Medical informatization management system and method
Through multi-dimensional weighted classification algorithm and adaptive multi-objective nonlinear optimization algorithm, the problems of low efficiency and difficulty in formulating personalized solutions when processing massive medical data are solved, and rapid and accurate diagnosis and optimization of treatment are achieved The plan improves the efficiency and effectiveness of medical services.
Patent Information
- Application Number
- CN202411253791.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-09
- Publication Date
- 2024-11-22
AI Technical Summary
Traditional medical information management systems are inefficient when processing large amounts of medical data, making it difficult to process and analyze massive data effectively in real time, resulting in delays and errors in the formulation of diagnostic and treatment plans. Standardized plans cannot fully consider individual differences, and it is difficult to treat the effects and side effects of treatment. balance.
A multi-dimensional weighted classification algorithm is used to calculate the disease diagnosis category, and a preliminary personalized treatment plan is formulated in combination with rule reasoning methods, and the treatment plan is optimized through an adaptive multi-objective nonlinear optimization algorithm to balance the treatment effect and side effects.
It improves the accuracy of disease diagnosis and targeted treatment plans, ensures the effectiveness and safety of treatment, reduces the risk of misdiagnosis and treatment delays, and improves the medical experience.
Smart Images

Figure CN119007988A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of medical information management, and in particular to a medical information management system and method. Background Art
[0002] With the rapid development of science and technology and the growing demand for medical care, the medical industry is facing unprecedented challenges and opportunities. In the traditional medical management model, a large amount of paper records and manual operations are not only inefficient, but also prone to data errors and information loss. In order to improve the quality of medical services, optimize resource allocation, reduce operating costs and improve patient experience, the need to build a medical information management system is becoming more urgent.
[0003] However, traditional medical information management systems are inefficient when processing large amounts of medical data, especially when faced with the expansion of hospital size and the increase in the types of medical services. It is difficult to effectively process and analyze massive amounts of medical data in real time, resulting in slow data processing. The formulation of diagnosis and treatment plans relies on a large amount of manual operations, which is prone to delays and errors. Standardized treatment plans cannot fully consider the individual differences of each patient, and personalized plans lack systematic formulation. There is a natural conflict between treatment effects and side effects, making it difficult to achieve ideal treatment effects. Summary of the invention
[0004] The present invention provides a medical information management system and method to solve the problem that traditional medical information management systems are inefficient in processing large amounts of medical data, especially in the face of expanding hospital scale and increasing types of medical services. It is difficult to effectively process and analyze massive amounts of medical data in real time, which leads to slow data processing speed. The formulation of diagnosis and treatment plans relies on a large amount of manual operations, which is prone to delays and errors; standardized treatment plans cannot fully consider the individual differences of each patient, and personalized plans lack systematic formulation; there is a natural conflict between treatment effects and side effects, making it difficult to achieve ideal treatment effects.
[0005] A medical information management system and method of the present invention specifically includes the following technical solutions:
[0006] A medical information management method comprises the following steps:
[0007] S1: Obtain the patient's medical data in real time and use a multidimensional weighted classification algorithm to calculate the patient's disease diagnosis category;
[0008] S2: Based on the patient's disease diagnosis category and medical data, use rule-based reasoning methods to develop a preliminary personalized treatment plan;
[0009] S3: Based on the preliminary personalized treatment plan, an adaptive multi-objective nonlinear optimization algorithm is used for optimization, and adaptive constraints are used to constrain the treatment plan to obtain the optimized treatment plan.
[0010] Preferably, the S1 specifically includes:
[0011] The multidimensional weighted classification algorithm obtains the processed medical data value by normalizing and bias correcting the patient's medical data.
[0012] Preferably, the S1 specifically includes:
[0013] The processed medical data values are layered according to the type of medical data to obtain the results of the patient's medical data after being processed at different layers; and the processing results of each layer are processed according to the layer weight to obtain the patient's disease diagnosis category.
[0014] Preferably, the S2 specifically includes:
[0015] The rule-based reasoning method introduces multi-attribute decision-making methods and rule-based reasoning mechanisms to analyze the medical data of each patient and generate a preliminary personalized treatment plan.
[0016] Preferably, the S2 specifically includes:
[0017] The rule reasoning mechanism selects rules related to the patient's medical data from the rule base, evaluates the applicability of each rule to each patient in turn, and obtains the score of each rule in each patient. The specific formula for rule reasoning is:
[0018]
[0019] Among them, S il represents the score of the ith patient after applying the lth rule; r lk (a ik ) represents the evaluation result of the lth rule on the kth medical data value of the ith patient; a ik Represents the kth medical data value of the ith patient.
