值。然后，对于该医疗对象所使用的所有气室单元，将其按照压力类型和温度类型进行分组，如下表8所示。然后，以编号为1的气室单元为例，该气室单元的数据类型为压力类型，向该气室单元传递多组压力预警阈值和对应的压力时长阈值。对于任一压力预警阈值，在该气室单元在该压力预警阈值下的第一持续时长不小于压力时长阈值的情况下，向该气室单元传递压力期望值，并调整该气室单元进行放气，直至压力值达到压力期望值。同时，该气室单元的数据类型为温度类型时，向该气室单元传递多组温度预警阈值和对应的温度时长阈值。对于任一温度预警阈值，在该气室单元在该温度预警阈值下的第二持续时长不小于温度时长阈值的情况下，向该气室单元传递温度期望值，并调整该气室单元进行降温，直至温度值达到温度期望值。其中，任一气室单元的类型属于压力类型或温度类型中的至少一种。In some optional embodiments, FIG. 5 is a flow chart of adjusting the air chamber unit according to an embodiment of the present invention. As shown in FIG. 5, for any medical object, multiple groups of pressure warning thresholds and corresponding pressure duration thresholds, multiple groups of temperature warning thresholds and corresponding temperature duration thresholds of the medical object are obtained through the above step S202. Then, for all the air chamber units used by the medical object, they are grouped according to the pressure type and temperature type, as shown in Table 8 below. Then, taking the air chamber unit numbered 1 as an example, the data type of the air chamber unit is the pressure type, and multiple groups of pressure warning thresholds and corresponding pressure duration thresholds are transmitted to the air chamber unit. For any pressure warning threshold, when the first continuous duration of the air chamber unit under the pressure warning threshold is not less than the pressure duration threshold, the pressure expected value is transmitted to the air chamber unit, and the air chamber unit is adjusted to deflate until the pressure value reaches the pressure expected value. At the same time, when the data type of the air chamber unit is the temperature type, multiple groups of temperature warning thresholds and corresponding temperature duration thresholds are transmitted to the air chamber unit. For any temperature warning threshold, when the second duration of the air chamber unit under the temperature warning threshold is not less than the temperature duration threshold, the temperature expectation value is transmitted to the air chamber unit, and the air chamber unit is adjusted to cool down until the temperature value reaches the temperature expectation value. Wherein, the type of any air chamber unit is at least one of a pressure type and a temperature type.
表8气室单元按照类型的分组示例Table 8 Grouping examples of air chamber units by type
本发明实施例提供的压力性损伤的预警方法，通过基于医疗对象的压力预警数据和温度预警数据，对医疗对象所用的气室单元进行调整，解决了医护对象对医疗对象的人工检查可能不及时，从而导致发生压力性损伤的问题，实现了对压力性损伤的及时预警，保障了医疗对象的健康，同时避免了整体气垫装置的调整，减少了对手术过程的干扰。The pressure injury warning method provided in the embodiment of the present invention adjusts the air chamber unit used for the medical object based on the pressure warning data and temperature warning data of the medical object, thereby solving the problem that the medical staff may not conduct timely manual inspection of the medical object, thereby causing pressure injuries, and achieves timely warning of pressure injuries, ensuring the health of the medical object. At the same time, it avoids the adjustment of the overall air cushion device and reduces interference with the surgical process.
在本实施例中提供了一种压力性损伤的预警方法，可用于上述的移动终端，如手术室内的操作电脑等，还可以通过以下步骤对压力性损伤进行预警：In this embodiment, a method for early warning of pressure injury is provided, which can be used in the above-mentioned mobile terminal, such as an operating computer in an operating room, etc., and early warning of pressure injury can also be performed through the following steps:
步骤S301，对于任一医疗对象，获取医疗对象进行手术所需的多个气室单元。详细请参见图1所示实施例的步骤S101，在此不再赘述。Step S301: for any medical object, a plurality of air chamber units required for the medical object to undergo surgery are obtained. Please refer to step S101 of the embodiment shown in FIG1 for details, which will not be described in detail here.
步骤S302，基于阈值确定模型，确定医疗对象的多组压力预警数据和多组温度预警数据，阈值确定模型基于多个样本医疗对象的所需气室单元的压力数据、温度数据和是否发生压力性损伤的关系训练得到。详细请参见图1所示实施例的步骤S102，在此不再赘述。Step S302, based on the threshold determination model, multiple groups of pressure warning data and multiple groups of temperature warning data of the medical object are determined, and the threshold determination model is trained based on the relationship between the pressure data, temperature data and whether pressure injury occurs of the required air chamber unit of multiple sample medical objects. For details, please refer to step S102 of the embodiment shown in Figure 1, which will not be repeated here.
步骤S303，基于多组压力预警数据和多组温度预警数据，调整多个气室单元，对压力性损伤进行预警。详细请参见图2所示实施例的步骤S203，在此不再赘述。Step S303, based on the multiple groups of pressure warning data and the multiple groups of temperature warning data, multiple air chamber units are adjusted to warn of pressure damage. For details, please refer to step S203 of the embodiment shown in FIG2 , which will not be described in detail here.
