Intelligent early warning method and system for adverse events based on patient safety risk indexes

By obtaining medical information from multiple patients, determining the floating range of risk indicators and matching the risk probability in the adverse event association map, the problem of low accuracy of adverse event warning caused by a single data source in the prior art is solved, and the patient is achieved Multi-dimensional assessment and efficient early warning of health status.

CN118919077AInactive Publication Date: 2024-11-08AFFILIATED HOSPITAL OF JIANGNAN UNIV

Patent Information

Application Number
CN202411398064.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-09
Publication Date
2024-11-08
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing intelligent early warning method for adverse events based on patient safety risk indicators relies on a single data source, which is difficult to fully reflect the actual situation of the patient, resulting in low warning accuracy.

Method used

By obtaining medical information from multiple patients, determining the floating range of risk indicators from different sources, screening out target risk indicators that exceed the preset safety range, and matching and calculating risk probability in the adverse event association map for early warning.

Benefits of technology

A comprehensive assessment of multi-dimensional changes in the patient's health status has been achieved, accurate warning of adverse events has been improved, and the accuracy and sensitivity of warnings have been enhanced.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118919077A_ABST
    Figure CN118919077A_ABST
Patent Text Reader

Abstract

The invention discloses an intelligent early warning method and system for adverse events based on patient safety risk indexes, and relates to the technical field of data processing. The method comprises the following steps: acquiring medical information of a plurality of patients; for each patient, based on a preset time window, determining floating ranges corresponding to a plurality of risk indexes of different sources in the medical information; screening out a plurality of risk indexes of which the floating ranges exceed a preset safe floating range from the risk indexes as target risk indexes; based on each target risk index, matching a plurality of adverse events in a preset adverse event association map, and calculating a risk probability corresponding to each adverse event; and if a target adverse event of which the risk probability is greater than or equal to a risk probability threshold exists in the adverse events, performing early warning on the patient based on the target adverse event. By implementing the technical scheme provided by the invention, the effect of improving the accuracy of adverse event early warning based on the patient safety risk index is achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and specifically to an intelligent early warning method, system, electronic device and storage medium for adverse events based on patient safety risk indicators. Background Art

[0002] With the continuous advancement of medical technology, patient safety has become the focus of global medical and health systems. Adverse medical events not only harm patients, but also increase medical costs and reduce medical quality. Therefore, effective prevention and timely detection of potential adverse medical events are of great significance to improving patient safety and medical quality.

[0003] At present, the existing intelligent early warning methods for adverse events based on patient safety risk indicators mainly rely on monitoring specific single data of patients for early warning of adverse events. However, in actual applications, the risk conditions of different patients are often multifaceted. Monitoring based on data from a single source is difficult to fully reflect the actual conditions of patients, resulting in deviations between the early warning results and the actual conditions of patients, which leads to low accuracy of intelligent early warning of adverse events based on patient safety risk indicators. Summary of the invention

[0004] The present application provides a method, system, electronic device and storage medium for intelligent early warning of adverse events based on patient safety risk indicators, which has the effect of improving the accuracy of intelligent early warning of adverse events based on patient safety risk indicators.

[0005] In the first aspect, the present application provides an intelligent early warning method for adverse events based on patient safety risk indicators, comprising: Access medical information for multiple patients; For each of the patients, based on a preset time window, determining a floating range corresponding to risk indicators from multiple different sources in the medical information; Among the risk indicators, multiple risk indicators whose floating range exceeds the preset safe floating range are selected as target risk indicators respectively; Based on each of the target risk indicators, multiple adverse events are matched in a preset adverse event association map, and the risk probability corresponding to each of the adverse events is calculated; If there is a target adverse event among the adverse events whose risk probability is greater than or equal to the risk probability threshold, the patient is warned based on the target adverse event.

[0006] In a second aspect of the present application, an intelligent early warning system for adverse events based on patient safety risk indicators is provided, the system comprising: An information acquisition module, used to acquire medical information of multiple patients; A risk indicator determination module is used to determine, for each of the patients, based on a preset time window, the floating ranges corresponding to the risk indicators from multiple different sources in the medical information; among the risk indicators, multiple risk indicators whose floating ranges exceed the preset safe floating range are selected as target risk indicators; A risk probability determination module, used to match multiple adverse events in a preset adverse event association map based on each of the target risk indicators, and calculate the risk probability corresponding to each of the adverse events; The adverse event warning module is used to warn the patient based on the target adverse event if there is a target adverse event whose risk probability is greater than or equal to a risk probability threshold among the adverse events.

[0007] In the third aspect of the present application, an electronic device is provided, comprising a memory, a processor, and a program stored in the memory and executable on the processor, wherein the program can implement an intelligent early warning method for adverse events based on patient safety risk indicators when loaded and executed by the processor.

[0008] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements an intelligent early warning method for adverse events based on patient safety risk indicators.