[0020] Preferably, the S2 specifically includes:
[0021] The multi-attribute decision-making method standardizes the score of each rule in each patient and obtains the standardized score of each rule:
[0022]
[0023] Among them, v il represents the standardized score of the ith patient after applying the lth rule; n represents the total number of patients;
[0024] Compare the standardized scores of all patients, take the maximum value to get the positive ideal solution, and take the minimum value to get the negative ideal solution; based on the positive ideal solution and the negative ideal solution, calculate the relative closeness of the patient under each rule:
[0025]
[0026] Among them, A il represents the relative proximity of the ith patient under the lth rule; represents the distance between the standardized score of the ith patient under the lth rule and the positive ideal solution; represents the distance between the standardized score of the i-th patient under the l-th rule and the negative ideal solution;
[0027] The rule with the largest relative proximity is selected to obtain a preliminary personalized treatment plan.
[0028] Preferably, the S3 specifically includes:
[0029] The adaptive multi-objective nonlinear optimization algorithm is used to balance the therapeutic effect and side effects. The nonlinear combination method is used to integrate the therapeutic effect and side effects, and the adaptive constraints are used to constrain the treatment plan. The calculation formula for the optimized treatment plan is:
[0030]
[0031] Among them, min represents the minimum value, which is used to find the minimum value of the objective function and obtain the optimized treatment plan; f(Q i ) represents the objective function, which is used to measure the initial personalized treatment plan Q for the i-th patient i The overall effect; ∈ is used to prevent the denominator from being zero; E(Q i ) represents the effect score of the initial personalized treatment plan for the i-th patient; B(Q i ) represents the side effect score of the preliminary personalized treatment plan for the ith patient; κ represents the adjustment coefficient, which is used to adjust the relative importance of treatment effect and side effects.
[0032] A medical information management system, comprising the following parts:
[0033] Medical data acquisition module, multi-dimensional weighted classification module, rule reasoning module, conditional constraint module, adaptive multi-objective nonlinear optimization module;
[0034] Medical data collection module: obtains the patient's medical data in real time and outputs the patient's medical data to the multi-dimensional weighted classification module and rule reasoning module;
[0035] Multidimensional weighted classification module: Based on the medical data of the patient output by the medical data acquisition module, a multidimensional weighted classification algorithm is used to calculate the patient's disease diagnosis category, and the patient's disease diagnosis category is output to the rule reasoning module;
[0036] Rule reasoning module: Based on the patient's medical data output by the medical data acquisition module and the patient's disease diagnosis category output by the multidimensional weighted classification module, a preliminary personalized treatment plan is formulated using the rule reasoning method, and the preliminary personalized treatment plan is output to the adaptive multi-objective nonlinear optimization module;
[0037] Conditional constraint module: Design adaptive constraint conditions and output the constraint conditions to the adaptive multi-objective nonlinear optimization module;
[0038] Adaptive multi-objective nonlinear optimization module: Based on the preliminary personalized treatment plan output by the rule reasoning module and the constraints output by the conditional constraint module, the preliminary personalized treatment plan is optimized using an adaptive multi-objective nonlinear optimization algorithm, and then constrained by adaptive constraints to obtain the optimized treatment plan.
[0039] The beneficial effects of the technical solution of the present invention are:
[0040] 1. By acquiring the patient's medical data in real time and using a multidimensional weighted classification algorithm to process the medical data quickly and efficiently, while comprehensively considering the weight, normalization and bias correction of the medical data, it ensures that medical data of different dimensions and magnitudes are comparable and can accurately reflect the patient's disease category, thereby improving the accuracy of disease diagnosis and reducing the risk of misdiagnosis caused by data bias or the difficulty in comparing data of different magnitudes, thereby improving the reliability and accuracy of medical diagnosis.
[0041] 2. According to the patient's disease diagnosis category and medical data, combined with medical guidelines and clinical experience, a preliminary personalized treatment plan is formulated using a rule reasoning method. The rule reasoning method introduces a multi-attribute decision-making method and a rule reasoning mechanism to analyze the medical data of each patient and determine a preliminary personalized treatment plan. This ensures that the formulation of the treatment plan is not only based on scientific medical guidelines and clinical experience, but also combines the individual characteristics of the patient, providing a preliminary treatment plan that is more in line with the patient's actual needs, thereby improving the targetedness and effectiveness of the treatment.