步骤S304，获取医疗对象预设范围内的多帧全景画面和医疗对象的气室压力数据，气室压力数据表示医疗对象在手术过程中使用的气室单元的压力数据。具体地，步骤S201至步骤S203通过气垫交换装置的自动化放气或降温，降低压力性损伤的风险。但在手术过程中，巡回护士对象需要按照一定周期对医疗对象的受压部位进行检测，及时进行干预。但巡回护士对象工作繁忙，可能会出现遗忘或执行不到位的情况，导致压力性损伤的发生，上述步骤S2033和步骤S2034通过语音播报对巡回护士对象进行提醒，但无法确定巡回护士对象是否对医疗对象进行了检测动作。因此，手术开始时通过手术室内的全景摄像头，持续采集手术室的多帧全景画面，并且获取医疗对象的气室压力数据，从而对巡回护士对象是否进行有效的医疗检查进行监控。其中，该多帧全景画面可以在手术进行的各个阶段中采集，数量可以为50张、100张或150张等，本发明实施例对此不进行限制。Step S304, obtain multiple frames of panoramic images within the preset range of the medical object and the air chamber pressure data of the medical object, the air chamber pressure data represents the pressure data of the air chamber unit used by the medical object during the operation. Specifically, steps S201 to S203 reduce the risk of pressure injury by automatically deflation or cooling of the air cushion exchange device. However, during the operation, the circulating nurse object needs to detect the compressed parts of the medical object according to a certain period and intervene in time. However, the circulating nurse object is busy at work and may forget or fail to perform in place, resulting in the occurrence of pressure injury. The above steps S2033 and S2034 remind the circulating nurse object through voice broadcast, but it is impossible to determine whether the circulating nurse object has performed a detection action on the medical object. Therefore, at the beginning of the operation, the panoramic camera in the operating room continuously collects multiple frames of panoramic images of the operating room, and obtains the air chamber pressure data of the medical object, so as to monitor whether the circulating nurse object performs an effective medical examination. Among them, the multiple frames of panoramic images can be collected at various stages of the operation, and the number can be 50, 100 or 150, etc., which is not limited in the embodiment of the present invention.
步骤S305，基于对象检测模型对第一帧全景画面进行识别，分别确定巡回护士对象、手术床和操作电脑，对象检测模型基于多张样本全景画面训练得到，用于识别画面中的对象和物体。具体地，由于手术进行过程中，巡回护士对象需要定时对医疗对象的受压部位进行医疗检查，以避免压力性损伤的发生。通过对象检测模型能够准确识别巡回护士对象，从而实现对巡回护士对象的监控。Step S305, based on the object detection model, the first frame of the panoramic picture is identified, and the circulating nurse object, the operating table and the operating computer are determined respectively. The object detection model is trained based on multiple sample panoramic pictures and is used to identify objects and objects in the picture. Specifically, during the operation, the circulating nurse object needs to regularly perform medical examinations on the compressed parts of the medical object to avoid the occurrence of pressure injuries. The circulating nurse object can be accurately identified through the object detection model, thereby realizing the monitoring of the circulating nurse object.
步骤S306，基于巡回护士对象、手术床和医疗对象的气室压力数据，对医疗对象的手术过程进行监控。具体地，通过该气室压力数据能够反映医疗对象所用的气室单元的当前压力情况，从而能够通过气室压力数据判断巡回护士对象是否对医疗对象进行了医疗检查，使得有效避免压力性损伤的发生。Step S306, based on the circulating nurse object, the operating table and the air chamber pressure data of the medical object, the surgical process of the medical object is monitored. Specifically, the air chamber pressure data can reflect the current pressure of the air chamber unit used by the medical object, so that the air chamber pressure data can be used to determine whether the circulating nurse object has performed a medical examination on the medical object, so as to effectively avoid the occurrence of pressure injuries.
步骤S307，基于对象检测模型对第一帧全景画面进行识别，分别确定巡回护士对象、手术床和操作电脑，对象检测模型基于多张样本全景画面训练得到，用于识别画面中的对象和物体。Step S307, identifying the first frame of the panoramic picture based on the object detection model, and determining the circulating nurse object, the operating table and the operating computer respectively. The object detection model is trained based on multiple sample panoramic pictures and is used to identify objects and objects in the picture.
在一些可选的实施方式中，该对象检测模型的训练过程包括以下步骤：In some optional implementations, the training process of the object detection model includes the following steps:
步骤b1，获取多张样本全景画面。具体地，本发明中以对象检测模型为Yolo目标检测模型为例进行说明。通过COCO(Microsoft Common Objects in Context)或ImageNet等数据集训练Yolo(You Only Look Once)目标检测预训练模型，然后该预训练模型基于多张样本全景画面进行训练，得到对象检测模型。Step b1, obtaining multiple sample panoramic pictures. Specifically, the present invention takes the Yolo target detection model as an example for explanation. The Yolo (You Only Look Once) target detection pre-trained model is trained by using data sets such as COCO (Microsoft Common Objects in Context) or ImageNet, and then the pre-trained model is trained based on multiple sample panoramic pictures to obtain an object detection model.
步骤b2，基于对象检测模型对多张样本全景画面进行识别，分别得到多个样本对象、样本手术床以及样本操作电脑的样本标注位置。具体地，图6是根据本发明实施例的样本标注位置的示意图，如图6所示，对于任一样本全景画面，对象检测模型对该样本全景画面进行识别，能够识别到各个对象和物体，以及对应的样本标注位置。该样本标注位置包括文件名、区域坐标、中心坐标和目标物体。Step b2, based on the object detection model, multiple sample panoramic images are identified to obtain sample annotation positions of multiple sample objects, sample operating tables, and sample operating computers. Specifically, FIG6 is a schematic diagram of sample annotation positions according to an embodiment of the present invention. As shown in FIG6, for any sample panoramic image, the object detection model identifies the sample panoramic image and can identify various objects and corresponding sample annotation positions. The sample annotation position includes the file name, region coordinates, center coordinates, and target object.
步骤b3，基于多个样本对象、样本手术床以及样本操作电脑的样本标注位置与实际位置之间的差异，对对象检测模型进行训练。具体地，通过基于样本标注位置和实际位置之间的差异，对对象检测模型进行训练，提高了对象检测模型的识别能力，从而实现对巡回护士对象的监控。Step b3, based on the differences between the sample annotated positions and the actual positions of the multiple sample objects, sample operating tables, and sample operating computers, the object detection model is trained. Specifically, by training the object detection model based on the differences between the sample annotated positions and the actual positions, the recognition ability of the object detection model is improved, thereby realizing the monitoring of the circulating nurse object.
