An early warning method for sepsis of multiple trauma patients based on artificial intelligence

Abstract

The present application relates to the technical field of physiological data processing, in particular to an early warning method for sepsis of multiple injury patients based on artificial intelligence. According to the monitoring data distribution of each index of each multiple injury patient at different monitoring moments, the high risk of each multiple injury patient at each index is obtained, and the high sensitivity of the multiple injury patient with sepsis at each index is obtained. According to the monitoring data distribution of each index of each multiple injury patient at different monitoring moments and the difference between adjacent monitoring moments, the dynamic change rate of each index of each multiple injury patient at each monitoring moment is obtained, and the sepsis prediction value of each index of each multiple injury patient is obtained. Then, the sepsis risk score of each multiple injury patient is obtained, and the early warning of sepsis of multiple injury patients is carried out. The present application can accurately evaluate the sepsis risk of each multiple injury patient, and improve the accuracy of early warning.

Description

Technical Field

[0001] This invention relates to the field of physiological data processing technology, specifically to an early warning method for sepsis in patients with multiple traumas based on artificial intelligence. Background Technology

[0002] Patients with multiple injuries are prone to developing sepsis, a systemic inflammatory response syndrome, due to severe tissue damage, immune system disorders, and increased risk of infection. The disease progresses rapidly and has a high mortality rate. Early identification and appropriate treatment can improve the prognosis of sepsis patients. Therefore, it is usually necessary to conduct a comprehensive analysis of the physiological status of patients with multiple injuries based on various physiological indicators and real-time monitoring data to achieve early warning of sepsis.

[0003] In existing technologies, regression analysis is typically performed on physiological indicators and the incidence of sepsis to screen for risk factors for sepsis in patients with multiple traumatic injuries, and a predictive model for sepsis is established based on this. However, because patients with multiple traumatic injuries experience systemic traumatic inflammatory responses due to tissue damage, which highly overlap with the early manifestations of septic infection and cause similar changes in related physiological indicators, the predictive model lacks specificity and cannot distinguish between traumatic inflammation and septic inflammation, leading to errors in the assessment of sepsis occurrence in patients with multiple traumatic injuries. Summary of the Invention

[0004] To address the technical problem of errors in predicting sepsis in patients with multiple traumatic injuries due to systemic traumatic inflammatory responses caused by tissue damage, which highly overlap with the early manifestations of sepsis infection, this invention aims to provide an artificial intelligence-based early warning method for sepsis in patients with multiple traumatic injuries. The specific technical solution adopted is as follows:

[0005] This invention proposes an early warning method for sepsis in patients with multiple traumatic injuries based on artificial intelligence, the method comprising:

[0006] Acquire monitoring data of multiple physiological indicators in patients with sepsis and non-septic multiple injuries at each monitoring time point;

[0007] Based on the distribution of monitoring data for each indicator for each patient with multiple injuries at different monitoring times, the baseline deviation of each indicator for each patient with multiple injuries at each monitoring time is obtained, and the high risk of each patient with multiple injuries in each indicator is obtained; based on the changes in the high risk of each indicator for different patients with multiple injuries, the high sensitivity of patients with sepsis and multiple injuries in each indicator is obtained.

[0008] Based on the distribution of monitoring data for each indicator for each patient with multiple injuries at different monitoring times, and the differences between adjacent monitoring times, the dynamic change rate of each indicator for each patient with multiple injuries at each monitoring time is obtained; based on the dynamic change rate and baseline deviation of each indicator for different patients with multiple injuries at all monitoring times, and the high sensitivity of patients with sepsis in each indicator for each indicator, the predictive value of sepsis for each patient with multiple injuries in each indicator is obtained.

[0009] Based on the predictive value and high risk of sepsis for each multiple trauma patient across different indicators, a sepsis risk score is obtained for each multiple trauma patient, enabling early warning of sepsis in multiple trauma patients.

[0010] Furthermore, the method for obtaining the baseline deviation includes:

[0011] For any given monitoring time, compare the monitoring data of each multiple injury patient with the standard reference range for each indicator. If the monitoring data has a standard reference range, set the baseline deviation of each indicator to 0.

[0012] If there is no standard reference range for the monitoring data, obtain the minimum value of the difference between the monitoring data and the boundary data of different boundaries within the standard reference range, and use the boundary data corresponding to the minimum value as the baseline data; calculate the ratio of the minimum difference value to the baseline data as the baseline deviation of each multiple injury patient for each indicator.