[0042] 3. Based on the preliminary personalized treatment plan, an adaptive multi-objective nonlinear optimization algorithm is used to balance the treatment effect and side effects. The optimization results are dynamically adjusted through nonlinear combinations and adaptive constraints to ensure that the treatment plan is both effective and safe. This ensures that while pursuing the best treatment effect, side effects are controlled within a reasonable range, thereby improving the patient's treatment effect and medical experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] Figure 1 This is a structural diagram of a medical information management system according to the present invention;
[0044] Figure 2 This is a flow chart of a medical information management method described in the present invention. DETAILED DESCRIPTION
[0045] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0046] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
[0047] The specific scheme of a medical information management system and method provided by the present invention is described in detail below with reference to the accompanying drawings.
[0048] See attached Figure 1 , which shows a structural diagram of a medical information management system provided by an embodiment of the present invention, the system includes the following parts:
[0049] Medical data acquisition module, multi-dimensional weighted classification module, rule reasoning module, conditional constraint module, adaptive multi-objective nonlinear optimization module;
[0050] Medical data collection module: obtains the patient's medical data in real time and outputs the patient's medical data to the multi-dimensional weighted classification module and rule reasoning module;
[0051] Multidimensional weighted classification module: Based on the medical data of the patient output by the medical data acquisition module, a multidimensional weighted classification algorithm is used to calculate the patient's disease diagnosis category, and the patient's disease diagnosis category is output to the rule reasoning module;
[0052] Rule reasoning module: Based on the patient's medical data output by the medical data acquisition module and the patient's disease diagnosis category output by the multidimensional weighted classification module, combined with medical guidelines and clinical experience, a preliminary personalized treatment plan is formulated using the rule reasoning method, and the preliminary personalized treatment plan is output to the adaptive multi-objective nonlinear optimization module;
[0053] Conditional constraint module: Design an adaptive constraint condition and output the constraint condition to the adaptive multi-objective nonlinear optimization module;
[0054] Adaptive multi-objective nonlinear optimization module: Based on the preliminary personalized treatment plan output by the rule reasoning module and the constraints output by the conditional constraint module, the preliminary personalized treatment plan is optimized using an adaptive multi-objective nonlinear optimization algorithm, and then constrained by adaptive constraints to obtain the optimized treatment plan.
[0055] See attached Figure 2 , which shows a flow chart of a medical information management method provided by an embodiment of the present invention, the method comprising the following steps:
[0056] S1. Obtain the patient's medical data in real time and use a multidimensional weighted classification algorithm to calculate the patient's disease diagnosis category;
[0057] With the expansion of hospital scale and the increase of medical service types, traditional medical information management systems can no longer meet the needs of hospitals. However, with the rapid development of information technology, the informatization process of the medical industry is also advancing. Real-time acquisition of patients' medical data and the use of multi-dimensional weighted classification algorithms to calculate the patient's disease diagnosis category can reduce dependence on manual operations and improve the level of medical information management.
[0058] The multidimensional weighted classification algorithm comprehensively considers the weight of medical data, the normalization of medical data values, and the correction of the deviation of medical data values. The medical data values are logarithmically transformed to adjust the dynamic range of the medical data values to ensure the comparability of medical data values of different orders of magnitude; the medical data values are normalized using the average value of the medical data; the deviation of the medical data values is adjusted by applying the correction amplitude and the ideal reference value to ensure the reasonable adjustment of the medical data values to obtain the processed medical data values; according to different medical data types, such as blood pressure, heart rate, blood sugar, and blood lipids, they are divided into different levels for processing, and the medical data values after processing at each level are weighted and summed according to the medical data weight to obtain the results of the patient's medical data after processing at different levels; the processing result of each level is multiplied by the corresponding level weight, and the weighted processing results of all levels are summed to find the category that maximizes the sum result, that is, the patient's disease diagnosis category;
[0059] The specific calculation formula for the patient's disease diagnosis category is:
[0060]
[0061] Among them, C i represents the disease diagnosis category of the i-th patient, such as heart disease and diabetes; Indicates finding the disease category c that makes the expression reach the maximum value; C represents the set of all disease categories; g represents the total number of medical data types contained in disease category c, that is, the total number of divided levels; Indicates the sum of all processing results from layer 1 to layer g; W j H represents the level weight of the j-th layer processing result; ij It represents the result of the medical data of the i-th patient after being processed by the j-th layer. The specific calculation formula is:
[0062]
