A patient monitoring and management system for critical care units based on data analysis

By obtaining and analyzing the data of the treatment monitoring cycle in the patient monitoring management system of the critical care department, calculating the reference index and change covariance of the disease cycle, the problem that the existing system cannot deeply analyze the disease is solved, and systematically the condition of the severely ill patients is achieved Monitoring and early warning have improved the treatment effect.

CN118737361BActive Publication Date: 2024-11-05THE FIRST PEOPLES HOSPITAL OF CHANGZHOU
View PDF 0 Cites 3 Cited by

Patent Information

Application Number
CN202411216197.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-02
Publication Date
2024-11-05
Estimated Expiration
2044-09-02

AI Technical Summary

Technical Problem

The existing patient monitoring and management system in critical care departments cannot automatically monitor patient expressions and analyze symptoms, which makes it difficult for medical staff to understand the patient's pain level or emotional status in a timely manner, and the monitoring data lacks depth, which affects the formulation of treatment plans.

Method used

Using the patient monitoring and management system of the critical care department based on data analysis, the medical resource usage data, abnormal time ratio of physiological indicators, condition weight and typical symptom data of the treatment monitoring cycle, the reference index of the condition cycle and the covariance of the condition change are calculated, and the condition changes are carried out. Monitoring and early warning.

Benefits of technology

Systematic periodic monitoring and in-depth analysis of the condition of severe patients is achieved, signs of deterioration of the condition can be discovered in advance, treatment strategies are adjusted in a timely manner, and patient safety and treatment effect are improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118737361B_ABST
    Figure CN118737361B_ABST
Patent Text Reader

Abstract

The present invention discloses a patient monitoring and management system for a critical care unit based on data analysis, relates to the field of clinical medicine, solves the problem of poor condition monitoring effect of the patient monitoring and management system for a critical care unit, comprises a data acquisition module: used for acquiring periodic condition monitoring data, a data analysis module: used for obtaining periodic condition analysis data according to the periodic condition monitoring data, a change monitoring module: used for obtaining condition change monitoring data of critically ill patients according to the periodic condition analysis data, a monitoring and early warning module: used for monitoring and early warning according to the periodic condition monitoring data and the condition change monitoring data of critically ill patients, and utilizes the periodic changes of the periodic condition reference index to more accurately analyze and predict the patient's condition change trend, which helps to discover signs of worsening of the condition in advance, adjust the treatment strategy in time, and avoid rapid worsening of the condition or excessive treatment.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of clinical medicine and relates to data analysis technology, specifically a intensive care unit patient monitoring and management system based on data analysis. Background Art

[0002] The existing patient monitoring and management system for critical care units has the following defects:

[0003] 1. The inability to automatically monitor the patient's facial expressions and analyze their symptoms results in medical staff being unable to promptly understand the patient's pain level or emotional state, affecting their comprehensive assessment of the condition.

[0004] 2. The inability to systematically analyze symptoms results in a lack of depth in monitoring data, making it difficult for medical staff to obtain comprehensive information support when formulating treatment plans.

[0005] To this end, we propose a patient monitoring and management system for intensive care units based on data analysis. Summary of the Invention

[0006] In response to the deficiencies in the prior art, the present invention aims to provide a patient monitoring and management system for critical care units based on data analysis. The present invention obtains the periodic medical resource usage data, the cumulative abnormal time ratio of periodic physiological indicators, and the patient's condition weight corresponding to each treatment monitoring cycle, obtains the patient's typical symptom data, defines the periodic medical resource usage data, the cumulative abnormal time ratio of periodic physiological indicators, the patient's condition weight, and the patient's typical symptom data as condition cycle monitoring data, calculates the periodic condition reference index corresponding to each treatment monitoring cycle according to the condition cycle monitoring data, obtains condition cycle analysis data, calculates the patient's condition cycle change covariance according to the condition cycle analysis data, divides the patient's condition cycle change covariance into intervals, obtains critical patient condition change monitoring data, and performs monitoring and early warning based on the condition cycle monitoring data and the critical patient condition change monitoring data.

[0007] In order to achieve the above objectives, the present invention adopts the following technical solutions: The specific working process of each module of a patient monitoring and management system for critical care units based on data analysis is as follows:

[0008] Data acquisition module: used to divide the time period during which critically ill patients receive treatment into multiple treatment monitoring cycles, respectively obtain the periodic medical resource usage data, the cumulative abnormal time ratio of periodic physiological indicators, and the patient's condition weight corresponding to each treatment monitoring cycle, obtain the patient's typical symptom data, and define the periodic medical resource usage data, the cumulative abnormal time ratio of periodic physiological indicators, the patient's condition weight, and the patient's typical symptom data as the condition cycle monitoring data;

[0009] Data analysis module: used to calculate the periodic disease reference index corresponding to each treatment monitoring cycle based on the disease cycle monitoring data, and obtain the disease cycle analysis data;

[0010] Change monitoring module: used to calculate the patient's condition cycle change covariance based on the condition cycle analysis data, and divide the patient's condition cycle change covariance into intervals to obtain the condition change monitoring data of critically ill patients;

[0011] Monitoring and early warning module: used to provide monitoring and early warning based on the disease cycle monitoring data and the monitoring data of the condition changes of critically ill patients.

[0012] Furthermore, the data acquisition module includes a visual data unit, a symptom data unit, a disease condition weight unit, a medical data unit, and a physiological parameter unit;

[0013] During the time period when critically ill patients receive treatment in the intensive care unit, mk treatment monitoring cycles are marked respectively, and the cycle start time corresponding to each treatment monitoring cycle is numerically obtained to obtain mk cycle start time values. The time value corresponding to the current moment is obtained as the reference time value, and the difference between the mk cycle start time values ​​and the reference time value is obtained respectively to obtain mk time differences;

[0014] Arrange the mk time differences in order of numerical value, and name the treatment monitoring cycles corresponding to the mk time differences as the m1 to mk treatment monitoring cycles according to the arrangement order from large to small;

[0015] The symptom data unit analyzes the patient's clinical symptoms and obtains the patient's typical symptom data;

[0016] The visual data unit acquires and analyzes facial images of critically ill patients in the m1th treatment monitoring cycle to obtain the facial target image cycle duration ratio;

[0017] The medical data unit obtains the periodic medical resource usage data corresponding to the m1 treatment monitoring period for critically ill patients;

[0018] The physiological parameter unit obtains the periodic physiological index data corresponding to the m1 treatment monitoring cycle of the critically ill patient and obtains the cumulative abnormal time ratio of the periodic physiological index;

[0019] The condition weight unit analyzes the treatment symptoms of critically ill patients in the m1 treatment monitoring cycle to obtain the patient's condition weight;

[0020] The facial target image cycle duration ratio, cycle medical resource usage data, and cycle physiological indicator cumulative abnormal time ratio corresponding to each treatment monitoring cycle are obtained respectively, and defined as the disease cycle monitoring data together with the patient's typical symptom data.

