Perioperative patient anesthesia risk assessment method and system based on past medical history

Abstract

The invention relates to the technical field of medical risk assessment, in particular to a perioperative patient anesthesia risk assessment method and system based on past medical history, and the method comprises the steps: obtaining a judgment matrix of past medical history information data of a to-be-assessed patient and a plurality of similar patients for anesthesia risk assessment importance; determining a past medical history difference value between any two patients; obtaining a reference set of to-be-evaluated patients, and determining a reference difference value of weight adjustment between each patient in the reference set and the to-be-evaluated patient; determining a weight adjustment influence value between the to-be-evaluated patient and each patient in the reference set of the to-be-evaluated patient; determining a fusion adjustment weight of each patient in the reference set for element adjustment in the judgment matrix of the to-be-evaluated patient; and adjusting each element in the judgment matrix of the to-be-assessed patient, and obtaining an anesthesia risk assessment result of the to-be-assessed patient based on the adjusted judgment matrix. The invention aims to improve the accuracy of anesthesia risk assessment of patients in the perioperative period.

Description

Technical Field

[0001] The present application relates to the technical field of medical risk assessment, and specifically to a method and system for perioperative patient anesthesia risk assessment based on previous medical history. Background Art

[0002] In the contemporary medical field, with the continuous advancement of medical technology, the number of surgeries in hospitals has shown a significant growth trend. In current clinical practice, comprehensive and detailed risk assessment of patients before surgery has become a key measure to ensure anesthesia safety. By systematically assessing the patient's condition, potential disease complications and anesthesia risks can be identified in advance, and targeted preventive measures can be taken during the perioperative period to effectively avoid or reduce the probability of risk events.

[0003] In recent years, with the popularization of anesthesia management systems, the application of artificial intelligence technology in perioperative anesthesia risk assessment has continued to expand. Machine learning technology is used to process complex clinical medical data, and intelligently assist doctors in making accurate judgments on anesthesia risks in the perioperative period. However, the existing methods allocate weights for past medical history information when evaluating anesthesia risks. This is based on the similarity of the patient's past medical history information, and cannot avoid the impact of differences in the judgment of the importance of past medical history information between similar patients on the risk assessment weight, resulting in lower accuracy in anesthesia risk assessment. Summary of the invention

[0004] In view of the above, it is necessary to provide an anesthesia risk assessment method and system for perioperative patients based on past medical history. Compared with the traditional anesthesia risk assessment method for perioperative patients, the accuracy of anesthesia risk assessment for perioperative patients is improved: In a first aspect, an embodiment of the present application provides a method for assessing anesthesia risk of a perioperative patient based on past medical history, the method comprising the following steps: Obtain the medical history information data of the patient to be evaluated and multiple similar patients, and obtain a judgment matrix of the importance of each patient's medical history information data to anesthesia risk assessment; Based on the difference in the past medical history information data between any two patients and the difference between the consistency ratios of the judgment matrices of the any two patients, determining the past medical history difference value between the any two patients; Based on the difference values ​​of the medical histories between any two patients, a reference set of patients to be evaluated is obtained; Based on the difference of the judgment matrix between the patient to be evaluated and each patient in the reference set, determining a reference difference value for weight adjustment between each patient in the reference set and the patient to be evaluated; Determine a weight-adjusted impact value between the patient to be evaluated and each patient in the reference set based on the previous medical history difference value between the patient to be evaluated and each patient in the reference set and the reference difference value; Determining, based on the distribution of the weight adjustment influence values, a fusion adjustment weight of each patient in the reference set for adjusting the elements in the judgment matrix of the patient to be evaluated; Based on the fusion adjustment weight, combined with the judgment matrix of each patient in the reference set, each element in the judgment matrix of the patient to be evaluated is adjusted, and a neural network is used to obtain an anesthesia risk assessment result of the patient to be evaluated based on the adjusted judgment matrix; The specific process of obtaining the difference value of the past medical history is as follows: The medical history information of each patient is encoded using character encoding technology to obtain character sequences; Calculate the distance between the character sequences of any two patients; Calculating the absolute value of the difference between the consistency ratios of the judgment matrices of any two patients; The past medical history difference value is the product of the distance and the absolute value of the difference.