[0009] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: By adopting the above technical solution, the patient's medical information is obtained, and risk indicators from multiple different sources of the patient are extracted, abnormal change trends are identified, and related possible adverse events are obtained by matching with the knowledge graph, and the risk probability of these adverse events is calculated, and finally intelligent early warning of high-risk adverse events is achieved. The pre-setting of risk probability thresholds can control the sensitivity of the early warning, and the knowledge graph supports association analysis to improve the accuracy of adverse event early warning. Compared with single indicator early warning, this technical solution can comprehensively evaluate the multi-dimensional changes in the patient's health status, achieve accurate evaluation of adverse events, and issue early warnings, which improves the accuracy of intelligent early warning of adverse events based on patient safety risk indicators. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a flow chart of an intelligent early warning method for adverse events based on patient safety risk indicators provided in an embodiment of the present application; Figure 2 It is a structural schematic diagram of an adverse event intelligent early warning system based on patient safety risk indicators provided in an embodiment of the present application; Figure 3It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0011] Description of reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0012] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0013] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0014] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0015] The present application embodiment provides an intelligent early warning method for adverse events based on patient safety risk indicators. In one embodiment, please refer to Figure 1 , Figure 1 This is a flow chart of the method for intelligent early warning of adverse events based on patient safety risk indicators provided by the embodiment of the present application. The method can be implemented by a computer program, which can be integrated in an application or run as an independent tool application. The method can also be implemented by a single-chip microcomputer or run on an intelligent early warning system for adverse events based on patient safety risk indicators based on the von Neumann system. Specifically, the method can include the following steps: Step 101: Obtain medical information of multiple patients.

[0016] Among them, medical information refers to various data reflecting the health status of patients. In the embodiments of the present application, it can be understood as including various data such as basic information of patients, medication records, physical sign records, laboratory test reports, number of visits, etc., which are used to describe the overall health and risk status of patients over a period of time.

[0017] Specifically, in order to collect various risk indicator data of different patients for subsequent risk analysis, it is necessary to obtain the medical information of multiple patients. The structured medical data of inpatients is extracted from the hospital electronic medical record system, including basic information of patients, medication records, physical signs records, laboratory test reports, etc. These structured data are obtained through database query, interface call, etc. At the same time, it is also necessary to extract the number of patient visits, surgical records, etc. from unstructured information such as doctors' daily records and nurses' logs by natural language processing and other methods. The effect of obtaining the medical information of multiple patients is to form a patient sample of sufficient scale, which contains the key risk indicator data of different patients over a period of time, and lays a data foundation for the subsequent steps of determining the floating range of risk indicators, screening target risk indicators, and calculating the probability of adverse events. Compared with monitoring only a single data indicator of a single patient, considering the comprehensive medical information of multiple patients can more comprehensively reflect the distribution and change trend of risk indicators, and improve the accuracy of subsequent risk analysis results.

[0018] Step 102: For each patient, based on a preset time window, determine the floating range corresponding to the risk indicators from multiple different sources in the medical information.

[0019] The preset time window refers to a specific time range for collecting historical data of risk indicators. In the embodiment of the present application, it can be understood as a time period such as the last 7 days, 14 days, etc., for obtaining multi-point data of each risk indicator during this period and calculating the floating range of the risk indicator during this period.

[0020] Risk indicators from different sources refer to various types of data indicators that reflect the health status of patients. In the embodiments of the present application, they can be understood as indicators such as medication dosage, physical sign changes, and number of visits. These indicators are derived from different aspects such as the patient's medication records, condition observations, and medical behaviors, and are used to comprehensively reflect multiple dimensions of the patient's health status and determine the potential risks of the patient.

[0021] The floating range refers to the normal fluctuation range of the risk indicator within a certain time window. In the embodiment of the present application, it can be understood as the range consisting of the mean value of the risk indicator plus or minus a preset multiple of the standard deviation, which is used to determine the normal high and low fluctuation limits of the same risk indicator within a given time window, reflecting the dynamic changes of the risk indicator.

[0022] Specifically, in order to determine whether there are abnormalities in the risk indicators of different patients, it is necessary to determine the floating range of each risk indicator based on the preset time window. For each risk indicator such as medication dosage, physical sign changes, and number of visits, the patient's daily indicator data is collected within the preset time window of the last 7 days. Taking the medication dosage as an example, the mean and standard deviation of the daily medication dosage within the 7-day window are calculated, and the mean minus 2 times the standard deviation is used as the lower limit of the medication dosage fluctuation during the window period, and the mean plus 2 times the standard deviation is used as the upper limit. Similarly, the floating range of indicators such as physical sign changes and number of visits can be calculated. The effect of determining the floating range in this way is that the normal fluctuation range of each risk indicator for the same patient within a given time window can be determined, and whether there are abnormal situations beyond the normal floating range, which provides a basis for the subsequent screening of target risk indicators. Compared with simply judging the data at a certain point in time, considering the floating range in the time dimension can more comprehensively reflect the changing trend of risk indicators.