[0021] Furthermore, the symptom data unit acquires typical symptom data of the patient, specifically as follows:

[0022] Obtain the cumulative symptom types that occur during the period of time that critically ill patients receive treatment in the intensive care unit, obtain the time value of the first appearance of each type of symptom during the patient monitoring process, and obtain multiple symptom first appearance time values;

[0023] According to the time values ​​of the first manifestation of multiple symptoms, the corresponding symptom types are named as the first to the hth clinical symptoms in order from far to near;

[0024] According to the admission records of the intensive care unit, several patients with the same symptoms as the critically ill patients are obtained as sample patients, and the clinical symptoms corresponding to each sample patient are obtained to obtain the clinical symptom record texts of multiple sample patients;

[0025] Performing identical text matching on clinical symptom records of multiple sample patients, taking clinical symptoms that exist in all clinical symptom records of sample patients as typical clinical symptoms, and obtaining multiple typical clinical symptoms;

[0026] The number of digits of the order in which each typical clinical symptom appears in the corresponding sample patients is obtained respectively, and multiple different order positions corresponding to each typical clinical symptom are obtained; the mode of the multiple different order positions corresponding to each typical clinical symptom is obtained respectively, and the typical order position corresponding to each typical clinical symptom is obtained;

[0027] Compare the first to hth clinical symptoms with multiple typical clinical symptoms respectively, count the clinical symptoms with the same symptom in the comparison results, obtain the second symptom number, calculate the ratio of the second symptom number to h, and obtain the patient's typical symptom similarity ratio;

[0028] Obtain whether the typical sequence rank corresponding to each typical clinical symptom is consistent with the ranks corresponding to the first to hth clinical symptoms;

[0029] If they are consistent, the corresponding clinical symptoms are marked as sequentially consistent clinical symptoms;

[0030] If inconsistent, the corresponding clinical symptoms were marked as sequence-inconsistent clinical symptoms;

[0031] Counting the number of clinical symptoms marked as sequentially consistent from the first to the hth clinical symptoms to obtain the number of clinical symptoms in the regular sequence;

[0032] Calculate the ratio of the number of clinical symptoms in the conventional sequence to h to obtain the ratio of the number of symptoms in the sequence;

[0033] The ratio of the number of sequentially consistent symptoms and the similarity ratio of the patient's typical symptoms were defined as the patient's typical symptom data.

[0034] Furthermore, the visual data unit obtains the facial target image period duration ratio as follows:

[0035] During the m1th treatment monitoring cycle, a facial image of a critically ill patient is acquired in real time by a first condition monitoring device to obtain a video stream of the patient's facial image, and a video duration of the video stream of the patient's facial image is acquired to obtain a first image cycle duration;

[0036] The video stream of the patient's facial image is intercepted with multiple patient facial images in units of single video frames, and the playback time of the single video frame in the video stream of the patient's facial image is obtained to obtain the unit video frame time;

[0037] Establishing a facial expression recognition model to perform image recognition on multiple patient facial images, dividing each patient facial image into target type facial recognition images and non-target type facial recognition images, and counting the number of target type facial recognition images to obtain the number of target type images;

[0038] The product of the number of target type images and the unit video frame duration is calculated, and then the ratio of the obtained product to the first image cycle duration is calculated to obtain the facial target image cycle duration ratio.

[0039] Furthermore, the medical data unit acquires periodic medical resource usage data as follows:

[0040] Obtain the online medical records of critically ill patients, obtain the medical expenses corresponding to the m1 treatment monitoring cycle of the critically ill patients through the online medical records, and obtain the cumulative medical expenses value of the cycle;

[0041] According to the online medical records of critically ill patients, the number of emergency medicine types used by the critically ill patients during the m1th treatment monitoring period is obtained, and the emergency medicines used are named the first to jth types of emergency medicines respectively;

[0042] Obtain the dosages of the first to j-th types of emergency drugs during the m1-th treatment monitoring period respectively, and obtain the dosages of the first to j-th drugs;

[0043] The dosage of the first to jth drugs, the number of emergency drug types, and the cumulative medical expenditure value of the period are defined as the period medical resource utilization data.

[0044] Furthermore, the physiological parameter unit obtains the cumulative abnormal time ratio of the periodic physiological index as follows:

[0045] In the m1th treatment monitoring cycle, the physiological indicators monitored for critically ill patients include the first to kth physiological indicators;

[0046] Performing periodic analysis on the first physiological indicator to obtain a first abnormal time ratio;

[0047] The details are as follows:

[0048] During the m1th treatment monitoring cycle, the first physiological indicator is monitored in real time by the monitoring equipment of the intensive care unit to obtain a monitoring indicator value;

[0049] If the obtained monitoring indicator value is within the normal interval corresponding to the first physiological indicator, it is determined that the first physiological indicator at the current moment is in the normal period;

[0050] If the obtained monitoring indicator value is not within the normal interval corresponding to the first physiological indicator, it is determined that the first physiological indicator at the current moment is in an abnormal period, and the time length value of the abnormal period is obtained to obtain the abnormal duration of the first physiological indicator;

[0051] Obtaining the cumulative monitoring duration of the first physiological indicator in the m1th treatment monitoring cycle to obtain the first cycle cumulative monitoring duration, and calculating the ratio of the abnormal duration of the first physiological indicator to the first cycle cumulative monitoring duration to obtain the first abnormal time ratio;

[0052] Repeat the process of obtaining the first abnormal time ratio, and obtain the abnormal time ratios of the second to k-th physiological indicators in the m1-th treatment monitoring cycle respectively, to obtain the second to k-th abnormal time ratios;

[0053] The first to kth abnormal time ratios are summed to obtain the cumulative abnormal time ratio of the periodic physiological index.

[0054] Furthermore, the condition weight unit obtains the patient's condition weight as follows:

[0055] The symptoms that occur in the patient during the m1th treatment monitoring cycle are divided into the first to tth treatment symptoms, and the symptom severity scores are respectively performed for the first to tth treatment symptoms to obtain the first to tth symptom severity scores;

[0056] Count the number of occurrences of the first to tth treatment symptoms during the m1th treatment monitoring period to obtain the number of occurrences of the first to tth symptoms;

[0057] The patient's condition weight corresponding to the m1th treatment monitoring period is obtained by calculating the number of occurrences of the first to tth symptoms and the severity scores of the first to tth symptoms corresponding to the m1th treatment monitoring period;

[0058] The details are as follows:

[0059] ;

[0060] Among them, Zym is the patient's condition weight corresponding to the m1th treatment monitoring cycle, Zc1 to Zct are the number of occurrences of the first to tth symptoms, and Zy1 to Zyt are the severity scores of the first to tth symptoms, respectively.

[0061] Furthermore, the data analysis module acquires the disease cycle analysis data as follows:

[0062] Obtaining condition cycle monitoring data, and obtaining the facial target image cycle duration ratio, patient condition weight, periodic medical resource usage data, and periodic physiological indicator cumulative abnormal time ratio corresponding to the m1 treatment monitoring cycle based on the condition cycle monitoring data;

[0063] According to the periodic medical resource usage data, the first to j-th drug dosages, the number of emergency drug types and the cumulative medical expenditure values ​​corresponding to the m1-th treatment monitoring period are obtained respectively;

[0064] The periodic medical resource utilization coefficient corresponding to the m1th treatment monitoring period is calculated by the formula using the first to jth drug dosages, the number of emergency drug types, and the periodic cumulative medical expenditure values ​​corresponding to the m1th treatment monitoring period;

[0065] The formula is as follows:

[0066] ;

[0067] Among them, Zzy is the period medical resource utilization coefficient, Jl1 to Jlj are the dosages of the first to jth drugs respectively, j is the quantity value corresponding to the type of emergency drugs, Jzl is the number of emergency drugs, and Lhf is the cumulative medical expenditure value of the period;

[0068] The periodic medical resource utilization coefficient, the facial target image period duration ratio corresponding to the m1th treatment monitoring period, the patient's condition weight, and the cumulative abnormal time ratio of the periodic physiological indicators are calculated by a formula to obtain the periodic condition reference index corresponding to the m1th treatment monitoring period;

[0069] The formula is as follows:

[0070] ;

[0071] Among them, Zzs1 is the reference index of the condition in the m1th cycle, Zym is the patient's condition weight, Zzy is the cycle medical resource utilization coefficient, Ysb is the cumulative abnormal time ratio of the physiological indicators in the cycle, and Mtb is the cycle duration ratio of the facial target image;

[0072] Repeat the process of obtaining the periodic disease condition reference index corresponding to the m1th treatment monitoring cycle, and obtain the periodic disease condition reference index corresponding to the m2th to mkth treatment monitoring cycles respectively;

[0073] The periodic disease condition reference index corresponding to the treatment monitoring periods m1 to mk is defined as the disease condition periodic analysis data.