[0005] In one embodiment, the medical history information data includes age, gender, basic physical index information, history of vascular diseases, history of respiratory diseases, history of endocrine diseases and history of nervous system diseases, wherein the basic physical index information includes heart rate, blood pressure, body temperature and weight.

[0006] In one embodiment, the reference set is obtained by: All patients were classified based on the difference in medical history between any two patients; All patients in the class to which the patient to be evaluated belongs, except the patient to be evaluated, constitute a reference set of patients to be evaluated.

[0007] In one embodiment, the process of determining the reference difference value is as follows: For any patient in the reference set of patients to be evaluated, calculate the absolute value of the difference between the elements at the same position of the judgment matrix of any patient and the judgment matrix of the patient to be evaluated, and record it as the element difference; The sum of all the element differences corresponding to each patient in the reference set is used as a reference difference value for weight adjustment between each patient in the reference set and the patient to be evaluated.

[0008] In one embodiment, the expression of the weight adjustment impact value is: ; in, represents the weight-adjusted impact value between the i-th and j-th patients; represents the weight-adjusted reference difference value between the i-th and j-th patients; represents the difference in medical history between the i-th and j-th patients; Represents an exponential function with a natural constant as base.

[0009] In one embodiment, the process of determining the fusion adjustment weight is as follows: Calculating the cumulative value of the weight-adjusted impact values ​​corresponding to all patients in the reference set; The fusion adjustment weight is the ratio of the weight adjustment influence value corresponding to each patient in the reference set to the accumulated value.

[0010] In one embodiment, the weight is adjusted based on the fusion, combined with the judgment matrix of each patient in the reference set, to adjust each element in the judgment matrix of the patient to be evaluated. The specific acquisition method is: ; in, represents the first The adjusted value of the elements; Indicates the first In the judgment matrix of each patient elements; Indicates the first The fusion adjustment weight of each patient for the elements in the judgment matrix of the patient to be evaluated; m represents the total number of patients in the reference set.

[0011] In a second aspect, an embodiment of the present application also provides a perioperative patient anesthesia risk assessment system based on past medical history, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the steps of any one of the above-mentioned methods for perioperative patient anesthesia risk assessment based on past medical history are implemented.

[0012] This application has at least the following beneficial effects: The present application aims at the problem that the existing method determines the risk assessment weight by the difference of medical history information, but there are differences in the judgment of the importance of medical history information of different patients for anesthesia risk assessment, which will affect the accuracy of anesthesia risk assessment; obtain a judgment matrix of the importance of medical history information data of each patient for anesthesia risk assessment; determine the medical history difference value according to the difference of medical history information data between different patients and the difference of the judgment matrix, and classify all patients based on the medical history difference value; comprehensively consider the similarity of medical history information between different patients and the similarity of the importance characteristics of medical history information between different patients in anesthesia assessment, and accurately obtain the reference set for weight allocation in anesthesia risk assessment of patients to be evaluated; further, based on the difference between the influence of each patient in the reference set on the patient to be evaluated in anesthesia risk assessment, adjust the judgment matrix of the patient to be evaluated, and then obtain the anesthesia risk assessment result according to the adjusted judgment matrix, which can improve the accuracy of anesthesia risk assessment for perioperative patients, and combine the difference of medical history importance characteristics to avoid the problem of deviation in anesthesia risk assessment results caused by the weight allocation in anesthesia risk assessment based only on the similarity of medical history information. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0014] Figure 1 A flowchart of the steps of a method for assessing anesthesia risk of perioperative patients based on past medical history provided in one embodiment of the present application; Figure 2 It is a schematic diagram of the process of determining the difference value of past medical history; Figure 3 Schematic diagram of the process of obtaining weights for fusion adjustment. DETAILED DESCRIPTION

[0015] In the description of the embodiments of the present application, words such as "exemplary", "or", "for example" and the like are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "or", "for example" and the like is intended to present related concepts in a concrete manner.