[0023] Based on the above embodiment, as an optional embodiment, in step 102: based on a preset time window, determining the floating ranges corresponding to the risk indicators from multiple different sources in the medical information, this step may also include the following steps: Step 201: For each risk indicator, multiple historical data points of the risk indicator are obtained within a preset time window.

[0024] Among them, historical data points refer to the values ​​of each sampling point of the risk indicator in the time dimension. In the embodiment of the present application, it can be understood as the daily monitoring value of a certain risk indicator of the patient within a preset time window, such as daily medication dosage, daily blood pressure value, etc. These historical data points are used to depict the change curve and trend of the risk indicator over a period of time, and provide sample data for calculating the floating range of the risk indicator within the time period.

[0025] Specifically, in order to calculate the floating range of risk indicators, it is necessary to obtain multiple historical data points of each risk indicator within the preset time window. For risk indicators such as medication dosage, physical sign changes, and number of visits extracted from medical information, collect the specific daily monitoring values ​​of these risk indicators within the preset time window of the last 7 days. For example, medication dosage can extract a detailed list of medications and dosage for each day within 7 days; physical sign changes can extract daily blood pressure, heart rate and other physical sign values; the number of visits can count the number of daily outpatient visits and hospitalizations within 7 days. By obtaining multi-point historical data of risk indicators within the time window, sufficient samples can be collected to calculate the floating range of risk indicators within the time period, determine whether the indicators are abnormal, and lay the foundation for subsequent risk analysis.

[0026] Step 202: Based on each historical data point, calculate the mean and standard deviation of the risk indicator; subtract a preset multiple of the standard deviation from the mean as the floating lower limit, and add the preset multiple of the standard deviation to the mean as the floating upper limit.

[0027] The floating lower limit refers to the lower limit of the risk indicator floating range. In the embodiment of the present application, it can be understood as the value obtained by subtracting the preset multiple standard deviation from the mean value of the risk indicator, which is used to represent the minimum value of the normal fluctuation of the risk indicator within a given time window.

[0028] The floating upper limit value refers to the upper limit of the floating range of the risk indicator. In the embodiment of the present application, it can be understood as the value obtained by adding the mean value of the risk indicator to the preset multiple standard deviation, which is used to represent the maximum value of the normal fluctuation of the risk indicator within a given time window.

[0029] Specifically, in order to accurately calculate the floating range of risk indicators, it is necessary to calculate the mean and standard deviation based on the collected historical data points, and use this to determine the upper and lower limits of the floating range. For the multi-point historical data of risk indicators such as medication dosage and physical signs, statistical methods are used to calculate the mean and standard deviation of these data. For example, the mean of a patient's 7-day medication data is 6 tablets / day, and the standard deviation is 2 tablets / day. After calculating the mean and standard deviation, the mean is subtracted from the preset multiple, such as 2 times the standard deviation to determine the floating lower limit, and the mean is added to the preset multiple standard deviation to determine the floating upper limit. That is, the lower limit of the floating range of the patient's medication dosage is 6-2×2=2 tablets / day, and the upper limit is 6+2×2=10 tablets / day. Determining the floating range based on statistical calculations can objectively reflect the normal fluctuation range and threshold of the risk indicator over the past period of time, provide a basis for subsequent judgment of whether the indicator is abnormal, and improve the accuracy of risk identification.

[0030] Step 203: Determine the floating range of the risk indicator based on the upper and lower limits of the floating range.

[0031] Specifically, in order to clearly determine the normal fluctuation range of the risk indicator, it is necessary to finally determine the floating range of the risk indicator based on the calculated upper and lower limits. After calculating the floating lower limit and upper limit of a risk indicator by statistical methods, the floating range of this risk indicator is determined with these two values ​​as the boundary. For example, the floating lower limit of a patient's blood pressure is calculated to be 120, and the floating upper limit is calculated to be 140. It can be determined that the floating range of the patient's blood pressure in the past 7 days is 120-140. In this way, the floating range is determined according to the upper and lower limits, forming a clear numerical range for the normal fluctuation of the risk indicator, which provides a basis for subsequent judgment of abnormal conditions of the risk indicator. As long as the indicator value monitored in real time exceeds the floating range, it can be prompted that there is an abnormality and a risk warning is required.

[0032] Step 103: Among the risk indicators, multiple risk indicators whose floating range exceeds the preset safe floating range are selected as target risk indicators.

[0033] Among them, the target risk index refers to the abnormal risk index that needs to be monitored and intervened through screening. In the embodiment of the present application, it can be understood as those risk indicators whose floating range exceeds the preset safe floating range, such as medication dosage, number of visits, etc., which are used to indicate that these indicators are abnormal and need timely intervention and risk control.