[0074] Furthermore, the change monitoring module acquires the monitoring data of the condition change of the critically ill patient, as follows:

[0075] Obtaining disease cycle analysis data, and obtaining a periodic disease reference index corresponding to the treatment monitoring cycles m1 to mk according to the disease cycle analysis data;

[0076] The periodic disease condition reference indices corresponding to the treatment monitoring periods m1 to mk are named as the periodic disease condition reference indices m1 to mk respectively;

[0077] Obtain the time values ​​of the cycle start times corresponding to the treatment monitoring cycles m1 to mk respectively, and obtain the start time values ​​of the cycles m1 to mk;

[0078] Calculate the average of the start time values ​​of cycles m1 to mk to obtain the average start time of the cycle;

[0079] Calculate the average of the disease condition reference index from cycle m1 to cycle mk to obtain the average value of the disease condition reference index;

[0080] The covariance of the patient's condition cycle change is obtained by calculating the average value of the cycle start time, the value of the start time of the m1 to mk cycles, the average value of the cycle condition reference index, and the condition reference index of the m1 to mk cycles;

[0081] The covariance of the patient's condition cycle change is calculated. The specific formula is as follows:

[0082] ;

[0083] Among them, Cov (X, Y) is the covariance of the patient's condition cycle change, X1 to Xmk are the starting time values ​​of the m1 to mk cycles, and Y1 to Ymk are the reference indexes of the condition of the m1 to mk cycles. is the average of the period start time, is the average value of the periodic disease reference index;

[0084] Obtaining the first cycle covariance change threshold and the second cycle covariance change threshold respectively, comparing the patient's condition cycle change covariance with the first cycle covariance change threshold and the second cycle covariance change threshold to obtain the critical patient condition change monitoring data;

[0085] The details are as follows:

[0086] When the patient's condition cycle change covariance is greater than or equal to the first cycle covariance change threshold, it is judged that the patient is in the first condition change interval;

[0087] When the patient's condition cycle change covariance is less than the first cycle covariance change threshold and greater than the second cycle covariance change threshold, it is judged that the patient's condition is in the second condition change interval;

[0088] When the covariance of the patient's condition cycle change is less than or equal to the second cycle covariance change threshold, it is judged that the patient's condition is severe and is in the third condition change interval.

[0089] Furthermore, the monitoring and early warning module performs monitoring and early warning according to the monitoring data of the critically ill patients' condition changes, as follows:

[0090] Obtain monitoring data on the condition changes of critically ill patients;

[0091] When a critically ill patient is in the first condition change range, the monitoring system issues an early warning of periodic worsening of the condition;

[0092] When the critically ill patient is in the third condition change interval, the monitoring system monitors the condition change of the critically ill patient to normal;

[0093] When a critically ill patient is in the second condition change range, the monitoring system will assess the patient's condition and issue an early warning based on the assessment results.

[0094] The details are as follows:

[0095] Obtaining condition cycle monitoring data, obtaining an abnormal time ratio corresponding to the mkth treatment monitoring cycle according to the condition cycle monitoring data, and obtaining the mkth abnormal time ratio;

[0096] Obtain the patient's typical symptom data, and obtain the ratio of the number of symptoms with consistent order and the similarity ratio of the patient's typical symptoms based on the patient's typical symptom data;

[0097] The mkth abnormal time ratio, the number ratio of symptoms with consistent sequence and the similarity ratio of typical symptoms of patients are calculated to obtain the severity assessment coefficient of patients;

[0098] The coefficient for evaluating the condition of critically ill patients is calculated. The specific formula is as follows:

[0099] ;

[0100] Among them, Zyp is the coefficient for judging the condition of severe patients, Ymk is the ratio of the mkth abnormal time, Sxy is the ratio of the number of symptoms with consistent sequence, and Hdx is the similarity ratio of the patient's typical symptoms;

[0101] Obtaining a threshold value of a critically ill patient's condition assessment coefficient, and numerically comparing the critically ill patient's condition assessment coefficient with the threshold value of a critically ill patient's condition assessment coefficient;

[0102] The details are as follows:

[0103] Obtain the mkth abnormal time ratio threshold, the sequential consistent symptom number ratio threshold, and the patient's typical symptom similarity ratio threshold respectively;

[0104] The threshold of the critical illness patient condition assessment coefficient is obtained by calculating the mkth abnormal time ratio threshold, the number of sequentially consistent symptoms ratio threshold, and the patient's typical symptom similarity ratio threshold;

[0105] When the critical patient condition assessment coefficient ratio is greater than the critical patient condition assessment coefficient threshold, the monitoring system will issue a critical patient treatment warning;

[0106] When the critical patient condition assessment coefficient is less than or equal to the critical patient condition assessment coefficient threshold, the monitoring system monitors the critical patient's condition normally.

[0107] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0108] 1. The present invention performs periodic monitoring of the condition of critically ill patients by acquiring periodic monitoring data of the condition, and can systematically analyze the periodic changes of the patient's condition, providing comprehensive information support for medical staff to formulate treatment plans;

[0109] 2. The present invention utilizes the cyclical changes of the cyclical disease reference index to more accurately analyze and predict the changing trend of the patient's disease condition, which helps to detect signs of disease deterioration in advance and adjust the treatment strategy in time to avoid rapid deterioration of the disease or overtreatment;

[0110] 3. The present invention provides real-time monitoring and early warning based on the monitoring data of the condition changes of critically ill patients. The medical team can quickly respond to changes in the condition and take necessary intervention measures in a timely manner, thereby improving the safety of patients and the treatment effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0111] To facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0112] Figure 1 is a block diagram of the overall system of the present invention;

[0113] Figure 2 This is a structural block diagram of the data acquisition module unit in the present invention;

[0114] Figure 3 This is a data interaction diagram in the present invention. DETAILED DESCRIPTION

[0115] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0116] Example 1

[0117] See also Figure 1 The present invention provides a technical solution: a patient monitoring and management system for a critical care unit based on data analysis, comprising a data acquisition module, a data analysis module, a change monitoring module, a monitoring and early warning module, and a server, wherein the data acquisition module, the data analysis module, the change monitoring module, and the monitoring and early warning module are respectively connected to the server, and the server controls the data acquisition module, the data analysis module, the change monitoring module, and the monitoring and early warning module respectively;

[0118] The data acquisition module acquires the disease cycle monitoring data;

