Movatterモバイル変換


[0]ホーム

URL:


CN120432174B - An artificial intelligence-based tumor nursing service management system - Google Patents

An artificial intelligence-based tumor nursing service management system

Info

Publication number
CN120432174B
CN120432174BCN202510948624.4ACN202510948624ACN120432174BCN 120432174 BCN120432174 BCN 120432174BCN 202510948624 ACN202510948624 ACN 202510948624ACN 120432174 BCN120432174 BCN 120432174B
Authority
CN
China
Prior art keywords
nursing
abnormal
medication
drug
time
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202510948624.4A
Other languages
Chinese (zh)
Other versions
CN120432174A (en
Inventor
彭银
张萱
吴师容
颜仁兴
李瑶
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Sichuan Cancer Hospital
Original Assignee
Sichuan Cancer Hospital
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Sichuan Cancer HospitalfiledCriticalSichuan Cancer Hospital
Priority to CN202510948624.4ApriorityCriticalpatent/CN120432174B/en
Publication of CN120432174ApublicationCriticalpatent/CN120432174A/en
Application grantedgrantedCritical
Publication of CN120432174BpublicationCriticalpatent/CN120432174B/en
Activelegal-statusCriticalCurrent
Anticipated expirationlegal-statusCritical

Links

Landscapes

Abstract

Translated fromChinese

本发明涉及肿瘤护理技术领域,具体为一种基于人工智能的肿瘤护理服务管理系统,系统包括用药检测模块、联合用药模块、体征识别模块、动作推送模块和资源调度模块,基于肿瘤患者每日用药数据,分析药品名称、服用剂量和服药时间,比较实际与标准剂量差异。本发明,通过自动分析患者连续用药模式、体征变化以及实时实验室监测数据,融合多源健康参数完成动态归集与联动判断,实现风险因素高频识别与敏感体征波动监控,及时生成干预措施推送信息,优化护理任务响应流程,借助多维数据融合与智能任务排序,实现患者风险管理与护理资源调度的精准匹配,从而推进肿瘤护理全过程的数据闭环和干预闭环,加强了护理决策的主动性与适应性。

The present invention relates to the field of tumor nursing technology, specifically an artificial intelligence-based tumor nursing service management system, the system includes a medication detection module, a combined medication module, a vital sign recognition module, an action push module and a resource scheduling module. Based on the daily medication data of tumor patients, the system analyzes the drug name, dosage and medication time, and compares the actual and standard dosage differences. The present invention automatically analyzes the patient's continuous medication pattern, vital sign changes and real-time laboratory monitoring data, integrates multi-source health parameters to complete dynamic aggregation and linkage judgment, realizes high-frequency identification of risk factors and monitoring of sensitive vital sign fluctuations, timely generates intervention measures push information, optimizes the nursing task response process, and uses multi-dimensional data fusion and intelligent task sorting to achieve accurate matching of patient risk management and nursing resource scheduling, thereby promoting the data closed loop and intervention closed loop of the entire tumor nursing process and enhancing the initiative and adaptability of nursing decision-making.