[0016] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the present application. The terms used in the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. It should be understood that, unless otherwise specified, " / " means or.

[0017] It should also be noted that the terms "first" and "second" in the present application are used to distinguish similar objects rather than to describe a specific order or sequence.

[0018] The specific scheme of the method and system for perioperative patient anesthesia risk assessment based on previous medical history provided by the present application is described in detail below with reference to the accompanying drawings.

[0019] See also Figure 1 , which shows a flowchart of a method for assessing anesthesia risk of perioperative patients based on past medical history provided by an embodiment of the present application, the method comprising the following steps: Step 1: Obtain the medical history information data of the patient to be evaluated and multiple similar patients, and obtain a judgment matrix of the importance of the medical history information data of each patient to the anesthesia risk assessment.

[0020] Obtain the medical history information data of the patient to be evaluated and similar patients in the hospital information management system, wherein the medical history information data includes age, gender, basic physical index information, history of vascular diseases, history of respiratory diseases, history of endocrine diseases and history of nervous system diseases, wherein the basic physical index information includes heart rate, blood pressure, body temperature and weight. When the patient to be evaluated needs anesthesia due to any disease, the patient who also needs anesthesia due to any of the diseases is regarded as a similar patient to the patient to be evaluated.

[0021] In this embodiment, the number of patients of the same type is α, and the value of α is preset manually and can be set by the implementer. In this embodiment, the value of α is 300.

[0022] Normally, the anesthesia risk assessment of the patient to be evaluated needs to be evaluated and analyzed based on the patient's medical history, and the anesthesia risk of the patient to be evaluated is evaluated and analyzed based on the results of previous anesthesia risk assessments of similar patients. In this case, the evaluation focuses on the similarity of the medical history information between patients, that is, the closer the medical history information is, the more conducive it is to the anesthesia risk assessment of the patient to be evaluated. However, in the actual evaluation process, even if the medical history of patients of the same type is similar, when conducting risk assessment, there are still differences in the importance of the medical history information of different patients to the assessment of the current perioperative anesthesia risk. Therefore, when conducting anesthesia risk assessment based on the medical history information of patients of the same type and the medical history information of the patient to be evaluated, the weight of the assessment should be allocated based on the differences in the importance of anesthesia risk assessment between patients of the same type, so as to obtain accurate anesthesia risk assessment results.

[0023] Therefore, in order to further accurately analyze the difference in importance judgment of the medical history information between the patient to be evaluated and other similar patients, the hierarchical analysis method is used to obtain the judgment matrix of the importance of the medical history information data of each patient for the anesthesia risk assessment. Among them, the hierarchical analysis method is a technology well known to those skilled in the art and will not be described in detail in this application.

[0024] Step 2: Classify the patients by comparing the similarity of medical history information between different patients and the similarity of the importance characteristics of medical history information in anesthesia risk assessment, and adjust the weight distribution of medical history information in anesthesia risk assessment according to the classification results.

[0025] Based on the analysis in step 1, when conducting anesthesia risk assessment for the patient to be assessed, in addition to assessing the perioperative anesthesia risk based on the patient's medical history information, it is also necessary to combine the medical history information of similar patients to make a comprehensive judgment on the anesthesia risk of the patient to be assessed. Usually, the anesthesia risk assessment results of similar patients are compared only by the similarity of medical history information between similar patients, without considering the differences in the importance of anesthesia risk assessment for different patients, which may lead to deviations in the anesthesia risk assessment of the patient to be assessed.