[0063] in, represents the sum of the m medical data values of the ith patient according to the medical data weight; m represents the total number of medical data of the ith patient; w k represents the k-th medical data weight, which determines the influence of the k-th medical data value of the ith patient on the result after the j-th layer processing; a ik represents the kth medical data value of the i-th patient; represents logarithmic processing, which adjusts the dynamic range of the kth medical data value of the ith patient through the logarithmic function to ensure that the medical data values are comparable between different orders of magnitude; μ k represents the average value of the kth medical data, which is used to normalize the medical data value; k represents the correction amplitude of the kth medical data value, which is used to adjust the deviation of the medical data value and can be set according to the specific implementation scenario and is not limited here; |·| represents the absolute value sign, and the absolute value is used to eliminate the influence of the positive and negative signs; u k represents the ideal reference value of the kth medical data value, which can be set according to the specific implementation scenario and is not limited here;
[0064] S2. Based on the patient's disease diagnosis category and medical data, use rule-based reasoning methods to develop a preliminary personalized treatment plan;
[0065] According to the patient's disease diagnosis category and medical data, combined with medical guidelines and clinical experience, a preliminary personalized treatment plan is formulated using a rule-based reasoning method. The rule-based reasoning method introduces a multi-attribute decision-making method and a rule-based reasoning mechanism to analyze the medical data of each patient and determine a preliminary personalized treatment plan;
[0066] The rule reasoning mechanism selects rules related to the patient's medical data from a predefined rule base. Each rule in the rule base corresponds to a treatment plan. The rules themselves are designed based on medical guidelines and clinical experience. The applicability of each rule to each patient is evaluated in turn. If the medical data meets the conditions of the rule, it is considered a match and a score is given to the rule. Otherwise, the score is zero. The scores are accumulated to obtain the score of each rule for each patient.
[0067] The multi-attribute decision-making method standardizes the score of each rule in each patient, with the purpose of eliminating the scale difference between different scores so that the scores can be compared on the same scale, and finding the maximum and minimum values of the standardized values of the scores in all rules. The maximum value is called the positive ideal solution, which represents the best treatment effect, and the minimum value is called the negative ideal solution, which represents the worst treatment effect. The distance between the standardized value of the score of each rule and the positive ideal solution and the negative ideal solution is calculated, and then the relative proximity of the patient under each rule is calculated, and the rule with the highest relative proximity is selected as the patient's initial personalized treatment plan;
[0068] The steps of rule reasoning method are as follows:
[0069] The first step is rule reasoning;
[0070] According to the medical rule base R and the patient's medical data, rule reasoning is performed for each patient. Each rule in the medical rule base R corresponds to a treatment plan.
[0071] The rule reasoning formula is:
[0072]
[0073] Among them, S il It represents the score of the ith patient after applying the lth rule, that is, the inference result of the lth rule of the ith patient, which is used to measure the applicability of the lth rule to the ith patient; represents the summation, which accumulates the scores of the m medical data of the i-th patient under the l-th rule; r lk (a ik ) represents the evaluation result of the lth rule on the kth medical data value of the ith patient, that is, it is 1 when it meets the rule conditions and 0 when it does not meet the rule conditions;
[0074] The second step is the application of multi-attribute decision-making methods;
[0075] Comprehensively evaluate the reasoning results of all rules through multi-attribute decision-making methods to select the best treatment plan;
[0076] Establish a standardized matrix to convert each rule inference result S of the i-th patient ilThe standardized formula is as follows:
[0077]
[0078] Among them, v il represents the standardized value of the score of the ith patient after applying the lth rule, that is, the standardized score of the ith patient after applying the lth rule; Represents the square root operation, which is used for standardization to ensure consistent score scales; represents the summation symbol, and the square sum of the scores after applying the first rule to all patients is calculated; n represents the total number of patients;
[0079] Calculate the positive ideal solution and the negative ideal solution, the formula is as follows:
[0080] V + =max(v il )
[0081] Among them, V + represents the positive ideal solution, that is, the maximum value in the standardized score; max(v il ) means taking the maximum value from the standardized scores of all patients;
[0082] V - =min(v il )
[0083] Among them, V - represents the negative ideal solution, i.e., the minimum value in the standardized score; max(v il ) means taking the minimum value from the standardized scores of all patients;
[0084] The distance between the standardized score of each patient under each rule and the positive ideal solution and the negative ideal solution is calculated as follows:
[0085]
[0086] in, represents the distance between the standardized score of the ith patient under the lth rule and the positive ideal solution; √· represents the square root symbol, which is used to calculate the actual Euclidean distance;
[0087]
[0088] in, represents the distance between the standardized score of the i-th patient under the l-th rule and the negative ideal solution;
[0089] Calculate the relative proximity, the formula is as follows:
[0090]
[0091] Among them, A il represents the relative proximity of the ith patient under the lth rule, which is used to select a preliminary personalized treatment plan;
[0092] Select a preliminary personalized treatment plan, the formula is as follows:
[0093]
[0094] Among them, Q i represents the preliminary personalized treatment plan for the i-th patient; represents the maximization operator, which is used to find the relative closeness A il The largest rule l is used to determine the optimal treatment plan.
