Personalized medical decision-making method based on artificial intelligence

Abstract

The invention relates to a personalized medical decision-making method based on artificial intelligence, and relates to the field of medical health and artificial intelligence, and the personalized medical decision-making method comprises the following steps: S1, inputting medical data of a patient in a patient information input module, including historical cases, examination reports, genomic sequences and real-time health monitoring data; and S2, based on the patient information, the patient health comprehensive evaluation module evaluates the health state of the patient, and the medical decision module outputs a preliminary treatment scheme according to the evaluation result. By collecting comprehensive medical data of a patient and comprehensively evaluating the health state of the patient based on the data, the illness state of the patient is more accurately grasped, a more accurate treatment scheme is made, individual differences, including age, physiological indexes, psychological conditions and disease duration, of the patient are fully considered, and by calculating the comprehensive evaluation score of the patient, the patient health state is comprehensively evaluated. The timeliness and effectiveness of a treatment scheme are ensured, and the rehabilitation speed of a patient is increased.

Description

Technical Field

[0001] The present invention relates to the fields of medical health and artificial intelligence, and specifically to a personalized medical decision-making method based on artificial intelligence. Background Art

[0002] In the field of medical health, traditional medical decision-making methods mainly rely on the doctor's experience and the patient's clinical symptoms. Although this method can provide effective treatment plans to a certain extent, it often has problems such as strong subjectivity, insufficient accuracy, and low personalization. With the explosive growth of medical data and the rapid development of artificial intelligence technology, medical decision-making methods based on big data and artificial intelligence have gradually become a research hotspot;

[0003] Although some AI-based medical decision-making systems have been developed, most systems still fail to make full use of patients' personalized information, such as genome sequences and psychological conditions, to develop more accurate treatment plans. At the same time, these systems are still insufficient in real-time monitoring of patients' treatment responses and health conditions, predicting treatment outcomes, and dynamically adjusting treatment plans based on predicted results. In addition, existing medical decision-making methods often lack a comprehensive assessment of the patient's health status, especially when considering multiple factors such as age, physiological indicators, psychological conditions, and duration of illness. It is difficult to give a scientific and reasonable assessment result, which makes it difficult to make precise decisions based on the patient's actual situation when formulating treatment plans, thus affecting the treatment effect and the patient's recovery process. In this regard, we propose a personalized medical decision-making method based on AI. Summary of the invention

[0004] The present invention aims at solving the technical problems existing in the prior art and provides a personalized medical decision-making method based on artificial intelligence.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: a personalized medical decision-making method based on artificial intelligence, the personalized medical decision-making method comprises the following steps:

[0006] S1. Input the patient's medical data in the patient information input module, including historical cases, examination reports, genome sequences, and real-time health monitoring data;

[0007] S2. Based on the patient information, the patient health comprehensive assessment module assesses the patient's health status. Based on the assessment results, the medical decision-making module outputs a preliminary treatment plan.

[0008] S3. Monitor the patient's treatment response and health status in real time, regularly use the medical decision-making module to analyze the current patient's treatment effect, and predict the patient's treatment outcome;

[0009] S4, comparing the predicted treatment results with the treatment results of the preliminary treatment plan. If the predicted results are consistent with the treatment results of the corresponding time period of the preliminary treatment plan, continue to implement the original treatment plan;

[0010] S5. If the predicted result is inconsistent with the treatment result of the corresponding time period of the preliminary treatment plan, the treatment plan is adjusted according to the patient's real-time health status assessment score;

[0011] S6. Follow steps S3-S5 until the patient recovers.

[0012] Preferably, the method for evaluating the patient's health status in step S2 is:

[0013] Based on the collected medical data of patients, age data, physiological index data, psychological condition data and illness duration data are extracted;

[0014] Based on the extracted data, the patient's comprehensive assessment score was calculated;

[0015] The calculation formula for the patient's comprehensive assessment score is:

[0016]

[0017] In the formula, S represents the comprehensive assessment score of the patient, n represents the number of influencing factors, and Q i represents the i-th influencing factor, W i represents the weight of the i-th influencing factor in turn;

[0018] The comprehensive assessment score affects the treatment time of medical decision-making. If the comprehensive assessment score is high, the treatment time is short, and if the comprehensive assessment score is low, the treatment time is long.