[0026] Step 2.1, based on the difference in medical history information data between any two patients and the difference between the consistency ratios of the judgment matrices of the any two patients, determine the difference value of the medical history between the any two patients.

[0027] Based on the above analysis, this application considers combining the importance characteristics of the medical history information of similar patients in anesthesia risk assessment, and divides the importance of the medical history information of the patient to be assessed in anesthesia risk assessment. Specifically, the greater the difference in the importance judgment of different patients' medical history information to anesthesia risk, and the smaller the difference in medical history information between different patients, it means that under the premise that the medical history information between patients is similar, in the process of anesthesia risk assessment of patients, only using medical history information as reference information will lead to large errors in weight distribution during anesthesia risk assessment, thereby reducing the effectiveness of anesthesia risk assessment.

[0028] Therefore, in this application, by comparing the consistency of the judgment matrix between different patients and the difference in medical history information between different patients, the difference value of the medical history between different patients during anesthesia risk assessment is obtained; specifically, the medical history information data of each patient is encoded using character encoding technology to obtain the character sequence of each patient, and the distance between the character sequences of any two patients is calculated; the smaller the distance, the smaller the difference in medical history information data between the any two patients. Calculate the consistency ratio (Consistency Ratio, CR) of the judgment matrix of each patient; the smaller the absolute value of the difference between the consistency ratios of the judgment matrices of the any two patients, the closer the importance characteristics of the medical history of the any two patients for anesthesia risk assessment. The consistency ratio belongs to the prior art in the hierarchical analysis method, and the calculation steps of the consistency ratio are: (1) Calculate the maximum eigenvalue of the judgment matrix; (2) Calculate the consistency index, and the calculation formula of the consistency index CI is: , where represents the maximum eigenvalue of the judgment matrix, and n represents the dimension of the judgment matrix; (3) finding the random consistency index; (4) calculating the consistency ratio. The calculation formula of the consistency ratio CR is: , where CI represents the consistency index and RI represents the random consistency index. The specific calculation process of the consistency ratio is a well-known technology and will not be described in detail in this application.

[0029] In this embodiment, UTF-8 (Unicode Transformation Format-8-bit) technology is used to encode the medical history information data. As other implementation methods, on the basis of being able to encode the medical history information data, the implementer may use other existing technologies for encoding, such as ASCII encoding, GB2312 encoding, etc., and this application does not impose any special restrictions.

[0030] In this embodiment, the distance between character sequences is the edit distance. As other implementation methods, on the basis of being able to measure the differences between character sequences, the implementer may adopt other existing technologies for measurement, such as the Hamming distance, etc., and this application does not impose any special restrictions.

[0031] Based on the above analysis, based on the distance between the character sequences of the two patients, combined with the difference between the consistency ratios of the judgment matrices of the two patients, the difference value of the medical history between the two patients is determined, and the expression is: ; in, represents the difference in medical history between the xth and yth patients; represents the distance between the character sequences of the xth and yth patients; Represents the absolute value of the difference between the consistency ratios of the judgment matrices of the xth and yth patients.

[0032] It should be noted that the larger the calculated medical history difference value is, the more dissimilar the medical history information between patients is, and the more dissimilar the importance characteristics of the medical history information in anesthesia assessment are. Figure 2 shown.

[0033] Step 2.2, based on the difference values ​​of the medical history between any two patients, obtain a reference set of patients to be evaluated.