Description

Tumor care service management system based on artificial intelligence
Technical Field
The invention relates to the technical field of tumor care, in particular to an artificial intelligence-based tumor care service management system.
Background
The tumor nursing field relates to health management, risk assessment, nursing intervention, symptom monitoring, follow-up management information integration and the like of a tumor patient in the whole process of diagnosis, treatment and rehabilitation, covers multidimensional nursing requirements of physiological psychosociety, behaviors and the like of the tumor patient, and is an important basis for realizing full life cycle health management and personalized nursing service of the tumor patient. The traditional tumor nursing service management system is used for nursing management activities such as patient information collection, illness state tracking nursing, risk assessment data recording, nursing scheme recommendation analysis, follow-up visit scheduling and the like by utilizing a manual input mode, common modes comprise paper medical record, manual registration, electronic form information input, rule-based data query, early warning tools and the like, the modes are mainly based on manual experience, and nursing staff is mainly relied on to regularly evaluate and process health and nursing requirements of patients.
The traditional technology adopts manual collection and information dispersion registration more, is difficult to support real-time linkage of health data and overall process risk management and control, has data fault between nursing risk index and patient state monitoring link, is easy to miss key information or delay abnormal response in the state of illness change stage, and when encountering frequent fluctuation of patient physical signs or adjustment of medication scheme, traditional means is difficult to coordinate nursing task and manpower arrangement rapidly, and influence intervention timeliness and service continuity of high-risk patients.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides an artificial intelligence-based tumor care service management system.
In order to achieve the purpose, the invention adopts the following technical scheme that the tumor care service management system based on artificial intelligence comprises:
The medicine detection module analyzes the medicine name, the medicine taking dosage and the medicine taking time based on the daily medicine taking data of a tumor patient, compares the actual and standard dosage differences, calculates the difference between the medicine taking interval and the medicine metabolism interval, judges risk characteristics and obtains offset medicine characteristics;
Based on the deviation medication characteristics, the combined medication module compares the sequence of the medicine combination with adverse reaction time, screens the combination with coincident existing time, analyzes the reference range detected by a laboratory, and counts the risk group to obtain the medicine risk superposition amount;
The physical sign recognition module compares the nursing stage of the patient with the risk information based on the drug risk superposition quantity, collects daily physiological data, judges the variation amplitude of physical sign parameters and stage standards, analyzes the accumulated fluctuation condition and obtains the abnormal concentration rate of physical signs;
And the action pushing module screens the sign with high fluctuation frequency based on the sign abnormal concentration rate, analyzes the combined performance of the sign, blood oxygen and respiratory frequency, judges whether the action is a respiratory intervention event, identifies the corresponding nursing action and obtains the intervention action instruction sequence number.
The invention is improved in that the offset medication characteristics comprise a dosage offset type, a medication interval type and a medicine early warning mark, the medicine risk superposition amount comprises a joint risk level, an adverse reaction mark and a laboratory abnormal item, the physical sign abnormal concentration rate comprises a sensitive physical sign group, a stage abnormal expression and a continuous fluctuation record, and the intervention action instruction sequence number comprises a task action number, an intervention type label and a nursing response mode.
The invention improves, the said medicine detection module includes:
the dose difference judging submodule is used for comparing actual taken doses with standard doses of medicines based on daily medication data of tumor patients, judging whether the dose difference of each medicine exceeds a safe reference range or not, screening medicine combinations with abnormal doses, and obtaining abnormal total dose difference;
the interval time comparison submodule calculates interval time of taking the same medicine twice continuously based on the dose difference abnormal total amount, compares actual interval with medicine suggestion interval, judges whether the condition exceeding a reference range exists or not, and counts accumulated condition of medicine interval abnormality to obtain interval time offset frequency;
and the offset characteristic generation submodule extracts corresponding medicine names based on the interval time offset frequency, performs combination association with the abnormal indexes to obtain combined abnormal response intensity, and extracts medicine combinations with high occurrence frequency and concentrated numerical amplitude to obtain offset medication characteristics.
The invention improves, the combined medication module includes:
The time sequence comparison sub-module analyzes the medicine name and the medicine taking time sequence based on the offset medicine characteristics, compares the actual medicine taking sequence of each medicine combination with the time sequence of occurrence of adverse reaction, identifies the combination of the actual medicine taking and the adverse reaction in time association, judges whether the combination has a rule, and obtains a time sequence coincidence group sequence;
Based on the time sequence coincidence group sequence, the risk linkage submodule analyzes laboratory detection results combined in the same medication period, compares the medication time of the medicine combination with synchronous occurrence of detection abnormality, and counts coincidence frequency in the same period to obtain risk coupling item frequency;
and the abnormal co-occurrence sub-module calculates an abnormal co-occurrence amplitude measurement according to the risk coupling item frequency, sorts the abnormal co-occurrence amplitude measurement according to each combination, and screens the combination with the optimal co-occurrence degree to obtain the drug risk superposition quantity.
The invention improves, the sign recognition module includes:
the stage reference contrast submodule analyzes physiological data of a tumor patient in a current nursing stage based on the drug risk superposition amount, compares standard data differences of each sign and a corresponding stage, determines critical signs generating fluctuation, and obtains sign stage deviation amplitude;
The continuous fluctuation measuring operator module calculates the daily variation trend of the continuous fluctuation measuring operator module in the continuous monitoring process according to the deviation amplitude of the sign stage, compares the sign data of each day with the data performance of the previous period, analyzes the continuous fluctuation condition of the sign along with time, optimizes the fluctuation data distribution and obtains the sign fluctuation intensity level;
The abnormal rate calculation submodule analyzes the physical sign items showing abnormal trend based on the physical sign fluctuation intensity level, screens the physical sign performance of abnormal change in the continuous monitoring period, judges the concentration of abnormal distribution and stage reference performance, and counts the distribution condition of abnormal data to obtain the abnormal concentration rate of the physical sign.
The invention improves, the said action pushing module includes:
the fluctuation feature screening submodule analyzes continuous fluctuation records based on the abnormal concentration rate of the signs, compares fluctuation frequencies of the signs in the current nursing stage, screens out the critical signs, determines the salient condition of the critical signs in the stage and obtains important sign identification indexes;
the combined abnormal judgment sub-module compares the current day fluctuation condition of the blood oxygen saturation and the respiratory frequency according to the key physical sign identification index, acquires the respiratory combined abnormal intensity level, compares the respiratory combined abnormal intensity level with an intervention starting standard, judges whether an intervention condition is met, and determines a respiratory system intervention event;
And the nursing action matching sub-module screens event types meeting the intervention conditions based on the respiratory system intervention events, compares matching items of the current event and a nursing action list, judges the type and the response mode of the matching action, optimizes a nursing resource allocation structure and obtains an intervention action instruction sequence number.
The invention improves, the system also includes:
The resource scheduling module analyzes the remaining working hours, task progress and skill labels of the nursing staff based on the intervention action command sequence, screens and matches the nursing staff, and combines task progress and history efficiency, and sorts and distributes priorities to obtain a nursing task priority sequence;
the care task priority sequence comprises a post assignment sequence, a resource allocation number and a scheduling priority label.
The invention improves, the resource scheduling module includes:
The working hour analysis submodule analyzes the rest working hour of the nursing staff based on the intervention action instruction sequence number, combines the actual participation task time length and skill labels of the nursing staff, screens staff which can complete the nursing task and have matched skills, compares the current working hour arrangement of each staff with the time requirement of the task to be distributed, and generates the available nursing resource quantity;
The task progress judging submodule analyzes the completion state of the current task of the nursing staff based on the available nursing resource quantity, compares the planned task progress, judges whether the actual progress is in a required range or not, and generates a scheduling adaptation deviation rate;
And the priority sequencing submodule analyzes the historical task completion performance of the personnel in the nursing response record based on the scheduling adaptation deviation rate, compares the residual working hours with the historical task participation condition, and judges the task response sequence of each nursing personnel in the actual nursing task to obtain the nursing task priority sequence.
Compared with the prior art, the invention has the advantages and positive effects that:
According to the invention, through automatic analysis of continuous medication mode, physical sign change and real-time laboratory monitoring data of a patient, dynamic collection and linkage judgment are completed by fusing multiple source health parameters, high-frequency identification of risk factors and fluctuation monitoring of sensitive physical signs are realized, intervention measure pushing information is timely generated, a nursing task response flow is optimized, accurate matching of patient risk management and nursing resource scheduling is realized by means of multidimensional data fusion and intelligent task sequencing, thus data closed loop and intervention closed loop of the whole tumor nursing process are advanced, and the initiative and adaptability of nursing decision are enhanced.
Drawings
FIG. 1 is a system flow diagram of the present invention;