[0034] Specifically, in order to identify abnormal indicators with real risks, it is necessary to screen out indicators whose floating range exceeds the safety range from each risk indicator as target risk indicators. First, preset a normal safe floating range, such as within one standard deviation of the mean. Then compare the floating range calculated for each risk indicator with the safety range to determine whether it exceeds the safety range. For example, if the floating range of an indicator is 5-15, and the safety range is 8-12, then the floating range exceeds the safety range and is abnormal. Finally, these risk indicators with excessive floating ranges are screened out as target risk indicators, such as medication dosage, number of medical visits, etc. In this way, by screening out truly abnormal target risk indicators, targeted early warning and intervention of key issues can be carried out to improve work efficiency.

[0035] Based on the above embodiment, as an optional embodiment, in step 103: among the risk indicators, multiple risk indicators whose floating range exceeds the preset safe floating range are screened out as target risk indicators respectively. This step may also include the following steps: Step 301: For each risk indicator, compare the floating range of the risk indicator with the preset safety floating range; when the floating upper limit value of the floating range is greater than or equal to the upper limit threshold of the preset safety floating range, or the floating lower limit value of the floating range is less than the lower limit threshold of the preset safety floating range, the risk indicator is determined as the target risk indicator.

[0036] Specifically, in order to accurately identify indicators that truly have abnormal risks, it is necessary to compare the calculated floating range of the risk indicator with the preset safe floating range to determine whether it exceeds the safe range, and determine the exceeded indicator as the target risk indicator. Preset a normal safe floating range, such as within plus or minus one standard deviation of the mean, and the upper and lower limit thresholds on the range. Calculate the floating upper and lower limits of each risk indicator.

[0037] Compare the floating upper and lower limits of the risk indicator with the upper and lower limit thresholds of the safety range one by one. When the floating upper limit value is greater than or equal to the upper safety limit threshold, or the floating lower limit value is less than the lower safety limit threshold, the risk indicator is determined to be the target risk indicator. By comparing the target risk indicator with the safety range, the abnormal indicators that really need to be monitored can be effectively screened out and targeted intervention can be carried out. At the same time, it also avoids paying too much attention to normal indicators and improves work efficiency.

[0038] Step 104: Based on each target risk indicator, multiple adverse events are matched in a preset adverse event association map, and the risk probability corresponding to each adverse event is calculated.

[0039] Among them, the preset adverse event association map refers to a pre-constructed knowledge map, which contains the association relationship between risk indicators and various adverse events. In the embodiment of the present application, it can be understood as a knowledge network, which stores the association logic between risk indicators and adverse events in the form of nodes and edges, and is used to intelligently match multiple related adverse event types according to the target risk indicators, calculate the probability of occurrence of these adverse events, and perform risk assessment.

[0040] Adverse events refer to various events that may have a negative impact on the patient's health. In the embodiments of this application, it can be understood as various accidents or conditions such as disease deterioration and adverse drug reactions related to the target risk indicator. It is used to indicate the possible results of abnormal risk indicators, evaluate the probability of these adverse events, and provide risk warnings and prevention for patients.

[0041] The risk probability refers to the probability of an adverse event occurring. In the embodiments of the present application, it can be understood that based on the degree of association between the target risk index and the adverse event, the numerical probability of an adverse event occurring is calculated to evaluate the risk of different adverse events occurring.

[0042] Specifically, in order to evaluate the probability risk of different types of adverse events, it is necessary to match the preset adverse event association graph based on the identified target risk indicators to calculate the risk probability of various adverse events. First, collect the patient's target risk indicators, such as excessive medication, increased number of visits, etc. Then, in the pre-established adverse event knowledge graph, match various related adverse events such as adverse drug reactions and worsening of the disease according to these risk indicators. Finally, according to the degree of correlation between the target risk indicators and each adverse event, calculate the probability of adverse drug reactions, worsening of the disease and other adverse events. In this way, by matching with the adverse event knowledge graph, the risk of different types of adverse events can be evaluated and risk warnings can be issued.

[0043] Based on the above embodiment, as an optional embodiment, in step 104: based on each target risk indicator, multiple adverse events are matched in a preset adverse event association map, and the risk probability corresponding to each adverse event is calculated. This step may also include the following steps: Step 401: In a preset adverse event association map, determine the adverse events associated with each target risk indicator.

[0044] Specifically, in order to find adverse events related to the target risk indicators, it is necessary to determine the adverse event nodes associated with each target risk indicator in the preset adverse event association map. For the determined target risk indicators, such as excessive medication, increased number of visits, etc., find the adverse event nodes associated with them in the constructed adverse event knowledge map. According to the preset association from the risk indicator node to the adverse event node in the map, find all adverse events related to the target risk indicator, such as adverse drug reactions, worsening of the disease, etc. In this way, by determining the relevant adverse events through the map, the various adverse events that may be caused by the target risk indicators can be intelligently derived based on the knowledge base, without being restricted by rules, to achieve a seamless connection between risks and events, laying the foundation for subsequent risk calculations.