[0095] S3. Based on the preliminary personalized treatment plan, an adaptive multi-objective nonlinear optimization algorithm is used for optimization, and adaptive constraints are used to constrain the optimized treatment plan;
[0096] Based on the preliminary personalized treatment plan, an adaptive multi-objective nonlinear optimization algorithm is used for optimization processing, and adaptive constraints are used to constrain the optimized treatment plan; the adaptive multi-objective nonlinear optimization algorithm aims to balance the relationship between treatment effect and side effects, achieve optimization through nonlinear combination, and use adaptive constraints to control the rationality of the optimization results;
[0097] Specifically, the treatment effect and side effects are integrated through the nonlinear combination method. The treatment effect is processed by logarithmic transformation to emphasize its importance in optimization; the side effects are processed by square root transformation to control their influence in optimization. In order to further balance the relationship between the treatment effect and the side effects, an interaction term is added. The interaction term combines the treatment effect and the side effects in a nonlinear way, so that the influence of the treatment effect and the side effects can be fully considered in the optimization process.
[0098] The calculation formula of the optimized treatment plan is:
[0099]
[0100] Among them, min represents the minimum value, which is used to obtain the minimum value of the objective function, that is, to obtain the optimized treatment plan; f(Q i ) represents the objective function, which is used to measure the initial personalized treatment plan Q for the i-th patient i The overall effect; ∈ represents a very small positive number, used to prevent the denominator from being zero; E(Q i) represents the effect score of the preliminary personalized treatment plan for the ith patient, which is obtained through evaluation of clinical experimental data, medical literature and experience data of medical experts. It is a technical means well known to those skilled in the art and will not be described in detail here; B(Q i ) represents the side effect score of the preliminary personalized treatment plan for the i-th patient, which is obtained by evaluating clinical experimental data, medical literature and experience data of medical experts. It is a technical means well known to those skilled in the art and will not be described in detail here; ln(1+E(Q i )) indicates that the effect score of the preliminary personalized treatment plan for the i-th patient is processed in logarithmic form to reduce the impact of extreme values; represents the square root processing of the side effect score of the preliminary personalized treatment plan for the i-th patient, emphasizing the impact of extremely large side effects; κ represents the adjustment coefficient, which is used to adjust the relative importance of treatment effect and side effects to achieve the best balance; It represents the nonlinear ratio of side effects to therapeutic effects, reflects the balance between therapeutic effects and side effects, and can reasonably guide the optimization of treatment plans;
[0101] At the same time, an adaptive constraint is designed. The constraint dynamically adjusts the allowable value of side effects according to the patient's treatment effect, so that the upper limit of side effects does not exceed the predefined safety threshold and can be appropriately relaxed as the treatment effect improves, ensuring the rationality of the treatment plan. The formula is as follows:
[0102]
[0103] Among them, max means taking the maximum value; B th represents a predefined side effect threshold, which can be set according to the specific implementation scenario and is not limited here; P represents an adjustment coefficient for controlling the relationship between treatment effect and side effect;
[0104] By comprehensively considering the patient's specific medical data, treatment effects and side effects, we ensure scientificity and rationality, help doctors develop accurate treatment plans, and improve the patient's treatment effects and medical experience.
[0105] In summary, a medical information management system and method have been completed.
[0106] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted 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 also possible or may be advantageous.
[0107] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.
[0108] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.
Claims
1. A medical information management method, characterized in that: The following steps are involved: S1: Obtain the patient's medical data in real time and use a multidimensional weighted classification algorithm to calculate the patient's disease diagnosis category; S2: Based on the patient's disease diagnosis category and medical data, use rule-based reasoning methods to develop a preliminary personalized treatment plan; S3: Based on the preliminary personalized treatment plan, an adaptive multi-objective nonlinear optimization algorithm is used for optimization, and adaptive constraints are used to constrain the treatment plan to obtain the optimized treatment plan.