[0013] Furthermore, the method for obtaining the high-risk status includes:

[0014] The mean difference in baseline deviation for each indicator between different monitoring times and the earliest monitoring time was obtained for each patient with multiple injuries, which was used as the high risk for each indicator for each patient with multiple injuries.

[0015] Furthermore, the highly sensitive acquisition method includes:

[0016] The sum of the high-risk levels for each indicator was obtained for all patients with multiple injuries and sepsis, which was taken as the high-risk level of sepsis.

[0017] The sum of the high-risk levels for each indicator for all patients with multiple injuries was obtained as the overall high-risk level;

[0018] The ratio between the high-risk level of sepsis and the overall high-risk level was obtained as a measure of high sensitivity for each indicator in patients with multiple injuries due to sepsis.

[0019] Furthermore, the method for obtaining the dynamic rate of change includes:

[0020] The monitoring data difference of each indicator for each patient with multiple injuries between each monitoring time and the previous monitoring time is obtained. The ratio of the monitoring data difference to the difference between the corresponding monitoring time is calculated as the dynamic change rate of each indicator for each patient with multiple injuries at each monitoring time.

[0021] Furthermore, the method for obtaining the predictive value of sepsis includes:

[0022] Based on the dynamic change rate and baseline deviation of each indicator for each multiple injury patient at all monitoring times, the pathological disorder degree of each indicator for each multiple injury patient is obtained.

[0023] The mean of pathological disorder for each indicator was obtained for all patients with multiple injuries due to sepsis, which was used as the overall level of pathological disorder for each indicator in patients with multiple injuries due to sepsis.

[0024] Based on the degree of pathological disorder for each indicator, the overall level of pathological disorder, and the high sensitivity of sepsis in multiple trauma patients for each indicator, the predictive value of sepsis for each indicator for each multiple trauma patient is obtained.

[0025] Furthermore, the method for obtaining the degree of pathological disorder includes:

[0026] The mean product of the dynamic change rate and baseline deviation of each indicator for each multiple injury patient at all monitoring times was obtained as the pathological disorder degree of each indicator for each multiple injury patient.

[0027] Furthermore, obtaining the sepsis predictive value for each multiple injury patient at each indicator includes:

[0028] The ratio of the pathological disorder level of each multiple injury patient in each indicator to the overall pathological disorder level of multiple injury patients with sepsis in each indicator is obtained as the sepsis risk level of each multiple injury patient in each indicator.

[0029] The product of the sepsis risk level for each multiple trauma patient and the high sensitivity of sepsis in each multiple trauma patient for each indicator is obtained as the predictive value of sepsis in each multiple trauma patient for each indicator.

[0030] Furthermore, the method for obtaining the sepsis risk score includes:

[0031] Based on the sepsis predictive value of different indicators for each multiple trauma patient, a weighted average of the high risk of different indicators was calculated to obtain a sepsis risk score for each multiple trauma patient.

[0032] Furthermore, the high-risk status of different indicators is weighted and averaged based on the sepsis predictive value of each multiple trauma patient for each indicator, to obtain a sepsis risk score for each multiple trauma patient, including:

[0033] The sepsis predictive value of each patient with multiple injuries on different indicators was obtained and weighted and summed to determine the high risk, which was then used as the first summed value.

[0034] The sum of the sepsis predictive values ​​for each multiple trauma patient across different indicators was obtained as the second summation value;

[0035] The ratio of the first cumulative value to the second cumulative value is used as the sepsis risk score for each patient with multiple injuries.

[0036] The present invention has the following beneficial effects:

[0037] This invention obtains the baseline deviation of each indicator for each multiple trauma patient at each monitoring time based on the monitoring data distribution of each indicator at different monitoring times. This helps to assess the relative abnormality of each indicator and obtain the high-risk status of each multiple trauma patient for each indicator, thus assessing the patient's risk level for each indicator and quantifying individualized risk characteristics. Based on the changes in high-risk status of each indicator among different multiple trauma patients, the invention obtains the high sensitivity of sepsis-related multiple trauma patients for each indicator, analyzing the unique characteristics of the indicators. Furthermore, based on the monitoring data distribution of each indicator for each multiple trauma patient at different monitoring times and the differences between adjacent monitoring times, the invention obtains the baseline deviation of each multiple trauma patient for each indicator at each monitoring time. The dynamic change rate of each indicator can capture the dynamic trend of each indicator and assess the severity and development trend of immune status dysregulation. Considering the differences in the rate of change and fluctuation of indicators among different patients at different monitoring times, based on the dynamic change rate and baseline deviation of each indicator for different multiple trauma patients at all monitoring times, and the high sensitivity of sepsis-affected multiple trauma patients for each indicator, the predictive value of sepsis for each indicator for each multiple trauma patient is obtained, quantifying the reference value of each indicator for the occurrence of sepsis. Based on the predictive value of sepsis for each multiple trauma patient in different indicators and the high risk, a sepsis risk score is obtained for each multiple trauma patient, enabling early warning of sepsis in multiple trauma patients. This invention improves the accuracy of early warning by accurately assessing the sepsis risk of each multiple trauma patient. Attached Figure Description

[0038] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1A flowchart illustrating an early warning method for sepsis in patients with multiple traumas based on artificial intelligence, provided as an embodiment of the present invention.

[0040] Figure 2 This is a flowchart illustrating a method for obtaining the predictive value of sepsis, as provided in one embodiment of the present invention. Detailed Implementation

[0041] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of an artificial intelligence-based early warning method for sepsis in patients with multiple traumas proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0042] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0043] The following description, in conjunction with the accompanying drawings, details the specific scheme of an early warning method for sepsis in patients with multiple traumas based on artificial intelligence, provided by this invention.

[0044] Please see Figure 1 The diagram illustrates a flowchart of an early warning method for sepsis in patients with multiple traumatic injuries based on artificial intelligence, according to an embodiment of the present invention. The specific method includes:

[0045] Step S1: Obtain monitoring data of multiple physiological indicators for patients with sepsis and non-septic multiple injuries at each monitoring time point.

[0046] In embodiments of the present invention, considering that multiple trauma patients themselves will experience systemic traumatic inflammatory response due to tissue damage, which highly overlaps with the early manifestations of sepsis, in order to avoid a large error in distinguishing between traumatic inflammation and sepsis, it is necessary to analyze the dynamic changes of patients' physiological indicators to provide early warning of sepsis. First, medical data of multiple trauma patients in the emergency department are collected, including physiological indicator data at multiple monitoring times from admission. Among them, multiple trauma patients are divided into sepsis and non-sepsis according to existing sepsis judgment rules. Physiological indicators include various blood indicators such as lactate, white blood cell count, and hemoglobin, as well as pro-inflammatory indicators such as the neutrophil-to-lymphocyte ratio and immunosuppressive indicators. Therefore, monitoring data of multiple physiological indicators of multiple trauma patients with and without sepsis are obtained at each monitoring time.

[0047] It should be noted that, in one embodiment of the present invention, monitoring data of multiple physiological indicators at multiple monitoring times within 48 hours of admission of patients with multiple injuries are obtained from medical records. The monitoring times are preset by the implementers based on relevant experience. In other embodiments of the present invention, the monitoring time range can be specifically set according to the specific circumstances, and will not be limited or described in detail here.

[0048] It should be noted that, in order to facilitate subsequent data processing, interpolation, mean, or median are used to fill missing values ​​in the monitoring data, remove or correct abnormal data, and ensure data quality. Furthermore, the acquired monitoring data is subjected to Z-score standardization to eliminate the influence of units in data calculation. The specific methods are well known to those skilled in the art and will not be elaborated here.

[0049] Step S2: Based on the monitoring data distribution of each indicator for each multiple injury patient at different monitoring times, obtain the baseline deviation of each indicator for each multiple injury patient at each monitoring time, and obtain the high risk of each multiple injury patient for each indicator; based on the changes in the high risk of each indicator for different multiple injury patients, obtain the high sensitivity of sepsis-related multiple injury patients for each indicator.

[0050] For patients with multiple injuries, the monitoring data for each indicator will change due to multiple organ damage or immune dysfunction. The deviation of these indicators is more severe after sepsis infection, with a greater difference from the indicators at the earliest admission monitoring time. By analyzing the distribution of monitoring data for each indicator at different monitoring times, we can more clearly understand the dynamic deviation characteristics of the data, reflecting the risk of disease deterioration and the immediate impact of trauma on each indicator. Based on the distribution of monitoring data for each indicator for each patient with multiple injuries at different monitoring times, we can obtain the baseline deviation of each indicator for each patient at each monitoring time and determine the high-risk status of each patient for each indicator.

[0051] Preferably, in one embodiment of the present invention, the method for obtaining the baseline deviation includes:

[0052] For any given monitoring time, compare the monitoring data of each multiple injury patient with the standard reference range for each indicator. If the monitoring data has a standard reference range, set the baseline deviation of each indicator to 0.

[0053] If there is no standard reference range for the monitoring data, obtain the minimum value of the difference between the monitoring data and the boundary data of different boundaries within the standard reference range, and use the boundary data corresponding to the minimum value as the baseline data; calculate the ratio of the minimum difference value to the baseline data as the baseline deviation of each multiple injury patient for each indicator.

[0054] It should be noted that, in the embodiments of the present invention, the standard reference range may be obtained in advance by implementers based on relevant professional knowledge.

[0055] To illustrate, suppose there exists a standard reference range of ab for any indicator. At any given monitoring time, the monitoring data x of the indicator does not exist within the standard reference range. If x is less than a, there is a minimum difference between x and the boundary data a within the corresponding standard range. Calculate the ratio of |xa| to a to obtain the baseline deviation of the corresponding indicator. If x is greater than b, there is a minimum difference between x and the boundary data b within the corresponding standard range. Calculate the ratio of |xb| to b to obtain the baseline deviation of the corresponding indicator.

[0056] Preferably, in one embodiment of the present invention, the method for obtaining high-risk information includes:

[0057] The mean difference in baseline deviation for each indicator between different monitoring times and the earliest monitoring time was obtained for each patient with multiple injuries, which was used as the high risk for each indicator for each patient with multiple injuries.

[0058] In one embodiment of the present invention, the formula for high risk is expressed as:

[0059] ;

[0060] in, Indicates the first The multiple injury patient in the first The high risk of this indicator; Indicates the first The multiple injury patient in the first Monitoring time at the next Baseline deviation of the indicator; Indicates the first The first multiple injury patient at the earliest monitoring time Baseline deviation of the indicator; This indicates the number of monitoring moments.

[0061] In the formula for high risk Indicates the calculation of the first The multiple injury patient in the first The greater the difference in baseline deviation of each indicator between the monitoring time and the earliest monitoring time, the greater the difference in baseline deviation relative to the earliest monitoring time, and the more different the deviation from the earliest monitoring time, the more likely it is to be an indicator of sepsis infection, and the greater the risk.

[0062] Comparing the high-risk changes of a certain indicator in patients with sepsis and those without sepsis can reflect whether the indicator shows more obvious abnormal changes when sepsis occurs, and is more helpful in identifying sensitive indicators closely related to sepsis. Based on the high-risk changes of each indicator in different patients with multiple injuries, the high sensitivity of each indicator in patients with sepsis with multiple injuries can be obtained.

[0063] Preferably, in one embodiment of the present invention, the highly sensitive acquisition method includes:

[0064] The sum of the high-risk levels for each indicator was obtained for all patients with multiple injuries and sepsis, which was taken as the high-risk level of sepsis.

[0065] The sum of the high-risk levels for each indicator for all patients with multiple injuries was obtained as the overall high-risk level;

[0066] The ratio between the high-risk level of sepsis and the overall high-risk level was obtained as a measure of high sensitivity for each indicator in patients with multiple injuries due to sepsis.

[0067] In one embodiment of the present invention, the formula for high sensitivity is expressed as:

[0068] ;

[0069] in, This indicates that the multiple trauma patients with sepsis were in the first... The high sensitivity of this indicator; This indicates the number of patients with multiple injuries due to sepsis; Indicates the first The first multiple trauma patient with sepsis was in the first The high risk of this indicator; This indicates the total number of patients with multiple injuries; Indicates the first The multiple injury patient in the first The high risk of this indicator.