[0119] See also Figure 2 ,The data acquisition module includes a visual data unit, a symptom data unit, a disease weight unit, a medical data unit, and a physiological parameter unit;

[0120] During the time period when critically ill patients receive treatment in the intensive care unit, mk treatment monitoring cycles are marked respectively, and the cycle start time corresponding to each treatment monitoring cycle is numerically obtained to obtain mk cycle start time values, and the time value corresponding to the current moment is obtained as the reference time value, and the difference between the mk cycle start time values ​​and the reference time value is obtained respectively to obtain mk time differences;

[0121] Arrange the mk time differences in order of numerical value, and name the treatment monitoring cycles corresponding to the mk time differences as the m1 to mk treatment monitoring cycles according to the arrangement order from large to small;

[0122] It should be noted here that:

[0123] In this application, mk is the quantity value corresponding to the marked treatment monitoring cycle, and mk is an integer greater than 0;

[0124] The symptom data unit analyzes the patient's clinical symptoms and obtains the patient's typical symptom data;

[0125] Obtain the cumulative symptom types that occur during the period of time that critically ill patients receive treatment in the intensive care unit, obtain the time value of the first appearance of each type of symptom during the patient monitoring process, and obtain multiple symptom first appearance time values;

[0126] According to the time values ​​of the first manifestation of multiple symptoms, the corresponding symptom types are named as the first to the hth clinical symptoms in order from far to near;

[0127] It should be noted here that:

[0128] h is the quantity value corresponding to the symptom type;

[0129] According to the admission records of the intensive care unit, several patients with the same symptoms as the critically ill patients are obtained as sample patients, and the clinical symptoms corresponding to each sample patient are obtained to obtain the clinical symptom record texts of multiple sample patients;

[0130] Performing identical text matching on clinical symptom records of multiple sample patients, taking clinical symptoms that exist in all clinical symptom records of sample patients as typical clinical symptoms, and obtaining multiple typical clinical symptoms;

[0131] The number of digits of the order in which each typical clinical symptom appears in the corresponding sample patients is obtained respectively, and multiple different order positions corresponding to each typical clinical symptom are obtained; the mode of the multiple different order positions corresponding to each typical clinical symptom is obtained respectively, and the typical order position corresponding to each typical clinical symptom is obtained;

[0132] It should be noted here that:

[0133] If there are the same modes, the corresponding typical clinical symptoms will be ranked in order;

[0134] Compare the first to hth clinical symptoms with multiple typical clinical symptoms respectively, count the clinical symptoms with the same symptom in the comparison results, obtain the second symptom number, calculate the ratio of the second symptom number to h, and obtain the patient's typical symptom similarity ratio;

[0135] Obtain whether the typical sequence rank corresponding to each typical clinical symptom is consistent with the ranks corresponding to the first to hth clinical symptoms;

[0136] If they are consistent, the corresponding clinical symptoms are marked as sequentially consistent clinical symptoms;

[0137] If inconsistent, the corresponding clinical symptoms were marked as sequence-inconsistent clinical symptoms;

[0138] It should be noted here that:

[0139] For example, a typical clinical symptom is randomly selected as a characteristic typical clinical symptom. If the characteristic typical clinical symptom is ranked second in the typical order, and the second clinical symptom of the critically ill patient is the same as the characteristic typical clinical symptom, the second clinical symptom is marked as a clinical symptom with consistent order.

[0140] Counting the number of clinical symptoms marked as sequentially consistent from the first to the hth clinical symptoms to obtain the number of clinical symptoms in the regular sequence;

[0141] Calculate the ratio of the number of clinical symptoms in the conventional sequence to h to obtain the ratio of the number of symptoms in the sequence;

[0142] The ratio of the number of sequentially consistent symptoms and the similarity ratio of the patient's typical symptoms were defined as the patient's typical symptom data;

[0143] The visual data unit acquires and analyzes facial images of critically ill patients in the m1th treatment monitoring cycle to obtain the facial target image cycle duration ratio;

[0144] The details are as follows:

[0145] During the m1th treatment monitoring cycle, a facial image of a critically ill patient is acquired in real time by a first condition monitoring device to obtain a video stream of the patient's facial image, and a video duration of the video stream of the patient's facial image is acquired to obtain a first image cycle duration;

[0146] The video stream of the patient's facial image is intercepted with multiple patient facial images in units of single video frames, and the playback time of the single video frame in the video stream of the patient's facial image is obtained to obtain the unit video frame time;

[0147] It should be noted here that:

[0148] In this application, the frame rate of the video stream of the patient's facial image is 30fps, so each frame of the image takes 0.33 seconds, that is, the unit video frame length involved here is 0.33 seconds;

[0149] Establishing a facial expression recognition model to perform image recognition on multiple patient facial images, dividing each patient facial image into target type facial recognition images and non-target type facial recognition images, and counting the number of target type facial recognition images to obtain the number of target type images;

[0150] It should be noted here that:

[0151] In this application, the target type facial recognition image is a painful expression image, and the non-target type facial recognition image is a non-painful expression image. The painful expressions involved here include but are not limited to tears, wailing, and eyes closed but tears rolling down. The non-painful expressions involved here include but are not limited to smiles and joy.

[0152] The facial expression recognition model involved here can be a recurrent neural network;

[0153] Calculate the product of the number of target type images and the unit video frame duration, and then calculate the ratio of the obtained product to the first image cycle duration to obtain the facial target image cycle duration ratio;

[0154] The medical data unit obtains the periodic medical resource usage data corresponding to the m1 treatment monitoring period of the critically ill patient;

[0155] The details are as follows:

[0156] Obtain the online medical records of critically ill patients, obtain the medical expenses corresponding to the m1 treatment monitoring cycle of the critically ill patients through the online medical records, and obtain the cumulative medical expenses value of the cycle;

[0157] It should be noted here that:

[0158] In this application, the cumulative medical expenses for a period do not include the cost of some basic examinations included in the initial hospitalization of the patient;

[0159] According to the online medical records of critically ill patients, the number of emergency medicine types used by the critically ill patients during the m1th treatment monitoring period is obtained, and the emergency medicines used are named the first to jth types of emergency medicines respectively;

[0160] It should be noted here that:

[0161] In this application, j is the quantity value corresponding to the type of emergency medicine used by the critically ill patient during the m1th treatment monitoring period, and j is an integer;

[0162] Among them, if the critically ill patient does not use any emergency medicine during the m1 treatment monitoring cycle, j is 0;

[0163] In this application, the classification of emergency medication types is based on specific reference to the emergency medication guidelines developed by the regional health department, among which common emergency medications include but are not limited to epinephrine, aminophylline, and dobutamine;

[0164] Obtain the dosages of the first to j-th types of emergency drugs during the m1-th treatment monitoring period respectively, and obtain the dosages of the first to j-th drugs;

[0165] The dosage of the first to jth drugs, the number of emergency drug types and the cumulative medical expenditure of the period are defined as the period medical resource utilization data;

[0166] The physiological parameter unit obtains the periodic physiological index data corresponding to the m1 treatment monitoring cycle of the critically ill patient and obtains the cumulative abnormal time ratio of the periodic physiological index;

[0167] The details are as follows:

[0168] In the m1th treatment monitoring cycle, the physiological indicators monitored for critically ill patients include the first to kth physiological indicators;

[0169] It should be noted here that:

