Intensive care data management system and method based on data analysis

Abstract

The invention discloses an intensive care data management system and method based on data analysis, and relates to the technical field of care management, and the management method comprises the following steps: analyzing the change condition of the clinical state of a patient, and carrying out the integration; alarm nodes in the clinical state change process of the patient are captured, and an alarm record is generated; any alarm record is effectively judged; carrying out difference analysis on different alarm records; clustering the similar clinical states of the patient based on the alarm record difference condition of each alarm node; extracting the clinical state of the patient of any alarm record, performing effective alarm evaluation on the alarm record, and performing personalized optimization on the alarm threshold of the effective alarm; carrying out real-time alarm evaluation on the real-time clinical data of the patient, and sending an alarm prompt when a personalized alarm threshold value is met; false alarm caused by fixed threshold setting is effectively reduced, it is ensured that resources focus on critical events, and the clinical response efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of monitoring management, and in particular to a critical care data management system and method based on data analysis. Background Art

[0002] The intensive care unit (ICU) is the core unit for treating critically ill patients in modern hospitals. It continuously generates massive, high-dimensional, dynamic physiological monitoring data and treatment information. Effective management and utilization of this data is crucial for real-time assessment of patient status and timely detection of disease deterioration. At present, critical care data is generally collected through bedside monitors with fixed threshold alarm systems. However, fixed thresholds cannot adapt to individual differences and dynamic changes in patients' conditions. The conditions and reactions of different patients vary significantly. It is difficult for existing systems to set personalized alarm thresholds, which can easily lead to false alarms or missed alarms, causing "alarm fatigue" for medical staff, seriously interfering with clinical decision-making efficiency, and may lead to the neglect of truly critical events. Summary of the Invention

[0003] The object of the present invention is to provide a critical care data management system and method based on data analysis to solve the problems raised in the prior art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: a method for managing intensive care data based on data analysis, the management method comprising the following steps: Step S1: Collect historical clinical data of patients in the intensive care unit, analyze and integrate changes in the patients' clinical status; capture alarm nodes during changes in the patients' clinical status and generate corresponding primary alarm records; Step S2: collecting clinical intervention information of any alarm record and performing effective judgment on the alarm record; based on the different effective judgment results between different alarm records, performing difference analysis between different alarm records; Step S3: Compare and analyze the changes in clinical status of different patients, and cluster patients with similar clinical status based on the differences in alarm records of each alarm node; Step S4: Extract the clinical status of the patient in any alarm record, and perform an effective alarm evaluation on the alarm record based on the comparison with similar clinical status; and optimize the alarm threshold of the effective alarm according to the effective judgment result of the alarm record; Step S5: Perform real-time alarm evaluation on the patient's real-time clinical data, extract the patient's personalized alarm threshold, and send an alarm reminder when the personalized alarm threshold is met.

[0005] Furthermore, step S1 includes the following steps: Step S11: collecting clinical data of the patient through a monitoring device at the patient's bedside, obtaining several monitoring indicators preset in the monitoring device, dividing the collected clinical data according to each monitoring indicator, and obtaining a clinical data set for each monitoring indicator; the monitoring indicators preset in the monitoring device include electrocardiogram monitoring such as heart rate and heart rhythm, blood pressure monitoring such as blood pressure fluctuation, and respiratory monitoring such as respiratory rate; Step S12: sorting the clinical data set of each monitoring indicator in the order of the collection time points and placing them in a two-dimensional rectangular coordinate system, presenting the changing trend of each monitoring indicator over time; arbitrarily selecting a collection time point, integrating the clinical data corresponding to each monitoring indicator at the selected collection time point, and obtaining the user's clinical status data set at the selected collection time point; the temporary status data set is a summary of the real-time values ​​of the patient's heart rate, blood pressure, respiratory rate and other monitoring indicators at any time point. By merging all monitoring indicators, the user's clinical status can be reflected; Step S13: Whenever a patient triggers an alarm at a certain time point, the time point is set as an alarm node, and the clinical status data group at the time point is extracted, while the rest of the patient's clinical information is collected to generate an alarm record of the patient at the time point.