FIG. 2 is a flow chart of a drug detection module according to the present invention;
FIG. 3 is a flow chart of a combination module of the present invention;
FIG. 4 is a flow chart of a sign recognition module according to the present invention;
FIG. 5 is a flow chart of the action pushing module of the present invention;
FIG. 6 is a flow chart of a resource scheduling module according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In the description of the present invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," etc. indicate or are based on the orientation or positional relationship shown in the drawings, merely to facilitate description of the invention and simplify description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the invention. Furthermore, in the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Examples:
referring to fig. 1, the invention provides a technical scheme that a tumor care service management system based on artificial intelligence comprises:
The medicine detection module analyzes medicine names, taking doses and taking time based on daily medicine data of tumor patients, compares the actual doses of the medicines with standard dose differences, calculates interval differences between continuous twice taking time and medicine metabolism time, judges whether any difference item exceeds a medicine safety reference range, and obtains offset medicine characteristics by correlating the medicine names, the dose differences and the time differences;
Based on the deviation medication characteristics, the combined medication module compares the use sequence of the medicine combinations with the occurrence time of adverse reactions, screens the medicine combinations with time coincidence, analyzes the reference range of the laboratory detection item on the same day, and calculates the simultaneous occurrence condition of the combined medication combinations and the detection item beyond the range to obtain the medicine risk superposition quantity;
The physical sign recognition module compares the current nursing stage of the patient with the risk data based on the drug risk superposition amount, collects daily physiological data of the nursing stage of the patient, judges the variation amplitude of each physical sign parameter and the stage reference standard, analyzes the accumulated amplitude of continuous fluctuation of each physical sign, counts the accumulated fluctuation variation times, and obtains the abnormal concentration rate of the physical sign;
The action pushing module screens vital sign items with critical fluctuation frequency based on abnormal concentration rate of the vital sign, analyzes the blood oxygen and respiratory frequency combination performance of the vital sign on the same day, judges whether blood oxygen change and respiratory frequency change are abnormal at the same time, determines respiratory system intervention events, screens nursing actions corresponding to the events and obtains intervention action instruction sequence numbers;
The resource scheduling module analyzes the remaining working hours, task progress and skill labels of the nursing staff based on the intervention action command sequence, screens the nursing staff matched with the skill labels, judges whether the current task progress of the staff meets scheduling requirements, compares the historical completion efficiency in the nursing response record, and prioritizes the screened nursing staff to obtain a priority sequence of the nursing task.
The offset medication characteristics comprise a dosage offset type, a medication interval type and a medicine early warning mark, the medicine risk superposition amount comprises a joint risk grade, an adverse reaction mark and a laboratory abnormal item, the abnormal concentration rate of signs comprises a sensitive sign group, a phase abnormal performance and a continuous fluctuation record, the intervention action instruction sequence number comprises a task action number, an intervention type mark and a nursing response mode, and the nursing task priority sequence comprises a post assignment sequence, a resource allocation number and a dispatching priority mark.
In the module 1, the difference between the actual dose of the drug and the standard dose refers to the difference between the actual dose of a certain drug actually taken by a patient and the recommended standard dose of the drug in pharmacopoeia, clinical route or drug instruction, the difference between intervals refers to the difference between the actual interval time between two consecutive administrations of the same drug and the recommended interval of the normal pharmacokinetics (metabolism cycle) of the drug, and the drug safety reference range refers to the reasonable interval of the dose and the medication interval of each drug set for ensuring the curative effect and safety in clinical application, which interval is usually derived from pharmacopoeia or authoritative clinical guidelines.
In the module 2, the use sequence refers to the actual use time sequence of various medicines of a patient, and the actual use time sequence is compared with the occurrence time sequence of adverse reactions, the time-coincident medicine combination refers to the fact that two or more medicines jointly used by the patient overlap with the occurrence time points of the adverse reactions in a certain specific time period, the medicine combination is screened out to pay attention to, the reference range of a detection item refers to the normal range or standard value of each index in laboratory detection (such as liver function, kidney function and the like), the range is used for judging whether the detection result is abnormal, and the occurrence condition refers to the fact that the combined medicine combination and the abnormality of the laboratory detection result are recorded in the same day or the same time period in the analysis process, so that the two are related.
In the module 3, the nursing stage refers to a specific stage of a tumor patient in the nursing process, such as a pre-operation stage, a post-operation stage, a chemotherapy stage or a rehabilitation stage, risk data refers to a medicine risk superposition quantity result generated in the combined medicine module and used for prompting the patient of medicine related nursing risks in the current stage, physiological data refers to vital signs collected by the patient every day and including parameters of blood pressure, heart rate, body temperature, blood oxygen, respiratory rate and the like which are directly related to the health state of the patient, a stage reference standard refers to a normal range of each physiological data specified by clinical nursing guidelines in each nursing stage, a change amplitude refers to an absolute difference value of an increase and decrease change of a certain physiological parameter actually monitored in the continuous monitoring process, and the accumulated amplitude refers to an accumulated sum of all single change amplitudes of the certain physiological parameter in a period of time and used for reflecting the fluctuation degree of the physical signs.
In the module 4, the key physical sign items refer to physiological parameters which are found to be most frequent in fluctuation and have the greatest influence on the current health risk of the patient after analysis, such as blood pressure, heart rate, blood oxygen and the like, the combined expression of blood oxygen and respiratory frequency refers to the combined change condition of two physical sign parameters of blood oxygen saturation and respiratory frequency in the same day or the same period, the respiratory system intervention event refers to the situation that respiratory system related nursing intervention is required to be carried out on the patient according to the combined abnormality of blood oxygen and respiratory frequency, and the corresponding nursing action refers to the matched specific nursing measure operation, such as oxygen inhalation, respiratory monitoring, doctor notification and other operation sequences according to the system judgment result.
In the module 5, the matching skill label refers to professional ability or qualification (such as chemotherapy nursing, respiratory nursing and the like) recorded in a nursing staff file and corresponds to the ability required by the current nursing task, the scheduling requirement refers to the allocation requirement of the current nursing task to the posts of the staff, such as professional skill requirement, allocable working hours, task progress condition and the like, the nursing response record refers to historical information of response speed, completion condition and the like of the nursing staff which is automatically recorded by the system and receives and completes the nursing task, and the historical completion efficiency refers to average response time or average completion quality of the nursing staff which completes the nursing tasks of the same type or the same difficulty in the past, so as to support the sequencing of the priority of the staff.
Referring to fig. 2, the medication detection module includes:
the dose difference judging submodule is used for comparing actual taken doses with standard doses of medicines based on daily medication data of tumor patients, judging whether the dose difference of each medicine exceeds a safe reference range or not, screening medicine combinations with abnormal doses, and obtaining abnormal total dose difference;
The method comprises the steps of automatically extracting medication records submitted by patients each day, respectively extracting the medicine name, actual administration dose and corresponding administration time of each medicine, taking the medicine name as a retrieval key value, calling the recommended dose range of the medicine registered in pharmacopoeia, instruction book or tumor treatment path in a preset database, determining the upper and lower limit values of safe use of the medicine as dose reference boundaries, then carrying out direct difference operation on the actual administration dose value of the patient and the called recommended dose, marking the medicine as normal dose if the result is within the safe use interval of the recommended dose, marking the medicine as abnormal dose if the result is beyond any one side boundary of the upper and lower limit, carrying out difference judgment on all medicines item by item, storing corresponding marks, screening according to the dose marks of all medicines, extracting all medicines judged as abnormal dose, constructing an abnormal medicine combination set, counting the medicines in the set, forming statistical results of the abnormal medicines, taking the statistical results of the medicines as output items, such as five medicines in the daily administration record of a certain patient, wherein the actual doses of the two medicines are twice and half of the recommended dose respectively, and the total number of the recommended medicines is determined to be abnormal by comparing the upper and lower than the recommended dose, if the total number is less than the recommended dose, and the total number of the abnormal medicines is 2 is different when the total number of the abnormal medicines is calculated and the abnormal.
The interval time comparison submodule calculates interval time of taking the same medicine twice continuously based on the dose difference abnormal total amount, compares actual interval with medicine suggestion interval, judges whether the condition exceeding a reference range exists or not, and counts accumulated condition of medicine interval abnormality to obtain interval time offset frequency;
Sequentially calling all relevant medicine taking time data of a patient in a history record for each medicine, sequentially arranging two medicine taking times of each medicine in continuous days, calculating medicine taking time intervals according to time, comparing the recommended medicine taking time intervals of the medicine in authority data with a set range, judging whether the medicine taking time intervals of the patient deviate from the recommended interval intervals or not one by one, if the time intervals are shorter than a recommended lower limit or longer than the recommended upper limit, marking the medicine taking time intervals as abnormal, continuously comparing the medicine taking time intervals in a multi-day medicine taking record, recording the number of intervals judged as abnormal, accumulating the number to obtain interval offset frequency, for example, for a certain medicine, the medicine taking time of the patient in one day is 8a day and 10 a night, if the interval time of the medicine recommended interval time is 12 hours, marking the medicine taking time intervals as offset, and if the medicine has interval frequency of similar medicine exceeding the upper limit or lower limit in three days in the record of continuous five days, accumulating the interval offset of the medicine in the period is 3, and counting the interval offset of the abnormal dosage for all intervals respectively.
The offset characteristic generation submodule extracts corresponding medicine names based on the interval time offset frequency, and performs combination association with abnormal indexes, and the formula is adopted:
;
Acquiring combined abnormal response intensityExtracting medicine combinations with high occurrence frequency and concentrated numerical amplitude to obtain offset medication characteristics, wherein,Represent the firstThe actual dosage of the seed medicine,Represent the firstThe standard dosage of the seed medicine,Represent the firstThe actual time interval between two consecutive administrations of the seed medicine,Represent the firstThe recommended taking interval of the seed medicine,Represent the firstThe state mark of the dosage difference and interval difference in the seed medicine with abnormality is taken as 0 or 1,Represents the co-amplification coefficient of the abnormal term for adjusting the influence of the simultaneous abnormal state,The number of kinds of the medicines is represented,Referring to synergistic dysregulation terms, where the expression dose and interval are simultaneously abnormal, this risk is given a higher/lower weight,The medicine has dose abnormality and medicine taking interval abnormality on the same day, namely 'combination abnormality', 0 or 1,0 is taken to indicate that the medicine has no abnormality at the same time of the dose difference and the interval difference on the same day, and 1 is taken to indicate that the medicine has abnormality at the dose difference and the interval difference on the same day, namely 'abnormal superposition'.
The combined abnormal response intensity refers to the difference between the actual taking dosage and the standard dosage of each medicine and the difference between the actual interval of two continuous taking medicines and the recommended interval when analyzing various taking medicine conditions of tumor patients, and the combined condition that the dosage and the interval are abnormal simultaneously is uniformly converted into a polymerization index capable of measuring the abnormal intensity, and the combined intensity and the concentrated performance of two abnormal phenomena of dosage difference and taking medicine interval difference in all the medicine projects of a certain patient are measured in a certain period, wherein the larger the numerical value is, the more obvious the abnormal performance or the more medicines are involved, and the higher the risk is.
Invoking the medicine names which are identified as having dose difference and interval offset, establishing a corresponding relation with the corresponding actual dose, standard dose, actual interval, suggested interval and combined abnormal state, analyzing the structural distribution of each parameter on numerical expression, adopting standardized normalization operation to perform unified calculation processing on the values under different dimensions, substituting the values into a calculation formula, specifically, for example, the actual dose of cisplatin is 90mg, the standard dose is 100mg, and the difference after normalization isThe actual interval was 18 hours, the recommended interval was 24 hours, and the normalized interval difference wasIf the joint anomaly state is 1, then it participates in the calculation as:
;
The actual dose of gemcitabine is 1200mg, the standard dose is 1000mg, and the difference after normalization isThe actual interval was 23 hours, the recommended interval was 24 hours, and the normalized difference wasThe joint anomaly state is 1,Let 2, substitution calculation be:
;
The paclitaxel dose is 160mg, the standard dose is 175mg, and the normalized difference isAt 19 hours intervals, 24 hours intervals were recommended with normalized differences ofThe joint anomaly state is 1, and the substitution calculation is as follows:
;
The three results are respectivelyAnd (3) summing to obtain:
;
the numerical result represents the concentration degree of response density formed by a plurality of medicine deviation indexes under the condition of double abnormality of dosage and time interval, the higher the numerical value is, the stronger deviation trend exists, medicine combinations with prominent response density are extracted according to the concentration degree, the ordering of medicines on risk distribution is established, the deviation medicine characteristics are formed, the formula realizes the quantitative description of the medicine combinations in the risk concentration through the cooperative consideration of dosage and interval difference and the participation operation of abnormal identification, and an evaluation basis is constructed in a medicine screening link.
Referring to fig. 3, the combination module includes:
the time sequence comparison sub-module analyzes the medicine name and the medicine taking time sequence based on the deviation medicine taking characteristics, compares the actual medicine taking sequence of each medicine combination with the time sequence of occurrence of adverse reaction, identifies the combination of the actual medicine taking and the adverse reaction which are related in time, judges whether the combination has a rule, and obtains a time sequence coincidence group sequence;
Firstly, all medicine items marked as having dose deviation, abnormal medicine taking interval or medicine early warning marks are taken, daily medicine taking records are matched one by one, medicine taking time of each medicine is extracted, a data table structure with medicine names as index fields and daily medicine taking time as a sequence is constructed, then all related medicine combinations are processed in a pairwise combination mode according to actual medicine taking behaviors of patients, the medicine taking time sequence of each group of medicine combinations is subjected to cross sequencing operation, actual medicine taking time sequence of each medicine is determined, then adverse reaction occurrence time in the day and three days after the day is extracted from electronic medical records of the patients, first record time of adverse reactions is compared with actual medicine taking time of each medicine in the medicine combinations, whether occurrence of the adverse reactions occurs within 48 hours after the completion of taking of all medicines is judged in the comparison process, if the condition is met, the combination is marked as having a correlation, then for the marked combination, whether the patient has repeatability in a chemotherapy cycle through accumulating whether the time sequence correlation of the repeated occurrence of the medicine combinations in a plurality of cycles is judged, for example, the patient has the repeated correlation with the time sequence which has the repeated occurrence of the time sequence after the time sequence of the first record and the adverse reactions are consistent with the final time sequence, and the final correlation record is the final time sequence is judged that the repeated time sequence is coincident with the time sequence of the final medicine record.
The risk coupling submodule analyzes laboratory detection results combined in the same medication period based on the time sequence coincidence group sequence, compares the medication time of the medicine combination with synchronous occurrence of detection abnormality, and counts coincidence frequency in the same period to obtain risk coupling item frequency;
Firstly, taking the corresponding medicine taking time of each pair of medicine combinations, synchronously taking laboratory detection records of the same patient in the medicine taking period in a database, respectively searching data values and detection times of various key detection items, setting a period boundary according to the medicine taking time window of each medicine combination, defining the medicine taking start day to the seventh day of each combination as a medicine taking period window, screening detection records with all detection times falling into the period window from the laboratory records, further judging whether the detection values exceed the corresponding reference value range, for example, setting the normal range of serum creatinine to 0.6 to 1.2mg/dL, if the detection result of the patient is 1.6mg/dL, marking the detection items as abnormal items, recording abnormal occurrence time points, comparing the abnormal time with the medicine taking time of the corresponding medicine combination, judging whether the detection abnormality occurs within 48 hours after the medicine combination taking, if the occurrence time and the medicine taking time are not more than 48 hours, synchronously appearing, regarding the detection records which are coincident once, accumulating the detection records which are coincident with all the synchronous conditions, counting the detection records which are coincident with each other in the same patient in different combinations, carrying out statistics on the three-phase and forming the three-phase combination in the same medicine taking period, and forming the three-phase-frequency combination as the three-risk-of the medicine combination, and forming the three-phase-risk combination, and taking the three-risk combination in the three-phase combination and taking time is used as the final medicine item, and the risk of the three-phase-risk combination and the medicine combination.
The abnormal co-occurrence submodule adopts the following formula according to the frequency of the risk coupling term:
;
Calculating the magnitude of abnormal co-occurrenceSequencing according to the abnormal co-occurrence amplitude of each combination, screening the combination with the optimal co-occurrence degree to obtain the drug risk superposition amount,Indicating the total number of drugs in the drug combination,Represent the firstThe medicine taking time of the seed medicine,Represent the firstThe occurrence time of the adverse reaction corresponding to the seed medicine,Represent the firstThe number of abnormal detection items in laboratory detection of the current day of the drug,Represent the firstThe magnitude of the dose shift of the seed drug,Represents the total number of laboratory test anomalies,Represent the firstThe laboratory detects the co-occurrence frequency of anomalies,Is the serial number of the laboratory for detecting the abnormal item,Is the serial number in the medicine combination.
The abnormal co-occurrence measure refers to a comprehensive quantitative index for measuring the synchronous co-occurrence degree between the medicine combination and adverse reaction event and laboratory abnormal detection in a specific medicine taking period, and can be used as a numerical basis for measuring the medicine risk superposition generated by the medicine combination in practical application, order and screen the risk co-occurrence degree of different medicine combinations, and be used for identifying medicine combinations with potential high risks and providing data support for subsequent risk intervention and nursing decision.
The absolute value of the difference (square re-prescription) is used for measuring the time distance from taking each medicine to the occurrence of adverse reaction, and the smaller the value is, the closer the adverse reaction is to the taking time (namely, the larger the linkage/risk is), the larger the value is, the far the two are (the risk is relatively low); The method is characterized in that laboratory detection abnormality and dosage abnormality are taken as 'abnormality intensity', root numbers are opened after addition, single extreme influence is avoided, the larger the numerical value is, the more the medicine is prominent in the current abnormality condition (laboratory/dosage), and the absolute value of time distance is combined with the abnormality intensity to reflect the 'integrated intensity of abnormality co-occurrence'. If both are high, the risk of abnormality is amplified, and if either is low, the overall risk impact is limited.
Reflecting the overall co-occurrence level of the detected abnormalities within the dosing period, the more the overall combined background abnormalities are, the greater the denominator is, the relatively reduced the risk score,The method ensures that the scale correction is carried out when different medicine groups are calculated, the more medicines are, the larger the denominator is, and the abnormal influence of a single medicine cannot be amplified infinitely.
Time for taking each drug in drug combinationAdverse reaction timeNumber of laboratory abnormalitiesAmplitude of dose shiftCo-occurrence frequency of abnormality detectionAnd performing joint calculation, and setting the normalized parameters as follows:
;
;
;
;
Substituting the normalized parameters into a formula, and firstly calculating a molecular part:
Group 1:
;
group 2:
;
Group 3:
;
the molecular summation is as follows:
;
calculating the number of medicinesThe co-occurrence frequency is summed to be
Therefore, the denominator is:
;
The following steps are obtained:
;
the obtained abnormal co-occurrence amplitudeAs a collective measure for quantifying the contribution of a drug combination to the potential risk of a patient throughout the care cycle, corresponding to all drug combinationsThe results are sequenced, and the combination with the optimal co-occurrence degree (namely, the highest risk polymerization degree) is screened, so that the abnormal co-occurrence magnitude measurement not only reflects the linkage risk level of the current combination, but also serves as a basic basis for judging and generating the drug risk superposition quantity.
Referring to fig. 4, the sign recognition module includes:
The stage reference comparison submodule analyzes physiological data of a tumor patient in a current nursing stage based on the drug risk superposition amount, compares standard data differences of each sign and a corresponding stage, determines the sign which generates fluctuation key, and obtains the sign stage deviation amplitude;
Firstly, retrieving the current nursing stage information of a patient, extracting a corresponding reference standard value set according to a stage label, wherein the value set comprises normal fluctuation ranges of physiological parameters such as blood pressure, heart rate, body temperature, blood oxygen saturation, respiratory frequency and the like, calling physiological data records reported by the patient every day during the stage, carrying out item-by-item comparison processing on the actual numerical value of each item of sign and the stage standard value set, carrying out difference value calculation on each item of sign parameter, carrying out bilateral judgment on each item of sign parameter and an upper limit threshold and a lower limit threshold set in the reference standard respectively, marking the sign parameter as an offset item if any difference value exceeds an upper limit interval and a lower limit interval, summarizing all sign offset items into an abnormal set, and then sequencing all the signs in the abnormal set from large to small according to the absolute value of the difference value, determining key signs causing offset, for example, the heart rate of a patient in a recovery stage after a certain chemotherapy is measured 110 times/min, the standard upper limit of the stage is 100 times/min, the difference value is 10 times/min, the standard is marked as offset, the standard is measured at 38.3 ℃ and exceeds the standard upper limit of the stage by 37.5 ℃ and the difference value is 0.8 ℃, the offset set is also counted, sequencing the influence weights of all the signs in the same stage by combining the influence weights of the signs on health risks, wherein the heart rate and the body temperature fluctuation are arranged in the first two positions, identifying the heart rate and the body temperature fluctuation as fluctuation key signs, and finally recording the offset amplitude of the sign stage by the maximum offset amplitude.
The continuous fluctuation measuring operator module calculates daily variation trend in the continuous monitoring process according to the deviation amplitude of the sign stage, compares the sign data of each day with the data performance of the previous period, analyzes the continuous fluctuation condition of the sign along with time, optimizes the fluctuation data distribution and obtains the sign fluctuation intensity level;
the method comprises the steps of reading historical monitoring data of a patient which is identified as a fluctuation key sign, constructing a time sequence according to a daily report sequence for each sign parameter, respectively calculating absolute difference values between every two adjacent days as fluctuation values of the same day, recording a daily average value sequence of the sign in a past complete monitoring period, carrying out difference analysis operation on the sign values of the current day and the sign values of the corresponding date of the previous period, judging whether the sign data are continuously higher or lower than similar data of the previous period, marking trend fluctuation events if the difference directions of the sign are consistent over three consecutive days, counting the occurrence frequency and the fluctuation direction of the trend fluctuation, carrying out grouping processing on the data of all fluctuation events according to the fluctuation value, carrying out distribution statistics on the frequency of the daily fluctuation values in each grouping interval, carrying out hierarchical judgment on the overall fluctuation trend according to the frequency weight, for example, carrying out continuous 5-day data of 20, 22, 24, 23 and 25 times/min, carrying out difference analysis on the data of the same date of the previous period is 18, 20, 19, 20 and 21 times/min, and if the difference value is continuously higher than 2-3, the fluctuation level is found to be higher than the 1-3, and the fluctuation level is the maximum value is found to be higher than the 1-3.
The abnormal rate calculation submodule analyzes a physical sign item showing an abnormal trend based on the physical sign fluctuation intensity level, screens physical sign performance of abnormal change in a continuous monitoring period, judges the concentration of abnormal distribution and stage reference performance, and counts the distribution condition of abnormal data to obtain the abnormal concentration rate of the physical sign;
Carrying out item-by-item rechecking on all sign items marked as high-intensity fluctuation, judging whether abnormal change behaviors exist in the sign item according to daily data records, judging whether the abnormal change behaviors exist in a specific date area or not according to the daily data records, wherein abnormal change judgment logic is that a sign measured value exceeds a phase reference upper limit or lower limit, or continuous three-day fluctuation directions are consistent and daily change amplitude exceeds a preset single-day deviation threshold value, carrying out item-by-item judgment on all records of each sign item in a complete monitoring period, accumulating abnormal times, counting data corresponding to abnormal occurrence dates, forming an abnormal record sequence, carrying out comparison operation on deviation directions, absolute difference values and phase standard deviation of each item of data in the abnormal record, judging whether the abnormal is statistically gathered in a specific date area or is concentrated in a specific parameter area, for example, a patient body temperature value exceeds 37.8 ℃ within 8 days, wherein 4 days appears on 2 nd to 5 th days, judging that the abnormal record is concentrated in time, then carrying out distribution analysis on the body temperature deviation values, finding that the deviation value in 4 abnormal records is more than 1.0 ℃ and is higher than 0.5 ℃ in time, counting the abnormal record is more than the average fluctuation value, the abnormal record is more than 4% in time, the total value is calculated as the total value, the abnormal record is calculated as the abnormal record is concentrated, the abnormal change is concentrated, and the abnormal change is calculated is about the total is about the abnormal change is about the abnormal record is about the normal value, and is about the normal value, for the abnormal change is about the normal record is about be about 80.
Referring to fig. 5, the action pushing module includes:
The fluctuation feature screening submodule analyzes continuous fluctuation records based on abnormal concentration rate of the signs, compares fluctuation frequency of each sign in the current nursing stage, screens out critical signs, determines the salient condition of the critical signs in the stage and obtains important sign identification indexes;
Reading all the sign data items marked as abnormal, sorting the continuous fluctuation records according to time sequence, counting the daily fluctuation times of each sign in the current nursing stage to form a corresponding relation table of signs and fluctuation frequencies, comparing the fluctuation frequency of each sign item in the table with a fluctuation threshold value set in the nursing stage, if the fluctuation frequency of a sign in a period is larger than the set threshold value, marking the sign as a frequency salient item, for example, when the nursing stage is a post-chemotherapy recovery period, setting the body temperature fluctuation threshold value as 3 times/week, if the condition that the temperature of a patient exceeds 3 times by more than a standard value occurs in the body temperature records, regarding the sign as a high-frequency fluctuation sign, screening the sign into a candidate set, then carrying out normalization processing on the sign in the candidate set, calculating the fluctuation amplitude, abnormal concentration rate and the corresponding reference value difference ratio of the nursing stage, if the ratio exceeds a preset strong deviation coefficient (for example, is set to be 2.0), further marking the sign as a performance critical sign, for example, if the ratio exceeds the critical sign in the three-phase, the critical sign is not satisfied by 60-100, and the fluctuation amplitude exceeds the critical sign within the critical sign, and the critical sign is only slightly exceeds the critical sign, and the critical sign is slightly exceeds the critical sign within the critical sign, namely, the fluctuation amplitude is 1-100, and the critical sign is slightly exceeds the critical sign is only 60-100 minutes, and the critical sign is output, and the critical sign is slightly exceeds the critical sign is detected within the critical sign is within the critical amplitude is not within the range and is 1-100 and is more than 100 minutes and is not satisfied, and is high.
The combined abnormality judgment sub-module compares the current day fluctuation conditions of the blood oxygen saturation and the respiratory frequency according to the key sign identification index, and adopts the formula:
;