[0170] The k involved here specifically refers to the number of types of physiological indicators monitored in real time for critically ill patients. In actual applications, the number of types of physiological indicators will be adjusted accordingly for different critically ill patients, and k is an integer greater than 0;

[0171] Performing periodic analysis on the first physiological indicator to obtain a first abnormal time ratio;

[0172] The details are as follows:

[0173] During the m1th treatment monitoring cycle, the first physiological indicator is monitored in real time by the monitoring equipment of the intensive care unit to obtain a monitoring indicator value;

[0174] If the obtained monitoring indicator value is within the normal interval corresponding to the first physiological indicator, it is determined that the first physiological indicator at the current moment is in the normal period;

[0175] If the obtained monitoring indicator value is not within the normal interval corresponding to the first physiological indicator, it is determined that the first physiological indicator at the current moment is in an abnormal period, and the time length value of the abnormal period is obtained to obtain the abnormal duration of the first physiological indicator;

[0176] Obtaining the cumulative monitoring duration of the first physiological indicator in the m1th treatment monitoring cycle to obtain the first cycle cumulative monitoring duration, and calculating the ratio of the abnormal duration of the first physiological indicator to the first cycle cumulative monitoring duration to obtain the first abnormal time ratio;

[0177] Repeat the process of obtaining the first abnormal time ratio, and obtain the abnormal time ratios of the second to k-th physiological indicators in the m1-th treatment monitoring cycle respectively, to obtain the second to k-th abnormal time ratios;

[0178] Sum the first to kth abnormal time ratios to obtain the cumulative abnormal time ratio of the periodic physiological index;

[0179] The condition weight unit analyzes the treatment symptoms of critically ill patients in the m1 treatment monitoring cycle to obtain the patient's condition weight;

[0180] The details are as follows:

[0181] The symptoms that occur in the patient during the m1th treatment monitoring cycle are divided into the first to tth treatment symptoms, and the symptom severity scores are respectively performed for the first to tth treatment symptoms to obtain the first to tth symptom severity scores;

[0182] It should be noted here that:

[0183] The specific treatment symptoms appearing here need to be specifically set according to the actual symptoms of the severe disease;

[0184] In specific clinical situations, the symptom severity score needs to be set accordingly based on the patient's specific symptoms and in combination with medical literature and the doctor's clinical diagnosis;

[0185] For example, if the patient is a pulmonary tuberculosis patient, the first treatment symptom may be dyspnea, the second treatment symptom may be chest pain, the third treatment symptom may be fever, the fourth treatment symptom may be cough, and the fifth treatment symptom may be a painful expression recognized by the facial expression recognition model. The first to fifth treatment symptoms are scored as F1 to F5, respectively, and F1>F2>F3>F4>F5>0 to obtain the severity scores of the first to fifth symptoms;

[0186] Count the number of occurrences of the first to tth treatment symptoms during the m1th treatment monitoring period to obtain the number of occurrences of the first to tth symptoms;

[0187] The patient's condition weight corresponding to the m1th treatment monitoring period is obtained by calculating the number of occurrences of the first to tth symptoms and the severity scores of the first to tth symptoms corresponding to the m1th treatment monitoring period;

[0188] The details are as follows:

[0189] ;

[0190] Among them, Zym is the patient's condition weight corresponding to the m1th treatment monitoring period, Zc1 to Zct are the number of occurrences of the first to tth symptoms, and Zy1 to Zyt are the severity scores of the first to tth symptoms, respectively;

[0191] See also Figure 3 Repeat the process of obtaining the facial target image cycle time ratio, patient condition weight, cycle medical resource usage data, and cycle physiological index cumulative abnormal time ratio corresponding to the m1th treatment monitoring cycle, respectively obtain the facial target image cycle time ratio, cycle medical resource usage data, and cycle physiological index cumulative abnormal time ratio corresponding to each treatment monitoring cycle, and define them together with the patient's typical symptom data as the condition cycle monitoring data;

[0192] The data acquisition module monitors the disease cycle data and transmits it to the data analysis module and the monitoring and early warning module;

[0193] The data analysis module performs periodic condition analysis on critically ill patients based on the condition cycle monitoring data to obtain condition cycle analysis data;

[0194] Obtaining condition cycle monitoring data, and obtaining the facial target image cycle duration ratio, patient condition weight, periodic medical resource usage data, and periodic physiological indicator cumulative abnormal time ratio corresponding to the m1 treatment monitoring cycle based on the condition cycle monitoring data;

[0195] According to the periodic medical resource usage data, the first to j-th drug dosages, the number of emergency drug types and the cumulative medical expenditure values ​​corresponding to the m1-th treatment monitoring period are obtained respectively;

[0196] The periodic medical resource utilization coefficient corresponding to the m1th treatment monitoring period is calculated by the formula using the first to jth drug dosages, the number of emergency drug types, and the periodic cumulative medical expenditure values ​​corresponding to the m1th treatment monitoring period;

[0197] The formula is as follows:

[0198] ;

[0199] Among them, Zzy is the period medical resource utilization coefficient, Jl1 to Jlj are the dosages of the first to jth drugs respectively, j is the quantity value corresponding to the type of emergency drugs, Jzl is the number of emergency drugs, and Lhf is the cumulative medical expenditure value of the period;

[0200] The periodic medical resource utilization coefficient, the facial target image period duration ratio corresponding to the m1th treatment monitoring period, the patient's condition weight, and the cumulative abnormal time ratio of the periodic physiological indicators are calculated by a formula to obtain the periodic condition reference index corresponding to the m1th treatment monitoring period;

[0201] The formula is as follows:

[0202] ;

[0203] Among them, Zzs1 is the reference index of the condition in the m1th cycle, Zym is the patient's condition weight, Zzy is the cycle medical resource utilization coefficient, Ysb is the cumulative abnormal time ratio of the physiological indicators in the cycle, and Mtb is the cycle duration ratio of the facial target image;

[0204] Repeat the process of obtaining the periodic disease condition reference index corresponding to the m1th treatment monitoring cycle, and obtain the periodic disease condition reference index corresponding to the m2th to mkth treatment monitoring cycles respectively;

[0205] The periodic disease reference index corresponding to the treatment monitoring period from m1 to mk is defined as the disease period analysis data;

[0206] The data analysis module acquires the disease cycle analysis data and transmits it to the change monitoring module and the monitoring and early warning module;

[0207] The change monitoring module monitors the condition changes of critically ill patients based on the condition cycle analysis data to obtain the condition change monitoring data of critically ill patients;

[0208] Obtaining disease cycle analysis data, and obtaining a periodic disease reference index corresponding to the treatment monitoring cycles m1 to mk according to the disease cycle analysis data;

[0209] The periodic disease condition reference indices corresponding to the treatment monitoring periods m1 to mk are named as the periodic disease condition reference indices m1 to mk respectively;

[0210] Obtain the time values ​​of the cycle start times corresponding to the treatment monitoring cycles m1 to mk respectively, and obtain the start time values ​​of the cycles m1 to mk;

[0211] Calculate the average of the start time values ​​of cycles m1 to mk to obtain the average start time of the cycle;

[0212] Calculate the average of the disease condition reference index from cycle m1 to cycle mk to obtain the average value of the disease condition reference index;

[0213] The covariance of the patient's condition cycle change is obtained by calculating the average value of the cycle start time, the value of the start time of the m1 to mk cycles, the average value of the cycle condition reference index, and the condition reference index of the m1 to mk cycles;