具体地，上述步骤S307包括：Specifically, the above step S307 includes:
步骤S3071，基于对象检测模型对第一帧全景画面进行识别，确定多个第一对象、手术床和操作电脑。具体地，对象检测模型在第一帧全景画面中识别出多个对象，将每个对象均作为第一对象。图7是根据本发明实施例的对象检测模型进行对象或物体识别的示意图，如图7所示，对象检测模型从第一帧全景画面中识别到了四个第一对象、手术床和操作电脑。Step S3071, based on the object detection model, the first frame of the panoramic picture is identified to determine multiple first objects, an operating table, and an operating computer. Specifically, the object detection model identifies multiple objects in the first frame of the panoramic picture, and each object is regarded as a first object. FIG7 is a schematic diagram of object or object recognition by an object detection model according to an embodiment of the present invention. As shown in FIG7, the object detection model identifies four first objects, an operating table, and an operating computer from the first frame of the panoramic picture.
步骤S3072，确定操作电脑的第一中心坐标。具体地，该操作电脑的第一中心坐标为操作电脑区域矩阵的中心点。Step S3072, determining the first center coordinates of the operating computer. Specifically, the first center coordinates of the operating computer are the center point of the operating computer area matrix.
步骤S3073，分别确定多个第一对象对应的第二中心坐标。具体地，由于全景画面中有多个第一对象，通过确定第一对象的第二中心坐标，从而确定巡回护士对象。Step S3073, respectively determine the second center coordinates corresponding to the plurality of first objects. Specifically, since there are a plurality of first objects in the panoramic image, the circulating nurse object is determined by determining the second center coordinates of the first objects.
步骤S3074，对于任一第一对象，确定第一对象的第二中心坐标和第一中心坐标之间的距离。具体地，通过中心坐标之间的距离确定巡回护士对象，该距离可以通过欧氏距离计算，也可通过其他方式确定，本发明实施例对此不进行限制。Step S3074: for any first object, determine the distance between the second center coordinate and the first center coordinate of the first object. Specifically, the circulating nurse object is determined by the distance between the center coordinates, which can be calculated by Euclidean distance or by other methods, which is not limited in the embodiment of the present invention.
步骤S3075，将多个第一对象对应的距离中最小的距离对应的第一对象，确定为巡回护士对象。具体地，由于巡回护士对象在手术开始时默认为在操作电脑旁工作，因此可以将距离操作对象最近的第一对象确定为巡回护士对象。Step S3075: The first object corresponding to the smallest distance among the distances corresponding to the multiple first objects is determined as the circulating nurse object. Specifically, since the circulating nurse object is assumed to work next to the operating computer at the beginning of the operation, the first object closest to the operating object can be determined as the circulating nurse object.
步骤S308，基于对象检测模型，对第一帧全景画面的下一帧全景画面进行识别，确定多个第二对象。具体地，对象检测模型在下一帧全景画面中识别出多个对象，将每个对象均作为第二对象。由于巡回护士对象在手术过程中不是固定不动的，因此与操作电脑之间的距离也会发生变化，需要持续确定巡回护士对象。Step S308, based on the object detection model, the next panoramic frame of the first panoramic frame is identified to determine multiple second objects. Specifically, the object detection model identifies multiple objects in the next panoramic frame, and each object is used as a second object. Since the circulating nurse object is not fixed during the operation, the distance between the circulating nurse object and the operating computer will also change, and the circulating nurse object needs to be continuously determined.
步骤S309，对巡回护士对象进行特征提取，得到巡回护士对象的第一特征向量。具体地，可以基于CNN(Convolutional Neural Network，卷积神经网络)对巡回护士对象进行特征提取，得到该巡回护士对象的128位的第一特征向量。其中，还可通过其他方式得到巡回护士对象的特征向量，本发明实施例对此不进行限制。Step S309, feature extraction is performed on the circulating nurse object to obtain a first feature vector of the circulating nurse object. Specifically, feature extraction can be performed on the circulating nurse object based on CNN (Convolutional Neural Network) to obtain a 128-bit first feature vector of the circulating nurse object. The feature vector of the circulating nurse object can also be obtained by other methods, which are not limited in the embodiment of the present invention.
步骤S310，分别对多个第二对象进行特征提取，得到多个第二对象对应的第二特征向量。具体地，对下一帧全景画面中的所有第二对象进行特征提取，得到多个第二特征向量，从而能够基于特征向量持续确定巡回护士对象。Step S310, extract features from multiple second objects respectively to obtain second feature vectors corresponding to the multiple second objects. Specifically, extract features from all second objects in the next panoramic picture frame to obtain multiple second feature vectors, so that the circulating nurse objects can be continuously determined based on the feature vectors.
步骤S311，对于任一第二特征向量，基于余弦相似度算法，确定第二特征向量与第一特征向量的相似值。具体地，还可通过其他算法确定第一特征向量和第二特征向量之间的相似值，本发明实施例对此不进行限制。Step S311: for any second eigenvector, determine the similarity value between the second eigenvector and the first eigenvector based on the cosine similarity algorithm. Specifically, the similarity value between the first eigenvector and the second eigenvector may also be determined by other algorithms, which is not limited in the embodiment of the present invention.
