技术领域Technical field
本发明属于数据处理技术领域，具体涉及一种基于互联网诊疗的电子病历处理方法和系统。The invention belongs to the field of data processing technology, and specifically relates to an electronic medical record processing method and system based on Internet diagnosis and treatment.
背景技术Background technique
随着医疗数据的增多，互联网医疗的崛起，越来越多的医院使用电子病历记录病患的信息和治疗数据，电子病历具有存储空间小、存储时间久、容易管理等优势，因此电子病历已经成为现代医疗服务中必不可少的工具，医院将电子病历存储到云服务器以更方便和更低的成本管理电子病历数据，用户甚至是其他医院的医师也可以利用互联网随时随地对电子病历进行查看。With the increase of medical data and the rise of Internet medical care, more and more hospitals use electronic medical records to record patient information and treatment data. Electronic medical records have the advantages of small storage space, long storage time, and easy management. Therefore, electronic medical records have It has become an indispensable tool in modern medical services. Hospitals store electronic medical records on cloud servers to manage electronic medical record data more conveniently and at lower costs. Users and even doctors from other hospitals can use the Internet to view electronic medical records anytime and anywhere. .
现有技术中，往往需要医师手动的在电脑屏幕上通过键盘完整地输入病人的病情情况以及诊断结论。首先，对于一些打字并不熟练的医师并不友好，反而会浪费医师时间，降低诊疗效率。其次，根据患者病情进行诊断时，完全依赖于医师的主观判断，但是各个医师的认知水平存在差异，可能存在疑难病情难以准确地做出判断的情况。In the existing technology, doctors are often required to manually input the patient's condition and diagnosis conclusion manually through the keyboard on the computer screen. First of all, it is not friendly to some doctors who are not proficient in typing. Instead, it will waste doctors' time and reduce the efficiency of diagnosis and treatment. Secondly, when making a diagnosis based on the patient's condition, it completely relies on the subjective judgment of the doctor. However, the cognitive level of each doctor is different, and it may be difficult to make accurate judgments on difficult conditions.
发明内容Contents of the invention
为了解决现有技术通过键盘完整地输入病人的病情情况以及诊断结论，对于一些打字并不熟练的医师并不友好，浪费医师时间，降低诊疗效率，根据患者病情进行诊断时，完全依赖于医师的主观判断，但是各个医师的认知水平存在差异，可能存在疑难病情难以准确判断的技术问题，本发明提供一种基于互联网诊疗的电子病历处理方法和系统。In order to solve the problem of the existing technology of completely inputting the patient's condition and diagnosis conclusion through the keyboard, it is not friendly to some doctors who are not skilled in typing, wastes the doctor's time, and reduces the efficiency of diagnosis and treatment. When making a diagnosis based on the patient's condition, it completely relies on the doctor's It is a subjective judgment, but the cognitive level of each doctor is different, and there may be technical problems that make it difficult to accurately judge difficult conditions. The present invention provides an electronic medical record processing method and system based on Internet diagnosis and treatment.
第一方面first
本发明提供了一种基于互联网诊疗的电子病历处理方法，包括：The present invention provides an electronic medical record processing method based on Internet diagnosis and treatment, including:
S101：获取患者的病情信息；S101: Obtain patient's condition information;
S102：提取病情信息中的结构化文本与非结构化文本；S102: Extract structured text and unstructured text from condition information;
S103：计算与各个历史病历的结构化文本匹配度；S103: Calculate the matching degree of structured text with each historical medical record;
S104：计算与各个历史病历的非结构化文本匹配度；S104: Calculate the matching degree of unstructured text with each historical medical record;
S105：根据结构化文本匹配度和非结构化文本匹配度，计算与各个历史病历的综合匹配度：S105: Calculate the comprehensive matching degree with each historical medical record based on the matching degree of structured text and the matching degree of unstructured text. :
其中，η表示结构化文本匹配度sima的权重系数，1-η表示非结构化文本匹配度simb的权重系数；Among them,η represents the weight coefficient of the structured text matching degreesima , and 1-eta represents the weight coefficient of the unstructured text matching degreesimb ;
S106：挑选综合匹配度最高的预设数量的历史病历，生成备选诊疗方案；S106: Select the preset number of historical medical records with the highest comprehensive matching degree and generate alternative diagnosis and treatment plans;
S107：推送备选诊疗方案，根据备选诊疗方案，挑选出诊疗方案；S107: Push alternative diagnosis and treatment plans, and select diagnosis and treatment plans based on the alternative diagnosis and treatment plans;
S108：根据病情信息以及对应的诊疗方案，生成电子病历；S108: Generate electronic medical records based on condition information and corresponding diagnosis and treatment plans;
S109：对电子病历进行脱敏处理；S109: Desensitize electronic medical records;
S110：生成私钥和公钥；S110: Generate private key and public key;
S111：利用公钥对脱敏后的电子病历进行加密并上传到云端；S111: Use the public key to encrypt the desensitized electronic medical record and upload it to the cloud;
S112：接收用户向云端发起的查阅请求；S112: Receive the query request initiated by the user to the cloud;
S113：验证用户的私钥，当用户的身份验证通过的情况下，展示脱敏后的电子病历。S113: Verify the user's private key. When the user's identity verification passes, display the desensitized electronic medical record.
第二方面Second aspect
本发明提供了一种基于互联网医疗的电子病历传输系统，用于执行第一方面中的基于互联网诊疗的电子病历处理方法。The present invention provides an electronic medical record transmission system based on Internet medical treatment, which is used to execute the electronic medical record processing method based on Internet diagnosis and treatment in the first aspect.
与现有技术相比，本发明至少具有以下有益技术效果：Compared with the prior art, the present invention at least has the following beneficial technical effects:
（1）在本发明中，根据患者的病情信息，从历史病历库中自动匹配出匹配度较高的历史病历，将匹配度较高的历史病历的诊疗方案作为备选诊疗方案，进而医师可以根据备选诊疗方案挑选出最终的诊疗方案。一方面，当备选诊疗方案中存在合适的诊疗方案时，医师可以直接选择其作为最终的诊疗方案，无需手动打字，减少因手动输入错误而引起的潜在问题，节省医师时间，提升诊疗效率；另一方面，即使是面对疑难病情，也可以将历史病历作为参考信息，避免陷入主观判断，提升诊疗准确性。(1) In the present invention, according to the patient's condition information, historical medical records with a higher matching degree are automatically matched from the historical medical record database, and the diagnosis and treatment plans of the historical medical records with a higher matching degree are used as alternative diagnosis and treatment plans, so that doctors can Select the final diagnosis and treatment plan based on the alternative diagnosis and treatment plans. On the one hand, when there is a suitable diagnosis and treatment plan among the alternative diagnosis and treatment plans, the doctor can directly select it as the final diagnosis and treatment plan without manual typing, which reduces potential problems caused by manual input errors, saves the doctor's time, and improves the efficiency of diagnosis and treatment; On the other hand, even when facing difficult conditions, historical medical records can be used as reference information to avoid subjective judgment and improve the accuracy of diagnosis and treatment.