[0034] Furthermore, based on the difference in medical history between any two patients, a hierarchical clustering algorithm is used to classify all patients, wherein the distance between classes is calculated by the shortest distance method. For example, in the classification process of the hierarchical clustering algorithm, there are class 1 and class 2, then the distance between class 1 and class 2 is: the minimum value of the difference in medical history between patients in class 1 and patients in class 2, and the termination condition of the hierarchical clustering algorithm is that the normalized value of the minimum value between classes is greater than a preset value. In the past, the basis for classifying patients was the similarity of the medical history information between patients. However, when evaluating the anesthesia risk of perioperative patients, although the medical history information of different patients is similar, there are differences in the importance of the medical history of different patients for anesthesia risk assessment, resulting in deviations in the weight allocation during anesthesia risk assessment. Therefore, this application classifies all patients based on the difference values ​​of the medical history between patients, combining the similarity of the medical history information between different patients and the similarity of the importance characteristics of the medical history information between different patients, to avoid classifying patients with medical history information that appears similar on the surface but may actually have different effects on anesthesia risk into the same category, so as to improve the accuracy of weight allocation when evaluating the anesthesia risk of patients to be evaluated. The specific hierarchical clustering algorithm is a technology well known to those skilled in the art and will not be described in detail in this application.

[0035] In this embodiment, the preset value is 0.8. The preset value is preset manually and can be set by the implementer according to actual conditions. This application does not impose any special restrictions.

[0036] Furthermore, based on the classification results, all patients in the class of the patient to be evaluated, except the patient to be evaluated, are used to form a reference set of patients to be evaluated, so as to reduce the impact of differences in the importance of previous medical history on the weight allocation in the patient's anesthesia risk assessment.

[0037] Step 2.3, based on the difference in the judgment matrix between the patient to be evaluated and each patient in its reference set, determine the reference difference value for weight adjustment between each patient in the reference set and the patient to be evaluated; based on the difference value in the past medical history between the patient to be evaluated and each patient in its reference set and the reference difference value, determine the weight adjustment influence value between the patient to be evaluated and each patient in its reference set.

[0038] On the basis of classification, the differences in weight allocation of risk assessment features with similarities are compared, and the weight adjustment value of the patient to be evaluated is analyzed through the comparison results, that is, the weight allocation of the patient to be evaluated is adjusted according to the difference in the judgment matrix between the patient to be evaluated and each patient in the reference set; specifically, for any patient in the reference set of patients to be evaluated, the absolute value of the difference between the elements in the same position between the judgment matrix of any patient and the judgment matrix of the patient to be evaluated is calculated, and recorded as the element difference; the sum of all the element differences corresponding to each patient in the reference set is used as the reference difference value for the weight adjustment between each patient in the reference set and the patient to be evaluated; the larger the reference difference value, the greater the influence of each patient in the reference set on the weight adjustment of the patient to be evaluated.

[0039] Further, based on the difference value of the medical history between the patient to be evaluated and each patient in the reference set and the reference difference value, the weight adjustment influence value between the patient to be evaluated and each patient in the reference set is determined, and the expression is: ; in, represents the weight-adjusted impact value between the i-th and j-th patients; represents the weight-adjusted reference difference value between the i-th and j-th patients; represents the difference in medical history between the i-th and j-th patients; Represents an exponential function with a natural constant as the base, in order to avoid the denominator being 0.

[0040] It should be noted that: the greater the weight adjustment influence value between the patient to be evaluated and each patient in the reference set, the greater the influence of each patient in the reference set on the weight distribution of the patient to be evaluated.

[0041] Step 2.4, based on the distribution of the weight adjustment influence value, determine the fusion adjustment weight of each patient in the reference set for the element adjustment in the judgment matrix of the patient to be evaluated.

[0042] Furthermore, based on the analysis results of the influence of each patient in the reference set on the weight adjustment of the patient to be evaluated, the fusion adjustment weight of each patient in the reference set for the element adjustment in the judgment matrix of the patient to be evaluated is calculated. The specific calculation method is: calculate the cumulative value of the weight adjustment influence values ​​corresponding to all patients in the reference set, and use the ratio of the weight adjustment influence value corresponding to each patient in the reference set to the cumulative value as the fusion adjustment weight of each patient in the reference set for the element adjustment in the judgment matrix of the patient to be evaluated. The larger the fusion adjustment weight, the greater the influence of each patient in the reference set on the weight distribution of the patient to be evaluated. The schematic diagram of the process of obtaining the fusion adjustment weight is shown in the figure. Figure 3shown.