步骤S312，将相似值最大的第二特征向量对应的第二对象，确定为新的巡回护士对象。具体地，相似值最大的第二特征向量对应的第二对象，也即和巡回护士对象最相似的对象，实现了对巡回护士对象的持续确定，保障了对巡回护士对象监控的准确度。图8是根据本发明实施例的持续确定巡回护士对象的流程示意图，如图8所示，通过持续采集手术过程中的全景画面，识别全景画面中的所有第二对象。然后，对巡回护士对象和所有第二对象进行特征提取，得到第一特征向量和多个第二特征向量。然后，依次比较第一特征向量和多个第二特征向量的相似值。然后，将相似值最大的第二特征向量对应的第二对象确定为新的巡回护士对象。然后，将新的巡回护士对象的第二特征向量作为新的第一特征向量，实现对巡回护士对象的更新。Step S312, the second object corresponding to the second feature vector with the largest similarity value is determined as a new circulating nurse object. Specifically, the second object corresponding to the second feature vector with the largest similarity value, that is, the object most similar to the circulating nurse object, realizes the continuous determination of the circulating nurse object and ensures the accuracy of monitoring the circulating nurse object. Figure 8 is a flow chart of continuously determining the circulating nurse object according to an embodiment of the present invention. As shown in Figure 8, all second objects in the panoramic picture are identified by continuously collecting the panoramic picture during the operation. Then, feature extraction is performed on the circulating nurse object and all second objects to obtain a first feature vector and multiple second feature vectors. Then, the similarity values of the first feature vector and the multiple second feature vectors are compared in turn. Then, the second object corresponding to the second feature vector with the largest similarity value is determined as a new circulating nurse object. Then, the second feature vector of the new circulating nurse object is used as the new first feature vector to realize the update of the circulating nurse object.
步骤S313，基于巡回护士对象、手术床和医疗对象的气室压力数据，对医疗对象的手术过程进行监控。Step S313, monitoring the surgical process of the medical subject based on the circulating nurse object, the operating table and the air chamber pressure data of the medical subject.
具体地，上述步骤S313包括：Specifically, the above step S313 includes:
步骤S3131，获取手术床的周边坐标，周边坐标包括手术床的左上角坐标、右上角坐标、左下角坐标和右下角坐标。具体地，图9是根据本发明实施例的手术床的周边坐标的示意图，如图9所示，基于对象检测模型能够确定手术床的中心坐标和周边坐标。Step S3131, obtaining the peripheral coordinates of the operating table, the peripheral coordinates including the upper left corner coordinates, the upper right corner coordinates, the lower left corner coordinates and the lower right corner coordinates of the operating table. Specifically, FIG9 is a schematic diagram of the peripheral coordinates of the operating table according to an embodiment of the present invention. As shown in FIG9, the central coordinates and peripheral coordinates of the operating table can be determined based on the object detection model.
步骤S3132，在预设时间段内，若巡回护士对象的坐标出现在周边坐标的第一预设范围内，确定巡回护士对象出现在手术床的第二预设范围内。具体地，通过巡回护士对象的坐标和手术床的周边坐标，能够判定巡回护士对象是否从操作电脑旁移动到手术床旁并围绕手术床走动一圈对医疗对象进行检查。其中，通过下表9中所示的位置关系进行判断。Step S3132: within the preset time period, if the coordinates of the circulating nurse object appear within the first preset range of the peripheral coordinates, it is determined that the circulating nurse object appears within the second preset range of the operating bed. Specifically, through the coordinates of the circulating nurse object and the peripheral coordinates of the operating bed, it can be determined whether the circulating nurse object moves from the operating computer to the operating bed and walks around the operating bed to examine the medical object. The determination is made based on the positional relationship shown in Table 9 below.
表9坐标判断规则Table 9 Coordinate judgment rules
其中，假设手术床的中心坐标为(X3，Y3)，左上角坐标为(X8，Y8)，左下角坐标为(X10，Y10)，右上角坐标为(X9，Y9)，右下角坐标为(X11，Y11)。在预设时间段内，当巡回护士对象的坐标与上述四个坐标重合或在上述四个坐标的第一预设范围内，并且满足上表9中的判断规则，则说明该巡回护士对象在手术床的第二预设范围内，也即巡回护士对象在手术床旁，且该巡回护士对象完成了绕手术床走动一圈的动作。其中，该预设时间段可以为3分钟、5分钟或6分钟等，该第一预设范围和第二预设范围都可自行规定，本发明实施例对上述预设值均不进行限制。Wherein, it is assumed that the center coordinates of the operating bed are (X3, Y3), the coordinates of the upper left corner are (X8, Y8), the coordinates of the lower left corner are (X10, Y10), the coordinates of the upper right corner are (X9, Y9), and the coordinates of the lower right corner are (X11, Y11). Within the preset time period, when the coordinates of the circulating nurse object coincide with the above four coordinates or are within the first preset range of the above four coordinates, and the judgment rules in Table 9 above are met, it means that the circulating nurse object is within the second preset range of the operating bed, that is, the circulating nurse object is next to the operating bed, and the circulating nurse object has completed the action of walking around the operating bed. Wherein, the preset time period can be 3 minutes, 5 minutes or 6 minutes, etc., and the first preset range and the second preset range can be defined by oneself, and the embodiments of the present invention do not limit the above preset values.
步骤S3133，在医疗对象的气室压力数据发生波动的情况下，获取气室压力数据的波动值。具体地，当医疗对象的气室压力数据发生波动时，说明巡回护士对象开始对医疗对象进行医疗检查，因此可以通过获取气室压力数据的波动值，判断巡回护士对象的医疗检查是否执行到位。Step S3133, when the air chamber pressure data of the medical object fluctuates, obtain the fluctuation value of the air chamber pressure data. Specifically, when the air chamber pressure data of the medical object fluctuates, it indicates that the circulating nurse object has started to perform a medical examination on the medical object, so by obtaining the fluctuation value of the air chamber pressure data, it can be judged whether the medical examination of the circulating nurse object is performed in place.