[0019] Preferably, the medical decision-making module constructs a model based on a long short-term memory network, and the method of constructing the model is:

[0020] According to the type of disease, collect historical medical data of cured patients of different age groups and different periods;

[0021] Preprocess the acquired historical medical data to remove duplicates, missing values, and outliers, convert data of different dimensions into the same dimension, convert time series data into sequence data, and divide the data into a training set, a validation set, and a test set, with the ratio of the training set, validation set, and test set being 70%:15%:15%;

[0022] Based on the preprocessed sequence data, physiological index factors, psychological condition factors and illness duration factors were selected as features to construct a long short-term memory network model;

[0023] Use the training set data to train the long short-term memory network model, use the validation set to monitor the performance of the model, use the test set to evaluate the accuracy of the model for the patient's current treatment plan, adjust the model parameters based on the evaluation results, and repeat training and evaluation until the model can accurately judge the patient's condition and provide a treatment plan.

[0024] Preferably, the long short-term memory network model structure is:

[0025] Input layer, which accepts preprocessed time series data as input;

[0026] LSTM layer, which captures long-term dependencies in the data through multiple layers of LSTM units;

[0027] Fully connected layer, mapping the output of the LSTM layer to the treatment plan;

[0028] The output layer outputs a preliminary treatment plan based on the model's predictions.

[0029] Preferably, the personalized medical decision-making method includes:

[0030] A patient information input module, which is used to collect and obtain the patient's medical data and pre-process the medical data;

[0031] A patient health comprehensive assessment module, the patient health comprehensive assessment module is electrically connected to the patient information input module, and the patient health comprehensive assessment module calculates the patient's health comprehensive assessment score based on the pre-processed medical data;

[0032] The medical decision-making module is electrically connected to the patient information input module and the patient health comprehensive assessment module. The medical decision-making module outputs a treatment plan based on the preprocessed medical data and comprehensive health assessment points, monitors the patient's condition in real time, analyzes the patient's treatment effect and predicts the trend of treatment results, and adjusts the treatment plan based on the predicted treatment results.

[0033] Preferably, the patient information input module includes:

[0034] A data acquisition unit, used for collecting and acquiring medical data of patients;

[0035] The data processing unit is used to pre-process the collected patient data.

[0036] Preferably, the medical decision-making module includes:

[0037] A preliminary treatment plan output unit outputs a preliminary treatment plan based on pre-processed medical data and comprehensive health assessment scores;

[0038] Patient real-time monitoring unit, used to monitor patients in real time and obtain their treatment response and health status;

[0039] The treatment plan adjustment unit is used to adjust the treatment plan according to the patient's real-time health status assessment score.

[0040] Preferably, the medical decision-making module will establish a patient treatment file based on the patient's information, recording the patient's entire process data from initial treatment to rehabilitation, including each adjustment of the treatment plan, treatment response, health monitoring data, and the final treatment effect evaluation.

[0041] Preferably, the personalized medical decision-making method includes: when the patient's health status assessment score drops below a preset threshold, an early warning mechanism is automatically triggered to remind medical personnel to adjust the treatment plan or take emergency medical measures in a timely manner.

[0042] Preferably, the personalized medical decision-making method includes: when the medical decision-making module outputs a preliminary treatment plan, it will output a main plan and alternative plans, and allow patients to provide feedback on treatment effects and adverse reactions during the treatment process, and automatically adjust the model treatment plan based on the patient's feedback.