（2）在本发明中，可以对患者的电子病历进行脱敏处理，保护患者的隐私和敏感信息，并提高数据的安全性。(2) In the present invention, the patient's electronic medical record can be desensitized, protecting the patient's privacy and sensitive information, and improving data security.
（3）在本发明中，可以利用公钥对脱敏后的电子病历进行加密，当用户的身份验证通过时，才有权限查阅电子病历，进一步地保障患者的电子病历在共享的过程中的信息安全，有效保护患者的隐私和敏感信息，降低数据泄露风险。(3) In the present invention, the public key can be used to encrypt the desensitized electronic medical record. Only when the user's identity verification is passed, the user has the authority to view the electronic medical record, further ensuring the security of the patient's electronic medical record during the sharing process. Information security effectively protects patients’ privacy and sensitive information and reduces the risk of data leakage.
附图说明Description of the drawings
下面将以明确易懂的方式，结合附图说明优选实施方式，对本发明的上述特性、技术特征、优点及其实现方式予以进一步说明。The following will describe the preferred embodiments in a clear and easy-to-understand manner with reference to the accompanying drawings, and further explain the above-mentioned characteristics, technical features, advantages and implementation methods of the present invention.
图1是本发明提供的一种基于互联网诊疗的电子病历处理方法的流程示意图。Figure 1 is a schematic flow chart of an electronic medical record processing method based on Internet diagnosis and treatment provided by the present invention.
图2是本发明提供的一种基于互联网诊疗的电子病历处理方法的结构示意图。Figure 2 is a schematic structural diagram of an electronic medical record processing method based on Internet diagnosis and treatment provided by the present invention.
具体实施方式Detailed ways
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对照附图说明本发明的具体实施方式。显而易见地，下面描述中的附图仅仅是本发明的一些实施例，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，并获得其他的实施方式。In order to explain the embodiments of the present invention or technical solutions in the prior art more clearly, the specific implementation modes of the present invention will be described below with reference to the accompanying drawings. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without exerting creative efforts, other drawings can also be obtained based on these drawings, and obtain Other embodiments.
为使图面简洁，各图中只示意性地表示出了与发明相关的部分，它们并不代表其作为产品的实际结构。另外，以使图面简洁便于理解，在有些图中具有相同结构或功能的部件，仅示意性地绘示了其中的一个，或仅标出了其中的一个。在本文中，“一个”不仅表示“仅此一个”，也可以表示“多于一个”的情形。In order to keep the drawings concise, only the parts related to the invention are schematically shown in each figure, and they do not represent the actual structure of the product. In addition, in order to make the drawings concise and easy to understand, in some drawings, only one of the components with the same structure or function is schematically illustrated or labeled. In this article, "a" not only means "only one", but can also mean "more than one".
还应当进一步理解，在本发明说明书和所附权利要求书中使用的术语“和/或”是指相关联列出的项中的一个或多个的任何组合以及所有可能组合，并且包括这些组合。It will be further understood that the term "and/or" as used in the specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items. .
在本文中，需要说明的是，除非另有明确的规定和限定，术语“安装”、“相连”、“连接”应做广义理解，例如，可以是固定连接，也可以是可拆卸连接，或一体地连接。可以是机械连接，也可以是电连接。可以是直接相连，也可以通过中间媒介间接相连，可以是两个元件内部的连通。对于本领域的普通技术人员而言，可以具体情况理解上述术语在本发明中的具体含义。In this article, it should be noted that, unless otherwise clearly stated and limited, the terms "installation", "connection" and "connection" should be understood in a broad sense. For example, it can be a fixed connection or a detachable connection, or Connected in one piece. The connection can be mechanical or electrical. It can be directly connected, or it can be indirectly connected through an intermediary, or it can be an internal connection between two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood on a case-by-case basis.
另外，在本发明的描述中，术语“第一”、“第二”等仅用于区分描述，而不能理解为指示或暗示相对重要性。In addition, in the description of the present invention, the terms "first", "second", etc. are only used to differentiate the description and cannot be understood as indicating or implying relative importance.
实施例1Example 1
在一个实施例中，参考说明书附图1，示出了本发明提供的基于互联网诊疗的电子病历处理方法的流程示意图。参考说明书附图2，示出了本发明提供的一种基于互联网诊疗的电子病历处理方法的结构示意图。In one embodiment, refer to FIG. 1 of the description, which shows a schematic flow chart of an electronic medical record processing method based on Internet diagnosis and treatment provided by the present invention. Referring to Figure 2 of the description, a schematic structural diagram of an electronic medical record processing method based on Internet diagnosis and treatment provided by the present invention is shown.
本发明提供的一种基于互联网诊疗的电子病历处理方法，包括：The invention provides an electronic medical record processing method based on Internet diagnosis and treatment, including:
S101：获取患者的病情信息。S101: Obtain the patient's condition information.
可选地，可以通过与患者进行面对面的问诊和检查，直接获取患者的症状、疼痛感受、病史等信息。也可以通过患者之前的电子病历、就诊记录、化验报告、放射影像报告等医学文档中获取患者的历史病情信息。Optionally, you can directly obtain the patient's symptoms, pain, medical history and other information through face-to-face consultation and examination. The patient's historical condition information can also be obtained from the patient's previous electronic medical records, medical records, laboratory reports, radiological imaging reports and other medical documents.
其中，病情信息可以是对于患者的基本情况的一些介绍。Among them, the condition information may be some introduction to the patient's basic situation.