步骤S3134，在巡回护士对象出现在手术床的第二预设范围内，并且波动值大于预设波动阈值的情况下，确定巡回护士对象对医疗对象进行医疗检查，实现对医疗对象的手术过程的监控。具体地，以波动值为7，按照超过压力期望值20％计算得到预设波动阈值，即预设波动阈值为6，为例进行说明。当巡回护士对象出现在手术床的第二预设范围内，也即巡回护士对象完成了绕手术床走动一圈的动作，在这个过程中，该波动值7大于预设波动阈值6，说明巡回护士对象对医疗对象的受压部位进行了医疗检查。其中，该预设波动阈值也可以基于其他方法计算得到或自行设置，本发明实施例对此不进行限制。Step S3134, when the circulating nurse object appears within the second preset range of the operating bed and the fluctuation value is greater than the preset fluctuation threshold, it is determined that the circulating nurse object performs a medical examination on the medical object to monitor the surgical process of the medical object. Specifically, taking the fluctuation value of 7, the preset fluctuation threshold is calculated according to 20% exceeding the expected pressure value, that is, the preset fluctuation threshold is 6, as an example for explanation. When the circulating nurse object appears within the second preset range of the operating bed, that is, the circulating nurse object completes the action of walking around the operating bed. In this process, the fluctuation value 7 is greater than the preset fluctuation threshold 6, indicating that the circulating nurse object has performed a medical examination on the compressed part of the medical object. Among them, the preset fluctuation threshold can also be calculated based on other methods or set by itself, and the embodiments of the present invention do not limit this.
在一些可选的实施方式中，图10是根据本发明实施例的监控手术过程的示意图，如图10所示，通过上述步骤b1至步骤b3训练得到对象检测模型。通过巡回护士对象是否对医疗对象进行绕床检查和医疗对象的气室压力数据是否发生波动，来判断巡回护士对象是否进行了医疗检查，从而实现对手术过程的监控。In some optional implementations, FIG10 is a schematic diagram of monitoring a surgical procedure according to an embodiment of the present invention. As shown in FIG10 , an object detection model is obtained by training through the above steps b1 to b3. Whether the circulating nurse object performs a bed-circling inspection on the medical object and whether the air chamber pressure data of the medical object fluctuates is determined to determine whether the circulating nurse object has performed a medical examination, thereby achieving monitoring of the surgical procedure.
在一些可选的实施方式中，图11是根据本发明实施例的压力性损伤的预警方法的系统示意图，如图11所示，上述步骤S301可以基于体位自适应模块实现，步骤S302可以基于监控阈值自动化模块实现，步骤S303可以基于自动化分析计算模块和气室单元控制模块实现，步骤S304至步骤S313可以基于巡回护士行为监控模块实现。In some optional embodiments, Figure 11 is a system schematic diagram of a warning method for pressure injuries according to an embodiment of the present invention. As shown in Figure 11, the above-mentioned step S301 can be implemented based on the body position adaptation module, step S302 can be implemented based on the monitoring threshold automation module, step S303 can be implemented based on the automation analysis and calculation module and the air chamber unit control module, and steps S304 to S313 can be implemented based on the circulating nurse behavior monitoring module.
本发明实施例提供的压力性损伤的预警方法，通过基于对象检测模型对巡回护士对象进行识别，并且通过获取医疗对象的气室压力数据，能够判断巡回护士对象是否对医疗对象进行了有效的医疗检查，降低了压力性损伤的发生风险。The early warning method for pressure injuries provided in the embodiment of the present invention can determine whether the circulating nurse object has performed an effective medical examination on the medical object by identifying the circulating nurse object based on the object detection model and obtaining the air chamber pressure data of the medical object, thereby reducing the risk of pressure injuries.
在本实施例中还提供了一种压力性损伤的预警装置，该装置用于实现上述实施例及优选实施方式，已经进行过说明的不再赘述。如以下所使用的，术语“模块”可以实现预定功能的软件和/或硬件的组合。尽管以下实施例所描述的装置较佳地以软件来实现，但是硬件，或者软件和硬件的组合的实现也是可能并被构想的。In this embodiment, a pressure injury early warning device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and/or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.
本实施例提供一种压力性损伤的预警装置，如图12所示，包括：This embodiment provides a pressure injury warning device, as shown in FIG12 , comprising:
获取模块1201，用于对于任一医疗对象，获取医疗对象进行手术所需的多个气室单元。The acquisition module 1201 is used to acquire, for any medical object, a plurality of air chamber units required for performing surgery on the medical object.
确定模块1202，用于基于阈值确定模型，确定医疗对象的多组压力预警数据和多组温度预警数据，阈值确定模型基于多个样本医疗对象的所需气室单元的压力数据、温度数据和是否发生压力性损伤的关系训练得到。Determination module 1202 is used to determine multiple groups of pressure warning data and multiple groups of temperature warning data of the medical object based on a threshold determination model, and the threshold determination model is trained based on the relationship between the pressure data, temperature data and whether pressure injury occurs of the required air chamber unit of multiple sample medical objects.
预警模块1203，用于基于多组压力预警数据和多组温度预警数据，调整多个气室单元，对压力性损伤进行预警。The early warning module 1203 is used to adjust multiple air chamber units based on multiple groups of pressure early warning data and multiple groups of temperature early warning data to issue early warnings for pressure injuries.
在一种可选的实施方式中，每组压力预警数据包括压力预警阈值和压力时长阈值，每组温度预警数据包括温度预警阈值和温度时长阈值；预警模块1203包括：In an optional implementation, each set of pressure warning data includes a pressure warning threshold and a pressure duration threshold, and each set of temperature warning data includes a temperature warning threshold and a temperature duration threshold; the warning module 1203 includes:
第一确定单元，用于对于任一组压力预警数据，确定气室单元在压力预警数据对应的压力预警阈值下的第一持续时长。The first determination unit is used to determine, for any set of pressure warning data, a first duration of time during which the air chamber unit is below a pressure warning threshold corresponding to the pressure warning data.
第二确定单元，用于对于任一组温度预警数据，确定气室单元在温度预警数据对应的温度预警阈值下的第二持续时长。The second determining unit is used to determine, for any set of temperature warning data, a second duration of time during which the air chamber unit is below the temperature warning threshold corresponding to the temperature warning data.