[0045] Based on the above embodiment, as an optional embodiment, in step 401: determining the adverse events associated with each target risk indicator in the preset adverse event association map, before this step, the following steps may also be included: Step 411: Acquire historical case data, where the historical case data includes multiple historical adverse events and historical risk indicators corresponding to each historical adverse event.

[0046] The historical case data refers to the medical records containing the patient's previous diseases and related indicator information. In the embodiment of the present application, it can be understood as the past case data extracted from the medical record database, including historical adverse events and corresponding risk indicators.

[0047] Specifically, regular historical case data are extracted from the hospital medical record database. These historical case data contain multiple historical disease diagnosis results of patients, which can be regarded as historical adverse events. At the same time, these cases also contain various vital signs, medication, medical treatment and other information, which can be used as risk indicators corresponding to historical adverse events. A large amount of case data containing historical adverse events and risk indicators is obtained, laying the foundation for constructing a preset adverse event association map. The construction of the map can learn the correlation between adverse events and risk indicators, which is used to assess the risk level of new cases.

[0048] Step 421: For each historical adverse event, a mapping relationship between the historical adverse event and each historical risk indicator is extracted from the historical case data.

[0049] Specifically, in order to construct a knowledge graph that reflects the association of adverse events, it is necessary to extract the mapping relationship between adverse events and risk indicators from historical case data. For each historical adverse event, such as pneumonia, traverse all case data. Identify the adverse event in the case and extract all its related risk indicators, such as symptoms such as cough and fever. Count the number of times the adverse event co-occurs with each risk indicator, establish a mapping relationship between the two, repeat the above process for all historical adverse events, and extract their mapping relationships with risk indicators. In this way, the joint association between adverse events and risk indicators can be learned from a large number of historical cases, and a reasonable mapping relationship can be constructed, laying the foundation for building a knowledge graph.

[0050] Step 431: construct a preset adverse event association graph with each historical risk indicator and each historical adverse event as a node and each mapping relationship as an edge.

[0051] Specifically, to represent the association between adverse events and risk indicators, it is necessary to construct a knowledge graph with the two as nodes and the mapping relationship as edges. The extracted historical adverse events are used as one of the nodes of the graph, such as pneumonia.

[0052] Historical risk indicators are also used as graph nodes, such as coughing. The mapping relationship between the two obtained from the previous statistics is set as the edge between the nodes. The weight of the edge represents the degree of association. The process is repeated to connect all adverse event nodes and risk indicator nodes. Finally, the entire adverse event association knowledge graph is constructed. This intuitive construction of the knowledge graph can clearly reflect the association between adverse events and risk indicators. The construction of the preset adverse event association graph makes risk determination more efficient and accurate.

[0053] Step 402: For each adverse event, a risk score of the adverse event is calculated based on the associated number and indicator type of the target risk indicator associated with the adverse event.

[0054] The number of associations refers to the number or number of edges between the adverse event node and the target risk indicator node in the graph. In the embodiment of the present application, it can be understood as how many target risk indicators are associated with an adverse event in the knowledge graph.

[0055] The indicator type refers to the category attribute of the target risk indicator. In the embodiment of the present application, it can be understood as the type of the target risk indicator, such as vital signs, medication dosage, frequency of visits, etc. It is used to indicate that different types of risk indicators have different degrees of influence on adverse events, and different weights can be given to them when performing risk calculations.

[0056] Specifically, in order to assess the risk level of different adverse events, it is necessary to calculate the risk score of adverse events based on the number and type of associations between adverse events and target risk indicators. First, for each identified adverse event, count how many target risk indicator nodes it is associated with in the knowledge graph, and what types of these indicators belong to. Then, according to the preset calculation formula, consider the number of associations of each adverse event and the weights of different types of indicators to calculate the risk score of the adverse event. For example, adverse event A is associated with 5 target risk indicators, including a high-weighted medication dosage indicator. It can be calculated that the risk score of A is 82 points. In this way, the risk score is calculated based on the number and type of indicators, which can intuitively assess the high and low risks of different adverse events, conduct more detailed risk grading of patients, and make adverse event warnings more targeted.

[0057] Based on the above embodiment, as an optional embodiment, in step 402: calculating the risk score of the adverse event based on the associated number and indicator type of the target risk indicator associated with the adverse event, this step may also include the following steps: Step 412: Based on a preset risk score mapping table, determine a first risk score corresponding to the associated quantity, and based on a preset risk weight mapping table, determine a risk weight corresponding to the indicator type.

[0058] The preset risk score mapping table refers to a table established in advance, which defines the risk scores corresponding to different association quantities. In the embodiment of the present application, it can be understood as a lookup table that lists the risk scores when adverse events are associated with different numbers of risk indicators. It is used to quickly convert the number of associations to risk scores, making the risk calculation process more quantitative.

[0059] The first risk score refers to the corresponding risk score found in the mapping table according to the association quantity. In the embodiment of the present application, it can be understood as the risk score obtained by considering only the association quantity, which is used to represent the quantitative calculation result of the risk contribution of the association quantity of the adverse event and the risk indicator to its risk.