Acquiring respiratory joint anomaly intensity levelsComparing with intervention start standard, judging whether the intervention condition is satisfied, determining respiratory intervention event, wherein,Representing the current day fluctuation amplitude of the blood oxygen saturation,Representing the amplitude of the current day fluctuation of the respiratory rate,Representing the base of the amplitude of the systolic pressure fluctuation on the same day,Indicating that when the number of physical sign abnormal items is on the day,Represent the firstFluctuation data of the secondary respiratory rate,Represent the firstFluctuation data of the blood oxygen saturation level,Indicating the total number of times when blood oxygen and respiratory rate are collected in combination;
The respiratory joint abnormal intensity level is a numerical grading index which is obtained by comprehensively analyzing factors such as synchronous change conditions of blood oxygen saturation and respiratory frequency of the patient in the same nursing period, systolic pressure fluctuation and abnormal quantity of physical signs and the like, is used for measuring the abnormal degree of the blood oxygen and respiratory frequency joint fluctuation expression, reflects the deviation level of the current respiratory system state of the patient relative to a normal standard, and represents that the higher the numerical value is, the more prominent the risk of synchronous abnormal fluctuation of the blood oxygen and respiratory frequency is, and the grade score is calculated first and then compared with a standard threshold interval to determine whether intervention is performed.
Comparing the fluctuation conditions of blood oxygen saturation and respiratory frequency in the same day, setting monitoring time points as 08:00, 12:00, 16:00 and 20:00, respectively recording blood oxygen saturation fluctuation ranges as 3.2%, 2.5%, 4.1% and 3.7% at four time points, respectively carrying out dimensionless treatment on the blood oxygen saturation fluctuation ranges as 2.8, 3.0, 3.5 and 2.9 times/min, and the systolic blood pressure fluctuation base as 6.1, 5.8, 6.5 and 6.0 mmHg, wherein the number of daily sign abnormal items is 2,3, 2 and 4 in sequence, the sampling time interval respectively records respiratory frequency fluctuation data and blood oxygen saturation fluctuation data pairs as (0.6,0.5 and 0.7,0.6), adopting 16:00 time interval data as core samples, and obtaining normalized parameter values after carrying out dimensionless treatment on all the data respectively:
Substituting the above parameters into a formula for calculation, and calculating a molecular part:
;
Denominator part:
;
And (3) comprehensive calculation:
;
The result shows that at the time point of sampling 16:00, the respiratory joint abnormal intensity level reflected by the synchronous fluctuation condition of respiratory frequency and blood oxygen saturation is 1.10, if the level value is above the upper limit of the intervention starting level interval in the judging standard, the level value is regarded as a trigger intervention condition, the corresponding time point of the data is marked as a starting node of a respiratory system intervention event, the level is used for matching task types needing immediate response in an intervention action list, so that the process of the next link in a nursing scheduling task chain is completed, and the formula is used for leading a plurality of physiological data difference items after normalization processing and a combined calculation mode, namely the fluctuation range, the frequency and the synchronism of the effective syndrome, so that the abnormal intensity level has more evaluation precision and recognition value.
The nursing action matching submodule screens event types meeting intervention conditions based on respiratory system intervention events, compares matching items of a current event and a nursing action list, judges types and response modes of matching actions, optimizes a nursing resource allocation structure and obtains intervention action instruction sequence numbers.
Extracting event content triggering intervention, reading event occurrence time, physiological parameter types, abnormal parameter performance and abnormal parameter amplitude, then reading a set nursing action list from a database, performing unfolding matching on matching condition fields of each nursing action in the list, judging whether parameter names recorded by each comparison event are consistent with the type of triggering parameters set in the nursing action, judging field matching items, if so, entering a next matching stage, performing content matching on the abnormal performance recorded in the event and abnormal descriptions set in the nursing action, if the matching items exist, judging that the nursing action is a candidate item, further comparing the abnormal amplitude with the response level set by the nursing action, for example, the blood oxygen saturation recorded in the event is lower than 88%, and the oxygen inhalation intervention triggering threshold set in the nursing action list is 90%, then the event meets the response condition of the action, marking the nursing action as an executable action, if a plurality of nursing actions meet the matching condition, and setting the priority of the matching action according to the use priority of nursing resources, for example, setting the priority of oxygen inhalation intervention for 1, notifying that the priority for 2, and finally setting the priority of executing person to be a final priority, and the priority of executing the matching action, for example, setting the priority of the priority to be a response mode of a matching instruction, and a response mode of a step number of a nurse is obtained, and a response sequence number is obtained, and a response mode of a response is obtained, and a response order is formed by the instruction is formed.
Referring to fig. 6, the resource scheduling module includes:
the working hour analysis sub-module analyzes the rest working hours of nursing staff based on the intervention action command sequence number, combines the actual participation task time length and skill labels, screens staff which can complete the nursing task and have matched skills, compares the current working hour arrangement of each staff with the time requirement of the task to be allocated, and generates the available nursing resource amount;
And (3) calling the required execution time of each intervention action as the task time requirement, calling the current residual working hour data of all on-duty nursing staff and the scheduled task time on the same day, constructing a working hour usage table of each nursing staff, calling the skill label information of the nursing staff, carrying out one-to-one matching judgment with the required skill requirement item in the intervention action, judging the staff as a skill matching staff if the skill label of the certain nursing staff is marked with the required intervention capability, such as 'respiratory intervention', 'chemo nursing', and the like, then carrying out numerical comparison operation on the current residual working hour of the matching staff and the required task time, marking the staff as 'allocable', otherwise being 'unallowable', for example, the task time required by an intervention instruction is 1.5 hours, nurses Zhang Mou the residual working hour is 2 hours, and the skill label contains 'respiratory nursing', judging that Zhang Mou is allocable staff, otherwise, judging that Li Mou has the residual working hour only 0.5 hours or the skill label does not contain the relevant item, and carrying out numerical comparison operation on the current residual working hour of the matching staff and the required time, if the residual working hour is not lower than the required time, marking the current residual working hour is equal to the required by the task time, marking the current residual working hour is equal to the required by the current working hour, and the corresponding resource is calculated by the corresponding to the current resource, and the total resource is allocated to the corresponding to the task time.
The task progress judging submodule analyzes the completion state of the current task of the nursing staff based on the available nursing resource amount, compares the planned task progress, judges whether the actual progress is in a required range or not, and generates a scheduling adaptation deviation rate;
reading a task list in execution and the planned start-stop time of each task according to the identity information of nursing staff, reading the actual operation record of each task, extracting the completed time and the completed progress percentage of each task, comparing the actual completed state with the planned progress, if the actual progress value is smaller than the planned progress value, recording as progress lag, otherwise, carrying out numerical conversion on the current task of each nursing staff for normal or advanced progress, counting the number of lag tasks and the lag average time of each nursing staff, and combining with an idle time window in the available nursing resource amount, judging whether the nursing staff has the scheduling capability of receiving new tasks, for example, the planned task completion degree of a nurse is 70%, the actual record is only completed by 50%, the lag is 20%, the available nursing time is 1 hour, the current task completion average lag time is 2 hours, judging that the scheduling load is larger, and not suitable for current task allocation, thereby establishing a scheduling adaptive record of each nursing staff, and carrying out numerical conversion on the lag degree and resource matching degree, regarding the lag deviation as high deviation, and the lag deviation is smaller than 5% as low deviation, and forming the scheduling adaptive difference rate of each nursing staff.
The priority sequencing sub-module analyzes the historical task completion performance of the staff in the nursing response record based on the scheduling adaptation deviation rate, compares the residual man-hour with the historical task participation condition, and judges the task response sequence of each nursing staff in the actual nursing task to obtain a nursing task priority sequence;
The method comprises the steps of calling a nursing response record database, extracting historical task completion conditions of all current assignable personnel, respectively calculating response starting time and task completion time of the similar task, comparing the response starting time with task completion time of the similar task, setting standard response time and completion time limit of the task, if the response time exceeds a set threshold value for multiple times in the historical task, marking as weak response capability, if the response time is within the standard response time, marking as stable response, then extracting total parameters and frequency of the current residual working hours and the historical task of each person, combining the historical task average completion time, calculating workload distribution density of the personnel in the nursing task, for example, the historical participation task of a nursing personnel B for 40 times, the average response time is 10 minutes, the average task time is 40 minutes, the current residual working hours is 3 hours, the residual task holding capacity of the nursing personnel is evaluated to be 3 hours, the similar conventional task can be covered by 4 to 5, the nursing personnel is compared with the residual working hours of the similar task, the nursing personnel is only 1 hour, the priority ranking list is established according to the priority ranking list, the priority ranking list is lower, the current residual working hours difference rate is good, the current residual working hours are listed as high priority personnel, and the priority ranking priority is output according to the priority ranking of the priority ranking task.
The present invention is not limited to the above embodiments, and any equivalent embodiments which can be changed or modified by the technical disclosure described above can be applied to other fields, but any simple modification, equivalent changes and modification made to the above embodiments according to the technical matter of the present invention will still fall within the scope of the technical disclosure.