放气单元，用于在第一持续时长不小于压力时长阈值的情况下，对气室单元进行放气操作，对压力性损伤进行预警。The deflation unit is used to deflate the air chamber unit when the first duration is not less than the pressure duration threshold, so as to give an early warning of pressure injury.
降温单元，用于在第二持续时长不小于温度时长阈值的情况下，对气室单元进行降温操作，对压力性损伤进行预警。The cooling unit is used to cool the air chamber unit when the second duration is not less than the temperature duration threshold, and to give an early warning of pressure damage.
在一种可选的实施方式中，该阈值确定模型的训练过程包括：In an optional implementation, the training process of the threshold determination model includes:
获取多个样本医疗对象的体位数据、术前诊断信息和样本医疗结果，样本医疗结果表示样本医疗对象是否发生压力性损伤；Acquiring body position data, preoperative diagnosis information, and sample medical results of a plurality of sample medical subjects, wherein the sample medical results indicate whether pressure injuries occur in the sample medical subjects;
对于任一样本医疗对象，获取样本医疗对象在手术过程中所用的多个气室单元的样本压力数据和样本温度数据；For any sample medical object, obtaining sample pressure data and sample temperature data of a plurality of air chamber units used by the sample medical object during surgery;
对气室单元的样本压力数据进行离散化处理，得到多组样本压力预警数据，样本压力预警数据包括样本压力预警阈值和样本压力时长阈值；Discretize the sample pressure data of the air chamber unit to obtain multiple groups of sample pressure warning data, the sample pressure warning data including a sample pressure warning threshold and a sample pressure duration threshold;
对多个气室单元的样本温度数据进行离散化处理，得到多组样本温度预警数据，样本温度预警数据包括样本温度预警阈值和样本温度时长阈值；Discretize the sample temperature data of multiple air chamber units to obtain multiple groups of sample temperature warning data, the sample temperature warning data including a sample temperature warning threshold and a sample temperature duration threshold;
将样本医疗对象的体位数据、术前诊断信息和样本医疗结果作为输入，多组样本压力预警数据和多组样本温度预警数据作为标签，对阈值确定模型进行训练。The body position data, preoperative diagnosis information and sample medical results of sample medical subjects are used as input, and multiple groups of sample pressure warning data and multiple groups of sample temperature warning data are used as labels to train the threshold determination model.
在一种可选的实施方式中，该装置还包括：In an optional embodiment, the device further comprises:
画面获取模块，用于获取医疗对象预设范围内的多帧全景画面和医疗对象的气室压力数据，气室压力数据表示医疗对象在手术过程中使用的气室单元的压力数据。The image acquisition module is used to acquire multiple frames of panoramic images within a preset range of the medical object and the air chamber pressure data of the medical object, where the air chamber pressure data represents the pressure data of the air chamber unit used by the medical object during surgery.
第一识别模块，用于基于对象检测模型对第一帧全景画面进行识别，分别确定巡回护士对象、手术床和操作电脑，对象检测模型基于多张样本全景画面训练得到，用于识别画面中的对象和物体。The first recognition module is used to recognize the first frame of the panoramic picture based on the object detection model, and respectively determine the circulating nurse object, the operating bed and the operating computer. The object detection model is trained based on multiple sample panoramic pictures and is used to recognize objects and objects in the picture.
监控模块，用于基于巡回护士对象、手术床和医疗对象的气室压力数据，对医疗对象的手术过程进行监控。The monitoring module is used to monitor the surgical process of the medical object based on the circulating nurse object, the operating table and the air chamber pressure data of the medical object.
在一种可选的实施方式中，该对象检测模型的训练过程包括：In an optional implementation, the training process of the object detection model includes:
获取多张样本全景画面；Get multiple sample panoramic images;
基于对象检测模型对多张样本全景画面进行识别，分别得到多个样本对象、样本手术床以及样本操作电脑的样本标注位置；Based on the object detection model, multiple sample panoramic images are identified to obtain sample annotation positions of multiple sample objects, sample operating tables, and sample operating computers;
基于多个样本对象、样本手术床以及样本操作电脑的样本标注位置与实际位置之间的差异，对对象检测模型进行训练。The object detection model is trained based on the differences between the sample annotated positions and the actual positions of multiple sample objects, sample operating tables, and sample operating computers.
在一种可选的实施方式中，第一识别模块包括：In an optional implementation, the first identification module includes:
识别单元，用于基于对象检测模型对第一帧全景画面进行识别，确定多个第一对象、手术床和操作电脑。The recognition unit is used to recognize the first frame of the panoramic picture based on the object detection model to determine multiple first objects, an operating table and an operating computer.
第三确定单元，用于确定操作电脑的第一中心坐标。The third determining unit is used to determine the first center coordinates of the operating computer.
第四确定单元，用于分别确定多个第一对象对应的第二中心坐标。The fourth determining unit is used to respectively determine the second center coordinates corresponding to the plurality of first objects.
距离确定单元，用于对于任一第一对象，确定第一对象的第二中心坐标和第一中心坐标之间的距离。The distance determining unit is used to determine, for any first object, the distance between the second center coordinates and the first center coordinates of the first object.
第五确定单元，用于将多个第一对象对应的距离中最小的距离对应的第一对象，确定为巡回护士对象。The fifth determining unit is used to determine the first object corresponding to the smallest distance among the distances corresponding to the multiple first objects as the circulating nurse object.
在一种可选的实施方式中，第一识别模块之后，该装置还包括：In an optional implementation, after the first identification module, the device further includes:
第二识别模块，用于基于对象检测模型，对第一帧全景画面的下一帧全景画面进行识别，确定多个第二对象。The second recognition module is used to recognize the next panoramic frame of the first panoramic frame based on the object detection model to determine a plurality of second objects.