举例而言，以下是一段关于患者病情信息的描述：患者于XXXX年XX月XX日因发热，最高达39℃，继而出现尿失禁。为求诊治，行抗炎治疗，症状缓解。行CT增强扫描示：右肾占位性病变，右肾中部可见局部向外凸出团块影，边界尚清晰，大小约为2.9cm×3.4cm，考虑肾癌的可能性大。在我院行腹部彩超示：左肾轻度积水，右肾实质性肿物。门诊拟以“右肾占位”收入我科。目前精神尚可，体力正常，食欲正常，睡眠正常，人口统计学信息下降3kg，排尿正常，大便正常，为进一步检查及治疗入院。既往史：平素健康，有糖尿病史，否认“高血压”、“冠心病”等疾病史，否认肝炎、结核、疟疾等传染病史，有鼻息肉手术史，否认外伤史，否认输血史，有青霉素过敏史。无食物过敏史，预防接种随当地进行。For example, the following is a description of the patient's condition information: The patient developed a fever on XXXX, XXXX, with a maximum temperature of 39°C, and then developed urinary incontinence. In order to seek diagnosis and treatment, anti-inflammatory treatment was performed, and the symptoms were relieved. An enhanced CT scan showed that there was a space-occupying lesion in the right kidney, and a local bulging mass could be seen in the middle of the right kidney. The boundary was still clear and the size was about 2.9cm × 3.4cm. The possibility of renal cancer was considered high. An abdominal color ultrasound performed in our hospital showed mild hydrops in the left kidney and a substantial mass in the right kidney. The outpatient plan is to admit the "right kidney mass" to our department. Currently, he is in good spirits, has normal physical strength, normal appetite, normal sleep, demographic information has dropped by 3kg, normal urination, and normal stool. He is admitted to the hospital for further examination and treatment. Past history: Normally healthy, has a history of diabetes, denies a history of "hypertension", "coronary heart disease" and other diseases, denies a history of infectious diseases such as hepatitis, tuberculosis, malaria, has a history of nasal polyp surgery, denies a history of trauma, denies a history of blood transfusion, has penicillin Allergy history. There is no history of food allergies, and vaccinations are carried out locally.
S102：提取病情信息中的结构化文本与非结构化文本。S102: Extract structured text and unstructured text from condition information.
其中，结构化文本是指按照一定规则和格式组织的文本数据，具有明确的字段和预定义的数据结构。病情信息中的结构化文本可以包括：症状、疼痛、血常规检测结果、尿常规检测结果、影像学检查结果、病理学检查结果、既往手术史、既往病史、诊断结果和人口统计学信息等。Among them, structured text refers to text data organized according to certain rules and formats, with clear fields and predefined data structures. The structured text in the condition information can include: symptoms, pain, routine blood test results, routine urine test results, imaging test results, pathology test results, past surgical history, past medical history, diagnosis results and demographic information, etc.
其中，非结构化文本是指没有明确定义的字段和数据结构的文本数据。Among them, unstructured text refers to text data without clearly defined fields and data structures.
在一种可能的实施方式中，S102具体为：In a possible implementation, S102 is specifically:
通过基于自然语言处理技术的文本分类模型，提取病情信息中的结构化文本与非结构化文本。Through a text classification model based on natural language processing technology, structured text and unstructured text in disease information are extracted.
S103：计算与各个历史病历的结构化文本匹配度。S103: Calculate the matching degree of structured text with each historical medical record.
具体而言，可以采用文本相似度算法，如余弦相似度、Jaccard相似度、编辑距离等，对结构化文本和目标文本进行相似度比较。这些算法可以根据文本的语义和语法特征，计算出文本之间的相似程度。Specifically, text similarity algorithms, such as cosine similarity, Jaccard similarity, edit distance, etc., can be used to compare the similarity between structured text and target text. These algorithms can calculate the degree of similarity between texts based on their semantic and grammatical features.
在一种可能的实施方式中，S103具体包括：In a possible implementation, S103 specifically includes:
S1031：计算与各个历史病历的症状匹配度sim1、疼痛匹配度sim2、血常规检测结果匹配度sim3、尿常规检测结果匹配度sim4、影像学检查匹配度sim5、病理学检查匹配度sim6、既往手术史匹配度sim7、既往病史匹配度sim8、诊断结果匹配度sim9和人口统计学信息匹配度sim10：S1031: Calculate the symptom matching degreesim1 , pain matching degreesim2 , blood routine test result matching degree sim3 , urine routine test result matching degreesim4 , imaging examination matching degreesim5 ,and pathological examination matching with each historical medical record Degreesim6 , past surgical history matching degreesim7 , past medical history matching degreesim8 , diagnosis result matching degreesim9 and demographic information matching degreesim10 :
其中，。in, .
S1032：根据症状匹配度sim1、疼痛匹配度sim2、血常规检测结果匹配度sim3、尿常规检测结果匹配度sim4、影像学检查匹配度sim5、病理学检查匹配度sim6、既往手术史匹配度sim7、既往病史匹配度sim8、诊断结果匹配度sim9和人口统计学信息匹配度sim10以及权重，计算结构化文本匹配度sima：S1032: According to the symptom matching degreesim1 , the pain matching degreesim2 , the blood routine test result matching degreesim3 , the urine routine test result matching degreesim4 , the imaging examination matching degreesim5 , the pathology examination matching degreesim6 , and the past The matching degree of surgical historysim7 , the matching degree of past medical historysim8 , the matching degree of diagnosis resultssim9 and the matching degree of demographic informationsim10 as well as the weights are used to calculate the structured text matching degreesima :
其中，αi表示不同文本匹配度的权重。Among them,αi represents the weight of different text matching degrees.
其中，权重是指不同文本匹配度在计算结构化文本匹配度过程中的重要性。举例来说，根据对疾病特征的了解和治疗的重要性，可以给予症状匹配度、检测结果匹配度等较高的权重，而给予既往病史匹配度较低的权重。Among them, weight refers to the importance of different text matching degrees in the process of calculating structured text matching degrees. For example, based on the understanding of disease characteristics and the importance of treatment, higher weights can be given to symptom matching, test result matching, etc., while lower weighting can be given to past medical history matching.
在本发明中，通过计算结构化文本匹配度，可以将当前患者的病情信息与历史病历进行比对和匹配。这有助于找到与患者病情相似的过往病例，提供更准确的参考和借鉴，为制定诊疗方案提供依据。通过计算结构化文本匹配度，可以快速筛选出与患者病情相近的历史病历，缩小医生的搜索范围，节省时间和精力。这有助于提高医疗工作的效率，加速诊断和治疗过程，为患者提供更及时和有效的医疗服务。In the present invention, by calculating the matching degree of structured text, the current patient's condition information can be compared and matched with historical medical records. This helps to find past cases that are similar to the patient's condition, provides more accurate references and provides a basis for formulating diagnosis and treatment plans. By calculating the matching degree of structured text, you can quickly filter out historical medical records that are similar to the patient's condition, narrow the search scope of doctors, and save time and energy. This helps improve the efficiency of medical work, accelerates the diagnosis and treatment process, and provides patients with more timely and effective medical services.