[0006] Furthermore, step S2 includes the following steps: Step S21: Whenever an alarm record is generated, the alarm response behavior of the medical staff is collected and features of the alarm response behavior of the medical staff are extracted to obtain a number of behavioral features of the medical staff; the response behavior of the medical staff is recorded in text form and features are extracted from the text. If the response behavior contains features such as "adjust", "process" and "take", it means that the alarm is valid; if it contains features such as "ignore" and "invalid", it means that the alarm is invalid; Step S22: Pre-build an invalid feature database, which contains several invalid features. The several behavioral features are compared with the invalid feature database respectively. If there is a behavioral feature that is the same as an invalid feature, the generated alarm record is marked as invalid. If any behavioral feature is different from any invalid feature, the generated alarm record is marked as valid. The invalid feature database stores several behavioral terms that can reflect the invalidity of the alarm, such as ignore, invalid, and normal. Step S23: Acquire a plurality of alarm records during the patient's clinical status change process, arbitrarily select one alarm record from the plurality of alarm records, and extract the clinical status data group of the selected alarm record; select clinical data of the i-th monitoring indicator from the clinical status data group, and if the selected alarm record has an invalid mark, set the clinical data of the i-th monitoring indicator as abnormal data; if the selected alarm record has a valid mark, set it as normal data; Step S24: The clinical data of the ith monitoring indicator in the plurality of alarm records are divided and summarized according to the mark, and the normal data range of the ith monitoring indicator is obtained as (d1 min ,d1 max ) and abnormal data range (d2 min ,d2 max ), if there is a common range between the two data ranges, the i-th monitoring indicator is set as the first feature marker; if there is no common range between the two data ranges, the preset alarm threshold of the i-th monitoring indicator is obtained (d i ) th , if d1 max <(d i ) th <d2 min or d2 max <(d i ) th <d1 min , then the i-th monitoring indicator is set as the second feature mark; the first feature mark indicates that the monitoring indicator will have a false alarm according to the preset alarm threshold, that is, the alarm threshold setting is unreasonable; the second feature mark indicates that the monitoring indicator alarms normally according to the preset alarm threshold, then the alarm threshold setting is reasonable and effective; Step S25: Acquire all alarm records of different patients and perform characteristic marking on each monitoring indicator. If the i-th monitoring indicator has the first abnormal mark in the alarm records of different patients, the i-th monitoring indicator is set as a personalized monitoring indicator. If the i-th monitoring indicator has the second characteristic mark in the alarm records of different patients, the i-th monitoring indicator is set as a regular monitoring indicator. Comprehensively analyze the feedback of the same monitoring indicator in the alarm records of different patients. If false alarms occur in different patients, it means that there are individual differences in the monitoring indicators, and subsequent personalized adjustments are required for different patients. If no false alarms occur, it means that the preset threshold can be continued.

[0007] Furthermore, step S3 includes the following steps: Step S31: arbitrarily select all alarm records of a patient, and arbitrarily select a target alarm record from all alarm records, and arbitrarily select the i-th monitoring indicator from the selected target alarm record. If the i-th monitoring indicator is a personalized monitoring indicator, then set the i-th monitoring indicator as the target monitoring indicator; Step S32: Randomly select a comparison alarm record from the remaining patients. If the i-th monitoring indicator is a routine monitoring indicator in the selected comparison alarm record, set the i-th monitoring indicator as a difference indicator. If the i-th monitoring indicator is a personalized monitoring indicator in the selected comparison alarm record, obtain the normal data range and abnormal data range of the i-th monitoring indicator in the two alarm records respectively, set the common range of the selected target alarm record to (d3, d4) and the common range of the selected comparison alarm record to (d5, d6), and obtain the common range size Δd1 of the i-th monitoring indicator in the selected target alarm record respectively. i =d4-d3 and the common range size Δd2 in the selected comparison alarm record i =d6-d5, the deviation degree of the two common ranges is calculated to be p i =|Δd1 i -Δd2 i | / Max(d6-d3,d4-d5), where Max() is the maximum value function; a deviation threshold p is preset. th , if p i <p th , then the i-th monitoring indicator is set as a similar indicator; Step S33: Compare the i-th monitoring index in each alarm record of any two patients, and count the number of comparisons where the i-th monitoring index is the same index between any two alarm records as m. i , set the total number of comparisons for the i-th monitoring indicator to m total , the proportion of the number of times the i-th monitoring indicator is a similar indicator is calculated to be η i =m i / m total ; Preset a frequency ratio threshold η th , if η i >η th , then the i-th monitoring indicator is set as a similar indicator; Step S34: Count the number of similar indicators between two patients as r, and set the total number of monitoring indicators as r ’ , we get the proportion of similar indicators δ=r / r ’ , preset a quantity ratio threshold δ th , if δ≥δ th , then the clinical status changes of the two patients are set as the same clinical status, and all the same clinical status of the remaining patients are divided and clustered.

[0008] Furthermore, step S4 includes the following steps: Step S41: arbitrarily select an alarm record of an alarm node from the process of clinical status change of a patient, arbitrarily select the i-th monitoring indicator from the selected alarm record, and obtain the clinical data of the i-th monitoring indicator in the selected alarm record as d i ; Step S42: When the i-th monitoring indicator is a conventional monitoring indicator, obtain the preset alarm threshold value (d i ) th , the abnormal degree of the i-th monitoring indicator is Y i =[d i -(d i ) th ] / (d i ) th When the i-th monitoring indicator is a personalized monitoring indicator, if the i-th monitoring indicator is the first feature mark in the selected alarm record, the abnormal data range of the i-th monitoring indicator in the alarm nodes of all patients with the same clinical status is obtained, and the abnormal data with the smallest value is selected as the updated alarm threshold of the i-th monitoring indicator (d i ) ’ th , the abnormal degree of the i-th monitoring indicator is Y i =[d i -(d i ) ’ th ] / (d i ) ’ th If the i-th monitoring indicator is the second characteristic mark in the selected alarm record, then obtain the characteristic mark of the i-th monitoring indicator in all alarm nodes of the patient. If all are the second characteristic marks, then the abnormality degree of the i-th monitoring indicator is Y i =[d i -(d i ) th ] / (d i ) th , if the first characteristic marker exists, the abnormality degree of the i-th monitoring indicator is Y i =[d i -(d i ) ’ th ] / (d i ) ’ th ; Step S43: Obtain the abnormality level of each monitoring indicator in the selected alarm record and set the alarm effective value E of the i-th monitoring indicator.i , if Y i ≤0, then E i =0, if Y i >0, then E i =1-Y i ; According to the formula: ; Calculate the effective evaluation value G of the selected alarm record; Step S44: Identify the mark of the selected alarm record. If the selected alarm record is a valid mark, set the valid evaluation value as the characteristic evaluation value. If the selected alarm record is an invalid mark, set the valid evaluation value as the abnormal evaluation value. Obtain the valid evaluation value of each alarm record of all patients with the same clinical state, divide all the valid evaluation values ​​into a characteristic evaluation value range and an abnormal evaluation value range respectively, if there is an overlapping range between the two evaluation value ranges, select the minimum abnormal evaluation value as the effective alarm threshold of the same clinical state of the patient, if there is no overlapping range between the two evaluation value ranges, select the maximum characteristic evaluation value as the effective alarm threshold of the same clinical state of the patient.

[0009] Furthermore, step S5 includes the following steps: Step S51: Acquire and collect clinical status data of any patient in real time, obtain clinical data of each monitoring index, set the real-time clinical data of the ith monitoring index as (d i ) now , obtain the patient's alarm threshold on the i-th monitoring indicator (d i ) ’’ th , the real-time abnormality degree of the i-th monitoring indicator is obtained as (Y i ) now =[(d i ) now -(d i ) ’’ th ] / (d i ) ’’ th ; Step S52: Obtain the real-time abnormality of each monitoring indicator and set a real-time effective value (E i ) now , if (Y i ) now ≤0, then (E i ) now =0, if (Y i ) now >0, then (E i ) now =1-Y i, accumulate to get the patient's real-time evaluation value G now ; Set the patient's effective alarm threshold to G th , if G now ≥G th , an alarm reminder will be sent to the patient's current clinical status.

[0010] In order to better implement the above method, a critical care data management system is also proposed. The management system includes a historical alarm collection module, an alarm difference analysis module, a clinical similarity clustering module, an alarm evaluation and optimization module, and a real-time abnormality judgment module; The historical alarm collection module is used to collect historical clinical data of patients in the intensive care unit, analyze and integrate changes in the patients' clinical status; capture alarm nodes during the process of changes in the patients' clinical status and generate corresponding primary alarm records; The alarm difference analysis module is used to collect clinical intervention information of any alarm record and make effective judgments on the alarm record; based on the different effective judgment results between different alarm records, it conducts difference analysis between different alarm records; The clinical similarity clustering module is used to compare and analyze the changes in clinical status of different patients and cluster patients of the same type based on the differences in alarm records of each alarm node; The alarm evaluation and optimization module is used to extract the clinical status of patients in any alarm record and conduct effective alarm evaluation based on the comparison with similar alarm records. Based on the effective judgment results of the alarm record, the alarm threshold of the effective alarm is personalized optimized. The real-time abnormality judgment module is used to perform real-time alarm evaluation on the patient's real-time clinical data, extract the patient's personalized alarm threshold, and send alarm reminders when the personalized alarm threshold is met.

[0011] Furthermore, the historical alarm collection module includes a clinical status integration unit and an alarm record generation unit; The clinical status integration unit is used to collect historical clinical data of patients in the intensive care unit, analyze changes in the patients' clinical status and integrate them; the alarm record generation unit is used to capture alarm nodes during changes in the patients' clinical status and generate corresponding alarm records.

[0012] Furthermore, the alarm difference analysis module includes an alarm validity identification unit and an alarm difference analysis unit; The alarm effective identification unit is used to collect the clinical intervention situation of any alarm record and make effective judgments on the alarm record; the alarm difference analysis unit is used to conduct difference analysis between different alarm records based on the different effective judgment results between different alarm records.

[0013] Furthermore, the alarm evaluation and optimization module includes a valid alarm evaluation unit and a personalized threshold optimization unit; The effective alarm evaluation unit is used to extract the patient's clinical status from any alarm record and perform effective alarm evaluation on the alarm record based on comparison with similar alarms; the personalized threshold optimization unit is used to perform personalized optimization of the alarm threshold of the effective alarm based on the effective judgment result of the alarm record.

[0014] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention establishes an effective alarm judgment mechanism and effective alarm evaluation to dynamically distinguish between critical events and invalid alarms, reducing false alarms caused by fixed threshold settings, effectively alleviating "alarm fatigue" among medical staff, ensuring that resources are focused on real critical events, and improving clinical response efficiency; 2. The present invention customizes monitoring index thresholds for different patients through clinical status clustering and personalized threshold optimization, which can adapt to individual differences of patients and dynamic changes in their condition, avoid underreporting caused by unified thresholds, and improve monitoring accuracy; 3. The present invention integrates multi-dimensional physiological indicator data, comprehensively evaluates the patient's condition through quantitative models, captures the trend of disease deterioration in real time, and assists medical staff in making quick decisions; it also improves the overall diagnosis and treatment efficiency and resource utilization of intensive care units. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic diagram of the steps of a critical care data management method based on data analysis; Figure 2 It is a structural diagram of a critical care data management system based on data analysis; Figure 3 It is a flow chart. DETAILED DESCRIPTION

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0017] Example: Figures 1 to 3 As shown, the present invention provides a critical care data management method based on data analysis, the management method comprising the following steps: Step S1: Collect historical clinical data of patients in the intensive care unit, analyze and integrate changes in the patients' clinical status; capture alarm nodes during changes in the patients' clinical status and generate corresponding primary alarm records; Wherein, step S1 includes the following steps: Step S11: collecting the patient's clinical data through the monitoring device at the patient's bedside, obtaining several monitoring indicators preset in the monitoring device, dividing the collected clinical data according to each monitoring indicator, and obtaining a clinical data set for each monitoring indicator; Step S12: sorting the clinical data set of each monitoring indicator in the order of the collection time points and placing them in a two-dimensional rectangular coordinate system, presenting the changing trend of each monitoring indicator over time; arbitrarily selecting a collection time point, integrating the clinical data corresponding to each monitoring indicator at the selected collection time point, and obtaining the user's clinical status data set at the selected collection time point; Step S13: Whenever a patient triggers an alarm at a certain time point, the time point is set as an alarm node, and the clinical status data group at the time point is extracted, while the rest of the patient's clinical information is collected to generate an alarm record of the patient at the time point.

[0018] Step S2: collecting clinical intervention information of any alarm record and performing effective judgment on the alarm record; based on the different effective judgment results between different alarm records, performing difference analysis between different alarm records; Wherein, step S2 includes the following steps: Step S21: Whenever an alarm record is generated, the alarm response behavior of the medical staff is collected and features of the alarm response behavior of the medical staff are extracted to obtain several behavioral features of the medical staff; Step S22: pre-build an invalid feature database, which contains several invalid features. The several behavioral features are compared with the invalid feature database respectively. If there is a behavioral feature that is the same as an invalid feature, the generated alarm record is marked as invalid. If any behavioral feature is different from any invalid feature, the generated alarm record is marked as valid. Step S23: Acquire a plurality of alarm records during the patient's clinical status change process, arbitrarily select one alarm record from the plurality of alarm records, and extract the clinical status data group of the selected alarm record; select clinical data of the i-th monitoring indicator from the clinical status data group, and if the selected alarm record has an invalid mark, set the clinical data of the i-th monitoring indicator as abnormal data; if the selected alarm record has a valid mark, set it as normal data; Step S24: The clinical data of the ith monitoring indicator in the plurality of alarm records are divided and summarized according to the mark, and the normal data range of the ith monitoring indicator is obtained as (d1 min ,d1 max) and abnormal data range (d2 min ,d2 max ), if there is a common range between the two data ranges, the i-th monitoring indicator is set as the first feature marker; if there is no common range between the two data ranges, the preset alarm threshold of the i-th monitoring indicator is obtained (d i ) th , if d1 max <(d i ) th <d2 min or d2 max <(d i ) th <d1 min , then the i-th monitoring indicator is set as the second characteristic mark; Example 1: Obtain 10 heart rate alarm records of a patient, and obtain normal values ​​of 105, 110, 118, 103, and 120, and abnormal data of 108, 122, 107, and 109. That is, the normal data range is (103, 120), and the abnormal data is (107, 122). Both have a common range (107, 120), so the heart rate is marked with the first feature; Step S25: Acquire all alarm records of different patients and perform characteristic marking on each monitoring indicator. If the i-th monitoring indicator has a first abnormal mark in the alarm records of different patients, the i-th monitoring indicator is set as a personalized monitoring indicator. If the i-th monitoring indicator has a second characteristic mark in the alarm records of different patients, the i-th monitoring indicator is set as a regular monitoring indicator.

[0019] Step S3: Compare and analyze the changes in clinical status of different patients, and cluster patients with similar clinical status based on the differences in alarm records of each alarm node; Wherein, step S3 includes the following steps: Step S31: arbitrarily select all alarm records of a patient, and arbitrarily select a target alarm record from all alarm records, and arbitrarily select the i-th monitoring indicator from the selected target alarm record. If the i-th monitoring indicator is a personalized monitoring indicator, then set the i-th monitoring indicator as the target monitoring indicator; Step S32: Randomly select a comparison alarm record from the remaining patients. If the i-th monitoring indicator is a routine monitoring indicator in the selected comparison alarm record, set the i-th monitoring indicator as a difference indicator. If the i-th monitoring indicator is a personalized monitoring indicator in the selected comparison alarm record, obtain the normal data range and abnormal data range of the i-th monitoring indicator in the two alarm records respectively, set the common range of the selected target alarm record to (d3, d4) and the common range of the selected comparison alarm record to (d5, d6), and obtain the common range size Δd1 of the i-th monitoring indicator in the selected target alarm record respectively. i =d4-d3 and the common range size Δd2 in the selected comparison alarm record i =d6-d5, the deviation degree of the two common ranges is calculated to be p i =|Δd1 i -Δd2 i | / Max(d6-d3,d4-d5), where Max() is the maximum value function; a deviation threshold p is preset. th , if p i <p th , then the i-th monitoring indicator is set as a similar indicator; Example 2: Set the normal range in the target patient's alarm record to (100, 115) and the abnormal range to (110, 120), and obtain a common range size of 5; set the normal range in the comparison patient's alarm record to (98, 118) and the abnormal range to (112, 120), and obtain a common range size of 6, and obtain the deviation degree p = 1 / Max(8,3) = 1 / 8 = 0.125; Step S33: Compare the i-th monitoring index in each alarm record of any two patients, and count the number of comparisons where the i-th monitoring index is the same index between any two alarm records as m. i , set the total number of comparisons for the i-th monitoring indicator to m total , the proportion of the number of times the i-th monitoring indicator is a similar indicator is calculated to be η i =m i / m total ; Preset a frequency ratio threshold η th , if η i >η th , then the i-th monitoring indicator is set as a similar indicator; Step S34: Count the number of similar indicators between two patients as r, and set the total number of monitoring indicators as r ’ , we get the proportion of similar indicators δ=r / r ’ , preset a quantity ratio threshold δ th , if δ≥δ th, then the clinical status changes of the two patients are set as the same clinical status, and all the same clinical status of the remaining patients are divided and clustered.

[0020] Step S4: Extract the clinical status of the patient in any alarm record, and perform an effective alarm evaluation on the alarm record based on the comparison with similar clinical status; and optimize the alarm threshold of the effective alarm according to the effective judgment result of the alarm record; Wherein, step S4 includes the following steps: Step S41: arbitrarily select an alarm record of an alarm node from the process of clinical status change of a patient, arbitrarily select the i-th monitoring indicator from the selected alarm record, and obtain the clinical data of the i-th monitoring indicator in the selected alarm record as d i ; Step S42: When the i-th monitoring indicator is a conventional monitoring indicator, obtain the preset alarm threshold value (d i ) th , the abnormal degree of the i-th monitoring indicator is Y i =[d i -(d i ) th ] / (d i ) th When the i-th monitoring indicator is a personalized monitoring indicator, if the i-th monitoring indicator is the first feature mark in the selected alarm record, the abnormal data range of the i-th monitoring indicator in the alarm nodes of all patients with the same clinical status is obtained, and the abnormal data with the smallest value is selected as the updated alarm threshold of the i-th monitoring indicator (d i ) ’ th , the abnormal degree of the i-th monitoring indicator is Y i =[d i -(d i ) ’ th ] / (d i ) ’ th If the i-th monitoring indicator is the second characteristic mark in the selected alarm record, then obtain the characteristic mark of the i-th monitoring indicator in all alarm nodes of the patient. If all are the second characteristic marks, then the abnormality degree of the i-th monitoring indicator is Y i =[d i -(d i ) th ] / (d i ) th , if the first characteristic marker exists, the abnormality degree of the i-th monitoring indicator is Y i =[d i -(di ) ’ th ] / (d i ) ’ th ; Step S43: Obtain the abnormality level of each monitoring indicator in the selected alarm record and set the alarm effective value E of the i-th monitoring indicator. i , if Y i ≤0, then E i =0, if Y i >0, then E i =1-Y i ; According to the formula: ; Calculate the effective evaluation value G of the selected alarm record; Step S44: Identify the mark of the selected alarm record. If the selected alarm record is a valid mark, set the valid evaluation value as the characteristic evaluation value. If the selected alarm record is an invalid mark, set the valid evaluation value as the abnormal evaluation value. Obtain the valid evaluation value of each alarm record of all patients with the same clinical state, divide all the valid evaluation values ​​into a characteristic evaluation value range and an abnormal evaluation value range respectively, if there is an overlapping range between the two evaluation value ranges, select the minimum abnormal evaluation value as the effective alarm threshold of the same clinical state of the patient, if there is no overlapping range between the two evaluation value ranges, select the maximum characteristic evaluation value as the effective alarm threshold of the same clinical state of the patient.

[0021] Step S5: Performing real-time alarm assessment on the patient's real-time clinical data, extracting the patient's personalized alarm threshold, and sending an alarm reminder when the personalized alarm threshold is met; Wherein, step S5 includes the following steps: Step S51: Acquire and collect clinical status data of any patient in real time, obtain clinical data of each monitoring index, and set the real-time clinical data of the ith monitoring index as (d i ) now , obtain the patient's alarm threshold on the i-th monitoring indicator (d i ) ’’ th , the real-time abnormality degree of the i-th monitoring indicator is obtained as (Y i ) now =[(d i ) now -(d i ) ’’ th ] / (d i ) ’’ th ; Step S52: Obtain the real-time abnormality of each monitoring indicator and set a real-time effective value (E i ) now , if (Y i ) now ≤0, then (E i ) now =0, if (Y i ) now >0, then (E i ) now =1-Y i , accumulate to get the patient's real-time evaluation value G now ; Set the patient's effective alarm threshold to G th , if G now ≥G th , an alarm reminder will be sent to the patient's current clinical status.

[0022] A critical care data management system, the management system includes a historical alarm collection module, an alarm difference analysis module, a clinical similarity clustering module, an alarm evaluation and optimization module and a real-time abnormality judgment module; The historical alarm collection module is used to collect historical clinical data of patients in the intensive care unit, analyze and integrate changes in the patients' clinical status; capture alarm nodes during the process of changes in the patients' clinical status and generate corresponding primary alarm records; The alarm difference analysis module is used to collect clinical intervention information of any alarm record and make effective judgments on the alarm record; based on the different effective judgment results between different alarm records, it conducts difference analysis between different alarm records; The clinical similarity clustering module is used to compare and analyze the changes in clinical status of different patients and cluster patients of the same type based on the differences in alarm records of each alarm node; The alarm evaluation and optimization module is used to extract the clinical status of patients in any alarm record and conduct effective alarm evaluation based on the comparison with similar alarm records. Based on the effective judgment results of the alarm record, the alarm threshold of the effective alarm is personalized optimized. The real-time abnormality judgment module is used to perform real-time alarm evaluation on the patient's real-time clinical data, extract the patient's personalized alarm threshold, and send alarm reminders when the personalized alarm threshold is met.

[0023] Among them, the historical alarm collection module includes a clinical status integration unit and an alarm record generation unit; The clinical status integration unit is used to collect historical clinical data of patients in the intensive care unit, analyze changes in the patients' clinical status and integrate them; the alarm record generation unit is used to capture alarm nodes during changes in the patients' clinical status and generate corresponding alarm records.

[0024] Among them, the alarm difference analysis module includes an alarm effective identification unit and an alarm difference analysis unit; The alarm effective identification unit is used to collect the clinical intervention situation of any alarm record and make effective judgments on the alarm record; the alarm difference analysis unit is used to conduct difference analysis between different alarm records based on the different effective judgment results between different alarm records.

[0025] Among them, the alarm evaluation and optimization module includes an effective alarm evaluation unit and a personalized threshold optimization unit; The effective alarm evaluation unit is used to extract the patient's clinical status from any alarm record and perform effective alarm evaluation on the alarm record based on comparison with similar alarms; the personalized threshold optimization unit is used to perform personalized optimization of the alarm threshold of the effective alarm based on the effective judgment result of the alarm record.

[0026] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A method for managing critical care data based on data analysis, characterized in that: The management method comprises the following steps: Step S1: Collect historical clinical data of patients in the intensive care unit, analyze and integrate changes in the patients' clinical status; capture alarm nodes during changes in the patients' clinical status and generate corresponding primary alarm records; Step S2: collecting clinical intervention information of any alarm record and performing effective judgment on the alarm record; based on the different effective judgment results between different alarm records, performing difference analysis between different alarm records; Step S3: Compare and analyze the changes in clinical status of different patients, and cluster patients with similar clinical status based on the differences in alarm records of each alarm node; Step S4: Extract the clinical status of the patient in any alarm record, and perform an effective alarm evaluation on the alarm record based on the comparison with similar clinical status; and optimize the alarm threshold of the effective alarm according to the effective judgment result of the alarm record; Step S5: Perform real-time alarm evaluation on the patient's real-time clinical data, extract the patient's personalized alarm threshold, and send an alarm reminder when the personalized alarm threshold is met.

2. A method for managing intensive care data based on data analysis according to claim 1, characterized in that: The step S1 comprises the following steps: Step S11: collecting the patient's clinical data through the monitoring device at the patient's bedside, obtaining several monitoring indicators preset in the monitoring device, dividing the collected clinical data according to each monitoring indicator, and obtaining a clinical data set for each monitoring indicator; Step S12: sorting the clinical data set of each monitoring indicator in the order of the collection time points and placing them in a two-dimensional rectangular coordinate system, presenting the changing trend of each monitoring indicator over time; arbitrarily selecting a collection time point, integrating the clinical data corresponding to each monitoring indicator at the selected collection time point, and obtaining the user's clinical status data set at the selected collection time point; Step S13: Whenever a patient triggers an alarm at a certain time point, the time point is set as an alarm node, and the clinical status data group at the time point is extracted, while the rest of the patient's clinical information is collected to generate an alarm record of the patient at the time point.

3. A method for managing intensive care data based on data analysis according to claim 2, characterized in that: The step S2 comprises the following steps: Step S21: Whenever an alarm record is generated, the alarm response behavior of the medical staff is collected and features of the alarm response behavior of the medical staff are extracted to obtain several behavioral features of the medical staff; Step S22: pre-build an invalid feature database, which contains several invalid features. The several behavioral features are compared with the invalid feature database respectively. If there is a behavioral feature that is the same as an invalid feature, the generated alarm record is marked as invalid. If any behavioral feature is different from any invalid feature, the generated alarm record is marked as valid. Step S23: Acquire a plurality of alarm records during the patient's clinical status change process, arbitrarily select one alarm record from the plurality of alarm records, and extract the clinical status data group of the selected alarm record; select clinical data of the i-th monitoring indicator from the clinical status data group, and if the selected alarm record has an invalid mark, set the clinical data of the i-th monitoring indicator as abnormal data; if the selected alarm record has a valid mark, set it as normal data; Step S24: The clinical data of the ith monitoring indicator in the plurality of alarm records are divided and summarized according to the mark, and the normal data range of the ith monitoring indicator is obtained as (d1 min ,d1 max ) and abnormal data range (d2 min ,d2 max ), if there is a common range between the two data ranges, the i-th monitoring indicator is set as the first feature marker; if there is no common range between the two data ranges, the preset alarm threshold of the i-th monitoring indicator is obtained (d i ) th , if d1 max <(d i ) th <d2 min or d2 max <(d i ) th <d1 min , then the i-th monitoring indicator is set as the second characteristic mark; Step S25: Acquire all alarm records of different patients and perform characteristic marking on each monitoring indicator. If the i-th monitoring indicator has a first abnormal mark in the alarm records of different patients, the i-th monitoring indicator is set as a personalized monitoring indicator. If the i-th monitoring indicator has a second characteristic mark in the alarm records of different patients, the i-th monitoring indicator is set as a regular monitoring indicator.

4. A method for managing intensive care data based on data analysis according to claim 3, characterized in that: The step S3 comprises the following steps: Step S31: arbitrarily select all alarm records of a patient, and arbitrarily select a target alarm record from all alarm records, and arbitrarily select the i-th monitoring indicator from the selected target alarm record. If the i-th monitoring indicator is a personalized monitoring indicator, then set the i-th monitoring indicator as the target monitoring indicator; Step S32: Randomly select a comparison alarm record from the remaining patients. If the i-th monitoring indicator is a routine monitoring indicator in the selected comparison alarm record, set the i-th monitoring indicator as a difference indicator. If the i-th monitoring indicator is a personalized monitoring indicator in the selected comparison alarm record, obtain the normal data range and abnormal data range of the i-th monitoring indicator in the two alarm records respectively, set the common range of the selected target alarm record to (d3, d4) and the common range of the selected comparison alarm record to (d5, d6), and obtain the common range size Δd1 of the i-th monitoring indicator in the selected target alarm record respectively. i =d4-d3 and the common range size Δd2 in the selected comparison alarm record i =d6-d5, the deviation degree of the two common ranges is calculated to be p i =|Δd1 i -Δd2 i | / Max(d6-d3,d4-d5), where Max() is the maximum value function; a deviation threshold p is preset. th , if p i <p th , then the i-th monitoring indicator is set as a similar indicator; Step S33: Compare the i-th monitoring index in each alarm record of any two patients, and count the number of comparisons where the i-th monitoring index is the same index between any two alarm records as m. i , set the total number of comparisons for the i-th monitoring indicator to m total , the proportion of the number of times the i-th monitoring indicator is a similar indicator is calculated to be η i =m i / m total ; Preset a frequency ratio threshold η th , if η i >η th , then the i-th monitoring indicator is set as a similar indicator; Step S34: Count the number of similar indicators between two patients as r, and set the total number of monitoring indicators as r ’ , we get the proportion of similar indicators δ=r / r ’ , preset a quantity ratio threshold δ th , if δ≥δ th , the clinical status changes of the two patients are set as the same clinical status, and all the same clinical status of the remaining patients are divided and clustered.

5. The method for managing intensive care data based on data analysis according to claim 4, characterized in that: The step S4 comprises the following steps: Step S41: arbitrarily select an alarm record of an alarm node from the process of clinical status change of a patient, arbitrarily select the i-th monitoring indicator from the selected alarm record, and obtain the clinical data of the i-th monitoring indicator in the selected alarm record as d i ; Step S42: When the i-th monitoring indicator is a conventional monitoring indicator, obtain the preset alarm threshold value (d i ) th , the abnormal degree of the i-th monitoring indicator is Y i =[d i -(d i ) th ] / (d i ) th When the i-th monitoring indicator is a personalized monitoring indicator, if the i-th monitoring indicator is the first feature mark in the selected alarm record, the abnormal data range of the i-th monitoring indicator in the alarm nodes of all patients with the same clinical status is obtained, and the abnormal data with the smallest value is selected as the updated alarm threshold of the i-th monitoring indicator (d i ) ’ th , the abnormal degree of the i-th monitoring indicator is Y i =[d i -(d i ) ’ th ] / (d i ) ’ th If the i-th monitoring indicator is the second characteristic mark in the selected alarm record, then obtain the characteristic mark of the i-th monitoring indicator in all alarm nodes of the patient. If all are the second characteristic marks, then the abnormality degree of the i-th monitoring indicator is Y i =[d i -(d i ) th ] / (d i ) th , if the first characteristic marker exists, the abnormality degree of the i-th monitoring indicator is Y i =[d i -(d i ) ’ th ] / (d i ) ’ th ; Step S43: Obtain the abnormality level of each monitoring indicator in the selected alarm record and set the alarm effective value E of the i-th monitoring indicator. i , if Y i ≤0, then E i =0, if Y i >0, then E i =1-Y i ; According to the formula: ； Calculate the effective evaluation value G of the selected alarm record; Step S44: Identify the mark of the selected alarm record. If the selected alarm record is a valid mark, set the valid evaluation value as the characteristic evaluation value. If the selected alarm record is an invalid mark, set the valid evaluation value as the abnormal evaluation value. Obtain the valid evaluation value of each alarm record of all patients with the same clinical state, divide all the valid evaluation values ​​into a characteristic evaluation value range and an abnormal evaluation value range respectively, if there is an overlapping range between the two evaluation value ranges, select the minimum abnormal evaluation value as the effective alarm threshold of the same clinical state of the patient, if there is no overlapping range between the two evaluation value ranges, select the maximum characteristic evaluation value as the effective alarm threshold of the same clinical state of the patient.

6. A method for managing intensive care data based on data analysis according to claim 5, characterized in that: The step S5 comprises the following steps: Step S51: Acquire and collect clinical status data of any patient in real time, obtain clinical data of each monitoring index, set the real-time clinical data of the ith monitoring index as (d i ) now , obtain the patient's alarm threshold on the i-th monitoring indicator (d i ) ’’ th , the real-time abnormality degree of the i-th monitoring indicator is obtained as (Y i ) now =[(d i ) now -(d i ) ’’ th ] / (d i ) ’’ th ; Step S52: Obtain the real-time abnormality level of each monitoring indicator and set a real-time effective value (E i ) now , if (Y i ) now ≤0, then (E i ) now =0, if (Y i ) now >0, then (E i ) now =1-Y i , accumulate to get the patient's real-time evaluation value G now ; Set the patient's effective alarm threshold to G th , if G now ≥G th , an alarm reminder will be sent to the patient's current clinical status.

7. A critical care data management system, configured to implement the critical care data management method based on data analysis according to any one of claims 1 to 6, characterized in that: The management system includes a historical alarm collection module, an alarm difference analysis module, a clinical similarity clustering module, an alarm evaluation and optimization module, and a real-time abnormality judgment module; The historical alarm collection module is used to collect historical clinical data of patients in the intensive care unit, analyze and integrate changes in the patients' clinical status; capture alarm nodes during changes in the patients' clinical status and generate corresponding primary alarm records; The alarm difference analysis module is used to collect clinical intervention information of any alarm record and make effective judgments on the alarm record; based on the different effective judgment results between different alarm records, the module conducts difference analysis between different alarm records; The clinical similarity clustering module is used to compare and analyze the changes in clinical status of different patients and cluster patients of the same type based on the differences in alarm records of each alarm node; The alarm evaluation and optimization module is used to extract the clinical status of the patient in any alarm record and perform effective alarm evaluation on the alarm record based on comparison with similar alarm records; According to the effective judgment results of the alarm records, the alarm threshold of the effective alarm is optimized individually; The real-time abnormality judgment module is used to perform real-time alarm evaluation on the patient's real-time clinical data, extract the patient's personalized alarm threshold, and send an alarm reminder when the personalized alarm threshold is met.

8. The intensive care data management system according to claim 7, characterized in that: The historical alarm collection module includes a clinical status integration unit and an alarm record generation unit; The clinical status integration unit is used to collect historical clinical data of patients in the intensive care unit, analyze changes in the patients' clinical status and integrate them; the alarm record generation unit is used to capture alarm nodes during changes in the patients' clinical status and generate corresponding primary alarm records.

9. The intensive care data management system according to claim 7, characterized in that: The alarm difference analysis module includes an alarm validity identification unit and an alarm difference analysis unit; The alarm effective identification unit is used to collect clinical intervention conditions of any alarm record and make effective judgments on the alarm record; The alarm difference analysis unit is used to perform difference analysis on different alarm records based on different valid judgment results between different alarm records.

10. The intensive care data management system according to claim 7, characterized in that: The alarm evaluation and optimization module includes an effective alarm evaluation unit and a personalized threshold optimization unit; The effective alarm evaluation unit is used to extract the clinical status of the patient in any alarm record and perform effective alarm evaluation on the alarm record based on the comparison with similar alarms; the personalized threshold optimization unit is used to perform personalized optimization of the alarm threshold of the effective alarm based on the effective judgment result of the alarm record.

Images