第一提取模块，用于对巡回护士对象进行特征提取，得到巡回护士对象的第一特征向量。The first extraction module is used to extract features of the circulating nurse object to obtain a first feature vector of the circulating nurse object.
第二提取模块，用于分别对多个第二对象进行特征提取，得到多个第二对象对应的第二特征向量。The second extraction module is used to extract features from the multiple second objects respectively to obtain second feature vectors corresponding to the multiple second objects.
相似确定模块，用于对于任一第二特征向量，基于余弦相似度算法，确定第二特征向量与第一特征向量的相似值。The similarity determination module is used to determine, for any second feature vector, a similarity value between the second feature vector and the first feature vector based on a cosine similarity algorithm.
对象确定模块，用于将相似值最大的第二特征向量对应的第二对象，确定为新的巡回护士对象。The object determination module is used to determine the second object corresponding to the second feature vector with the largest similarity value as a new circulating nurse object.
在一种可选的实施方式中，监控模块包括：In an optional implementation, the monitoring module includes:
坐标获取单元，用于获取手术床的周边坐标，周边坐标包括手术床的左上角坐标、右上角坐标、左下角坐标和右下角坐标。The coordinate acquisition unit is used to acquire the peripheral coordinates of the operating table, wherein the peripheral coordinates include the upper left corner coordinates, the upper right corner coordinates, the lower left corner coordinates and the lower right corner coordinates of the operating table.
范围确定单元，用于在预设时间段内，若巡回护士对象的坐标出现在周边坐标的第一预设范围内，确定巡回护士对象出现在手术床的第二预设范围内。The range determination unit is used to determine that the circulating nurse object appears within a second preset range of the operating table if the coordinates of the circulating nurse object appear within a first preset range of the peripheral coordinates within a preset time period.
波动获取单元，用于在医疗对象的气室压力数据发生波动的情况下，获取气室压力数据的波动值。The fluctuation acquisition unit is used to acquire the fluctuation value of the air chamber pressure data when the air chamber pressure data of the medical object fluctuates.
监控单元，用于在巡回护士对象出现在手术床的第二预设范围内，并且波动值大于预设波动阈值的情况下，确定巡回护士对象对医疗对象进行医疗检查，实现对医疗对象的手术过程的监控。The monitoring unit is used to determine that the circulating nurse object performs a medical examination on the medical object and monitor the surgical process of the medical object when the circulating nurse object appears within the second preset range of the operating table and the fluctuation value is greater than the preset fluctuation threshold.
上述各个模块和单元的更进一步的功能描述与上述对应实施例相同，在此不再赘述。The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.
本实施例中的压力性损伤的预警装置是以功能单元的形式来呈现，这里的单元是指ASIC(Application Specific Integrated Circuit，专用集成电路)电路，执行一个或多个软件或固定程序的处理器和存储器，和/或其他可以提供上述功能的器件。The early warning device for pressure injury in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and/or other devices that can provide the above functions.
本发明实施例还提供一种计算机设备，具有上述图12所示的压力性损伤的预警装置。An embodiment of the present invention further provides a computer device having the pressure injury warning device shown in FIG. 12 above.
请参阅图13，图13是本发明可选实施例提供的一种计算机设备的结构示意图，如图13所示，该计算机设备包括：一个或多个处理器10、存储器20，以及用于连接各部件的接口，包括高速接口和低速接口。各个部件利用不同的总线互相通信连接，并且可以被安装在公共主板上或者根据需要以其它方式安装。处理器可以对在计算机设备内执行的指令进行处理，包括存储在存储器中或者存储器上以在外部输入/输出装置(诸如，耦合至接口的显示设备)上显示GUI的图形信息的指令。在一些可选的实施方式中，若需要，可以将多个处理器和/或多条总线与多个存储器和多个存储器一起使用。同样，可以连接多个计算机设备，各个设备提供部分必要的操作(例如，作为服务器阵列、一组刀片式服务器、或者多处理器系统)。图13中以一个处理器10为例。Please refer to Figure 13, which is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention. As shown in Figure 13, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses for communication, and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed in the computer device, including instructions stored in or on the memory to display graphical information of the GUI on an external input/output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and/or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). In Figure 13, a processor 10 is taken as an example.
处理器10可以是中央处理器，网络处理器或其组合。其中，处理器10还可以进一步包括硬件芯片。上述硬件芯片可以是专用集成电路，可编程逻辑器件或其组合。上述可编程逻辑器件可以是复杂可编程逻辑器件，现场可编程逻辑门阵列，通用阵列逻辑或其任意组合。The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.
其中，所述存储器20存储有可由至少一个处理器10执行的指令，以使所述至少一个处理器10执行实现上述实施例示出的方法。The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.
存储器20可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储根据计算机设备的使用所创建的数据等。此外，存储器20可以包括高速随机存取存储器，还可以包括非瞬时存储器，例如至少一个磁盘存储器件、闪存器件、或其他非瞬时固态存储器件。在一些可选的实施方式中，存储器20可选包括相对于处理器10远程设置的存储器，这些远程存储器可以通过网络连接至该计算机设备。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required by at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
存储器20可以包括易失性存储器，例如，随机存取存储器；存储器也可以包括非易失性存储器，例如，快闪存储器，硬盘或固态硬盘；存储器20还可以包括上述种类的存储器的组合。The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.
该计算机设备还包括输入装置30和输出装置40。处理器10、存储器20、输入装置30和输出装置40可以通过总线或者其他方式连接，图13中以通过总线连接为例。The computer device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means, and FIG13 takes the connection via a bus as an example.
输入装置30可接收输入的数字或字符信息，以及产生与该计算机设备的用户设置以及功能控制有关的键信号输入，例如触摸屏、小键盘、鼠标、轨迹板、触摸板、指示杆、一个或者多个鼠标按钮、轨迹球、操纵杆等。输出装置40可以包括显示设备、辅助照明装置(例如，LED)和触觉反馈装置(例如，振动电机)等。上述显示设备包括但不限于液晶显示器，发光二极管，显示器和等离子体显示器。在一些可选的实施方式中，显示设备可以是触摸屏。The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.
本发明实施例还提供了一种计算机可读存储介质，上述根据本发明实施例的方法可在硬件、固件中实现，或者被实现为可记录在存储介质，或者被实现通过网络下载的原始存储在远程存储介质或非暂时机器可读存储介质中并将被存储在本地存储介质中的计算机代码，从而在此描述的方法可被存储在使用通用计算机、专用处理器或者可编程或专用硬件的存储介质上的这样的软件处理。其中，存储介质可为磁碟、光盘、只读存储记忆体、随机存储记忆体、快闪存储器、硬盘或固态硬盘等；进一步地，存储介质还可以包括上述种类的存储器的组合。可以理解，计算机、处理器、微处理器控制器或可编程硬件包括可存储或接收软件或计算机代码的存储组件，当软件或计算机代码被计算机、处理器或硬件访问且执行时，实现上述实施例示出的方法。The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.
虽然结合附图描述了本发明的实施例，但是本领域技术人员可以在不脱离本发明的精神和范围的情况下做出各种修改和变型，这样的修改和变型均落入由所附权利要求所限定的范围之内。Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410379180.2ACN118266870A (en) | 2024-03-29 | 2024-03-29 | Early warning method and device for pressure injury and computer equipment |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410379180.2ACN118266870A (en) | 2024-03-29 | 2024-03-29 | Early warning method and device for pressure injury and computer equipment |
| Publication Number | Publication Date |
|---|---|
| CN118266870Atrue CN118266870A (en) | 2024-07-02 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410379180.2APendingCN118266870A (en) | 2024-03-29 | 2024-03-29 | Early warning method and device for pressure injury and computer equipment |
| Country | Link |
|---|---|
| CN (1) | CN118266870A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012056405A2 (en)* | 2010-10-28 | 2012-05-03 | Enhanced Surface Dynamics, Inc. | Pressure sensor assembly and associated method for preventing the development of pressure injuries |
| CN108245340A (en)* | 2018-04-19 | 2018-07-06 | 张玉梅 | A kind of pressure sore prevention air bed |
| CN111973153A (en)* | 2020-08-18 | 2020-11-24 | 上海交通大学医学院附属新华医院 | Method and device for preventing pressure sores and periosteum syndrome in plasters or braces |
| CN114145711A (en)* | 2021-11-16 | 2022-03-08 | 北京中医药大学东直门医院 | Monitoring system for preventing human body pressure injury |
| CN115699198A (en)* | 2020-06-05 | 2023-02-03 | 威博外科公司 | Digitization of operating rooms |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012056405A2 (en)* | 2010-10-28 | 2012-05-03 | Enhanced Surface Dynamics, Inc. | Pressure sensor assembly and associated method for preventing the development of pressure injuries |
| CN108245340A (en)* | 2018-04-19 | 2018-07-06 | 张玉梅 | A kind of pressure sore prevention air bed |
| CN115699198A (en)* | 2020-06-05 | 2023-02-03 | 威博外科公司 | Digitization of operating rooms |
| CN111973153A (en)* | 2020-08-18 | 2020-11-24 | 上海交通大学医学院附属新华医院 | Method and device for preventing pressure sores and periosteum syndrome in plasters or braces |
| CN114145711A (en)* | 2021-11-16 | 2022-03-08 | 北京中医药大学东直门医院 | Monitoring system for preventing human body pressure injury |
| Publication | Publication Date | Title |
|---|---|---|
| JP7108267B2 (en) | Biological information processing system, biological information processing method, and computer program | |
| US11051768B1 (en) | Determining when to emit an alarm | |
| CN113226175B (en) | Device and method for detecting stroke in a patient | |
| US11538581B2 (en) | Monitoring system, device and computer-implemented method for monitoring pressure ulcers | |
| JP6310476B2 (en) | Method and system for reducing the load caused by harmful alarms in clinical settings | |
| CN109937456B (en) | Patient monitoring system and method configured to suppress alarms | |
| US20250000461A1 (en) | System and method for detecting health events | |
| CN118266870A (en) | Early warning method and device for pressure injury and computer equipment | |
| CN116013548B (en) | Intelligent ward monitoring method and device based on computer vision | |
| TWI847574B (en) | A method and system for monitoring vital signs, electric equipment, and a computer-readable storage medium | |
| JP7325576B2 (en) | Terminal device, output method and computer program | |
| TW202130330A (en) | Monitoring system, device and computer-implemented method for monitoring pressure ulcers | |
| Al-Kalidi et al. | Respiratory rate measurement in children using a thermal camera | |
| Kodama et al. | Video‐based neonatal state assessment method for timing of procedures | |
| Wang et al. | Guest Editorial Camera-Based Health Monitoring in Real-World Scenarios | |
| US20250160684A1 (en) | Remote patient monitoring | |
| CN117017249B (en) | Blood pressure detecting device | |
| US20240156412A1 (en) | Vital sign obtaining device, non-transitory computer readable storage medium, and vital sign obtaining system | |
| US20230178200A1 (en) | Direct medical treatment predictions using artificial intelligence | |
| US20220378343A1 (en) | Sensor and vital sign information processing system | |
| WO2025101405A1 (en) | Medical record generation for virtual nursing | |
| JP7282534B2 (en) | Medical information processing system and medical information processing device | |
| Vijay et al. | Deep Learning-Based Smart Healthcare System for Patient's Discomfort Detection | |
| US20240312628A1 (en) | Learning device, determination device, method for generating trained model, and recording medium | |
| WO2024149613A1 (en) | System and method for patient monitoring based on condition and activity level |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |