Prognosis evaluation and early intervention method for multi-injury patient

Abstract

The invention relates to the technical field of medical data mining, in particular to a prognosis evaluation and early intervention method for a multi-injury patient, and the method comprises the steps: firstly, calculating the injury condition difference and carrying out clustering analysis, carrying out the systematic processing of the multi-dimensional dynamic data of the patient, and determining the important attention field of the injury condition of the patient; secondly, evaluating an intervention scheme of each multi-injury patient in historical data by analyzing the injury condition attention degree and physiological data change after early intervention, and determining a corresponding intervention score; then, the prediction intervention score of the to-be-scored patient is comprehensively characterized by combining the deviation characteristic represented by the injury condition difference with the intervention score, so that the accuracy of the obtained prediction intervention score is higher; and under the condition that the deep learning model is not utilized, the efficiency of correspondingly obtaining the prediction intervention score is also higher.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical data mining, and particularly relates to a method for prognosis evaluation and early intervention of multiple injury patients. BACKGROUND

[0002] Multiple injury is one of the most complex and critical conditions in the field of trauma medicine, and is commonly seen in serious trauma events such as traffic accidents, high-altitude falls, and industrial injuries. Such patients usually involve injuries to multiple organ systems, with characteristics of rapid disease progression, high mortality, and short intervention window. The determination of the intervention scheme for traditional multiple injury patients relies on the experience judgment of doctors and standardized scoring systems such as ISS and TRISS. Due to the complex data dimensions of multiple injury patients that need to be judged and the non-intuitive nature of the data itself, there are problems such as long response time, insufficient individualization, and high probability of misjudgment.

[0003] Considering that deep learning models can combine multi-dimensional data for comprehensive analysis and scoring determination, the prior art usually inputs multiple injury patient data into a trained convolutional neural network model to output a predicted intervention score for each intervention scheme. However, the training of a convolutional neural network model requires a large number of data samples, resulting in generally poor efficiency. Moreover, the physiological monitoring dimension data of multiple injury patients is usually complex, and in the case of insufficient training samples, the accuracy of the convolutional neural network model in outputting the predicted intervention score cannot be guaranteed. Therefore, the accuracy and efficiency of the prior art in determining the predicted intervention score of each multiple injury patient for each intervention scheme using a convolutional neural network model are both low. SUMMARY

[0004] In order to solve the technical problem of the prior art that the accuracy and efficiency of the prior art in determining the predicted intervention score of each multiple injury patient for each intervention scheme using a convolutional neural network model are both low, the purpose of the present application is to provide a method for prognosis evaluation and early intervention of multiple injury patients, and the technical solution adopted is as follows: The first aspect of the present application provides a method for prognosis evaluation and early intervention of multiple injury patients, comprising: obtaining the part score vector of each multiple injury patient and the pre-intervention data sequence and post-intervention data sequence of each physiological monitoring dimension in the medical database; determining the injury severity difference according to the deviation of the part score vector and all pre-intervention data sequences between each multiple injury patient and every other multiple injury patient, and determining the injury severity attention degree according to the similarity of each multiple injury patient and the multiple injury patients under the same node in each physiological monitoring dimension after hierarchical clustering according to the injury severity difference; determine an intervention score of each multiple-injury patient on the corresponding intervention scheme according to the injury attention degree and the time-series data change of each physiological monitoring dimension of each multiple-injury patient in the historical data before and after the implementation of the corresponding intervention scheme; determine a predicted intervention score of the patient to be scored on each intervention scheme according to the injury difference between the patient to be scored and each multiple-injury patient in the historical data and the intervention score.

[0005] Further, the injury difference acquisition process comprises: take each multiple-injury patient as a target patient in turn, and take each multiple-injury patient other than the target patient as a contrast patient; determine the corresponding part score difference according to the Euclidean distance between the part score vector of the target patient and the part score vector of the contrast patient; determine the corresponding physiological data difference according to the sequence deviation between the pre-intervention data sequence of the target patient and the pre-intervention data sequence of the contrast patient; determine the injury difference between the target patient and the contrast patient according to the product between the positive correlation mapping value of the physiological data difference and the part score difference.

[0006] Further, the physiological data difference acquisition process comprises: under each physiological monitoring dimension, calculate the DTW distance between the pre-intervention data sequence of the target patient and the pre-intervention data sequence of the contrast patient through the dynamic time warping algorithm; and take the cumulative value of the corresponding DTW distance under all physiological monitoring dimensions as the physiological data difference between the target patient and the contrast patient.

[0007] Further, the injury attention degree acquisition process comprises: cluster all multiple-injury patients according to the injury difference through the BIRCH clustering algorithm to obtain a CF clustering tree; and take the CF tree layer where the corresponding sample of each multiple-injury patient is located as the corresponding analysis layer in the CF clustering tree; take a preset number of CF tree layers with a layer number less than and adjacent to the layer number of the analysis layer as the corresponding contrast layer; and take each multiple-injury patient and other multiple-injury patients belonging to the same node in the corresponding all contrast layers as the reference patients of each multiple-injury patient; The mean value of all data in the pre-intervention data sequence of each polytrauma patient in each physiological monitoring dimension is taken as the corresponding pre-intervention monitoring characteristic value; the pre-intervention fluctuation degree is determined according to the distribution dispersion of all pre-intervention monitoring characteristic values corresponding to each polytrauma patient and all corresponding reference patients; the pre-intervention monitoring deviation value of each polytrauma patient is determined according to the deviation of the pre-intervention monitoring characteristic value of each polytrauma patient relative to the preset standard physiological monitoring numerical range in each physiological monitoring dimension. The local attention degree of each reference patient is determined according to the product between the negative correlation mapping value of the pre-intervention fluctuation degree of each reference patient and the pre-intervention monitoring deviation value; the trauma condition attention degree of each polytrauma patient is determined according to the cumulative value of all local attention degrees corresponding to all reference patients of each polytrauma patient.

[0008] Further, the pre-intervention fluctuation degree acquisition process comprises: The pre-intervention fluctuation degree is determined according to the standard deviation of all pre-intervention monitoring characteristic values corresponding to each polytrauma patient and all corresponding reference patients in each physiological monitoring dimension.

[0009] Further, the pre-intervention monitoring deviation value acquisition process comprises: When the pre-intervention monitoring characteristic value is less than or equal to the maximum value of the preset standard physiological monitoring numerical range and greater than or equal to the minimum value of the preset standard physiological monitoring numerical range, the corresponding pre-intervention monitoring deviation value is set to 0; When the pre-intervention monitoring characteristic value is greater than the maximum value of the preset standard physiological monitoring numerical range, the difference between the pre-intervention monitoring characteristic value and the maximum value of the preset standard physiological monitoring numerical range is taken as the pre-intervention monitoring deviation value; When the pre-intervention monitoring characteristic value is less than the minimum value of the preset standard physiological monitoring numerical range, the difference between the minimum value of the preset standard physiological monitoring numerical range and the pre-intervention monitoring characteristic value is taken as the pre-intervention monitoring deviation value.

[0010] Further, the intervention score acquisition process comprises: Based on the principle of obtaining the pre-intervention monitoring deviation value from the pre-intervention data sequence, the post-intervention monitoring deviation value of each polytrauma patient is determined according to the post-intervention data sequence of each polytrauma patient in each physiological monitoring dimension; based on the principle of obtaining the pre-intervention fluctuation degree from the pre-intervention data sequence, the post-intervention fluctuation degree of each polytrauma patient is determined according to the post-intervention data sequence of each polytrauma patient in each physiological monitoring dimension; The difference between the pre-intervention fluctuation degree and the post-intervention fluctuation degree is normalized to determine the corresponding stability growth value; The difference between the pre-intervention monitoring bias value and the post-intervention monitoring bias value is normalized under each physiological monitoring dimension to determine an intervention evaluation value of each multiple trauma patient after implementation of a corresponding intervention scheme; The intervention evaluation value, the stability growth value, and the injury attention degree are combined to comprehensively determine an intervention dimension score of each multiple trauma patient under each physiological monitoring dimension; The intervention dimension scores under all physiological monitoring dimensions are accumulated to determine an intervention score of each multiple trauma patient in the historical data for a corresponding intervention scheme.

[0011] Further, the intervention dimension score acquisition process includes: The intervention dimension score of each multiple trauma patient under each physiological monitoring dimension is determined according to the product of the intervention evaluation value, the stability growth value, and the injury attention degree.

[0012] Further, the predicted intervention score acquisition process includes: Each multiple trauma patient in the historical data is taken as a historical patient, a corresponding intervention scheme of each historical patient is taken as a historical scheme, and an injury difference between the historical patient and the patient to be scored is taken as a historical difference; The historical evaluation score between the patient to be scored and the historical patient is determined by normalizing the product of the negative correlation mapping value of the historical difference and the intervention score of the historical patient for a corresponding intervention scheme. The predicted intervention score of the patient to be scored for each intervention scheme is determined according to the accumulation of all corresponding historical evaluation scores between all historical patients and the patient to be scored under each intervention scheme.

[0013] Further, the part score vector acquisition process includes: According to the medical database, the AIS score of each injury area of each multiple trauma patient is acquired by means of AIS coding; wherein the injury area includes head and neck, face, chest, abdomen, pelvic cavity, limbs, and skin. According to the head and neck, face, chest, abdomen, pelvic cavity, limbs, and skin, all injury areas of each multiple trauma patient are sequentially arranged to obtain a corresponding part score vector.

[0014] In a second aspect, the present application provides a multiple trauma patient prognosis evaluation and early intervention system, which includes: A data acquisition and preprocessing module is configured to acquire, in a medical database, a part score vector of each multiple trauma patient, and a pre-intervention data sequence and a post-intervention data sequence of each physiological monitoring dimension; The first determining module is configured to determine a difference in injury condition of each multiple-injury patient according to a bias condition corresponding to a position score vector between each multiple-injury patient and each other multiple-injury patient and all pre-intervention data sequences; and determine an injury condition attention degree according to a similarity condition in each physiological monitoring dimension between each multiple-injury patient and multiple-injury patients under the same node after hierarchical clustering is performed according to the difference in injury condition. The second determining module is configured to determine an intervention score of each multiple-injury patient on a corresponding intervention scheme according to the injury condition attention degree and a time-series data change condition of each physiological monitoring dimension of each multiple-injury patient in the historical data before and after implementation of the corresponding intervention scheme. The intervention scheme evaluation module is configured to determine a predicted intervention score of a patient to be scored on each intervention scheme according to the difference in injury condition between the patient to be scored and each multiple-injury patient in the historical data and the intervention score.

[0015] In a third aspect, a computer device is provided, including a memory and a processor. The memory is configured to store computer program code, and the processor is configured to call and run the computer program code from the memory to execute the method according to the first aspect or any embodiment of the first aspect.

[0016] In a fourth aspect, a computer program product is provided, including computer program code, which, when executed, performs the method according to the first aspect or any embodiment of the first aspect.

[0017] In a fifth aspect, a computer-readable storage medium is provided, which stores computer program code, which, when executed, performs the method according to the first aspect or any embodiment of the first aspect.

[0018] The present application has the following beneficial effects: Firstly, the present application can systematically process multiple-dimension dynamic data of a patient by calculating a difference in injury condition and performing clustering analysis, and determine a key attention field of the injury condition of the patient. Secondly, the present application can evaluate an intervention scheme of each multiple-injury patient in the historical data and determine a corresponding intervention score by analyzing an injury condition attention degree and a physiological data change after early intervention. Then, the present application can comprehensively represent a predicted intervention score of a patient to be scored by combining a bias feature represented by the difference in injury condition with the intervention score, so that the accuracy of the predicted intervention score is higher. Moreover, the present application can obtain the predicted intervention score more efficiently without using a deep learning model. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages thereof, simple introduction to the drawings needed in the embodiments or prior art description will be given below. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative effort based on these drawings.

[0020] Figure 1 A flow chart of a method for prognosis evaluation and early intervention of multiple injury patients provided by an embodiment of the present application; Figure 2 A structural diagram of a system for prognosis evaluation and early intervention of multiple injury patients provided by an embodiment of the present application; Figure 3 A structural diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined purposes, the specific embodiments, structures, features and effects of a method for prognosis evaluation and early intervention of multiple injury patients according to the present application are described in detail below in combination with the drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment, and the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form. In addition, the terms "first", "second" are only used for description purposes, and cannot be understood as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Therefore, the features with "first", "second" can be explicitly or implicitly included one or more features.

[0022] 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 the present application belongs.

[0023] The specific scheme of the method for prognosis evaluation and early intervention of multiple injury patients provided by the present application will be specifically described below in combination with the drawings.

[0024] The present application provides a method for prognosis evaluation and early intervention of multiple injury patients, please refer to Figure 1 which shows a flow chart of a method for prognosis evaluation and early intervention of multiple injury patients provided by an embodiment of the present application, the method comprises: Step S101: obtaining the position score vector of each multiple injury patient and the pre-intervention data sequence and post-intervention data sequence of each physiological monitoring dimension in the medical database.

[0025] The data of the multiple-injury patient after detection or physical examination is stored in the medical database, so the data of the multiple-injury patient is collected through the medical database.

[0026] Preferably, in some possible implementation manners of the embodiments of the present application, the obtaining process of the site score vector comprises: According to the medical database, the AIS score of each injury area of each multiple-injury patient is obtained by means of AIS coding; wherein the injury area includes head and neck, face, chest, abdomen, pelvic cavity, limbs and skin; all injury areas of each multiple-injury patient are arranged in sequence according to the head and neck, face, chest, abdomen, pelvic cavity, limbs and skin, to obtain the corresponding site score vector. It should be noted that the AIS coding is a technical means familiar to those skilled in the art, which will not be described further herein; and the arrangement order of the injury area in the site score vector can be adjusted according to the specific implementation environment, which will not be described further herein.

[0027] Then the data of each physiological monitoring dimension is collected. In one specific implementation manner of the embodiments of the present application, the physiological monitoring dimensions include heart rate, respiratory rate, intracranial pressure, systolic blood pressure, blood oxygen saturation and Glasgow coma score. In one specific implementation manner of the embodiments of the present application, the heart rate data can be collected by an electrocardiograph or a pulse oximeter; the respiratory rate data can be collected by a chest and abdominal belt sensor or an impedance method; the intracranial pressure data can be collected by an intracerebral catheter; the systolic blood pressure data can be collected by an arterial blood pressure monitoring device; the blood oxygen saturation data can be collected by a pulse oximeter; the Glasgow coma score data can be collected by a clinical evaluation method; wherein the sampling frequency of the heart rate data and the systolic blood pressure data is set to be collected once every 5 seconds; the blood oxygen saturation data and the respiratory rate data are set to be collected once every 1 minute; the intracranial pressure and the Glasgow coma score are collected once every 10 minutes; the length of the collection time period of each multiple-injury patient is set to be 1 hour, which can be adjusted according to the specific implementation environment; in addition, for the historical data, that is, each multiple-injury patient in the medical database, the data of each physiological monitoring dimension is collected once in the collection time period before and after the implementation of the corresponding intervention scheme, specifically: after arranging the data of each physiological monitoring dimension collected in the collection time period before the implementation of the intervention scheme in time sequence, the corresponding pre-intervention data sequence is obtained; after arranging the data of each physiological monitoring dimension collected in the collection time period after the implementation of the intervention scheme in time sequence, the corresponding post-intervention data sequence is obtained. It should be noted that the data analyzed in the embodiments of the present application is all data authorized by the user for use, which will not be described further.

[0028] Step S102: determining the injury difference according to the position score vector between each polytrauma patient and each other polytrauma patient and the bias corresponding to all pre-intervention data sequences; after hierarchical clustering according to the injury difference, determining the injury attention degree according to the similarity between each polytrauma patient and the polytrauma patients under the same node in each physiological monitoring dimension.

[0029] The position score vector comprehensively represents the trauma severity of each injury site of each polytrauma patient, and the pre-intervention data sequence represents the physiological monitoring dimension information reflecting the physiological state of the polytrauma patient before being processed by the intervention scheme, so for any two polytrauma patients, the higher the similarity of the corresponding two position score vectors and pre-intervention data sequences, the smaller the injury difference should be, that is, the closer the trauma performance of the two polytrauma patients.

[0030] Preferably, in some possible implementation manners of the embodiment of the present application, the injury difference acquisition process comprises: In turn, each polytrauma patient is taken as a target patient, and each polytrauma patient other than the target patient is taken as a contrast patient; by comparing and analyzing the target patient and the contrast patient, the injury difference between the two polytrauma patients can be obtained.

[0031] According to the Euclidean distance between the position score vector of the target patient and the position score vector of the contrast patient, the corresponding position score difference is determined. The greater the Euclidean distance between the two position score vectors, the greater the difference between the two position score vectors, and therefore the greater the position score difference, the greater the injury difference.

[0032] According to the sequence bias between the pre-intervention data sequence of the target patient and the pre-intervention data sequence of the contrast patient, the corresponding physiological data difference is determined; in one specific implementation manner of the embodiment of the present application, the physiological data difference acquisition process comprises: in each physiological monitoring dimension, the DTW distance between the pre-intervention data sequence of the target patient and the pre-intervention data sequence of the contrast patient is calculated by using the dynamic time warping algorithm; and the cumulative value of the corresponding DTW distance in all physiological monitoring dimensions is taken as the physiological data difference between the target patient and the contrast patient. According to the dynamic time warping algorithm, the greater the DTW distance between two sequences, the lower the sequence similarity of the two sequences; therefore, the greater the physiological data difference, the greater the corresponding injury difference. Finally, according to the positive correlation mapping value of the physiological data difference and the product between the position score difference, the injury difference between the target patient and the contrast patient is determined according to the correlation.

[0033] In one specific implementation manner of the embodiment of the present application, the injury difference acquisition process is represented by a formula as follows: ; wherein, for the target patient injury difference between the target patient and the corresponding first contrast patient; for the target patient injury difference between the target patient and the corresponding first contrast patient; is a linear normalization function; is the number of physiological monitoring dimensions; is the distance between the pre-intervention data sequence of the target patient under the first physiological monitoring dimension and the pre-intervention data sequence of the corresponding first contrast patient; is the physiological data difference between the target patient and the corresponding first contrast patient.

[0034] Since multiple injury patients have more injuries in different areas, and the attention degree of each physiological monitoring dimension data is different for different positions, the overall data performance of each multiple injury patient and each multiple injury patient similar to the target patient in physiological monitoring dimension data is analyzed in the present application, so as to avoid the deviation of the injury attention degree caused by single analysis. Therefore, further according to the physiological data difference, the clustering analysis algorithm is processed, so as to analyze the injury attention degree of the patients with similar injuries.

[0035] Preferably, in some possible implementation manners of the embodiments of the present application, the injury attention degree acquisition process comprises: ​​According to the difference between the injury conditions of all multiple injury patients, clustering is performed by a BIRCH clustering algorithm to obtain a CF clustering tree; in the CF clustering tree, a CF tree layer in which a sample corresponding to each multiple injury patient is located is taken as a corresponding analysis layer; a preset number of CF tree layers whose layer numbers are less than the layer number of the analysis layer and are adjacent to the layer number of the analysis layer are taken as corresponding comparison layers; each multiple injury patient and other multiple injury patients belonging to the same node in all corresponding comparison layers are taken as reference patients of each multiple injury patient. In a specific implementation manner of the embodiment of the present application, the preset number is set to 3, which can be adjusted according to a specific implementation environment. For example, the CF tree layer in which a sample corresponding to a certain multiple injury patient is located is the 5th layer, the analysis layer is the 5th layer, and the comparison layers are the 4th layer, the 3rd layer and the 2nd layer. The greater the difference between the layer number of the comparison layer and the layer number of the analysis layer, the greater the difference between the corresponding multiple injury patients, and therefore the present application selects the preset number as 3, so that each multiple injury patient and the corresponding reference patient present similar injury condition characteristics, thereby analyzing the injury condition characteristics of all reference patients as a whole to comprehensively analyze the injury condition attention degree of the corresponding multiple injury patient.

[0036] The mean value of all data in the data sequence before intervention of each multiple injury patient in each physiological monitoring dimension is taken as a corresponding monitoring feature value before intervention; the fluctuation degree before intervention is determined according to the distribution dispersion of all monitoring feature values before intervention corresponding to each multiple injury patient and all corresponding reference patients; preferably, in some possible implementation manners of the embodiment of the present application, the process of obtaining the fluctuation degree before intervention includes: under each physiological monitoring dimension, the fluctuation degree before intervention is determined according to the standard deviation of all monitoring feature values before intervention corresponding to each multiple injury patient and all corresponding reference patients. For all reference patients, the greater the standard deviation of all monitoring feature values before intervention corresponding to all reference patients, the more dispersed the distribution of the monitoring feature values before intervention, and the lower the reliability of the deviation degree; and the data of different physiological monitoring dimensions is normalized by the standard deviation, the dimension is eliminated to standardize the data, and the robustness of the obtained injury condition attention degree is higher.

[0037] Under each physiological monitoring dimension, the monitoring deviation value before intervention of each multiple injury patient is determined according to the deviation of the monitoring feature value before intervention of each multiple injury patient relative to a preset standard physiological monitoring numerical range. Preferably, in a specific implementation manner of the embodiment of the present application, the process of obtaining the monitoring deviation value before intervention includes: When the pre-intervention monitoring characteristic value is less than or equal to the maximum value of the preset standard physiological monitoring value range and greater than or equal to the minimum value of the preset standard physiological monitoring value range, the corresponding pre-intervention monitoring deviation value is set to 0; when the pre-intervention monitoring characteristic value is greater than the maximum value of the preset standard physiological monitoring value range, the difference between the pre-intervention monitoring characteristic value and the maximum value of the preset standard physiological monitoring value range is taken as the pre-intervention monitoring deviation value; when the pre-intervention monitoring characteristic value is less than the minimum value of the preset standard physiological monitoring value range, the difference between the minimum value of the preset standard physiological monitoring value range and the pre-intervention monitoring characteristic value is taken as the pre-intervention monitoring deviation value. That is, for each polytrauma patient, the greater the deviation of the corresponding physiological monitoring dimension data from the standard range, the greater the corresponding pre-intervention monitoring deviation value, that is, the greater the deviation from the normal condition, and then the greater the based injury condition attention degree should be.

[0038] The local attention degree of each reference patient is determined according to the product of the negative correlation mapping value of the pre-intervention fluctuation degree of each reference patient and the pre-intervention monitoring deviation value, and the injury condition attention degree of each polytrauma patient is determined according to the cumulative value of all local attention degrees corresponding to all reference patients of each polytrauma patient. In one specific implementation manner of the embodiment of the present application, the acquisition process of the injury condition attention degree is expressed by a formula as follows: ; wherein, is the injury condition attention degree of the i th polytrauma patient under the j th physiological monitoring dimension; is the total number of all reference patients corresponding to the i th polytrauma patient; is the pre-intervention monitoring deviation value of the i th polytrauma patient corresponding to the j th reference patient under the j th physiological monitoring dimension; is the pre-intervention fluctuation degree of the i th polytrauma patient under the j th physiological monitoring dimension; is the pre-intervention monitoring deviation value of the i th polytrauma patient corresponding to the j th reference patient under the j th physiological monitoring dimension; is the pre-intervention fluctuation degree of the i th polytrauma patient under the j th physiological monitoring dimension; is the pre-intervention fluctuation degree of the i th polytrauma patient under the j th physiological monitoring dimension; is the pre-intervention fluctuation degree of the i th polytrauma patient under the j th physiological monitoring dimension; is the pre-intervention fluctuation degree of the i th polytrauma patient under the j th physiological monitoring dimension; is the pre-intervention fluctuation degree of the i th polytrauma patient under the j th physiological monitoring dimension; is the pre-intervention fluctuation degree of the i th polytrauma patient under the j th physiological monitoring dimension; is the pre-intervention fluctuation degree of the i th polytrauma patient under the j th physiological monitoring dimension;

[0039] It should be noted that the preset standard physiological monitoring value range of each physiological monitoring dimension can be obtained according to the normal range value of the corresponding physiological monitoring dimension. In a specific implementation manner of the embodiment of the present application, the preset standard physiological monitoring value range of heart rate is set to 60-100 times per minute; the preset standard physiological monitoring value range of respiratory rate is set to 12-20 times per minute; the preset standard physiological monitoring value range of intracranial pressure is set to 5-15 mmHg; the preset standard physiological monitoring value range of systolic pressure is set to 90-120 mmHg; the preset standard physiological monitoring value range of blood oxygen saturation is set to 95%-100%; and the GCS score is set to 10-15 points. The specific implementation environment can be adjusted by itself, and no further description is made herein. The injury condition attention degree is obtained by analyzing the deviation characteristics of the physiological monitoring dimension data of each multiple injury patient corresponding to the reference patient with similar characteristics relative to the standard data value range. Compared with the method of analyzing the standard deviation characteristics of the physiological monitoring data of each multiple injury patient, the influence of accidental factors can be greatly avoided, and the obtained injury condition attention degree is more accurate.

[0040] Step S103: determining an intervention score of each multiple injury patient on the corresponding intervention scheme according to the injury condition attention degree and the time sequence data change of each physiological monitoring dimension of each multiple injury patient in the historical data before and after the implementation of the corresponding intervention scheme.

[0041] For each multiple injury patient in the historical data, the more normal the physiological monitoring dimension data after the implementation of the corresponding intervention scheme is, the better the intervention effect of the corresponding intervention scheme is. Therefore, the score of the corresponding intervention scheme is further determined based on the change of the physiological monitoring dimension data of each multiple injury patient in the historical data before and after the implementation of the intervention scheme.

[0042] Preferably, in some possible implementation manners of the embodiment of the present application, the intervention score acquisition process comprises: Based on the principle of obtaining the pre-intervention monitoring deviation value according to the pre-intervention data sequence, the post-intervention monitoring deviation value of each multiple injury patient is determined according to the post-intervention data sequence of each physiological monitoring dimension of each multiple injury patient. Based on the principle of obtaining the pre-intervention fluctuation degree according to the pre-intervention data sequence, the post-intervention fluctuation degree of each multiple injury patient is determined according to the post-intervention data sequence of each physiological monitoring dimension of each multiple injury patient. That is, after the pre-intervention data sequence in the pre-intervention monitoring deviation value and pre-intervention fluctuation degree acquisition process is replaced by the post-intervention data sequence, the post-intervention monitoring deviation value and post-intervention fluctuation degree of each multiple injury patient are determined by the same calculation method, and the specific calculation process is not described further herein.

[0043] The difference between the fluctuation degree before the intervention and the fluctuation degree after the intervention is normalized to determine the corresponding stability growth value. First, the data of each physiological monitoring dimension under the normal body state is usually stable, and trauma can cause the data to present a higher fluctuation, so the greater the difference between the fluctuation degree before the intervention and the fluctuation degree after the intervention, the more stable the intervention after the intervention is, and the better the stability effect of the intervention is. Therefore, the greater the stability growth value is, the greater the intervention score should be.

[0044] Under each physiological monitoring dimension, the difference between the monitoring deviation value before the intervention and the monitoring deviation value after the intervention is normalized to determine the intervention evaluation value of each multiple trauma patient after the implementation of the corresponding intervention scheme. Similarly, the monitoring deviation value before the intervention under the normal body state is usually 0, and the closer to 0, the more likely the body state is normal. Therefore, the greater the difference between the monitoring deviation value before the intervention and the monitoring deviation value after the intervention, the more normal the body of the multiple trauma patient after the intervention is, and the better the intervention effect is. Therefore, the greater the intervention evaluation value is, the greater the intervention score should be.

[0045] The injury attention degree is the attention degree of each multiple trauma patient to each physiological monitoring dimension, and the greater the injury attention degree is, the more the corresponding physiological monitoring dimension needs to be paid attention to. Therefore, the weight in scoring the corresponding physiological monitoring dimension should be greater. Further, the intervention dimension score of each multiple trauma patient under each physiological monitoring dimension is determined by combining the intervention evaluation value, the stability growth value and the injury attention degree. The intervention dimension score is obtained by multiplying the intervention evaluation value, the stability growth value and the injury attention degree. Further, the intervention score of each multiple trauma patient on the corresponding intervention scheme in the historical data is determined according to the cumulative value of the intervention dimension scores of all physiological monitoring dimensions. The intervention effect of each multiple trauma patient after the implementation of the corresponding intervention scheme is evaluated by combining all physiological monitoring dimensions, so that the intervention score obtained is more comprehensive to represent the intervention effect.

[0046] In one specific implementation of the embodiment of the present application, the intervention score is obtained by the formula: ; wherein, is the intervention score of the i th multiple trauma patient on the corresponding intervention scheme; is the number of physiological monitoring dimensions; is the monitoring deviation value before the intervention of the i th multiple trauma patient under the j th physiological monitoring dimension; is the monitoring deviation value after the intervention of the i th multiple trauma patient under the j th physiological monitoring dimension. ​​​​​ the first physiological monitoring dimension for the first multiple-injury patient; the first physiological monitoring dimension for the first multiple-injury patient; the first physiological monitoring dimension for the first multiple-injury patient; the first physiological monitoring dimension for the first multiple-injury patient; the first physiological monitoring dimension for the first multiple-injury patient; the first physiological monitoring dimension for the first multiple-injury patient; the first physiological monitoring dimension for the first multiple-injury patient; the first physiological monitoring dimension for the first multiple-injury patient; the first physiological monitoring dimension for the first multiple-injury patient; is a linear normalization function; through normalization processing, the intervention evaluation value and the stability increment value cannot be negative, avoiding affecting the calculation.

[0047] Step S104: determining the predicted intervention score of the patient to be scored on each intervention scheme according to the injury difference between the patient to be scored and each multiple-injury patient in the historical data and the intervention score.

[0048] The patient to be scored is a multiple-injury patient who has not been intervened by an intervention scheme, so for the patient to be scored, the predicted intervention score of each intervention scheme needs to be determined; for the patient to be scored, it only has the pre-intervention data sequence of each physiological monitoring dimension, so the injury difference between the patient to be scored and each multiple-injury patient in the historical data can be calculated; the smaller the injury difference is, the closer the trauma performance between the patient to be scored and the corresponding multiple-injury patient is, and the more reference the intervention result of the corresponding multiple-injury patient, that is, the intervention score, has to the patient to be scored; therefore, according to this feature, the injury difference between the patient to be scored and each multiple-injury patient is used as the weight to weight the corresponding intervention score, and then the overall size of the weighted intervention score of each intervention scheme is combined to determine the more accurate predicted intervention score of the patient to be scored on each intervention scheme.

[0049] Preferably, in some possible implementation manners of the embodiment of the present application, the acquisition process of the predicted intervention score comprises: each multiple-injury patient in the historical data is regarded as a historical patient; the intervention scheme corresponding to each historical patient is regarded as a historical scheme; the injury difference between the patient to be scored and the historical patient is regarded as a historical difference; the product of the negative correlation mapping value of the historical difference and the intervention score of the historical patient on the corresponding intervention scheme is normalized to determine the historical evaluation score between the patient to be scored and the historical patient; Because the smaller the difference in injury conditions, the more referenceable the intervention score of the corresponding historical patient under the corresponding historical plan, the intervention score of the historical patient on the corresponding intervention plan is weighted with the value after negative correlation mapping of the historical difference, so as to obtain a more referenceable historical evaluation score of the patient to be scored on the intervention plan of the corresponding historical patient; and the types of intervention plans are limited, so each intervention plan usually corresponds to multiple historical patients, so in order to further analyze the predicted intervention score of the patient to be scored on each intervention plan, after traversing and calculating the historical evaluation score between the patient to be scored and each historical patient, the predicted intervention score of the patient to be scored on each intervention plan is determined according to the cumulative value of all historical evaluation scores corresponding to all historical patients under each intervention plan and the patient to be scored, so that the obtained predicted intervention score is more accurate.

[0050] In a specific implementation of the embodiment of the present invention, the process of obtaining the predicted intervention score includes: ;in, Patients to be scored In the Predicted intervention scores on the intervention options; For the historical data The number of polytrauma patients under each intervention plan; Patients to be scored Compared with historical data Under this intervention program The differences in injury severity among multiple trauma patients; It is the Softmax normalization function. Normalization by the Softmax normalization function can make the sum of all normalized values ​​1. Therefore, after negative correlation mapping and weighting, the values ​​are integrated by accumulation to obtain a more accurate prediction of the intervention score. For the historical data Under the intervention program Intervention score for polytrauma patients.

[0051] Further, based on the process of obtaining the predicted intervention score, the predicted intervention score of each patient to be scored for each intervention plan is determined, so as to quantify the evaluation of the intervention plan; in a specific implementation method of an embodiment of the present invention, all types of intervention plans are arranged in descending order according to the predicted intervention score corresponding to each patient to be scored and then stored in a medical database, so as to more intuitively assist in the selection of intervention plans.

[0052] In summary, a method for prognosis evaluation and early intervention of multiple injury patients first calculates injury difference and performs cluster analysis, can systematically process multi-dimensional dynamic data of patients, and determines the key attention field of the injury of the patient. Secondly, by analyzing the injury attention degree and the physiological data change after early intervention, the intervention scheme of each multiple injury patient in the historical data is evaluated, and the corresponding intervention score is determined. Then, by combining the deviation characteristics represented by the injury difference and the intervention score, the predicted intervention score of the patient to be scored is comprehensively represented, so that the accuracy of the obtained predicted intervention score is higher; and without using a deep learning model, the efficiency of obtaining the predicted intervention score is also higher.

[0053] The application also provides a system for prognosis evaluation and early intervention of multiple injury patients, please refer to Figure 2 which shows a structure diagram of a system for prognosis evaluation and early intervention of multiple injury patients provided by an embodiment of the application, and the system comprises a data acquisition and preprocessing module 201, a first determination module 202, a second determination module 203 and an intervention scheme evaluation module 204.

[0054] The data acquisition and preprocessing module 201 is used for acquiring the part score vector of each multiple injury patient and the pre-intervention data sequence and post-intervention data sequence of each physiological monitoring dimension in the medical database; The first determination module 202 is used for determining the corresponding injury difference according to the deviation corresponding to the part score vector and all pre-intervention data sequences between each multiple injury patient and other multiple injury patients; after hierarchical clustering according to the injury difference, the corresponding injury attention degree is determined according to the similarity of each multiple injury patient and the multiple injury patients under the same node in each physiological monitoring dimension; The second determination module 203 is used for determining the intervention score of each multiple injury patient on the corresponding intervention scheme according to the injury attention degree and the time series data change of each physiological monitoring dimension of each multiple injury patient in the historical data before and after the implementation of the corresponding intervention scheme; The intervention scheme evaluation module 204 is used for determining the predicted intervention score of the patient to be scored on each intervention scheme according to the injury difference and the intervention score between the patient to be scored and each multiple injury patient in the historical data.

[0055] It should be noted that the system provided by the above embodiment is only used as an example for the division of the above functional modules, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the system for prognosis evaluation and early intervention of multiple injury patients and the method for prognosis evaluation and early intervention of multiple injury patients provided by the above embodiment belong to the same concept, and the specific implementation process is described in the method embodiment, which will not be repeated here.

[0056] The embodiment of the present application further provides a computer device, please refer to Figure 3 which shows a computer device structure schematic diagram provided by an embodiment of the present application, the computer device includes memory 301, processor 302 and computer program 303 stored in the memory 301 and running on the processor 302, wherein the processor 302 executes the computer program 303, so that the computer device can execute any one of the above-mentioned methods for prognosis evaluation and early intervention of multiple injury patients.

[0057] The embodiment of the present application further provides a computer program product, when the computer program product runs on the computer device, so that the computer device can execute any one of the above-mentioned methods for prognosis evaluation and early intervention of multiple injury patients.

[0058] The embodiment of the present application further provides a computer readable storage medium, the computer readable storage medium stores computer program code, when the computer program code runs on the computer device, so that the computer device can execute any one of the above-mentioned methods for prognosis evaluation and early intervention of multiple injury patients.

[0059] In the embodiments provided in the present application, it should be understood that the computer device, computer program product and computer readable storage medium provided are all used to execute the corresponding method provided above, so the beneficial effects that can be achieved are referred to the beneficial effects of the method provided above, which will not be repeated here.

[0060] It should be noted that the above-mentioned embodiment of the present application is only for description, and does not represent the advantages and disadvantages of the embodiment. The processes described in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0061] Each embodiment in the specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other, and each embodiment mainly describes the difference from other embodiments.

Claims

1. A method for prognosis assessment and early intervention of patients with multiple injuries, characterized in that: The method comprises: Obtain the site score vector of each polytrauma patient and the pre-intervention data series and post-intervention data series of each physiological monitoring dimension in the medical database; Determine the corresponding injury difference based on the deviation between the site score vector and all pre-intervention data sequences of each polytrauma patient and each other polytrauma patient; after performing hierarchical clustering based on the injury difference, determine the corresponding injury concern level based on the similarity between each polytrauma patient and polytrauma patients under the same node in each physiological monitoring dimension; Determine the intervention score of each polytrauma patient on the corresponding intervention plan based on the injury concern level and the changes in the time series data of each physiological monitoring dimension of each polytrauma patient before and after the implementation of the corresponding intervention plan in the historical data; According to the difference in injury conditions between the patient to be scored and each polytrauma patient in historical data and the intervention score, a predicted intervention score for the patient to be scored in each intervention plan is determined.

2. A method for prognosis assessment and early intervention of patients with multiple injuries according to claim 1, characterized in that: The process of obtaining the injury difference includes: Each polytrauma patient was sequentially considered as a target patient, and each polytrauma patient other than the target patient was considered as a comparison patient; determining a corresponding site score difference according to a Euclidean distance between the site score vector of the target patient and the site score vector of the comparison patient; Determining corresponding physiological data differences based on sequence deviations between the target patient's pre-intervention data sequence and the comparison patient's pre-intervention data sequence; The injury difference between the target patient and the comparison patient is determined according to the product of the positive correlation mapping value of the physiological data difference and the site score difference.

3. A method for prognosis assessment and early intervention of patients with multiple injuries according to claim 2, characterized in that: The process of obtaining the physiological data difference includes: In each physiological monitoring dimension, the DTW distance between the pre-intervention data sequence of the target patient and the pre-intervention data sequence of the comparison patient is calculated by the dynamic time warping algorithm; the cumulative value of the corresponding DTW distances in all physiological monitoring dimensions is used as the physiological data difference between the target patient and the comparison patient.

4. A method for prognosis assessment and early intervention of patients with multiple injuries according to claim 1, characterized in that: The process of obtaining the injury concern level includes: Clustering is performed using the BIRCH clustering algorithm based on the injury differences among all polytrauma patients to obtain a CF clustering tree; in the CF clustering tree, the CF tree layer where the sample corresponding to each polytrauma patient is located is used as the corresponding analysis layer; A preset number of CF tree layers whose number of layers is smaller than that of the analysis layer and adjacent to the analysis layer are used as corresponding comparison layers; each polytrauma patient and other polytrauma patients belonging to the same node in all corresponding comparison layers are used as reference patients for each polytrauma patient; The mean of all data in the pre-intervention data series of each polytrauma patient in each physiological monitoring dimension was used as the corresponding pre-intervention monitoring characteristic value; the pre-intervention fluctuation degree was determined based on the distribution dispersion of all pre-intervention monitoring characteristic values ​​corresponding to each polytrauma patient and all corresponding reference patients; in each physiological monitoring dimension, the pre-intervention monitoring deviation value of each polytrauma patient was determined based on the deviation of the pre-intervention monitoring characteristic value of each polytrauma patient relative to the preset standard physiological monitoring value range; The local attention level of each reference patient is determined based on the product of the negative correlation mapping value of the pre-intervention fluctuation level of each reference patient and the pre-intervention monitoring deviation value; the injury attention level of each multiple injury patient is determined based on the cumulative value of all local attention levels corresponding to all reference patients of each multiple injury patient.

5. A method for prognosis assessment and early intervention of patients with multiple injuries according to claim 4, characterized in that: The process of obtaining the volatility before intervention includes: Under each physiological monitoring dimension, the degree of pre-intervention fluctuation was determined based on the standard deviation of all pre-intervention monitoring characteristic values ​​for each polytrauma patient and all corresponding reference patients.

6. A method for prognosis assessment and early intervention of patients with multiple injuries according to claim 4, characterized in that: The process of obtaining the monitoring deviation value before intervention includes: When the pre-intervention monitoring characteristic value is less than or equal to the maximum value of the preset standard physiological monitoring value range and greater than or equal to the minimum value of the preset standard physiological monitoring value range, the corresponding pre-intervention monitoring deviation value is set to 0; When the pre-intervention monitoring characteristic value is greater than the maximum value of the preset standard physiological monitoring value range, the difference between the pre-intervention monitoring characteristic value and the maximum value of the preset standard physiological monitoring value range is used as the pre-intervention monitoring deviation value; When the pre-intervention monitoring characteristic value is less than the minimum value of the preset standard physiological monitoring value range, the difference between the minimum value of the preset standard physiological monitoring value range and the pre-intervention monitoring characteristic value is used as the pre-intervention monitoring deviation value.

7. A method for prognosis assessment and early intervention of patients with multiple injuries according to claim 4, characterized in that: The process of obtaining the intervention score includes: Based on the principle of obtaining the pre-intervention monitoring deviation value based on the pre-intervention data sequence, the post-intervention monitoring deviation value of each polytrauma patient is determined according to the post-intervention data sequence of each polytrauma patient in each physiological monitoring dimension; based on the principle of obtaining the pre-intervention fluctuation degree based on the pre-intervention data sequence, the post-intervention fluctuation degree of each polytrauma patient is determined according to the post-intervention data sequence of each polytrauma patient in each physiological monitoring dimension; Normalizing the difference between the degree of fluctuation before the intervention and the degree of fluctuation after the intervention to determine a corresponding stability growth value; Under each physiological monitoring dimension, the difference between the monitoring deviation value before intervention and the monitoring deviation value after intervention is normalized to determine the intervention evaluation value of each polytrauma patient after the corresponding intervention plan is implemented; Combining the intervention evaluation value, the stability growth value, and the injury concern level, comprehensively determining an intervention dimension score for each polytrauma patient under each physiological monitoring dimension; According to the cumulative value of the intervention dimension scores under all physiological monitoring dimensions, the intervention score of each polytrauma patient in the historical data on the corresponding intervention plan is determined.

8. A method for prognosis assessment and early intervention of patients with multiple injuries according to claim 7, characterized in that: The process of obtaining the intervention dimension score includes: An intervention dimension score for each polytrauma patient in each physiological monitoring dimension is determined according to the product of the intervention evaluation value, the stability growth value, and the injury concern level.

9. The method for prognosis assessment and early intervention of patients with multiple injuries according to claim 1, characterized in that: The process of obtaining the predicted intervention score includes: Each polytrauma patient in the historical data is regarded as a historical patient; the intervention plan corresponding to each historical patient is regarded as a historical plan; and the difference in injury between the patient to be scored and the historical patient is regarded as the historical difference; Normalizing the product of the negative correlation mapping value of the historical difference and the intervention score of the historical patient on the corresponding intervention plan to determine a historical evaluation score between the patient to be scored and the historical patient; The predicted intervention score of the patient to be scored under each intervention scheme is determined based on the accumulated value of all corresponding historical evaluation scores between all historical patients under each intervention scheme and the patient to be scored.

10. The method for prognosis assessment and early intervention of patients with multiple injuries according to claim 1, characterized in that: The process of obtaining the part score vector includes: The AIS score for each injured area of ​​each polytrauma patient was obtained using AIS coding based on the medical database; the injured areas included the head and neck, face, chest, abdomen, pelvis, limbs, and skin. According to the head and neck, face, chest, abdomen, pelvis, limbs and skin, all the injured areas of each polytrauma patient were arranged in sequence to obtain the corresponding location score vector.

Images