Claims (8)

Translated fromChinese
1.一种基于人工智能的肿瘤护理服务管理系统,其特征在于,所述系统包括:1. An artificial intelligence-based tumor nursing service management system, characterized in that the system includes:用药检测模块基于肿瘤患者每日用药数据,分析药品名称、服用剂量和服药时间,比较实际与标准剂量差异,计算服药间隔与药物代谢间隔的差异,判断风险特征,得到偏移用药特征;The medication detection module analyzes the drug name, dosage, and time of administration based on the daily medication data of cancer patients, compares the difference between the actual and standard dosages, calculates the difference between the medication interval and the drug metabolism interval, determines the risk characteristics, and obtains the deviation medication characteristics;联合用药模块基于所述偏移用药特征,比较药品组合的顺序与不良反应时间,筛查存在时间重合的药品组合,分析实验室检测的参考范围,统计风险组,得到药物风险叠加量;Based on the offset medication characteristics, the combined medication module compares the order of drug combinations and the adverse reaction time, screens drug combinations with overlapping time, analyzes the reference range of laboratory tests, calculates the risk groups, and obtains the drug risk superposition amount;体征识别模块基于所述药物风险叠加量,比较患者护理阶段与风险信息,采集每日生理数据,判定体征参数与阶段标准的变化幅度,并分析累计波动情况,得到体征异常集中率;The physical sign recognition module compares the patient care stage with the risk information based on the drug risk superposition, collects daily physiological data, determines the variation range of physical sign parameters and stage standards, and analyzes the cumulative fluctuations to obtain the abnormal physical sign concentration rate;动作推送模块基于所述体征异常集中率,筛选波动频次高的体征,分析该体征与血氧、呼吸频率的组合表现,判断是否为呼吸干预事件,识别对应护理动作,得到干预动作指令序号。The action push module screens the signs with high fluctuation frequency based on the abnormal concentration rate of the signs, analyzes the combined performance of the signs with blood oxygen and respiratory rate, determines whether it is a respiratory intervention event, identifies the corresponding nursing action, and obtains the intervention action instruction sequence number.2.根据权利要求1所述的基于人工智能的肿瘤护理服务管理系统,其特征在于,所述偏移用药特征包括剂量偏移类型、服药间隔类别、药品预警标识,所述药物风险叠加量包括联合风险等级、不良反应标记、实验室异常项,所述体征异常集中率包括敏感体征分组、阶段异常表现、连续波动记录,所述干预动作指令序号包括任务动作编号、干预类别标签、护理响应方式。2. The artificial intelligence-based tumor nursing service management system according to claim 1 is characterized in that the deviation medication characteristics include dosage deviation type, medication interval category, and drug warning mark; the drug risk superposition amount includes combined risk level, adverse reaction marker, and laboratory abnormality item; the abnormal physical sign concentration rate includes sensitive physical sign grouping, stage abnormal performance, and continuous fluctuation record; the intervention action instruction sequence number includes task action number, intervention category label, and nursing response method.3.根据权利要求1所述的基于人工智能的肿瘤护理服务管理系统,其特征在于,所述用药检测模块包括:3. The artificial intelligence-based tumor nursing service management system according to claim 1, wherein the medication detection module comprises:剂量差异判定子模块基于肿瘤患者每日用药数据,比较实际服用剂量与药品标准剂量,判断每种药品的剂量差异是否超出安全参考范围,筛选剂量存在异常的药品组合,得到剂量差异异常总量;The dose difference determination submodule compares the actual dosage with the standard dosage of each drug based on the daily medication data of cancer patients, determines whether the dosage difference of each drug exceeds the safety reference range, screens drug combinations with abnormal dosages, and obtains the total amount of abnormal dosage differences;间隔时间对比子模块基于所述剂量差异异常总量,计算连续两次服用同一药品的间隔时间,比较实际间隔与药品建议间隔,判断是否存在超出参考范围的情况,并统计药品间隔异常的累计情况,得到间隔时间偏移频数;The interval comparison submodule calculates the interval between two consecutive doses of the same drug based on the total amount of dosage difference abnormalities, compares the actual interval with the recommended interval of the drug, determines whether there is a situation that exceeds the reference range, and counts the cumulative situation of drug interval abnormalities to obtain the interval time deviation frequency;偏移特征生成子模块基于所述间隔时间偏移频数,提取对应药品名称,与异常指标进行组合关联,获取组合异常响应强度,提取其中出现频次高且数值幅度集中的药品组合,得到偏移用药特征。The offset feature generation submodule extracts the corresponding drug name based on the interval time offset frequency, combines and associates it with the abnormal indicators, obtains the combined abnormal response intensity, extracts the drug combination with high frequency and concentrated numerical amplitude, and obtains the offset medication feature.4.根据权利要求1所述的基于人工智能的肿瘤护理服务管理系统,其特征在于,所述联合用药模块包括:4. The artificial intelligence-based tumor nursing service management system according to claim 1, wherein the combined medication module comprises:时序比对子模块基于所述偏移用药特征,分析药品名称与服药时间序列,比较各药品组合的实际用药顺序与不良反应出现的时间顺序,识别实际用药与不良反应在时间上关联的药品组合,判断药品组合是否存在规律,得到时序重合组序列;The time series comparison submodule analyzes the drug names and medication time series based on the offset medication characteristics, compares the actual medication sequence of each drug combination with the time sequence of adverse reactions, identifies drug combinations with temporal correlation between actual medication and adverse reactions, determines whether there is a pattern in the drug combination, and obtains a time series coincidence group sequence;风险联动子模块基于所述时序重合组序列,分析药品组合在同一用药周期内的实验室检测结果,比较药品组合的用药时间与检测异常的同步出现情况,并统计在同周期内的重合频数,得到风险耦合项频数;The risk linkage submodule analyzes the laboratory test results of the drug combination in the same medication cycle based on the time-series coincidence group sequence, compares the synchronization of the medication time of the drug combination and the abnormality of the test, and counts the coincidence frequency in the same cycle to obtain the frequency of risk coupling items;异常共现子模块根据所述风险耦合项频数,计算异常共现幅度量,依据各药品组合的异常共现幅度量进行排序,筛定共现程度最优的药品组合,得到药物风险叠加量。The abnormal co-occurrence submodule calculates the abnormal co-occurrence amplitude according to the frequency of the risk coupling items, sorts the drug combinations according to the abnormal co-occurrence amplitude, screens the drug combination with the best co-occurrence degree, and obtains the drug risk superposition amount.5.根据权利要求1所述的基于人工智能的肿瘤护理服务管理系统,其特征在于,所述体征识别模块包括:5. The artificial intelligence-based tumor nursing service management system according to claim 1, wherein the vital sign recognition module comprises:阶段基准对比子模块基于所述药物风险叠加量,分析肿瘤患者在当前护理阶段的生理数据,比较每项体征与对应阶段的标准数据差异,确定产生波动关键的体征,得到体征阶段偏移幅度;The stage benchmark comparison submodule analyzes the physiological data of the cancer patient at the current care stage based on the drug risk superposition, compares the difference between each physical sign and the standard data of the corresponding stage, determines the physical sign that causes the fluctuation, and obtains the physical sign stage deviation amplitude;连续波动测算子模块根据所述体征阶段偏移幅度,计算其在连续监测过程中的每日变化趋势,比较各日体征数据与上一周期的数据表现,分析体征随时间的持续波动情况,优化波动数据分布,得到体征波动强度水平;The continuous fluctuation measurement submodule calculates the daily change trend of the vital sign during the continuous monitoring process based on the deviation amplitude of the vital sign stage, compares the vital sign data of each day with the data performance of the previous cycle, analyzes the continuous fluctuation of the vital sign over time, optimizes the distribution of the fluctuation data, and obtains the intensity level of the vital sign fluctuation;异常率计算子模块基于所述体征波动强度水平,分析表现出异常趋势的体征项目,筛选其在连续监测期间内出现异常变化的体征表现,判断异常分布与阶段基准表现的集中性,并统计异常数据的分布情况,得到体征异常集中率。The abnormality rate calculation submodule analyzes the physical sign items showing abnormal trends based on the level of physical sign fluctuation intensity, screens the physical sign manifestations that show abnormal changes during the continuous monitoring period, determines the concentration of abnormal distribution and stage benchmark manifestations, and statistically analyzes the distribution of abnormal data to obtain the physical sign abnormality concentration rate.6.根据权利要求1所述的基于人工智能的肿瘤护理服务管理系统,其特征在于,所述动作推送模块包括:6. The artificial intelligence-based tumor nursing service management system according to claim 1, wherein the action push module comprises:波动特征筛选子模块基于所述体征异常集中率,分析连续波动记录,比较各体征在当前护理阶段内的波动频次,筛选表现关键的体征,并确定关键体征在阶段中的突出情况,得到重点体征识别指标;The fluctuation feature screening submodule analyzes the continuous fluctuation records based on the abnormal concentration rate of the physical signs, compares the fluctuation frequency of each physical sign in the current nursing stage, screens the key physical signs, and determines the prominence of the key physical signs in the stage to obtain the key physical sign identification index;联合异常判断子模块根据所述重点体征识别指标,比较血氧饱和度和呼吸频率的当日波动情况,获取呼吸联合异常强度等级,与干预启动标准进行对比,判断是否满足干预条件,确定呼吸系统干预事件;The combined abnormality judgment submodule compares the daily fluctuations of blood oxygen saturation and respiratory rate based on the key vital sign identification indicators, obtains the intensity level of combined respiratory abnormality, compares it with the intervention initiation standard, determines whether the intervention conditions are met, and determines the respiratory system intervention event;护理动作匹配子模块基于所述呼吸系统干预事件,筛选符合干预条件的事件类型,比较当前事件与护理动作清单的匹配项,判断匹配动作的类别及响应方式,优化护理资源分配结构,得到干预动作指令序号。The nursing action matching submodule screens the event types that meet the intervention conditions based on the respiratory system intervention events, compares the current events with the matching items in the nursing action list, determines the category and response method of the matching actions, optimizes the nursing resource allocation structure, and obtains the intervention action instruction sequence number.7.根据权利要求1所述的基于人工智能的肿瘤护理服务管理系统,其特征在于,所述系统还包括:7. The artificial intelligence-based tumor nursing service management system according to claim 1, characterized in that the system further comprises:资源调度模块基于所述干预动作指令序号,分析护理人员剩余工时、任务进度与技能标签,筛选匹配护理人员,结合任务进展及历史效率,排序分配优先级,得到护理任务优先序列;The resource scheduling module analyzes the remaining working hours, task progress and skill tags of the nursing staff based on the intervention action instruction sequence number, selects and matches the nursing staff, and sorts and allocates priorities based on the task progress and historical efficiency to obtain the nursing task priority sequence;所述护理任务优先序列包括岗位指派顺序、资源分配编号、调度优先标签。The nursing task priority sequence includes job assignment order, resource allocation number, and scheduling priority label.8.根据权利要求7所述的基于人工智能的肿瘤护理服务管理系统,其特征在于,所述资源调度模块包括:8. The artificial intelligence-based tumor nursing service management system according to claim 7, wherein the resource scheduling module comprises:工时分析子模块基于所述干预动作指令序号,分析护理人员剩余工时,结合其实际参与任务时长与技能标签,筛选能够完成护理任务且技能匹配的人员,并比较各人员的当前工时安排与即将分配任务的时间需求,生成可用护理资源量;The work time analysis submodule analyzes the remaining work time of the nursing staff based on the intervention action instruction sequence number, and screens the staff who can complete the nursing task and have matching skills based on their actual participation time and skill tags. It also compares the current work time schedule of each staff member with the time requirement of the upcoming task to generate the amount of available nursing resources.任务进度判断子模块基于所述可用护理资源量,分析护理人员当前任务的完成状态,对照计划任务进度,判断其实际进展是否处于要求范围,生成调度适配偏差率;The task progress judgment submodule analyzes the completion status of the nursing staff's current task based on the available nursing resources, compares the planned task progress, determines whether the actual progress is within the required range, and generates a scheduling adaptation deviation rate;优先级排序子模块基于所述调度适配偏差率,分析护理响应记录中人员的历史任务完成表现,比较其剩余工时与历史任务参与情况,判断各护理人员在实际护理任务中的任务响应顺序,得到护理任务优先序列。The priority sorting submodule analyzes the historical task completion performance of personnel in the nursing response records based on the scheduling adaptation deviation rate, compares their remaining working hours with their historical task participation, determines the task response order of each nursing staff in the actual nursing tasks, and obtains the nursing task priority sequence.
CN202510948624.4A2025-07-102025-07-10 An artificial intelligence-based tumor nursing service management systemActiveCN120432174B (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN202510948624.4ACN120432174B (en)2025-07-102025-07-10 An artificial intelligence-based tumor nursing service management system

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN202510948624.4ACN120432174B (en)2025-07-102025-07-10 An artificial intelligence-based tumor nursing service management system

Publications (2)

Publication NumberPublication Date
CN120432174A CN120432174A (en)2025-08-05
CN120432174Btrue CN120432174B (en)2025-09-16

Family

ID=96554225

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN202510948624.4AActiveCN120432174B (en)2025-07-102025-07-10 An artificial intelligence-based tumor nursing service management system

Country Status (1)

CountryLink
CN (1)CN120432174B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN105279393A (en)*2015-10-122016-01-27厦门大学Method for evaluating adverse drug reactions based on weighting network
CN120089346A (en)*2025-05-062025-06-03西安交通大学医学院第一附属医院 A system, method, medium and device for intelligent follow-up of daytime tumor patients

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
US20170242962A1 (en)*2016-02-182017-08-24UniMedSoft, Inc.Online managed medical portal for patients and physicians
US20250144291A1 (en)*2023-07-232025-05-08Manta Implant LLCArtificial intelligence based implantable drug delivery system
CN117911216A (en)*2024-01-262024-04-19苏州德品医疗科技股份有限公司Outside-hospital nursing cloud health management system
CN119314642A (en)*2024-11-292025-01-14新能康技术有限公司 An information management system and method for chronic disease patients based on intelligent AI
CN120199520A (en)*2025-03-172025-06-24赣州市妇幼保健院 An intelligent tumor nursing monitoring system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN105279393A (en)*2015-10-122016-01-27厦门大学Method for evaluating adverse drug reactions based on weighting network
CN120089346A (en)*2025-05-062025-06-03西安交通大学医学院第一附属医院 A system, method, medium and device for intelligent follow-up of daytime tumor patients

Also Published As

Publication numberPublication date
CN120432174A (en)2025-08-05

Similar Documents

PublicationPublication DateTitle
Linley et al.Estimated HIV incidence and prevalence in the United States 2010–2016
Galvagno Jr et al.Helicopter emergency medical services for adults with major trauma
Tsumoto et al.Similarity-based behavior and process mining of medical practices
Kalne et al.The purpose of time-motion studies (TMSs) in healthcare: a literature review
CN111695836B (en) Clinical trial online operation management and control integrated system
CN113593724A (en)Anticoagulant drug treatment management follow-up system
CN112801488A (en)Clinical trial quality real-time management and control optimization method and system
Tsumoto et al.Clustering-based analysis in hospital information systems
CN106919804A (en)Medicine based on clinical data recommends method, recommendation apparatus and server
CN105005709A (en)Process mining method based on single-disease treatment process
US20080147444A1 (en)Blood product utilization system and methods
Griffey et al.The emergency department trigger tool: validation and testing to optimize yield
Yih et al.Sequential data-mining for adverse events after recombinant herpes zoster vaccination using the tree-based scan statistic
CN120432174B (en) An artificial intelligence-based tumor nursing service management system
JP3861986B2 (en) Risk management method and risk management support system for medical nursing work
CN110827004A (en)Nursing platform system based on clinical big data
CN118430729A (en)Intelligent medical information management system and method
CN118116560A (en)Scheduling method for narcotics
Ball et al.Tuberculosis skin test conversion among health care workers at a military medical center
JP2002269231A (en)Clinical data analysis processing method, system, computer program and medium
Tsumoto et al.Characterizing hospital services using temporal data mining
CN120032794B (en) Monitoring and management system for rational use of antimicrobial drugs based on the whole process of clinical pathway
Tsumoto et al.Temporal Data Mining in AI-based Patient Navigation Service
CN120280070B (en)Clinical trial patient screening and dynamic follow-up management method based on artificial intelligence
FrancisBarriers to Blood Availability Within the New Orleans Area

Legal Events

DateCodeTitleDescription
PB01Publication
PB01Publication
SE01Entry into force of request for substantive examination
SE01Entry into force of request for substantive examination
GR01Patent grant
GR01Patent grant

[8]ページ先頭

©2009-2025 Movatter.jp