[0070] In highly sensitive formulas, This indicates that all patients with sepsis and multiple injuries were in the first... The sum of the high-risk indicators is used as the high-risk level of sepsis. This indicates that all patients with multiple injuries were in the first... The sum of the high-risk indicators is used as the overall high-risk level; This represents the ratio between the high-risk level of sepsis and the overall high-risk level. The higher the ratio, the more likely the patient with sepsis has developed it on the [number]th day. The higher the risk level of each indicator and the more obvious the abnormal changes, the more likely the sepsis-related multiple trauma patients are to develop sepsis in the first day. The higher the sensitivity of an indicator, the greater its sensitivity.

[0071] Step S3: Based on the distribution of monitoring data for each indicator for each patient with multiple injuries at different monitoring times and the differences between adjacent monitoring times, obtain the dynamic change rate of each indicator for each patient with multiple injuries at each monitoring time; based on the dynamic change rate and baseline deviation of each indicator for different patients with multiple injuries at all monitoring times, and the high sensitivity of patients with multiple injuries with sepsis to each indicator, obtain the sepsis predictive value of each patient with multiple injuries to each indicator.

[0072] Patients with multiple traumatic injuries who develop sepsis experience dramatic fluctuations in their immune status in the early stages, accompanied by a more intense and persistent pro-inflammatory response than that caused by traumatic inflammation. This leads to significant changes in relevant indicators. By analyzing the distribution of monitoring data for each indicator at different monitoring times for each patient with multiple traumatic injuries, as well as the differences between adjacent monitoring times, we continuously and dynamically monitor relevant indicators, quantifying the dynamic change rate of each indicator at each monitoring time to reflect the fluctuation of the indicators. The smaller the difference between monitoring times, the greater the change in the indicator, and the greater the dynamic change rate, indicating larger fluctuations. Based on the distribution of monitoring data for each indicator at different monitoring times for each patient with multiple traumatic injuries, as well as the differences between adjacent monitoring times, we obtain the dynamic change rate of each indicator for each patient with multiple traumatic injuries at each monitoring time.

[0073] Preferably, in one embodiment of the present invention, the method for obtaining the dynamic rate of change includes:

[0074] The monitoring data difference of each indicator for each patient with multiple injuries between each monitoring time and the previous monitoring time is obtained. The ratio of the monitoring data difference to the difference between the corresponding monitoring time is calculated as the dynamic change rate of each indicator for each patient with multiple injuries at each monitoring time.

[0075] In one embodiment of the present invention, the formula for the dynamic rate of change is expressed as:

[0076] ;

[0077] in, Indicates the first The multiple injury patient in the first Monitoring time at the next The dynamic rate of change of the indicator; Indicates the first The multiple injury patient in the first Monitoring time at the next Monitoring data for each indicator; Indicates the first The multiple injury patient in the first Monitoring time at the next Monitoring data for each indicator; Indicates the first The multiple injury patient in the first Monitoring time and the previous monitoring time The differences between them; This indicates taking the absolute value.

[0078] In the formula for the rate of dynamic change, the first... The multiple injury patient in the first Monitoring time and number Between monitoring times The greater the difference in the monitoring data of the indicators, the more significant the difference. Monitoring time and the previous monitoring time The smaller the difference between them, the greater the change in the data within a shorter period of time, and the greater the dynamic rate of change.

[0079] After admission and surgery, patients with multiple traumatic injuries should maintain stable baseline deviations or gradually return to normal in subsequent monitoring timeframes if they do not develop sepsis. A smaller dynamic change rate indicates better baseline performance. Conversely, for patients with sepsis, significant fluctuations and larger baseline deviations are observed in the indicators across multiple monitoring timeframes. High sensitivity of each indicator in patients with sepsis reflects the degree of abnormal changes that occur during sepsis; higher sensitivity and greater significance are more helpful in analyzing sepsis occurrence. Therefore, by analyzing the dynamic change rate and baseline deviation of each indicator in different patients with multiple traumatic injuries across all monitoring timeframes, the predictive value of each indicator for sepsis in each patient with multiple traumatic injuries can be more comprehensively and accurately assessed. Based on the dynamic change rate and baseline deviation of each indicator in different patients with multiple traumatic injuries across all monitoring timeframes, and the high sensitivity of each indicator in patients with sepsis, the predictive value of each indicator for sepsis in each patient with multiple traumatic injuries can be obtained.

[0080] Preferably, in one embodiment of the present invention, the method for obtaining the predictive value of sepsis is described in [reference needed]. Figure 2 It illustrates a flowchart of a method for obtaining the predictive value of sepsis, including:

[0081] Step S201: Based on the dynamic change rate and baseline deviation of each indicator for each multiple injury patient at all monitoring times, obtain the pathological disorder degree of each indicator for each multiple injury patient.

[0082] Preferably, in one embodiment of the present invention, the method for obtaining the degree of pathological disorder includes:

[0083] The mean product of the dynamic change rate and baseline deviation of each indicator for each multiple injury patient at all monitoring times was obtained as the pathological disorder degree of each indicator for each multiple injury patient.

[0084] In one embodiment of the present invention, the formula for the degree of pathological disorder is expressed as:

[0085] ;

[0086] in, Indicates the first The multiple injury patient in the first The degree of pathological disorder of each indicator; Indicates the number of monitoring moments; Indicates the first The multiple injury patient in the first Monitoring time at the next The dynamic rate of change of the indicator; Indicates the first The multiple injury patient in the first The monitoring time at the next monitoring time The baseline deviation of the indicator.

[0087] In the formula for pathological disorder, the greater the dynamic change rate, the greater the baseline deviation, the greater the fluctuation and instability of the indicator data, and the greater the pathological disorder.

[0088] Step S202: Obtain the mean of pathological disorder for each indicator for all patients with multiple injuries due to sepsis, as the overall pathological disorder level for each indicator in patients with multiple injuries due to sepsis.

[0089] Although there are individual differences among patients, the relevant indicators of sepsis infection show roughly the same dynamic trend. By calculating the mean, the pathological disorder level of all patients with sepsis and multiple injuries is quantified, and the overall pathological disorder level of each indicator in patients with sepsis and multiple injuries is assessed. The greater the pathological disorder, the more specific and reliable the sepsis is reflected in each indicator.

[0090] Step S203: Based on the pathological disorder degree of each multiple trauma patient in each indicator, the overall pathological disorder level, and the high sensitivity of multiple trauma patients with sepsis in each indicator, obtain the predictive value of sepsis for each multiple trauma patient in each indicator.

[0091] Preferably, in one embodiment of the present invention, obtaining the sepsis predictive value for each multiple trauma patient at each indicator includes:

[0092] The ratio of the pathological disorder level of each multiple injury patient in each indicator to the overall pathological disorder level of multiple injury patients with sepsis in each indicator is obtained as the sepsis risk level of each multiple injury patient in each indicator.

[0093] The product of the sepsis risk level for each multiple trauma patient and the high sensitivity of sepsis in each multiple trauma patient for each indicator is obtained as the predictive value of sepsis in each multiple trauma patient for each indicator.

[0094] In one embodiment of the present invention, the formula for the predictive value of sepsis is expressed as follows:

[0095] ;

[0096] ;

[0097] in, Indicates the first The multiple injury patient in the first The predictive value of this indicator for sepsis; Indicates the first The multiple injury patient in the first The degree of pathological disorder of each indicator; This indicates that the multiple trauma patients with sepsis were in the first... The overall pathological disorder level of the indicators; This indicates the number of patients with multiple injuries due to sepsis; Indicates the first The multiple injury patient in the first The degree of pathological disorder of each indicator; This indicates that the multiple trauma patients with sepsis were in the first... High sensitivity of this indicator.

[0098] In the formula for predicting the value of sepsis, This indicates that all patients with sepsis and multiple injuries were in the first... The mean of the pathological disorder of each indicator, that is, the overall pathological disorder level of patients with sepsis and multiple injuries in each indicator. The larger the mean, the greater the overall pathological disorder level, and the greater the reliability of the sepsis reference. Indicates the first The multiple injury patient in the first The pathological disorder of the indicators and the multiple trauma patients with sepsis on the first day The ratio of the overall pathological disorder level of each indicator represents the degree of sepsis risk for each multiple trauma patient in each indicator. The higher the ratio, the greater the risk of sepsis in the first indicator. The multiple injury patient in the first The pathological disorder of the index relative to sepsis in multiple trauma patients on the first day The greater the overall pathological disorder level of each indicator, the greater the corresponding risk of sepsis, and the greater the sensitivity. The more obvious the changes in the corresponding indicators, the greater the predictive value of each indicator for sepsis.

[0099] Step S4: Based on the sepsis predictive value and high risk of each multiple trauma patient in different indicators, obtain a sepsis risk score for each multiple trauma patient to provide early warning of sepsis in multiple trauma patients.

[0100] Each patient with multiple trauma exhibits different physiological changes after admission. The predictive value of sepsis can reflect the relative contribution of each indicator. Therefore, by analyzing the predictive value and high risk of sepsis of different indicators, the sepsis risk score of each patient with multiple trauma can be more accurately quantified.

[0101] Preferably, in one embodiment of the present invention, the method for obtaining a sepsis risk score includes:

[0102] Based on the sepsis predictive value of different indicators for each multiple trauma patient, a weighted average of the high risk of different indicators was calculated to obtain a sepsis risk score for each multiple trauma patient.

[0103] In one embodiment of the present invention, a weighted average of the high-risk factors of different indicators is calculated based on the sepsis predictive value of each multiple trauma patient for different indicators to obtain a sepsis risk score for each multiple trauma patient, including:

[0104] The sepsis predictive value of each patient with multiple injuries on different indicators was obtained and weighted and summed to determine the high risk, which was then used as the first summed value.

[0105] The sum of the sepsis predictive values ​​for each multiple trauma patient across different indicators was obtained as the second summation value;

[0106] The ratio of the first cumulative value to the second cumulative value is used as the sepsis risk score for each patient with multiple injuries.

[0107] In one embodiment of the present invention, the formula for the sepsis risk score is expressed as follows:

[0108] ;

[0109] in, Indicates the first Sepsis risk score for patients with multiple traumas; Indicates the first The multiple injury patient in the first The predictive value of this indicator for sepsis; Indicates the first The multiple injury patient in the first The high risk of this indicator; Indicates the number of items in the indicator.

[0110] In the formula for sepsis risk scoring, Indicates the first The first cumulative value is obtained by weighting and summing the predictive value of sepsis for multiple trauma patients across different indicators to determine high risk. Indicates the first The sum of the predictive values ​​of sepsis for different indicators in patients with multiple injuries is used as the second summation value; the larger the ratio, the greater the predictive value of sepsis, the greater the reliability of high risk, the greater the proportion in reflecting sepsis risk, the greater the high risk type, and the higher the sepsis risk score.

[0111] Based on this, a sepsis risk score is obtained for each patient with multiple injuries. In another embodiment of the present invention, early warning of sepsis is also provided for patients with multiple injuries, including: obtaining the mean sepsis risk score of all patients with multiple injuries who have sepsis, as a first sepsis risk score level; obtaining the mean sepsis risk score of all patients with multiple injuries who do not have sepsis, as a second sepsis risk score level; obtaining the mean of the first sepsis risk score level and the second sepsis risk score level as a warning threshold for sepsis. The lower the sepsis risk score is compared to the warning threshold, the lower the risk of sepsis; the higher the sepsis risk score is compared to the warning threshold, the higher the risk of sepsis. Early warning is more necessary to facilitate timely intervention and treatment, and reduce the mortality rate of sepsis.

[0112] In summary, this invention obtains the high-risk status of each multiple injury patient for each indicator based on the distribution of monitoring data for each indicator at different monitoring times, and also obtains the high sensitivity of multiple injury patients with sepsis for each indicator. Based on the distribution of monitoring data for each indicator for each multiple injury patient at different monitoring times, and the differences between adjacent monitoring times, it obtains the dynamic change rate of each indicator for each multiple injury patient at each monitoring time, and obtains the sepsis predictive value for each indicator for each multiple injury patient. Furthermore, it obtains a sepsis risk score for each multiple injury patient, enabling early warning of sepsis in multiple injury patients. This invention improves the accuracy of early warning by accurately assessing the sepsis risk of each multiple injury patient.

[0113] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0114] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. An early warning method of sepsis in multiple trauma patients based on artificial intelligence, characterized in that, The method comprises: Obtaining monitoring data of multiple physiological indexes of multiple trauma patients with sepsis and non-sepsis at each monitoring time; According to the monitoring data distribution of each index of each multiple trauma patient at different monitoring times, the baseline deviation of each index of each multiple trauma patient at each monitoring time is obtained, and the high risk of each index of each multiple trauma patient is obtained; according to the change of the high risk of each index of different multiple trauma patients, the high sensitivity of each index of multiple trauma patients with sepsis is obtained; According to the monitoring data distribution of each index of each multiple trauma patient at different monitoring times, and the difference between adjacent monitoring times, the dynamic change rate of each index of each multiple trauma patient at each monitoring time is obtained; according to the dynamic change rate and baseline deviation of each index of different multiple trauma patients at all monitoring times, and the high sensitivity of multiple trauma patients with sepsis at each index, the sepsis prediction value of each index of each multiple trauma patient is obtained; According to the sepsis prediction value and high risk of each index of each multiple trauma patient, the sepsis risk score of each multiple trauma patient is obtained, and early warning of sepsis of multiple trauma patients is carried out; The method for obtaining the sepsis prediction value comprises: Obtaining the product mean of the dynamic change rate and the baseline deviation of each index of each multiple trauma patient at all monitoring times as the pathological disorder degree of each index of each multiple trauma patient; Obtaining the mean of the pathological disorder degree of each index of all multiple trauma patients with sepsis as the overall pathological disorder level of each index of multiple trauma patients with sepsis; According to the pathological disorder degree of each index of each multiple trauma patient, the overall pathological disorder level and the high sensitivity of each index of multiple trauma patients with sepsis, the sepsis prediction value of each index of each multiple trauma patient is obtained.

2. The method of claim 1, wherein the method is based on artificial intelligence. The method for obtaining the baseline deviation comprises: For any monitoring time, compare the monitoring data of each index of each multiple trauma patient with the standard reference range, if the monitoring data exists in the standard reference range, set the baseline deviation of each index of each multiple trauma patient to 0; If the monitoring data does not exist in the standard reference range, obtain the minimum value of the difference between the monitoring data and the different boundary data in the standard reference range, and take the boundary data corresponding to the minimum value as the reference data; calculate the ratio of the minimum value and the reference data as the baseline deviation of each index of each multiple trauma patient.

3. The method of claim 1, wherein the method is based on artificial intelligence. The method for obtaining the high risk comprises: Obtaining the difference mean of the baseline deviation of each index of each multiple trauma patient between different monitoring times and the earliest monitoring time as the high risk of each index of each multiple trauma patient.

4. The method of claim 1, wherein the method is based on artificial intelligence. The method for obtaining the high sensitivity comprises: Obtaining the cumulative sum of the high risk of each index of all multiple trauma patients with sepsis as the high risk level of sepsis; Obtaining the cumulative sum of the high risk of each index of all multiple trauma patients as the overall high risk level; Obtaining the ratio between the high risk level of sepsis and the overall high risk level as the high sensitivity of each index of multiple trauma patients with sepsis.

5. The method of claim 1, wherein the method is based on artificial intelligence. The method for obtaining the dynamic change rate comprises: The difference between the monitoring data of each index of each multiple injury patient at each monitoring time and the previous monitoring time is obtained, and the ratio between the monitoring data difference and the difference between the corresponding monitoring time is calculated as the dynamic change rate of each index of each multiple injury patient at each monitoring time.

6. The method of claim 1, wherein the method is based on artificial intelligence. The obtaining of the sepsis prediction value of each multiple injury patient at each index comprises: The ratio between the pathological disorder degree of each index of each multiple injury patient and the overall pathological disorder level of each index of the multiple injury patients with sepsis is obtained as the sepsis risk degree of each index of each multiple injury patient. The product of the sepsis risk degree of each index of each multiple injury patient and the high sensitivity of each index of the multiple injury patients with sepsis is obtained as the sepsis prediction value of each index of each multiple injury patient.

7. The method of claim 1, wherein the method is based on artificial intelligence. The obtaining method of the sepsis risk score comprises: The high risk of different indexes is weighted and averaged according to the sepsis prediction value of each multiple injury patient at different indexes to obtain the sepsis risk score of each multiple injury patient.

8. The method of claim 7, wherein the method is based on artificial intelligence. The high risk of different indexes is weighted and averaged according to the sepsis prediction value of each multiple injury patient at different indexes to obtain the sepsis risk score of each multiple injury patient, which comprises: The sepsis prediction value of each multiple injury patient at different indexes is weighted and accumulated as a first accumulated value. The accumulated value of the sepsis prediction value of each multiple injury patient at different indexes is obtained as a second accumulated value. The ratio between the first accumulated value and the second accumulated value is obtained as the sepsis risk score of each multiple injury patient.

Images