在一种可能的实施方式中，S103还包括：In a possible implementation, S103 also includes:
S1033：通过以下方式确定不同文本匹配度的权重αi：S1033: Determine the weightαi of different text matching degrees in the following way:
通过对症状匹配度、疼痛匹配度、血常规检测结果匹配度、尿常规检测结果匹配度、影像学检查匹配度、病理学检查匹配度、既往手术史匹配度、既往病史匹配度、诊断结果匹配度、和人口统计学信息匹配度进行两两比较，结合九级标度法，建立判别矩阵A：By matching the symptoms, pain, blood routine test results, urine routine test results, imaging examinations, pathology examinations, past surgical history, past medical history, and diagnosis results Degree, and matching degree of demographic information are compared in pairs, combined with the nine-level scaling method, to establish a discriminant matrixA :
其中，aij表示第i个文本匹配度相对于第j个文本匹配度的重要程度，aij的取值通过九极标度法确定，n=10。Among them,aij represents the importance of thei- th text matching degree relative to thej- th text matching degree. The value ofaij is determined by the nine-pole scaling method,n =10.
其中，九级标度法（Nine-Point Scale）是一种用于比较和评估对象或概念相对重要性、优劣或程度的量表方法。通常由一个包含九个等级的量表组成，每个等级用于表示不同的程度或程度。被评估者需要根据自己的感觉或认知，在这九个等级中选择一个最符合对第i个文本匹配度相对于第j个文本匹配度的重要程度的评价。Among them, the Nine-Point Scale is a scale method used to compare and evaluate the relative importance, merit, or degree of objects or concepts. Typically consists of a scale with nine levels, each level used to represent a different degree or degree. The evaluator needs to choose one of these nine levels based on his or her own feeling or cognition that is most consistent with the evaluation of the importance of thei- th text match relative to thej -th text match.
计算判别矩阵A的特征向量和特征值：Calculate the eigenvectors and eigenvalues of the discriminant matrixA :
其中，λ表示判别矩阵A的特征值，ω表示判别矩阵A的特征向量，取最大的特征值记为λmax，与最大的特征值对应的特征向量记为ωmax，。Among them,λ represents the eigenvalue of the discriminant matrixA ,ω represents the eigenvector of the discriminant matrixA , the largest eigenvalue is recorded asλmax , and the eigenvector corresponding to the largest eigenvalue is recorded asωmax , .
对最大的特征值对应的特征向量ωmax进行归一化处理：Normalize the eigenvectorωmax corresponding to the largest eigenvalue:
其中，归一化后的向量的各个分量/>分别代表各个文本匹配度的权重，分别记为α1、α2、…、αn。Among them, the normalized vector Each component of /> Represent the weight of each text matching degree, respectively, recorded asα1 ,α2 ,...,αn .
在本发明中，提供了一种系统化的方法来确定权重，基于准则间的两两比较和专家判断，可以考虑症状匹配度、疼痛匹配度、检测结果匹配度等多个因素，综合考虑它们的重要性，从而更全面地评估和比较不同文本匹配度的贡献，使决策过程更加客观和科学。通过权重的确定，可以减少主观偏见和随意性，提供可量化的依据进行决策。In the present invention, a systematic method is provided to determine the weight. Based on pairwise comparisons between criteria and expert judgment, multiple factors such as symptom matching, pain matching, and detection result matching can be considered, and they are comprehensively considered importance, thereby more comprehensively assessing and comparing the contributions of different text matching degrees, making the decision-making process more objective and scientific. Through the determination of weights, subjective bias and arbitrariness can be reduced and quantifiable basis can be provided for decision-making.
S104：计算与各个历史病历的非结构化文本匹配度。S104: Calculate the matching degree of unstructured text with each historical medical record.
在一种可能的实施方式中，S104具体包括子步骤S1041至S1047：In a possible implementation, S104 specifically includes sub-steps S1041 to S1047:
S1041：构建基于循环神经网络的文本匹配模型。S1041: Build a text matching model based on recurrent neural network.
其中，文本匹配模型包括：输入层、状态层、注意力层、全连接层和匹配层。Among them, the text matching model includes: input layer, state layer, attention layer, fully connected layer and matching layer.
S1042：将各个非结构化文本组成单词向量序列[x1, x2,…,xm]。S1042: Combine each unstructured text into a word vector sequence [x1 ,x2 ,…,xm ].
S1043：在状态层中，计算单词向量在t时刻的隐状态：S1043: In the state layer, calculate the hidden state of the word vector at timet :
其中，表示前向循环的当前状态，/>表示后向循环的当前状态，GRU()表示经过循环神经网络的非线性计算，ut表示/>的权重系数，vt表示/>的权重系数，pt表示t时刻隐状态的偏置项。in, Represents the current status of the forward loop, /> represents the current state of the backward loop, GRU() represents the nonlinear calculation through the recurrent neural network,ut represents /> The weight coefficient of ,vt represents/> The weight coefficient of ,pt represents the bias term of the hidden state at timet .
S1044：在注意力层中，为每个单词向量分配权重γ，并进行累加得到当前注意力层的隐状态st：S1044: In the attention layer, assign a weightγ to each word vector, and accumulate it to obtain the hidden statest of the current attention layer:
。 .
S1045：输出单词向量的特征值O：S1045: Output the eigenvalueO of the word vector:
。 .
S1046：在全连接层中，汇聚单词向量的特征值。S1046: In the fully connected layer, aggregate the feature values of word vectors.
S1047：在匹配层中，通过余弦相似度计算非结构化文本匹配度simb：S1047: In the matching layer, the unstructured text matching degreesimb is calculated through cosine similarity:
其中，B表示患者的病情信息中的非结构化文本，C表示各个历史病历中的非结构化文本，OB表示患者的病情信息中的非结构化文本的特征值，OC表示各个历史病历中的非结构化文本的特征值。Among them,B represents the unstructured text in the patient's condition information,C represents the unstructured text in each historical medical record,OB represents the feature value of the unstructured text in the patient's condition information, andOC represents each historical medical record. Characteristic values of unstructured text in .