2. The medical information management method according to claim 1, characterized in that: The S1 specifically includes: The multidimensional weighted classification algorithm obtains the processed medical data value by normalizing and bias correcting the patient's medical data.
3. The medical information management method according to claim 2, characterized in that: The S1 specifically includes: The processed medical data values are layered according to the type of medical data to obtain the results of the patient's medical data after being processed at different layers; and the processing results of each layer are processed according to the layer weight to obtain the patient's disease diagnosis category.
4. The medical information management method according to claim 1, characterized in that: The S2 specifically includes: The rule-based reasoning method introduces multi-attribute decision-making methods and rule-based reasoning mechanisms to analyze the medical data of each patient and generate a preliminary personalized treatment plan.
5. The medical information management method according to claim 4, characterized in that: The S2 specifically includes: The rule reasoning mechanism selects rules related to the patient's medical data from the rule base, evaluates the applicability of each rule to each patient in turn, and obtains the score of each rule in each patient. The specific formula for rule reasoning is: Among them, S il represents the score of the ith patient after applying the lth rule; r lk (a ik ) represents the evaluation result of the lth rule on the kth medical data value of the ith patient; a ik Represents the kth medical data value of the ith patient.
6. The medical information management method according to claim 5, characterized in that: The S2 specifically includes: The multi-attribute decision-making method standardizes the score of each rule in each patient and obtains the standardized score of each rule: Among them, b il represents the standardized score of the ith patient after applying the lth rule; n represents the total number of patients; Compare the standardized scores of all patients, take the maximum value to get the positive ideal solution, and take the minimum value to get the negative ideal solution; based on the positive ideal solution and the negative ideal solution, calculate the relative closeness of the patient under each rule: Among them, A il represents the relative proximity of the ith patient under the lth rule; represents the distance between the standardized score of the ith patient under the lth rule and the positive ideal solution; represents the distance between the standardized score of the i-th patient under the l-th rule and the negative ideal solution; The rule with the largest relative proximity is selected to obtain a preliminary personalized treatment plan.
7. The medical information management method according to claim 1, characterized in that: The S3 specifically includes: The treatment effect and side effects are balanced through an adaptive multi-objective nonlinear optimization algorithm; the treatment effect and side effects are integrated through the nonlinear combination method and the introduction of nonlinear interaction terms, and at the same time, the adaptive constraints are used to constrain the optimized treatment plan; the calculation formula for the optimized treatment plan is: Among them, min represents the minimum value, which is used to find the minimum value of the objective function and obtain the optimized treatment plan; f(Q i ) represents the objective function, which is used to measure the initial personalized treatment plan Q for the i-th patient i The overall effect; ∈ is used to prevent the denominator from being zero; E(Q i ) represents the effect score of the initial personalized treatment plan for the i-th patient; B(Q i ) represents the side effect score of the preliminary personalized treatment plan for the ith patient; κ represents the adjustment coefficient, which is used to adjust the relative importance of treatment effect and side effects.
8. A medical information management system, characterized in that: Includes the following sections: Medical data acquisition module, multi-dimensional weighted classification module, rule reasoning module, conditional constraint module, adaptive multi-objective nonlinear optimization module; Medical data collection module: obtains the patient's medical data in real time and outputs the patient's medical data to the multi-dimensional weighted classification module and rule reasoning module; Multidimensional weighted classification module: Based on the medical data of the patient output by the medical data acquisition module, a multidimensional weighted classification algorithm is used to calculate the patient's disease diagnosis category, and the patient's disease diagnosis category is output to the rule reasoning module; Rule reasoning module: Based on the patient's medical data output by the medical data acquisition module and the patient's disease diagnosis category output by the multidimensional weighted classification module, a preliminary personalized treatment plan is formulated using the rule reasoning method, and the preliminary personalized treatment plan is output to the adaptive multi-objective nonlinear optimization module; Conditional constraint module: Design adaptive constraint conditions and output the constraint conditions to the adaptive multi-objective nonlinear optimization module; Adaptive multi-objective nonlinear optimization module: Based on the preliminary personalized treatment plan output by the rule reasoning module and the constraints output by the conditional constraint module, the preliminary personalized treatment plan is optimized using an adaptive multi-objective nonlinear optimization algorithm, and then constrained by adaptive constraints to obtain an optimized treatment plan.
Citation Information
Cited By
Method and system for recommending personalized treatment scheme of lung cancer and storage medium
CN121964045A
A method, system, and storage medium for recommending personalized treatment plans for lung cancer.
CN121964045B