[0214] The covariance of the patient's condition cycle change is calculated. The specific formula is as follows:

[0215] ;

[0216] Among them, Cov (X, Y) is the covariance of the patient's condition cycle change, X1 to Xmk are the starting time values ​​of the m1 to mk cycles, and Y1 to Ymk are the reference indexes of the condition of the m1 to mk cycles. is the average of the period start time, is the average value of the periodic disease reference index;

[0217] Obtaining the first cycle covariance change threshold and the second cycle covariance change threshold respectively, comparing the patient's condition cycle change covariance with the first cycle covariance change threshold and the second cycle covariance change threshold to obtain the critical patient condition change monitoring data;

[0218] It should be noted here that:

[0219] The first-cycle covariance change threshold is greater than 0, the second-cycle covariance change threshold is less than 0, and the absolute values ​​of the first-cycle covariance change threshold and the second-cycle covariance change threshold are the same;

[0220] The details are as follows:

[0221] When the patient's condition cycle change covariance is greater than or equal to the first cycle covariance change threshold, it is judged that the patient is in the first condition change interval;

[0222] When the patient's condition cycle change covariance is less than the first cycle covariance change threshold and greater than the second cycle covariance change threshold, it is judged that the patient's condition is in the second condition change interval;

[0223] When the patient's condition cycle change covariance is less than or equal to the second cycle covariance change threshold, it is judged that the patient's condition is in the third condition change interval;

[0224] It should be noted here that:

[0225] The critically ill patients corresponding to the first condition change interval are in the stage of cyclical worsening of their condition, the critically ill patients corresponding to the third condition change interval are in the stage of cyclical improvement of their condition, and the critically ill patients corresponding to the first condition change interval have no obvious cyclical changes in their condition;

[0226] The monitoring and early warning module provides monitoring and early warning based on the monitoring data of the critically ill patients' condition changes;

[0227] Obtain monitoring data on the condition changes of critically ill patients;

[0228] When a critically ill patient is in the first condition change range, the monitoring system issues an early warning of periodic worsening of the condition;

[0229] When the critically ill patient is in the third condition change interval, the monitoring system monitors the condition change of the critically ill patient to normal;

[0230] When a critically ill patient is in the second condition change range, the monitoring system will assess the patient's condition and issue an early warning based on the assessment results.

[0231] The details are as follows:

[0232] Obtaining condition cycle monitoring data, obtaining an abnormal time ratio corresponding to the mkth treatment monitoring cycle according to the condition cycle monitoring data, and obtaining the mkth abnormal time ratio;

[0233] Obtain the patient's typical symptom data, and obtain the ratio of the number of symptoms with consistent order and the similarity ratio of the patient's typical symptoms based on the patient's typical symptom data;

[0234] The mkth abnormal time ratio, the number ratio of symptoms with consistent sequence and the similarity ratio of typical symptoms of patients are calculated to obtain the severity assessment coefficient of patients;

[0235] The coefficient for evaluating the condition of critically ill patients is calculated. The specific formula is as follows:

[0236] ;

[0237] Among them, Zyp is the coefficient for judging the condition of severe patients, Ymk is the ratio of the mkth abnormal time, Sxy is the ratio of the number of symptoms with consistent sequence, and Hdx is the similarity ratio of the patient's typical symptoms;

[0238] Obtaining a threshold value of a critically ill patient's condition assessment coefficient, and numerically comparing the critically ill patient's condition assessment coefficient with the critically ill patient's condition assessment coefficient threshold value;

[0239] The details are as follows:

[0240] Obtain the mkth abnormal time ratio threshold, the sequential consistent symptom number ratio threshold, and the patient's typical symptom similarity ratio threshold respectively;

[0241] The threshold of the critical illness patient condition assessment coefficient is obtained by calculating the mkth abnormal time ratio threshold, the number of sequentially consistent symptoms ratio threshold, and the patient's typical symptom similarity ratio threshold;

[0242] The threshold value of the coefficient for critically ill patients is calculated. The specific formula is as follows:

[0243] ;

[0244] Among them, Zypy is the threshold value of the coefficient for judging the condition of severe patients, Ymky is the threshold value for the ratio of the mkth abnormal time, Sxyy is the threshold value for the ratio of the number of symptoms with consistent sequence, and Hdxy is the threshold value for the similarity ratio of the typical symptoms of patients;

[0245] When the critical patient condition assessment coefficient ratio is greater than the critical patient condition assessment coefficient threshold, the monitoring system will issue a critical patient treatment warning;

[0246] When the critical patient condition assessment coefficient is less than or equal to the critical patient condition assessment coefficient threshold, the monitoring system monitors the critical patient's condition normally;

[0247] In this application, if a corresponding calculation formula appears, the above calculation formula is dimensionless and its numerical calculation is performed. The weight coefficient, proportional coefficient and other coefficients in the formula are set to a result value obtained by quantifying each parameter. Regarding the size of the weight coefficient and the proportional coefficient, as long as it does not affect the proportional relationship between the parameter and the result value, it is acceptable.

[0248] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A patient monitoring and management system for critical care units based on data analysis, It is characterized in that include: Data acquisition module: used to divide the time period of critically ill patients receiving treatment into multiple treatment monitoring cycles; The ratio of the number of symptoms with consistent order and the similarity ratio of the patient's typical symptoms corresponding to each treatment monitoring cycle are obtained to obtain the patient's typical symptom data; The data acquisition module includes a symptom data unit, which acquires typical symptom data of the patient; The symptom data unit acquires typical symptom data of the patient, as follows: Obtain the cumulative symptom types that occur during the period of time when the critically ill patient receives treatment in the critical care department, obtain the first appearance time value corresponding to each type of symptom during the patient monitoring process, and obtain multiple symptom first appearance time values; According to the values ​​of the first manifestation time of multiple symptoms, the corresponding symptom types are named as the first to the hth clinical symptoms in order from far to near; Obtain several patients with the same symptoms as the critically ill patients as sample patients, obtain the text of the clinical symptoms corresponding to each sample patient, and obtain the clinical symptom record texts of multiple sample patients; Performing identical text matching on clinical symptom record texts of multiple sample patients, taking clinical symptoms existing in the clinical symptom record texts of each sample patient as typical clinical symptoms, and obtaining multiple typical clinical symptoms; The number of digits of each typical clinical symptom appearing in the corresponding sample patients is obtained respectively, and a plurality of different rank orders corresponding to each typical clinical symptom is obtained; the mode is obtained for a plurality of different rank orders corresponding to each typical clinical symptom respectively, and a typical rank order corresponding to each typical clinical symptom is obtained; Compare the first to h clinical symptoms with multiple typical clinical symptoms respectively, count the clinical symptoms with the same comparison results, obtain the second symptom number, calculate the ratio of the second symptom number to h, and obtain the patient's typical symptom similarity ratio; Obtain whether the typical sequence rank corresponding to each typical clinical symptom is consistent with the ranks corresponding to the first to the hth clinical symptoms; If they are consistent, the corresponding clinical symptoms are marked as sequentially consistent clinical symptoms; If they are inconsistent, the corresponding clinical symptoms are marked as sequence-inconsistent clinical symptoms; Counting the number of clinical symptoms marked as sequentially consistent from the first to the hth clinical symptoms, and obtaining the number of clinical symptoms in the regular sequence; Calculate the ratio of the number of clinical symptoms in the conventional sequence to h to obtain the ratio of the number of symptoms in the consistent sequence; The ratio of the number of sequentially consistent symptoms and the similarity ratio of the patient's typical symptoms were defined as the patient's typical symptom data; Acquire facial images of critically ill patients in each treatment monitoring cycle, and divide the facial images into target type facial recognition images and non-target type facial recognition images, calculate the ratio of the appearance duration of the target type facial recognition images to the duration of the corresponding image cycle, and obtain the facial target image cycle duration ratio; The abnormal time period of the physiological indicators of critically ill patients in each treatment monitoring cycle is judged, and the ratio of the abnormal duration of each indicator to the corresponding cumulative monitoring duration of the cycle is calculated to obtain multiple abnormal time ratios, and the multiple abnormal time ratios are summed to obtain the cumulative abnormal time ratio of the periodic physiological indicators; The severity score and frequency of symptoms in each treatment monitoring cycle were calculated to obtain the patient condition weights corresponding to different treatment monitoring cycles; The amount of medicine and cost of critically ill patients in each treatment monitoring cycle are obtained to obtain periodic medical resource usage data; the data obtained in the treatment monitoring cycle is defined as the disease cycle monitoring data; Data analysis module: Calculate the periodic medical resource utilization coefficient corresponding to each treatment monitoring cycle based on the disease cycle monitoring data, and calculate the periodic disease reference index by combining the facial target image cycle duration ratio, the patient's disease weight, and the cumulative abnormal time ratio of the periodic physiological indicators to obtain the disease cycle analysis data; Change monitoring module: used to calculate the patient's condition cycle change covariance based on the condition cycle analysis data, and divide the critically ill patients into the first condition change interval, the second condition change interval and the third condition change interval according to the patient's condition cycle change covariance, so as to obtain the critically ill patients' condition change monitoring data; Monitoring and early warning module: used for monitoring and early warning based on the disease cycle monitoring data and the monitoring data of the condition changes of critically ill patients.