需要说明的是，基于循环神经网络的非结构化文本匹配模型能够通过学习文本序列的特征和上下文信息，引入注意力机制，建立文本特征表示，并通过余弦相似度计算匹配度，从而提高非结构化文本的匹配性能和准确性。这样的模型可以在匹配非结构化文本任务中发挥重要作用，并提供更精确的结果和更好的匹配结果。It should be noted that the unstructured text matching model based on recurrent neural networks can learn the characteristics and contextual information of text sequences, introduce an attention mechanism, establish text feature representation, and calculate the matching degree through cosine similarity, thereby improving unstructured text matching. optimized text matching performance and accuracy. Such models can play an important role in the task of matching unstructured text and provide more accurate results and better matching results.
S105：根据结构化文本匹配度和非结构化文本匹配度，计算与各个历史病历的综合匹配度：S105: Calculate the comprehensive matching degree with each historical medical record based on the matching degree of structured text and the matching degree of unstructured text. :
其中，η表示结构化文本匹配度sima的权重系数，1-η表示非结构化文本匹配度simb的权重系数。Among them,eta represents the weight coefficient of the structured text matching degreesima , and 1-eta represents the weight coefficient of the unstructured text matching degreesimb .
其中，本领域技术人员可以根据实际情况设置结构化文本匹配度sima的权重的η大小，本发明不做限定。如果在实践中发现结构化文本的匹配度更重要，则可以增加结构化文本的权重系数，以更大程度地反映其对综合匹配度的影响。这种灵活性和可调节性使得方法可以适应不同的应用场景和病情特点。Among them, those skilled in the art can set the sizeη of the weight of the structured text matching degreesima according to the actual situation, which is not limited by the present invention. If the matching degree of structured text is found to be more important in practice, the weight coefficient of structured text can be increased to reflect its impact on the comprehensive matching degree to a greater extent. This flexibility and adjustability allows the method to be adapted to different application scenarios and disease characteristics.
在本发明中，结构化文本和非结构化文本都可以提供病情信息的重要方面。通过综合考虑两者的匹配度，可以更全面地评估历史病历与当前患者病情的相似程度。结构化文本包括具体的指标和数值，非结构化文本则包含更多的描述性信息，通过权衡两者的贡献，综合匹配度可以更准确地反映历史病历与患者病情的匹配程度。可以提高医疗决策的可靠性和精确性，为医生提供更好的参考和支持，促进个性化和精准的诊疗方案的确定。In the present invention, both structured text and unstructured text can provide important aspects of condition information. By comprehensively considering the match between the two, a more comprehensive assessment can be made of how similar the historical medical records are to the current patient's condition. Structured text includes specific indicators and values, while unstructured text contains more descriptive information. By weighing the contributions of the two, the comprehensive matching degree can more accurately reflect the degree of matching between historical medical records and the patient's condition. It can improve the reliability and accuracy of medical decision-making, provide doctors with better reference and support, and promote the determination of personalized and accurate diagnosis and treatment plans.
S106：挑选综合匹配度最高的预设数量的历史病历，生成备选诊疗方案。S106: Select the preset number of historical medical records with the highest comprehensive matching degree and generate alternative diagnosis and treatment plans.
其中，预设数量可以是10个，本发明对于预设数量的具体数值不做限定。The preset number may be 10, and the present invention does not limit the specific value of the preset number.
具体而言，可以挑选出综合匹配度最高的历史病历中的诊疗方案，汇总到一起生成备选诊疗方案。Specifically, the diagnosis and treatment plans in the historical medical records with the highest comprehensive matching degree can be selected and summarized together to generate alternative diagnosis and treatment plans.
S107：推送所述备选诊疗方案，根据备选诊疗方案，挑选出诊疗方案。S107: Push the alternative diagnosis and treatment plan, and select the diagnosis and treatment plan based on the alternative diagnosis and treatment plan.
具体而言，医师可以通过在阅读推送的备选诊疗方案之后，挑选出最符合当前病情的诊疗方案，在诊疗方案输入界面进行自动化填充，无需手动打字，减少因手动输入错误而引起的潜在问题，节省医师时间，提升诊疗效率。另一方面，即使是面对疑难病情，也可以将历史病历作为参考信息，避免陷入主观判断，提升诊疗准确性。Specifically, doctors can select the diagnosis and treatment plan that best suits the current condition after reading the pushed alternative diagnosis and treatment plans, and automatically fill in the diagnosis and treatment plan input interface without manual typing, reducing potential problems caused by manual input errors. , save doctors time and improve diagnosis and treatment efficiency. On the other hand, even when facing difficult conditions, historical medical records can be used as reference information to avoid subjective judgment and improve the accuracy of diagnosis and treatment.
S108：根据病情信息以及对应的诊疗方案，生成电子病历。S108: Generate an electronic medical record based on the condition information and the corresponding diagnosis and treatment plan.
具体而言，将患者的个人信息、病史记录、体格检查记录、血常规检查记录、尿常规检查记录、影像学检查记录、诊断记录、诊疗方案和随访记录生成电子病历。Specifically, the patient's personal information, medical history records, physical examination records, routine blood examination records, routine urine examination records, imaging examination records, diagnosis records, diagnosis and treatment plans and follow-up records are generated into an electronic medical record.
S109：对电子病历进行脱敏处理。S109: Desensitize electronic medical records.
具体而言，可以将患者的姓名、身份证号码、地址、电话号码等个人身份信息从电子病历中删除或替换为脱敏标识，如用匿名编码或虚拟标识符代替。还可以将电子病历中的日期和时间信息进行脱敏处理，可以对日期进行模糊化处理，如仅保留年份或将具体日期替换为通用日期。Specifically, the patient's name, ID number, address, phone number and other personally identifiable information can be deleted from the electronic medical record or replaced with a desensitized identifier, such as an anonymous code or virtual identifier. Date and time information in electronic medical records can also be desensitized, and dates can be blurred, such as retaining only the year or replacing specific dates with universal dates.
为了更全面、更准确地进行脱敏处理，在一种可能的实施方式中， S109具体包括：In order to perform desensitization processing more comprehensively and accurately, in a possible implementation, S109 specifically includes:
S1091：将电子病历中的文本组成单词向量序列。S1091: Form text in electronic medical records into a sequence of word vectors.
S1092：通过文本匹配模型输出单词向量的特征值。S1092: Output the feature value of the word vector through the text matching model.
需要说明的是，在本发明中，文本匹配模型一方面可以用于计算非结构化文本的匹配度，另一方面也可以用于对电子病历进行脱敏处理。It should be noted that in the present invention, the text matching model can be used to calculate the matching degree of unstructured text on the one hand, and can also be used to desensitize electronic medical records on the other hand.