[0060] The preset risk weight mapping table refers to a table established in advance, which defines the risk weights corresponding to different indicator types. In the embodiment of the present application, it can be understood as a lookup table that lists the weight coefficients of different types of risk indicators for quickly obtaining the weight value corresponding to the indicator type.

[0061] Risk weight refers to the weight of different types of risk indicators when calculating risk scores. In the embodiment of the present application, it can be understood as the corresponding weight coefficient found in the mapping table based on the indicator type, where the sum of the risk weights corresponding to all indicator types is 1, which is used to indicate the impact of a certain type of risk indicator on the risk of adverse events.

[0062] Specifically, in order to quantitatively calculate the risk score, it is necessary to determine the risk score and weight corresponding to the associated number and indicator type based on the preset mapping table. First, consult the risk score mapping table, and find the corresponding first risk score such as 50 points according to the associated number of adverse events, such as 5. Then consult the risk weight mapping table, and find the corresponding risk weight such as 1.2 according to the type of related indicators such as medication dosage. In this way, the risk score and weight corresponding to the quantity and type can be quickly obtained through the preset mapping table, so that the calculation process can be standardized and quantified. Different associated quantities can be converted into computable scores, and different types of indicators also have different weight considerations, making the results more comprehensive and accurate.

[0063] Step 422: The percentage by which the floating range of the target risk indicator exceeds the preset safe floating range is taken as the second risk score.

[0064] Among them, the second risk score refers to the risk score calculated based on the floating range of the target risk indicator. In the embodiment of the present application, it can be understood as the percentage of the target risk indicator value deviating from the safe range, indicating its abnormality, which is used to judge the abnormality of a single risk indicator and provide a basic basis for the comprehensive risk calculation of multiple indicators.

[0065] Specifically, in order to evaluate the degree of abnormality of the target risk indicator value, it is necessary to calculate the percentage of it exceeding the safe floating range as the second risk score. First, the actual floating range of the target risk indicator is counted, for example, a 20 basis point increase in blood pressure. Then, the safe floating range of blood pressure is searched in the preset parameters, for example, 10 basis points. When the percentage of the actual floating range of 20 basis points exceeding the safe range of 10 basis points is calculated, (20-10) / 10=100% is obtained. This 100% is used as the second risk score to represent the degree of abnormality of the blood pressure indicator. This intuitively quantifies the abnormal level of a single risk indicator and provides a data basis for the comprehensive risk assessment of multiple indicators.

[0066] Step 432: Calculate the product of the first risk score and the risk weight, and add the product to the second risk score to obtain the risk score of the adverse event.

[0067] Specifically, in order to comprehensively consider the two aspects of association analysis and numerical anomalies, it is necessary to calculate the product of the first risk score and the risk weight, and then add the second risk score to obtain the final risk score of the adverse event. First, the first risk score is calculated based on the number of associations, for example, 50 points. Then the risk weight of the relevant indicator is obtained by looking up the table, for example, 1.2, and the first risk score is multiplied by the weight, that is, 50 times 1.2 to get 60 points. In addition, the second risk score is calculated based on the numerical anomaly of the indicator, for example, 70 points are obtained. Finally, the two risk scores are added, that is, 60+70=130 points, as the final risk score. In this way, both association analysis and numerical anomalies are comprehensively considered, making the risk model more comprehensive and the calculation results more accurate.

[0068] Step 403: Calculate the sum of the risk scores, divide the risk score of each adverse event by the sum, and obtain the risk probability corresponding to each adverse event.

[0069] Specifically, in order to obtain a standardized risk probability result, it is necessary to calculate the sum of all adverse event risk scores, and divide the risk score of each adverse event by the sum to obtain a normalized risk probability. Calculate the risk scores of all relevant adverse events, such as 80 points for event A, 60 points for event B, and 100 points for event C. By adding up the risk scores of all adverse events, the total score is obtained, for example, A+B+C=80+60+100=240 points. Then divide the risk score of each adverse event by the total score to obtain a standardized probability result, such as the risk probability of A is 80 / 240=0.33. In this way, the dimension of the risk score can be removed, and a comparable probability result in the range of 0 to 1 can be obtained. The risk of adverse events is sorted by probability, and adverse event warnings are performed.

[0070] Step 105: If there is a target adverse event among the adverse events whose risk probability is greater than or equal to the risk probability threshold, the patient is warned based on the target adverse event.

[0071] Specifically, all the calculated risk probabilities of adverse events are traversed, and the risk probability of each adverse event is compared with the preset risk probability threshold. When it is found that the risk probability of a certain adverse event is greater than or equal to the risk probability threshold, the system will mark the adverse event as a target adverse event. The setting of this risk probability threshold needs to be determined according to the specific situation of the medical institution and the severity of different types of adverse events to achieve the best early warning effect. Once the target adverse events are determined, the system will warn the patient based on these target adverse events. The form of the early warning can be diverse, such as displaying a warning message in the electronic medical record system, sending a text message or email reminder to the responsible medical staff, or triggering the rapid response system within the hospital. The early warning information usually contains the patient's basic information, relevant risk indicator data, the type of target adverse event for early warning, and recommended preventive measures. Such an early warning mechanism can ensure that medical staff are informed of the patient's potential risks in a timely manner, so as to take corresponding preventive or intervention measures.

[0072] Reference Figure 2 , is an adverse event intelligent early warning system based on patient safety risk indicators provided in an embodiment of the present application, the system comprises: an information acquisition module, a risk indicator determination module, a risk probability determination module, and an adverse event early warning module, wherein: An information acquisition module, used to acquire medical information of multiple patients; The risk indicator determination module is used to determine the floating range corresponding to the risk indicators from multiple different sources in the medical information for each patient based on a preset time window; among the risk indicators, multiple risk indicators whose floating range exceeds the preset safe floating range are selected as target risk indicators respectively; A risk probability determination module is used to match multiple adverse events in a preset adverse event association map based on each target risk indicator, and calculate the risk probability corresponding to each adverse event; The adverse event warning module is used to warn the patient based on the target adverse event if there is a target adverse event with a risk probability greater than or equal to a risk probability threshold among the adverse events.

[0073] Based on the above embodiments, the risk indicator determination module is also used to obtain multiple historical data points of the risk indicator for each risk indicator within a preset time window; based on each historical data point, calculate the mean and standard deviation of the risk indicator; subtract a preset multiple of the standard deviation from the mean as the floating lower limit value, and add a preset multiple of the standard deviation to the mean as the floating upper limit value; determine the floating range of the risk indicator based on the lower limit value and the lower limit value of the floating range.

[0074] Based on the above embodiment, the risk indicator determination module also includes a risk indicator that is one of a medication dosage indicator, a physical sign change indicator, and a number of doctor visits indicator.

[0075] Based on the above embodiment, the risk indicator determination module is also used to compare the floating range of the risk indicator with the preset safety floating range for each risk indicator; when the floating upper limit value of the floating range is greater than or equal to the upper limit threshold of the preset safety floating range, or the floating lower limit value of the floating range is less than the lower limit threshold of the preset safety floating range, the risk indicator is determined as the target risk indicator.

[0076] On the basis of the above embodiment, the risk probability determination module is also used to determine the adverse events associated with each target risk indicator in a preset adverse event association map; for each adverse event, the risk score of the adverse event is calculated based on the associated number and indicator type of the target risk indicator associated with the adverse event; the sum of each risk score is calculated, and the risk score of each adverse event is divided by the sum to obtain the risk probability corresponding to each adverse event.

[0077] Based on the above embodiment, the risk probability determination module is also used to determine the first risk score corresponding to the associated quantity based on a preset risk score mapping table, and determine the risk weight corresponding to the indicator type based on a preset risk weight mapping table; the percentage of the floating range of the target risk indicator exceeding the preset safety floating range is used as the second risk score; the product of the first risk score and the risk weight is calculated, and the product is added to the second risk score to obtain the risk score of the adverse event.

[0078] Based on the above embodiment, the risk probability determination module is also used to obtain historical case data, which includes multiple historical adverse events and historical risk indicators corresponding to each historical adverse event; for each historical adverse event, the mapping relationship between the historical adverse event and each historical risk indicator is extracted from the historical case data; with each historical risk indicator and each historical adverse event as a node and each mapping relationship as an edge, a preset adverse event association map is constructed.

[0079] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0080] The present application also discloses an electronic device. Figure 3 , Figure 3The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0081] The communication bus 302 is used to realize the connection and communication between these components.

[0082] The user interface 303 may include a display interface and a camera interface. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0083] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0084] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface diagrams and applications, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0085] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program of an intelligent early warning method for adverse events based on patient safety risk indicators.

[0086] exist Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program stored in the memory 305 for an intelligent early warning method for adverse events based on patient safety risk indicators. When executed by one or more processors 301, the electronic device 300 executes one or more methods in the above-mentioned embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0087] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0088] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0089] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0090] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0091] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0092] The above are only exemplary embodiments of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0093] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not recorded in the present disclosure. The description and examples are to be regarded as exemplary only.

Claims

1. An intelligent early warning method for adverse events based on patient safety risk indicators, characterized in that: include: Access medical information for multiple patients; For each of the patients, based on a preset time window, determining a floating range corresponding to risk indicators from multiple different sources in the medical information; Among the risk indicators, multiple risk indicators whose floating range exceeds the preset safe floating range are selected as target risk indicators respectively; Based on each of the target risk indicators, multiple adverse events are matched in a preset adverse event association map, and the risk probability corresponding to each of the adverse events is calculated; If there is a target adverse event among the adverse events whose risk probability is greater than or equal to the risk probability threshold, then an early warning is given to the patient based on the target adverse event; The determining, based on a preset time window, the floating ranges corresponding to the risk indicators from multiple different sources in the medical information includes: For each of the risk indicators, obtaining multiple historical data points of the risk indicator within the preset time window; Calculating the mean and standard deviation of the risk indicator based on each of the historical data points; The mean value minus the preset multiple of the standard deviation is used as the floating lower limit value, and the mean value plus the preset multiple of the standard deviation is used as the floating upper limit value; The floating range of the risk indicator is determined according to the upper and lower limits of the floating range.

2. The intelligent early warning method for adverse events based on patient safety risk indicators according to claim 1, characterized in that: The risk indicator is one of a medication dosage indicator, a physical sign change indicator, and a number of medical visits indicator.

3. The intelligent early warning method for adverse events based on patient safety risk indicators according to claim 1, characterized in that: Among the risk indicators, multiple risk indicators whose floating range exceeds the preset safe floating range are selected as target risk indicators, including: For each of the risk indicators, comparing the floating range of the risk indicator with the preset safe floating range; When the floating upper limit value of the floating range is greater than or equal to the upper limit threshold of the preset safe floating range, or the floating lower limit value of the floating range is less than the lower limit threshold of the preset safe floating range, the risk indicator is determined as the target risk indicator.

4. The intelligent early warning method for adverse events based on patient safety risk indicators according to claim 1, characterized in that: Based on each of the target risk indicators, matching multiple adverse events in a preset adverse event association map, and calculating the risk probability corresponding to each of the adverse events, includes: In the preset adverse event association map, determining the adverse events associated with each of the target risk indicators; For each of the adverse events, calculating a risk score for the adverse event based on the associated number and indicator type of the target risk indicator associated with the adverse event; The sum of the risk scores is calculated, and the risk scores of the adverse events are divided by the sum to obtain the risk probability corresponding to the adverse events.

5. The intelligent early warning method for adverse events based on patient safety risk indicators according to claim 4, characterized in that: The step of calculating the risk score of the adverse event based on the associated number and indicator type of the target risk indicator associated with the adverse event comprises: Based on a preset risk score mapping table, determine a first risk score corresponding to the associated quantity, and based on a preset risk weight mapping table, determine a risk weight corresponding to the indicator type; The percentage by which the floating range of the target risk indicator exceeds the preset safe floating range is taken as a second risk score; The product of the first risk score and the risk weight is calculated, and the product is added to the second risk score to obtain the risk score of the adverse event.

6. The method for intelligent early warning of adverse events based on patient safety risk indicators according to claim 4, characterized in that: Before determining the adverse events associated with each of the target risk indicators in the preset adverse event association map, the method further includes: Acquiring historical case data, wherein the historical case data includes a plurality of historical adverse events and a historical risk indicator corresponding to each of the historical adverse events; For each of the historical adverse events, extracting a mapping relationship between the historical adverse event and each of the historical risk indicators from the historical case data; The preset adverse event association graph is constructed with each of the historical risk indicators and each of the historical adverse events as nodes and each of the mapping relationships as edges.

7. An intelligent early warning system for adverse events based on patient safety risk indicators for implementing the intelligent early warning method for adverse events based on patient safety risk indicators as claimed in claim 1, characterized in that: The system comprises: An information acquisition module, used to acquire medical information of multiple patients; A risk indicator determination module is used to determine, for each of the patients, based on a preset time window, the floating ranges corresponding to the risk indicators from multiple different sources in the medical information; among the risk indicators, multiple risk indicators whose floating ranges exceed the preset safe floating range are selected as target risk indicators; A risk probability determination module, used to match multiple adverse events in a preset adverse event association map based on each of the target risk indicators, and calculate the risk probability corresponding to each of the adverse events; An adverse event warning module, configured to warn the patient based on a target adverse event if there is a target adverse event whose risk probability is greater than or equal to a risk probability threshold among the adverse events; The risk indicator determination module is used to obtain multiple historical data points of the risk indicator within the preset time window for each risk indicator; calculate the mean and standard deviation of the risk indicator based on each historical data point; subtract a preset multiple of the standard deviation from the mean as a floating lower limit value, and add the preset multiple of the standard deviation to the mean as a floating upper limit value; determine the floating range of the risk indicator based on the lower limit value and the lower limit value of the floating range.

8. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the intelligent early warning method for adverse events based on patient safety risk indicators as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the intelligent early warning method for adverse events based on patient safety risk indicators as described in any one of claims 1-6 is executed.

Citation Information

Patent Citations

  • Risk conduction early warning method based on association graph

    CN111951104A

  • Early warning method and system for new coronal pneumonia

    CN112216397A

  • Credit risk early warning method and device

    CN113516553A

  • Hospital safety risk early warning management method and system

    CN115662584A

  • Risk prediction method for chronic diseases and related equipment

    CN115862842A

Cited By

  • Medical device with alarm adjustment tool

    EP4840390A1