[0043] Step 3, based on the fusion adjustment weight, combined with the judgment matrix of each patient in the reference set, adjust each element in the judgment matrix of the patient to be evaluated, and use a neural network to obtain the anesthesia risk assessment result of the patient to be evaluated based on the adjusted judgment matrix.

[0044] Based on the fusion adjustment weight, combined with the judgment matrix of each patient in the reference set, each element in the judgment matrix of the patient to be evaluated is adjusted, and the expression is: ; in, represents the first The adjusted value of the elements; Indicates the first In the judgment matrix of each patient elements; Indicates the first The fusion adjustment weight of the elements in the judgment matrix of the patient to be evaluated is adjusted by each patient; Represents the total number of patients in the reference set.

[0045] Obtain the medical history information data of a preset number of similar patients of the patient to be evaluated, and adjust the judgment matrix of the preset number of similar patients according to the method of adjusting the judgment matrix of the patient to be evaluated, and divide the adjusted judgment matrix of the preset number of similar patients into a training set and a test set according to a ratio of 7:3, train the convolutional neural network model according to the divided training set, and verify the convolutional neural network model using the test set. The specific training process of the convolutional neural network model is a known technology and will not be described in detail in this application.

[0046] In this embodiment, the value of the preset number is 1000. The value of the preset number is preset manually and can be set by the implementer. This application does not impose any special restrictions.

[0047] After adjusting the elements in the judgment matrix of the patient to be evaluated, the adjusted judgment matrix of the patient to be evaluated is used as the input of the trained neural network model to output the anesthesia risk assessment result of the patient to be evaluated. The anesthesia risk assessment result is a grading of 1-10, where 1-3 is low risk, 3-6 is medium risk, and 6-10 is high risk. The optimization algorithm of the convolutional neural network model is Adam, and the loss function is the cross entropy loss function.

[0048] Based on the same inventive concept as the above method, an embodiment of the present application also provides a perioperative patient anesthesia risk assessment system based on past medical history, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned perioperative patient anesthesia risk assessment methods based on past medical history are implemented.

[0049] In summary, the present application aims at the existing method of determining risk assessment weights by the differences in medical history information, but there are differences in the judgment of the importance of medical history information of different patients for anesthesia risk assessment, which will affect the accuracy of anesthesia risk assessment; obtain a judgment matrix of the importance of medical history information data of each patient for anesthesia risk assessment; determine the medical history difference value based on the differences in medical history information data between different patients and the differences in the judgment matrix, and classify all patients based on the medical history difference value; comprehensively consider the similarities of medical history information between different patients and the importance of medical history information between different patients in anesthesia The similarity of the importance features during the evaluation can accurately obtain a reference set for weight allocation during the anesthesia risk assessment of the patient to be evaluated; further, based on the differences in the degree of influence of each patient in the reference set on the patient to be evaluated during the anesthesia risk assessment, the judgment matrix of the patient to be evaluated is adjusted, and then the anesthesia risk assessment result is obtained based on the adjusted judgment matrix, which can improve the accuracy of the anesthesia risk assessment of perioperative patients. Combined with the differences in the importance features of previous medical history, it can avoid the problem of deviation in the anesthesia risk assessment results caused by allocating weights during anesthesia risk assessment only based on the similarity of previous medical history information.

[0050] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

[0051] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the basic features of the present application. Therefore, no matter from which point of view, the above embodiments of the present application should be regarded as exemplary and non-restrictive.