[0043] The beneficial effects of the present invention are: by collecting comprehensive medical data of patients and comprehensively evaluating the health status of patients based on these data, the patient's condition can be more accurately grasped, and a more accurate treatment plan can be formulated, which fully considers the individual differences of patients, including age, physiological indicators, psychological conditions and duration of illness, and calculates the comprehensive evaluation score of patients, and formulates personalized treatment plans accordingly. This personalized medical decision-making method can better meet the actual needs of patients and improve the treatment effect. By real-time monitoring of the patient's treatment response and health status, and regularly using the medical decision-making module to analyze the current treatment effect and predict the treatment results, once the predicted results are found to be inconsistent with the initial treatment plan, the treatment plan will be adjusted in time. This dynamic adjustment mechanism can ensure the timeliness and effectiveness of the treatment plan and improve the patient's recovery speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A flowchart of the steps of this personalized medical decision-making method;

[0045] Figure 2 This is the structure diagram of the personalized medical decision-making module. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0047] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0048] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0049] The embodiment of the present application provides a personalized medical decision-making method based on artificial intelligence, and the personalized medical decision-making method includes the following steps:

[0050] S1. Enter the patient's medical data in the patient information input module, including historical cases, examination reports, genome sequences, and real-time health monitoring data, to provide a solid foundation for subsequent health assessment and medical decision-making;

[0051] S2. Based on the patient information, the patient health comprehensive assessment module assesses the patient's health status. The assessment results reflect factors such as the severity of the patient's disease, the patient's physiological condition, and potential health risks. Based on the assessment results, the medical decision-making module outputs a preliminary treatment plan that takes into account the individual differences and specific needs of the patient;

[0052] S3. Real-time monitoring of the patient's treatment response and health status, including drug response and changes in physiological indicators. Regular use of the medical decision-making module to analyze the current patient's treatment effect, evaluate the effectiveness of the current treatment plan, and predict the patient's treatment outcome in order to adjust the strategy in a timely manner.

[0053] S4. Compare the predicted treatment results with the treatment results of the preliminary treatment plan. If the predicted results are consistent with the treatment results of the corresponding time period of the preliminary treatment plan, indicating that the current treatment plan is effective, continue to implement the original treatment plan;

[0054] S5. If the predicted result is inconsistent with the treatment result of the corresponding time period of the preliminary treatment plan, indicating that the patient needs a different treatment path, the treatment plan is adjusted according to the patient's real-time health status assessment score, including changing the drug dosage, replacing the drug, adding or reducing certain treatment procedures, etc., to ensure that the treatment plan is more in line with the patient's current condition;

[0055] S6. Follow steps S3-S5 until the patient recovers, and continuously monitor, analyze, predict and adjust the treatment plan as appropriate until the patient reaches the recovery standard.

[0056] Furthermore, the method for evaluating the patient's health status in step S2 is:

[0057] Based on the collected medical data of patients, age data, physiological index data, psychological condition data and illness duration data are extracted;

[0058] Age data: The patient’s age is an important factor in assessing their physiological function, susceptibility to disease, and recovery ability;

[0059] Physiological indicator data: real-time or recent physiological monitoring data reflects the patient's current health status;

[0060] Psychological status data: information on the patient's psychological status obtained through questionnaires, psychological tests, etc., such as anxiety and depression levels, which have a significant impact on treatment compliance and recovery speed;

[0061] Disease duration data: The duration of the disease provides clues to the rate of disease progression and patient tolerance, which is critical for developing long-term treatment plans;

[0062] Based on the extracted data, the patient's comprehensive assessment score was calculated;

[0063] The calculation formula for the patient's comprehensive assessment score is:

[0064]

[0065] In the formula, S represents the comprehensive assessment score of the patient, n represents the number of influencing factors, and Q i represents the i-th influencing factor, W i represents the weight of the i-th influencing factor in turn;

[0066] The comprehensive assessment score directly reflects the patient's overall health status and the difficulty of treatment. A high score means that the patient is in good health, the treatment is less difficult, and the expected recovery is faster; while a low score indicates that the patient is in poor health and requires longer treatment and closer attention.

[0067] Based on the comprehensive assessment score, the medical decision-making module will formulate a corresponding treatment schedule. For patients with high comprehensive assessment scores, the system recommends a shorter treatment cycle because such patients tend to recover faster and respond more positively to treatment. On the contrary, for patients with low comprehensive assessment scores, the system tends to formulate more detailed and long-term treatment plans to ensure that patients receive adequate attention and effective treatment.

[0068] Furthermore, the medical decision-making module constructs a model based on a long short-term memory network, and the method of constructing the model is:

[0069] According to the type of disease, we collect historical medical data from cured patients of different ages and at different times. These data are the basis for model learning and contain key information such as the development process of the disease, the patient's physiological reactions, psychological changes, and treatment effects.

[0070] Preprocess the acquired historical medical data, remove duplicates, missing values, and outliers to ensure data integrity and consistency, convert data of different dimensions into the same dimension, eliminate the impact of dimension differences on model training, help the model converge faster and find the optimal solution, and convert time series data into sequence data to meet the LSTM model's processing requirements for sequence data. Divide the data into training set, validation set, and test set. The ratio of training set, validation set, and test set is 70%:15%:15%. The training set is used for the learning process of the model, the validation set is used to monitor the performance of the model and prevent overfitting, and the test set is used to evaluate the model's generalization ability for unknown data.

[0071] Based on the preprocessed sequence data, physiological index factors, psychological condition factors and illness duration factors are selected as features to construct a long short-term memory network model. The long short-term memory network can effectively handle long-distance dependency problems and is suitable for analyzing and predicting time series data. These features can fully reflect the patient's health status and treatment needs, providing rich information input for the model.

[0072] Use the training set data to train the long short-term memory network model, use the validation set to monitor the performance of the model, use the test set to evaluate the accuracy of the model for the patient's current treatment plan, adjust the model parameters based on the evaluation results, and repeat training and evaluation until the model can accurately judge the patient's condition and provide a treatment plan.

[0073] Furthermore, the long short-term memory network model structure is:

[0074] The input layer accepts preprocessed time series data as input, including the patient's historical medical records, vital signs monitoring data, and other relevant clinical information;

[0075] LSTM layer, which captures long-term dependencies in data through multi-layer LSTM units. The LSTM layer is composed of multiple stacked LSTM units. Each LSTM unit controls the transmission of information through three "gate" structures. The multi-layer LSTM structure can capture more complex long-term dependencies in data;

[0076] Fully connected layers map the output of the LSTM layer to treatment plans. The output usually contains high-level feature representations of the data.

[0077] Output layer,Based on the output of the fully connected layer, the output layer generates a preliminary,treatment plan.

[0078] Further, personalized medical decision-making methods include:

[0079] Patient information input module, which is used to collect and obtain the patient's medical data and pre-process the medical data. This module is not limited to collecting medical records in the hospital, but also includes health data from wearable devices, remote monitoring systems, gene sequencing platforms, and self-reported health data from patients. The data range is wide, including but not limited to medical history, laboratory test results, imaging examinations, vital signs monitoring, daily activity level, sleep quality, eating habits, family medical history and genetic information, etc.;

[0080] A patient health comprehensive assessment module, which is electrically connected to the patient information input module, and which calculates the patient's comprehensive health assessment score based on the preprocessed medical data, and integrates the assessment results of different dimensions into a comprehensive health assessment score, which reflects the patient's overall health status and existing risks;

[0081] The medical decision-making module is electrically connected to the patient information input module and the patient comprehensive health assessment module. The medical decision-making module outputs a treatment plan based on the preprocessed medical data and comprehensive health assessment points, including multiple options such as drug therapy, surgical treatment, physical therapy, psychotherapy, nutritional advice, and lifestyle adjustments. It integrates a real-time monitoring function to monitor the patient's condition in real time, continuously track the patient's vital signs, symptom changes, and treatment compliance, analyze the patient's treatment effect and predict the trend of treatment results, and adjust the treatment plan based on the predicted treatment results.

[0082] Furthermore, the patient information input module includes:

[0083] Data acquisition units for collecting and acquiring patients’ medical data, including but not limited to hospital information systems, electronic medical record systems, laboratory information systems, radiology information systems, wearable devices, remote health monitoring systems, patient self-reporting applications or platforms, and gene sequencing companies;

[0084] The data processing unit is used to pre-process the collected patient data. The primary task of the data processing unit is to clean the data to eliminate noise, errors, duplications and irrelevant information in the data. This includes checking the consistency, completeness, accuracy and timeliness of the data, and taking appropriate measures to correct or delete it.

[0085] Furthermore, the medical decision-making module includes:

[0086] The preliminary treatment plan output unit outputs a preliminary treatment plan based on the pre-processed medical data and comprehensive health assessment score. Taking into account the uniqueness and complexity of each patient, the preliminary treatment plan output unit emphasizes personalized customization. It tailors the most suitable treatment plan for the patient based on factors such as the patient's age, gender, genetic background, disease type, severity of the disease, previous treatment experience, and current health status;

[0087] The patient real-time monitoring unit is used to monitor patients in real time, and realize real-time monitoring of patients' vital signs, symptom changes, drug reactions and other dimensions. These monitoring data provide an important basis for timely adjustment of treatment plans, and obtain patients' treatment responses and health conditions. The real-time monitoring data will be integrated into the patient's health records;

[0088] The treatment plan adjustment unit, based on the data provided by the patient's real-time monitoring unit, will conduct a dynamic evaluation and calculate the patient's real-time health status assessment score. This assessment score reflects the changing trend of the patient's current health status and the effectiveness of the treatment, and adjusts the treatment plan. Treatment plan adjustment is an ongoing process. As the patient's treatment deepens and data continues to accumulate, the treatment plan adjustment unit will continuously optimize the treatment plan to ensure that the patient obtains the best treatment effect.

[0089] Furthermore, the medical decision-making module will establish a patient treatment file based on the patient information, recording the entire process data of the patient from initial treatment to rehabilitation, including each adjustment of the treatment plan, treatment response, health monitoring data and the final treatment effect evaluation. The treatment file integrates multi-source data to provide the medical team with comprehensive patient information, support the evaluation of treatment effects and the optimization of medical decisions. At the same time, the security and privacy protection of the file are strictly guaranteed to ensure that the data is not accessed without authorization, thereby improving the personalization and efficiency of medical services and providing valuable information for medical research and clinical practice.

[0090] Furthermore, the personalized medical decision-making method includes: when the patient's health status assessment score drops below the preset threshold, the early warning mechanism is automatically triggered to remind medical personnel to adjust the treatment plan or take emergency medical measures in time. This process includes real-time monitoring, evaluation and analysis, threshold comparison, automatic early warning and notification response, etc., which aims to ensure that patients receive timely and effective treatment and improve the overall quality and efficiency of medical services.

[0091] Furthermore, the personalized medical decision-making method includes: the medical decision-making module no longer only provides a single treatment plan, but will comprehensively consider the patient's specific situation, disease characteristics, treatment goals and the limitations of existing medical resources to generate a main plan and multiple alternative plans. In order to better understand the patient's acceptance of the treatment plan, the treatment effect and possible adverse reactions, the personalized medical decision-making method has established a complete feedback mechanism, allowing patients to provide feedback on the treatment effect and adverse reactions during the treatment process, and automatically adjust the model treatment plan according to the patient's feedback.

[0092] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0093] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0094] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A personalized medical decision-making method based on artificial intelligence, characterized in that: The personalized medical decision-making approach includes the following steps: S1. Input the patient's medical data in the patient information input module, including historical cases, examination reports, genome sequences, and real-time health monitoring data; S2. Based on the patient information, the patient health comprehensive assessment module assesses the patient's health status. Based on the assessment results, the medical decision-making module outputs a preliminary treatment plan. S3. Monitor the patient's treatment response and health status in real time, regularly use the medical decision-making module to analyze the current patient's treatment effect, and predict the patient's treatment outcome; S4, comparing the predicted treatment results with the treatment results of the preliminary treatment plan. If the predicted results are consistent with the treatment results of the corresponding time period of the preliminary treatment plan, continue to implement the original treatment plan; S5. If the predicted result is inconsistent with the treatment result of the corresponding time period of the preliminary treatment plan, the treatment plan is adjusted according to the patient's real-time health status assessment score; S6. Follow steps S3-S5 until the patient recovers.

2. The personalized medical decision-making method based on artificial intelligence according to claim 1, characterized in that: The method for evaluating the patient's health status in step S2 is: Based on the collected medical data of patients, physiological index data, psychological condition data and illness duration data are extracted; Based on the extracted data, the patient's comprehensive assessment score was calculated; The calculation formula for the patient's comprehensive assessment score is: In the formula, S represents the comprehensive assessment score of the patient, n represents the number of influencing factors, and Q i represents the i-th influencing factor, W i represents the weight of the i-th influencing factor in turn.

3. The personalized medical decision-making method based on artificial intelligence according to claim 1, characterized in that: The medical decision-making module builds a model based on the long short-term memory network, and the method of building the model is: According to the type of disease, collect historical medical data of cured patients of different age groups and different periods; Preprocess the acquired historical medical data to remove duplicates, missing values, and outliers, convert data of different dimensions into the same dimension, convert time series data into sequence data, and divide the sequence data into a training set, a validation set, and a test set, with the ratio of the training set, validation set, and test set being 70%:15%:15%; Based on the preprocessed sequence data, physiological index factors, psychological condition factors and illness duration factors were selected as features to construct a long short-term memory network model; Use the training set data to train the long short-term memory network model, use the validation set to monitor the performance of the model, use the test set to evaluate the accuracy of the model for the patient's current treatment plan, adjust the model parameters based on the evaluation results, and repeat training and evaluation until the model can accurately judge the patient's condition and provide a treatment plan.

4. The personalized medical decision-making method based on artificial intelligence according to claim 3, characterized in that: The long short-term memory network model structure is: Input layer, which accepts preprocessed time series data as input; LSTM layer, which captures long-term dependencies in the data through multiple layers of LSTM units; Fully connected layer, mapping the output of the LSTM layer to the treatment plan; The output layer outputs a preliminary treatment plan based on the model's predictions.

5. The personalized medical decision-making method based on artificial intelligence according to claim 1, characterized in that: Personalized medical decision-making approaches include: A patient information input module, which is used to collect and obtain the patient's medical data and pre-process the medical data; A patient health comprehensive assessment module, the patient health comprehensive assessment module is electrically connected to the patient information input module, and the patient health comprehensive assessment module calculates the patient's health comprehensive assessment score based on the pre-processed medical data; The medical decision-making module is electrically connected to the patient information input module and the patient health comprehensive assessment module. The medical decision-making module outputs a treatment plan based on the preprocessed medical data and comprehensive health assessment points, monitors the patient's condition in real time, analyzes the patient's treatment effect and predicts the trend of treatment results, and adjusts the treatment plan based on the predicted treatment results.

6. The personalized medical decision-making method based on artificial intelligence according to claim 1, characterized in that: The patient information input module includes: A data acquisition unit, used for collecting and acquiring medical data of patients; The data processing unit is used to pre-process the collected patient data.

7. The personalized medical decision-making method based on artificial intelligence according to claim 1, characterized in that: The medical decision-making module includes: A preliminary treatment plan output unit outputs a preliminary treatment plan based on pre-processed medical data and comprehensive health assessment scores; Patient real-time monitoring unit, used to monitor patients in real time and obtain their treatment response and health status; The treatment plan adjustment unit is used to adjust the treatment plan according to the patient's real-time health status assessment score.

8. The personalized medical decision-making method based on artificial intelligence according to claim 1, characterized in that: The medical decision-making module will establish a patient treatment file based on patient information, recording the entire process data of the patient from initial treatment to recovery, including each adjustment of the treatment plan, treatment response, health monitoring data and the final treatment effect evaluation.

9. The personalized medical decision-making method based on artificial intelligence according to claim 1, characterized in that: Personalized medical decision-making methods include: when the patient's health status assessment score drops below a preset threshold, an early warning mechanism is automatically triggered to remind medical personnel to adjust the treatment plan or take emergency medical measures in a timely manner.

10. The personalized medical decision-making method based on artificial intelligence according to claim 1, characterized in that: The personalized medical decision-making method includes: when the medical decision-making module outputs a preliminary treatment plan, it will output the main plan and alternative plans, and allow patients to provide feedback on the treatment effects and adverse reactions during the treatment process, and automatically adjust the model treatment plan based on the patient's feedback.

Images