S1093：通过余弦相似度计算电子病历中的文本与敏感词数据库中的各个敏感词的敏感词匹配度simc：S1093: Calculate the sensitive word matching degreesimc between the text in the electronic medical record and each sensitive word in the sensitive word database through cosine similarity:
其中，D表示电子病历中的文本，E表示敏感词数据库中的各个敏感词，OD表示电子病历中的文本的特征值，OE表示敏感词数据库中的各个敏感词的特征值。Among them,D represents the text in the electronic medical record,E represents each sensitive word in the sensitive word database,OD represents the feature value of the text in the electronic medical record, andOE represents the feature value of each sensitive word in the sensitive word database.
S1094：当电子病历中的目标文本与敏感词数据库中的敏感词的敏感词匹配度simc大于预设匹配度的情况下，对目标文本进行隐私保护处理。S1094: When the sensitive word matching degreesimc between the target text in the electronic medical record and the sensitive words in the sensitive word database is greater than the preset matching degree, perform privacy protection processing on the target text.
需要说明的是，余弦相似度计算是一种简单且高效的计算方法，能够在较短的时间内完成匹配度的计算，通过余弦相似度计算电子病历中的文本与敏感词数据库中的各个敏感词的敏感词匹配度，可以获得准确的敏感词匹配度，提高脱敏处理的效率，适用于大规模的电子病历数据处理，进而将敏感词匹配度大于预设匹配度的目标文本进行脱敏处理，有效保护患者的个人隐私和敏感信息，确保这些信息不被未经授权的人员或机构访问、使用或泄露。It should be noted that cosine similarity calculation is a simple and efficient calculation method that can complete the calculation of matching degree in a short time. Cosine similarity is used to calculate the text in the electronic medical record and each sensitive word in the sensitive word database. Sensitive word matching of words can obtain accurate sensitive word matching, improve the efficiency of desensitization processing, and is suitable for large-scale electronic medical record data processing, and then desensitize target texts whose sensitive word matching degree is greater than the preset matching degree. Process and effectively protect patients' personal privacy and sensitive information to ensure that this information is not accessed, used or disclosed by unauthorized persons or institutions.
在一种可能的实施方式中，S1094具体为：In a possible implementation, S1094 is specifically:
当电子病历中的目标文本与敏感词数据库中的敏感词的敏感词匹配度simc大于预设匹配度的情况下，对目标文本进行隐藏、删除或者替换为*号。When the sensitive word matching degreesimc between the target text in the electronic medical record and the sensitive words in the sensitive word database is greater than the preset matching degree, the target text is hidden, deleted, or replaced with an * symbol.
其中，通过隐藏、删除或替换敏感词，可以有效保护电子病历中的敏感信息，防止敏感数据的泄露。这有助于遵守隐私保护法规和医疗保密要求，确保患者的隐私权利得到保护。Among them, by hiding, deleting or replacing sensitive words, sensitive information in electronic medical records can be effectively protected and the leakage of sensitive data can be prevented. This helps comply with privacy regulations and medical confidentiality requirements, ensuring patients' privacy rights are protected.
S110：生成私钥和公钥。S110: Generate private key and public key.
在一种可能的实施方式中，S110具体包括子步骤S1101至S1104：In a possible implementation, S110 specifically includes sub-steps S1101 to S1104:
S1101：选择两个大素数a和b，计算以及/>：S1101: Select two large prime numbersa andb and calculate and/> :
S1102：随机选择一个整数e，使得随机数e满足：S1102: Randomly select an integere so that the random numbere satisfies:
其中，表示随机数e与/>互质。in, Represents the random numbere and/> Relatively prime.
S1103：计算随机数e的逆元：S1103: Calculate the inverse element of the random numbere :
S1104：将(G,e)作为私钥，将(G,d)作为公钥。S1104: Use (G ,e ) as the private key and (G ,d ) as the public key.
需要说明的是，使用上述方法生成私钥和公钥可以提供安全的加密和身份验证机制，保护敏感数据的机密性和完整性，并确保只有经过授权的人可以访问和操作电子病历。It should be noted that using the above method to generate private and public keys can provide a secure encryption and authentication mechanism, protect the confidentiality and integrity of sensitive data, and ensure that only authorized people can access and operate electronic medical records.
在一种可能的实施方式中，S110还包括子步骤S1105：In a possible implementation, S110 also includes sub-step S1105:
S1105：构建关于随机数e和逆元d的混沌映射关系式：S1105: Construct a chaotic mapping relationship between the random numbere and the inverse elementd :
其中，k表示验证次数，λ1、λ2、λ3、λ4和λ5表示控制参数且均为常数。Among them,k represents the number of verifications,λ1 ,λ2 ,λ3 ,λ4 andλ5 represent control parameters and are all constants.
需要说明的是，混沌映射关系式的作用是为了保护随机数e和逆元d，在后续的每一次验证中，随机数e和逆元d均会发生变化。现有技术中的混沌映射关系式，现有的二维混沌映射存在混沌参数范围不连续，参数空间中存在许多周期窗口，混沌行为较脆弱，当参数受到干扰时，会出现混沌行为很容易消失，发生混沌退化的问题。而本发明首先初始化两个参数多项式，然后通过模运算将任意值折叠到一个固定的范围内，最后从非线性多项式生成混沌映射，生成具有鲁棒混沌性的二维混沌映射，弥补了现有混沌映射关系式中存在的缺点。It should be noted that the role of the chaotic mapping relationship is to protect the random numbere and inverse elementd . In each subsequent verification, the random numbere and inverse elementd will change. Chaos mapping relational expression in the existing technology. The existing two-dimensional chaotic mapping has a discontinuous range of chaotic parameters. There are many periodic windows in the parameter space. The chaotic behavior is relatively fragile. When the parameters are disturbed, the chaotic behavior will easily disappear. , the problem of chaotic degradation occurs. The present invention first initializes two parameter polynomials, then folds any value into a fixed range through modular operation, and finally generates a chaotic map from the nonlinear polynomial to generate a two-dimensional chaotic map with robust chaos, which makes up for the existing problems. Shortcomings in the chaotic mapping relationship.
S111：利用公钥对脱敏后的电子病历进行加密并上传到云端。S111: Use the public key to encrypt the desensitized electronic medical record and upload it to the cloud.
S112：接收用户向云端发起的查阅请求。S112: Receive the query request initiated by the user to the cloud.
其中，用户可以从电脑、手机、平板电脑等各种客户端向云端发起查阅请求。Among them, users can initiate search requests to the cloud from various clients such as computers, mobile phones, tablets, etc.
其中，用户可以是患者、医师等，甚至是其他互联网医疗机构的医师。Among them, users can be patients, doctors, etc., or even doctors from other Internet medical institutions.
S113：验证用户的私钥，当用户的身份验证通过的情况下，展示脱敏后的电子病历。S113: Verify the user's private key. When the user's identity verification passes, display the desensitized electronic medical record.
需要说明的是，验证私钥的过程，是上述加密过程的逆过程，为避免重复，本发明不再限定。It should be noted that the process of verifying the private key is the reverse process of the above-mentioned encryption process, and is no longer limited in the present invention to avoid duplication.
与现有技术相比，本发明至少具有以下有益技术效果：Compared with the prior art, the present invention at least has the following beneficial technical effects:
（1）在本发明中，根据患者的病情信息，从历史病历库中自动匹配出匹配度较高的历史病历，将匹配度较高的历史病历的诊疗方案作为备选诊疗方案，进而医师可以根据备选诊疗方案挑选出最终的诊疗方案。一方面，当备选诊疗方案中存在合适的诊疗方案时，医师可以直接选择其作为最终的诊疗方案，无需手动打字，减少因手动输入错误而引起的潜在问题，节省医师时间，提升诊疗效率。另一方面，即使是面对疑难病情，也可以将历史病历作为参考信息，避免陷入主观判断，提升诊疗准确性。(1) In the present invention, according to the patient's condition information, historical medical records with a higher matching degree are automatically matched from the historical medical record database, and the diagnosis and treatment plans of the historical medical records with a higher matching degree are used as alternative diagnosis and treatment plans, so that doctors can Select the final diagnosis and treatment plan based on the alternative diagnosis and treatment plans. On the one hand, when there is a suitable diagnosis and treatment plan among the alternative diagnosis and treatment plans, the doctor can directly select it as the final diagnosis and treatment plan without manual typing, which reduces potential problems caused by manual input errors, saves the doctor's time, and improves the efficiency of diagnosis and treatment. On the other hand, even when facing difficult conditions, historical medical records can be used as reference information to avoid subjective judgment and improve the accuracy of diagnosis and treatment.
（2）在本发明中，可以对患者的电子病历进行脱敏处理，保护患者的隐私和敏感信息，并提高数据的安全性。(2) In the present invention, the patient's electronic medical record can be desensitized, protecting the patient's privacy and sensitive information, and improving data security.
（3）在本发明中，可以利用公钥对脱敏后的电子病历进行加密，当用户的身份验证通过时，才有权限查阅电子病历，进一步地保障患者的电子病历在共享的过程中的信息安全，有效保护患者的隐私和敏感信息，降低数据泄露风险。(3) In the present invention, the public key can be used to encrypt the desensitized electronic medical record. Only when the user's identity verification is passed, the user has the authority to view the electronic medical record, further ensuring the patient's electronic medical record during the sharing process. Information security effectively protects patients’ privacy and sensitive information and reduces the risk of data leakage.
实施例2Example 2
在一个实施例中，本发明提供的一种基于互联网医疗的电子病历传输系统，用于执行实施例1中的基于互联网诊疗的电子病历处理方法。In one embodiment, the present invention provides an electronic medical record transmission system based on Internet medical care, which is used to execute the electronic medical record processing method based on Internet diagnosis and treatment in Embodiment 1.
本发明提供的一种基于互联网医疗的电子病历传输系统可以实现上述实施例1中的基于互联网诊疗的电子病历处理方法的步骤和效果，为避免重复，本发明不再赘述。The electronic medical record transmission system based on Internet medical treatment provided by the present invention can realize the steps and effects of the electronic medical record processing method based on Internet diagnosis and treatment in the above-mentioned Embodiment 1. To avoid duplication, the present invention will not describe them in detail.
与现有技术相比，本发明至少具有以下有益技术效果：Compared with the prior art, the present invention at least has the following beneficial technical effects:
（1）在本发明中，根据患者的病情信息，从历史病历库中自动匹配出匹配度较高的历史病历，将匹配度较高的历史病历的诊疗方案作为备选诊疗方案，进而医师可以根据备选诊疗方案挑选出最终的诊疗方案。一方面，当备选诊疗方案中存在合适的诊疗方案时，医师可以直接选择其作为最终的诊疗方案，无需手动打字，减少因手动输入错误而引起的潜在问题，节省医师时间，提升诊疗效率。另一方面，即使是面对疑难病情，也可以将历史病历作为参考信息，避免陷入主观判断，提升诊疗准确性。(1) In the present invention, according to the patient's condition information, historical medical records with a higher matching degree are automatically matched from the historical medical record database, and the diagnosis and treatment plans of the historical medical records with a higher matching degree are used as alternative diagnosis and treatment plans, so that doctors can Select the final diagnosis and treatment plan based on the alternative diagnosis and treatment plans. On the one hand, when there is a suitable diagnosis and treatment plan among the alternative diagnosis and treatment plans, the doctor can directly select it as the final diagnosis and treatment plan without manual typing, which reduces potential problems caused by manual input errors, saves the doctor's time, and improves the efficiency of diagnosis and treatment. On the other hand, even when facing difficult conditions, historical medical records can be used as reference information to avoid subjective judgment and improve the accuracy of diagnosis and treatment.
（2）在本发明中，可以对患者的电子病历进行脱敏处理，保护患者的隐私和敏感信息，并提高数据的安全性。(2) In the present invention, the patient's electronic medical record can be desensitized, protecting the patient's privacy and sensitive information, and improving data security.
（3）在本发明中，可以利用公钥对脱敏后的电子病历进行加密，当用户的身份验证通过时，才有权限查阅电子病历，进一步地保障患者的电子病历在共享的过程中的信息安全，有效保护患者的隐私和敏感信息，降低数据泄露风险。(3) In the present invention, the public key can be used to encrypt the desensitized electronic medical record. Only when the user's identity verification is passed, the user has the authority to view the electronic medical record, further ensuring the security of the patient's electronic medical record during the sharing process. Information security effectively protects patients’ privacy and sensitive information and reduces the risk of data leakage.
以上实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。The technical features of the above embodiments can be combined in any way. To simplify the description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, all possible combinations should be used. It is considered to be within the scope of this manual.