2. According to claim 1, a patient monitoring and management system for critical care units based on data analysis, It is characterized in that The data acquisition module also includes a visual data unit, a disease weight unit, a medical data unit and a physiological parameter unit; During the time period when the critically ill patients are receiving treatment in the intensive care unit, mk treatment monitoring cycles are marked respectively, and the cycle start time corresponding to each treatment monitoring cycle is numerically obtained to obtain mk cycle start time values, and the time value corresponding to the current moment is obtained as the reference time value, and the difference between the mk cycle start time values ​​and the reference time value is obtained respectively to obtain mk time difference values; Arrange the mk time difference values ​​in order according to their numerical values, and name the treatment monitoring cycles corresponding to the mk time difference values ​​as the m1 to mk treatment monitoring cycles according to the arrangement order from large to small; The visual data unit acquires and analyzes facial images of critically ill patients in the m1th treatment monitoring cycle to obtain the facial target image cycle duration ratio; The medical data unit obtains the periodic medical resource usage data of the critically ill patients in the m1th treatment monitoring cycle; The physiological parameter unit acquires the periodic physiological index data of the critically ill patient in the m1th treatment monitoring cycle to obtain the cumulative abnormal time ratio of the periodic physiological index; The condition weight unit analyzes the treatment symptoms of the critically ill patients in the m1th treatment monitoring cycle to obtain the patient's condition weight; The facial target image cycle duration ratio, cycle medical resource usage data, and cycle physiological index cumulative abnormal time ratio corresponding to each treatment monitoring cycle are obtained respectively, and defined as the disease cycle monitoring data together with the patient's typical symptom data.

3. According to claim 2, a patient monitoring and management system for critical care units based on data analysis, It is characterized in that The visual data unit acquires the period duration ratio of the facial target image as follows: In the m1th treatment monitoring cycle, the facial image of the critically ill patient is acquired in real time by the first condition monitoring device to obtain a video stream of the facial image of the patient, and the video duration of the video stream of the facial image of the patient is acquired to obtain the duration of the first image cycle; The video stream of the patient's facial image is intercepted into a plurality of patient's facial images in units of a single video frame, and the playing time of the single video frame in the video stream of the patient's facial image is obtained to obtain the unit video frame time; Establish a facial expression recognition model to perform image recognition on multiple patient facial images respectively, divide each patient facial image into a target type facial recognition image and a non-target type facial recognition image respectively, count the number of target type facial recognition images, and obtain the number of target type images; The product of the number of target type images and the unit video frame duration is calculated, and then the ratio of the obtained product to the first image cycle duration is calculated to obtain the facial target image cycle duration ratio.

4. According to claim 2, a patient monitoring and management system for critical care units based on data analysis, It is characterized in that The medical data unit acquires periodic medical resource usage data as follows: Obtain the medical expenses of critically ill patients corresponding to the m1 treatment monitoring cycle through online medical records, and obtain the cumulative medical expenses value of the cycle; According to the online medical records corresponding to the critically ill patients, the number of types of emergency drugs used by the critically ill patients in the m1th treatment monitoring cycle is obtained, and the emergency drugs used are named as the first to jth types of emergency drugs respectively; The dosages of the first to j-th types of emergency drugs in the m1-th treatment monitoring period are respectively obtained to obtain the dosages of the first to j-th drugs; The dosage of the first to jth drugs, the number of emergency drug types, and the cumulative medical expenditure value of the period are defined as the period medical resource utilization data.

5. According to claim 2, a patient monitoring and management system for critical care units based on data analysis, It is characterized in that The physiological parameter unit obtains the cumulative abnormal time ratio of the periodic physiological index, as follows: In the m1th treatment monitoring cycle, the physiological indicators monitored for critically ill patients include the first to kth physiological indicators; Performing periodic analysis on the first physiological indicator to obtain a first abnormal time ratio; The details are as follows: In the m1th treatment monitoring cycle, the first physiological index is monitored in real time by the monitoring equipment of the intensive care unit to obtain the value of the monitoring index; If the value of the monitored indicator is within the normal interval corresponding to the first physiological indicator, it is determined that the first physiological indicator at the current moment is in the normal period; If the value of the monitored indicator is not within the normal interval corresponding to the first physiological indicator, it is determined that the first physiological indicator at the current moment is in an abnormal period, and the time length of the abnormal period is obtained to obtain the abnormal duration of the first physiological indicator; Obtaining the cumulative monitoring time of the first physiological indicator in the m1th treatment monitoring cycle to obtain the first cycle cumulative monitoring time, calculating the ratio of the abnormal time of the first physiological indicator to the first cycle cumulative monitoring time to obtain the first abnormal time ratio; Repeat the process of acquiring the first abnormal time ratio, and acquire the abnormal time ratios of the second to k-th physiological indicators in the m1-th treatment monitoring cycle respectively, to obtain the second to k-th abnormal time ratios; The first to kth abnormal time ratios are summed to obtain the cumulative abnormal time ratio of the periodic physiological index.

6. A patient monitoring and management system for critical care units based on data analysis according to claim 2, It is characterized in that The condition weight unit obtains the patient's condition weight, specifically as follows: The symptoms that occur in the patient during the m1th treatment monitoring cycle are divided into the first to tth treatment symptoms, and the symptom severity scores are respectively performed for the first to tth treatment symptoms to obtain the first to tth symptom severity scores; Count the number of occurrences of the first to tth treatment symptoms in the m1th treatment monitoring period, and obtain the number of occurrences of the first to tth symptoms; The patient's condition weight corresponding to the m1th treatment monitoring period is obtained by calculating the number of occurrences of the first to tth symptoms and the severity scores of the first to tth symptoms corresponding to the m1th treatment monitoring period; The details are as follows: ; Among them, Zym is the patient's condition weight corresponding to the m1th treatment monitoring cycle, Zc1 to Zct are the number of occurrences of the first to tth symptoms, and Zy1 to Zyt are the severity scores of the first to tth symptoms, respectively.

7. According to claim 1, a patient monitoring and management system for critical care units based on data analysis, It is characterized in that The data analysis module acquires the disease cycle analysis data, as follows: Obtaining disease cycle monitoring data, and obtaining facial target image cycle duration ratio, patient disease weight, cycle medical resource usage data, and cycle physiological index cumulative abnormal time ratio corresponding to the m1 treatment monitoring cycle according to the disease cycle monitoring data; According to the periodic medical resource usage data, the first to j-th drug usage dosages, the number of emergency drug types and the periodic cumulative medical expenditure values ​​corresponding to the m1-th treatment monitoring period are obtained respectively; The period medical resource utilization coefficient corresponding to the m1th treatment monitoring cycle is obtained by calculating the dosage of the first to jth drugs, the number of emergency drug types and the cumulative medical expenditure value of the period through a formula; The formula is as follows: ; Among them, Zzy is the period medical resource utilization coefficient, Jl1 to Jlj are the first to jth drug dosages, j is the quantity value corresponding to the emergency drug type, Jzl is the number of emergency drug types, and Lhf is the period cumulative medical expenditure value; The periodic medical resource utilization coefficient, the facial target image period duration ratio corresponding to the m1th treatment monitoring period, the patient's condition weight, and the periodic physiological index cumulative abnormal time ratio are calculated by a formula to obtain the periodic condition reference index corresponding to the m1th treatment monitoring period; The formula is as follows: ; Among them, Zzs1 is the reference index of the m1th cycle condition, Zym is the patient condition weight, Zzy is the cycle medical resource utilization coefficient, Ysb is the cumulative abnormal time ratio of the cycle physiological index, and Mtb is the facial target image cycle duration ratio; Repeat the process of obtaining the periodic disease condition reference index corresponding to the m1th treatment monitoring cycle, and obtain the periodic disease condition reference indexes corresponding to the m2th to mkth treatment monitoring cycles respectively; The periodic disease reference index corresponding to the treatment monitoring period from m1 to mk is defined as disease period analysis data; The periodic analysis data is transmitted to the change monitoring module, and the change monitoring module obtains the monitoring data of the condition changes of critically ill patients.

8. A patient monitoring and management system for critical care units based on data analysis according to claim 7, It is characterized in that The change monitoring module acquires the monitoring data of the condition change of the critically ill patient, as follows: Obtaining disease cycle analysis data, and obtaining the cycle disease reference index corresponding to the treatment monitoring cycle from m1 to mk according to the disease cycle analysis data; The periodic disease condition reference indexes corresponding to the treatment monitoring periods from m1 to mk are named as the periodic disease condition reference indexes from m1 to mk respectively; Obtain time values ​​for the start time of the treatment monitoring cycles m1 to mk respectively, and obtain the start time values ​​of the cycles m1 to mk; Calculate the average of the start time values ​​of the cycles m1 to mk to obtain the average start time of the cycle; Calculate the average of the disease condition reference indexes from cycle m1 to cycle mk to obtain the average of the disease condition reference indexes; The covariance of the patient's condition cycle change is obtained by calculating the average value of the cycle start time, the values ​​of the start time of the m1 to mk cycles, the average value of the cycle condition reference index, and the m1 to mk cycle condition reference index; The covariance of the patient's condition periodic changes is calculated, and the specific formula configuration is as follows: ; Among them, Cov (X, Y) is the covariance of the patient's condition cycle change, X1 to Xmk are the starting time values ​​of the m1 to mk cycles, and Y1 to Ymk are the reference indexes of the m1 to mk cycles. is the average of the cycle start time, is the average value of the periodic disease reference index; The first cycle covariance change threshold and the second cycle covariance change threshold are obtained respectively, and the patient's condition cycle change covariance is numerically compared with the first cycle covariance change threshold and the second cycle covariance change threshold to obtain the monitoring data of the condition change of the critically ill patient; The numerical comparison process is as follows: When the patient's condition periodic change covariance is greater than or equal to the first periodic covariance change threshold, it is judged that the severe condition is in the first condition change interval; When the patient's condition periodic change covariance is less than the first period covariance change threshold and greater than the second period covariance change threshold, it is judged that the severe condition is in the second condition change interval; When the patient's condition periodic change covariance is less than or equal to the second period covariance change threshold, it is judged that the severe condition is in the third condition change interval; The monitoring data of the condition changes of critically ill patients are transmitted to the monitoring and early warning module.

9. A patient monitoring and management system for critical care units based on data analysis according to claim 8, It is characterized in that The monitoring and early warning module performs monitoring and early warning according to the monitoring data of the condition change of the critically ill patient, as follows: Obtain monitoring data on the condition changes of critically ill patients; When a critically ill patient is in the first condition change interval, the monitoring system issues an early warning of periodic deterioration of the condition; When the critically ill patient is in the third condition change interval, the monitoring system monitors the condition change of the critically ill patient to normal; When a critically ill patient is in the second condition change range, the monitoring system will assess the condition of the critically ill patient and issue an early warning based on the assessment results; The details are as follows: Acquire the disease cycle monitoring data, and acquire the abnormal time ratio corresponding to the mkth treatment monitoring cycle according to the disease cycle monitoring data to obtain the mkth abnormal time ratio; Obtain the patient's typical symptom data, and obtain the ratio of the number of symptoms with consistent sequence and the similarity ratio of the patient's typical symptoms based on the patient's typical symptom data; The coefficient of critically ill patients' condition assessment is obtained by calculating the ratio of mk abnormal time, the ratio of the number of symptoms with consistent sequence, and the similarity ratio of typical symptoms of patients; The coefficient of critically ill patients’ condition assessment is calculated, and the specific formula is as follows: ; Among them, Zyp is the coefficient for judging the condition of critically ill patients, Ymk is the ratio of the mkth abnormal time, Sxy is the ratio of the number of symptoms with consistent sequence, and Hdx is the similarity ratio of typical symptoms of patients; Obtaining a threshold value of a coefficient for judging the condition of a critically ill patient, and comparing the coefficient for judging the condition of a critically ill patient with the threshold value of the coefficient for judging the condition of a critically ill patient; The details are as follows: Obtain the mkth abnormal time ratio threshold, the sequential consistent symptom quantity ratio threshold, and the patient's typical symptom similarity ratio threshold respectively; The threshold of the coefficient of critical patient condition assessment is obtained by calculating the mkth abnormal time ratio threshold, the threshold of the number of symptoms with consistent sequence ratio, and the threshold of the similarity ratio of typical symptoms of patients; When the critical patient condition assessment coefficient ratio is greater than the critical patient condition assessment coefficient threshold, a critical patient treatment warning is issued; When the critically ill patient's condition assessment coefficient is less than or equal to the critically ill patient's condition assessment coefficient threshold, the critically ill patient's condition is monitored normally.

Citation Information

Cited By

  • Disease monitoring management system and method for critical patients

    CN119418876A

  • Condition monitoring management system and method for critically ill patients

    CN119418876B