Claims

1. A method for assessing the anesthesia risk of perioperative patients based on past medical history, characterized in that: The method comprises the following steps: Obtain the medical history information data of the patient to be evaluated and multiple similar patients, and obtain a judgment matrix of the importance of each patient's medical history information data to anesthesia risk assessment; Based on the difference in the past medical history information data between any two patients and the difference between the consistency ratios of the judgment matrices of the any two patients, determining the past medical history difference value between the any two patients; Based on the difference values ​​of the medical histories between any two patients, a reference set of patients to be evaluated is obtained; Based on the difference of the judgment matrix between the patient to be evaluated and each patient in the reference set, determining a reference difference value for weight adjustment between each patient in the reference set and the patient to be evaluated; Determine a weight-adjusted impact value between the patient to be evaluated and each patient in the reference set based on the previous medical history difference value between the patient to be evaluated and each patient in the reference set and the reference difference value; Determining, based on the distribution of the weight adjustment influence values, a fusion adjustment weight of each patient in the reference set for adjusting the elements in the judgment matrix of the patient to be evaluated; Based on the fusion adjustment weight, combined with the judgment matrix of each patient in the reference set, each element in the judgment matrix of the patient to be evaluated is adjusted, and a neural network is used to obtain an anesthesia risk assessment result of the patient to be evaluated based on the adjusted judgment matrix; The specific process of obtaining the difference value of the past medical history is as follows: The medical history information of each patient is encoded using character encoding technology to obtain character sequences; Calculate the distance between the character sequences of any two patients; Calculating the absolute value of the difference between the consistency ratios of the judgment matrices of any two patients; The past medical history difference value is the product of the distance and the absolute value of the difference.

2. The method for assessing anesthesia risk of perioperative patients based on past medical history according to claim 1, characterized in that: The medical history information data includes age, gender, basic physical index information, history of vascular diseases, history of respiratory diseases, history of endocrine diseases and history of nervous system diseases, wherein the basic physical index information includes heart rate, blood pressure, body temperature and weight.

3. The method for assessing anesthesia risk of perioperative patients based on past medical history according to claim 1, characterized in that: The process of obtaining the reference set is as follows: All patients were classified based on the difference in medical history between any two patients; All patients in the class to which the patient to be evaluated belongs, except the patient to be evaluated, constitute a reference set of patients to be evaluated.

4. The method for assessing anesthesia risk of perioperative patients based on past medical history according to claim 1, characterized in that: The process of determining the reference difference value is as follows: For any patient in the reference set of patients to be evaluated, calculate the absolute value of the difference between the elements at the same position of the judgment matrix of any patient and the judgment matrix of the patient to be evaluated, and record it as the element difference; The sum of all the element differences corresponding to each patient in the reference set is used as a reference difference value for weight adjustment between each patient in the reference set and the patient to be evaluated.

5. The method for assessing anesthesia risk of perioperative patients based on past medical history according to claim 1, characterized in that: The expression of the weight adjustment influence value is: ； in, represents the weight-adjusted impact value between the i-th and j-th patients; represents the weight-adjusted reference difference value between the i-th and j-th patients; represents the difference in medical history between the i-th and j-th patients; Represents an exponential function with a natural constant as base.

6. The method for assessing anesthesia risk of perioperative patients based on past medical history according to claim 1, characterized in that: The determination process of the fusion adjustment weight is as follows: Calculating the cumulative value of the weight-adjusted impact values ​​corresponding to all patients in the reference set; The fusion adjustment weight is the ratio of the weight adjustment influence value corresponding to each patient in the reference set to the accumulated value.

7. The method for assessing anesthesia risk of perioperative patients based on past medical history according to claim 1, characterized in that: The method for adjusting the weight based on the fusion and combining the judgment matrix of each patient in the reference set to adjust each element in the judgment matrix of the patient to be evaluated is as follows: ； in, represents the first The adjusted value of the elements; Indicates the first In the judgment matrix of each patient elements; Indicates the first The fusion adjustment weight of each patient for the elements in the judgment matrix of the patient to be evaluated; m represents the total number of patients in the reference set.

8. A perioperative patient anesthesia risk assessment system based on past medical history, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method for assessing anesthesia risk of perioperative patients based on past medical history are implemented as described in any one of claims 1-7.

Images