以上实施例仅表达了本发明的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对发明专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本发明构思的前提下，还可以做出若干变形和改进，这些都属于本发明的保护范围。因此，本发明专利的保护范围应以所附权利要求为准。The above embodiments only express several embodiments of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention. It should be noted that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the scope of protection of the patent of the present invention should be determined by the appended claims.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310930499.5ACN116646046B (en) | 2023-07-27 | 2023-07-27 | An electronic medical record processing method and system based on Internet diagnosis and treatment |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310930499.5ACN116646046B (en) | 2023-07-27 | 2023-07-27 | An electronic medical record processing method and system based on Internet diagnosis and treatment |
| Publication Number | Publication Date |
|---|---|
| CN116646046A CN116646046A (en) | 2023-08-25 |
| CN116646046Btrue CN116646046B (en) | 2023-11-17 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310930499.5AActiveCN116646046B (en) | 2023-07-27 | 2023-07-27 | An electronic medical record processing method and system based on Internet diagnosis and treatment |
| Country | Link |
|---|---|
| CN (1) | CN116646046B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116828002A (en)* | 2023-08-29 | 2023-09-29 | 北京南天智联信息科技股份有限公司 | Data processing method and system based on Internet of things data center |
| CN117058748B (en)* | 2023-09-07 | 2024-09-24 | 杭州励普科技有限公司 | Electronic document reading method and system based on deep reading identification |
| CN117591643B (en)* | 2023-11-10 | 2024-05-10 | 杭州市余杭区数据资源管理局 | Project text duplicate checking method and system based on improved structuring processing |
| CN117892358B (en)* | 2024-03-18 | 2024-07-05 | 北方健康医疗大数据科技有限公司 | Verification method and system for limited data desensitization method |
| CN119623479B (en)* | 2025-02-17 | 2025-06-10 | 北京凯普顿医药科技开发有限公司 | A cardiovascular disease assessment and management method and system based on big data |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881463A (en)* | 2015-05-22 | 2015-09-02 | 清华大学深圳研究生院 | Reference medical record search method and device based on structural medical record database |
| WO2018120447A1 (en)* | 2016-12-28 | 2018-07-05 | 北京搜狗科技发展有限公司 | Method, device and equipment for processing medical record information |
| CN109698018A (en)* | 2018-12-24 | 2019-04-30 | 广州天鹏计算机科技有限公司 | Medical text handling method, device, computer equipment and storage medium |
| CN112768082A (en)* | 2021-02-04 | 2021-05-07 | 常熟和医信息技术有限公司 | Method for automatically giving disease diagnosis and treatment scheme according to electronic medical record text |
| CN112837770A (en)* | 2021-01-21 | 2021-05-25 | 北京理工大学 | A privacy-preserving similar medical record query method in a large-scale electronic medical system |
| CN113361230A (en)* | 2021-05-27 | 2021-09-07 | 重庆南鹏人工智能科技研究院有限公司 | Method for carrying out electronic medical record diagnosis and treatment quality control based on clinical diagnosis and treatment guideline |
| CN116168794A (en)* | 2023-04-23 | 2023-05-26 | 成都本千医疗科技有限公司 | Big data supervision's electronic medical record collection management platform |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881463A (en)* | 2015-05-22 | 2015-09-02 | 清华大学深圳研究生院 | Reference medical record search method and device based on structural medical record database |
| WO2018120447A1 (en)* | 2016-12-28 | 2018-07-05 | 北京搜狗科技发展有限公司 | Method, device and equipment for processing medical record information |
| CN109698018A (en)* | 2018-12-24 | 2019-04-30 | 广州天鹏计算机科技有限公司 | Medical text handling method, device, computer equipment and storage medium |
| CN112837770A (en)* | 2021-01-21 | 2021-05-25 | 北京理工大学 | A privacy-preserving similar medical record query method in a large-scale electronic medical system |
| CN112768082A (en)* | 2021-02-04 | 2021-05-07 | 常熟和医信息技术有限公司 | Method for automatically giving disease diagnosis and treatment scheme according to electronic medical record text |
| CN113361230A (en)* | 2021-05-27 | 2021-09-07 | 重庆南鹏人工智能科技研究院有限公司 | Method for carrying out electronic medical record diagnosis and treatment quality control based on clinical diagnosis and treatment guideline |
| CN116168794A (en)* | 2023-04-23 | 2023-05-26 | 成都本千医疗科技有限公司 | Big data supervision's electronic medical record collection management platform |
| Publication number | Publication date |
|---|---|
| CN116646046A (en) | 2023-08-25 |
| Publication | Publication Date | Title |
|---|---|---|
| CN116646046B (en) | An electronic medical record processing method and system based on Internet diagnosis and treatment | |
| US12216799B2 (en) | Systems and methods for computing with private healthcare data | |
| EP2365458B1 (en) | A computer implemented method for determining the presence of a disease in a patient | |
| CN109314641B (en) | System and method for verifying and performing operations on homomorphic encrypted data | |
| Durham et al. | Quantifying the correctness, computational complexity, and security of privacy-preserving string comparators for record linkage | |
| KR102113806B1 (en) | Method and system for managing personal medical information data | |
| US20230148326A1 (en) | Systems and methods for de-identifying patient data | |
| US20130332195A1 (en) | System and methods for epidemiological data collection, management and display | |
| US9529968B2 (en) | System and method of integrating mobile medical data into a database centric analytical process, and clinical workflow | |
| CN110875093A (en) | Treatment scheme processing method, device, equipment and storage medium | |
| EP4115314B1 (en) | Systems and methods for computing with private healthcare data | |
| US20240143838A1 (en) | Apparatus and a method for anonymizing user data | |
| US12073930B1 (en) | Apparatus and a method for generating a user report | |
| US20110125646A1 (en) | Methods and systems for managing personal health records by individuals | |
| Stolba et al. | The security issue of federated data warehouses in the area of evidence-based medicine | |
| WO2021236520A1 (en) | Method and system for detection of waste, fraud, and abuse in information access using cognitive artificial intelligence | |
| CN111814169B (en) | Digestive tract disease data encryption obtaining method and risk prediction system | |
| Deepa et al. | A novel electronic medical record design using cryptography and steganography techniques | |
| WO2016203752A1 (en) | Information processing device, information processing method, and storage medium | |
| Patel et al. | Privacy preservation for big data healthcare management | |
| Bangare et al. | Smart Health Care System using Blockchain and Machine Learning | |
| Bywar et al. | Applications of AI and Blockchain in Healthcare | |
| JP4622462B2 (en) | Information processing system, information processing apparatus, information processing method, and computer program | |
| CN111209407A (en) | Data processing method and device, electronic equipment and computer readable storage medium | |
| TWI858927B (en) | Systems and methods for implementing medical data exchange and claims settlement |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |