A method and system for auxiliary diagnosis and treatment of sarcopenia

Abstract

The present invention provides a sarcopenia auxiliary diagnosis and treatment method and system, which relates to the field of medical data processing, wherein the method comprises: determining multiple target sarcopenia diagnostic exercises for the patient to be diagnosed based on basic information of the patient to be diagnosed and basic information, exercise test information and sarcopenia status of multiple sample sarcopenia patients; obtaining the limb skeletal muscle content of the patient to be diagnosed according to the limb skeletal muscle content of multiple sample sarcopenia patients; determining the sarcopenia status of the patient to be diagnosed according to the basal metabolic rate, grip strength, limb skeletal muscle content of the patient to be diagnosed and test data of each target sarcopenia diagnostic exercise; determining a recommended auxiliary treatment plan for the patient to be diagnosed according to a disease and exercise association map, a basal metabolic rate and nutrition association map, a psychological intervention knowledge map, the basic information of the patient to be diagnosed, diet and exercise habits, sarcopenia status and psychological status test data, and having the advantage of realizing intelligent auxiliary diagnosis and treatment of sarcopenia.

Description

Technical Field

[0001] The present invention relates to the field of medical data processing, and in particular to a sarcopenia auxiliary diagnosis and treatment method and system. Background Art

[0002] Sarcopenia refers to a syndrome caused by the continuous loss of skeletal muscle mass, strength and function. Skeletal muscle is the driving force of the human body's motor system. Muscle aging and atrophy are important signs of human aging, and are very likely to cause problems such as fractures and joint injuries. Elderly people with sarcopenia have difficulty standing, walk slowly, and are prone to falling and fractures. Sarcopenia can also affect organ function and may cause heart and lung failure, or even death.

[0003] Sarcopenia screening requires the measurement of muscle strength, intensity, mobility and muscle mass. Mobility measurement, walking speed, sit-to-stand time and balance test are comprehensive manifestations of mobility, muscle strength, motor control ability, etc. At present, when hospitals conduct screening and diagnosis of sarcopenia, the screening work is often dispersed. Not only does the screening take a long time, but the accuracy of the test data is not easy to guarantee. In addition, in the prior art, the treatment prescription for sarcopenia is usually formulated by medical professionals based on the patient's health status, age, exercise history and personal goals, which is inefficient.

[0004] Therefore, there is a need to provide a sarcopenia auxiliary diagnosis and treatment method and system to achieve intelligent auxiliary diagnosis and treatment of sarcopenia. Summary of the invention

[0005] The present invention provides a sarcopenia auxiliary diagnosis and treatment method, comprising: obtaining basic information, exercise test information, sarcopenia status and limb skeletal muscle content of multiple sample sarcopenia patients, wherein the exercise test information includes test data of the sample sarcopenia patients in multiple sarcopenia diagnostic exercises; establishing a disease and exercise association map, a basal metabolic rate and nutrition association map and a psychological intervention knowledge map; obtaining basic information of the patient to be diagnosed; based on the basic information of the patient to be diagnosed and the basic information, exercise test information and sarcopenia status of the multiple sample sarcopenia patients, determining multiple target sarcopenia diagnostic exercises for the patient to be diagnosed; obtaining test data of the patient to be diagnosed in each of the target sarcopenia diagnostic exercises; and determining the target sarcopenia diagnostic exercises of the patient to be diagnosed according to the multiple sample sarcopenia patients. limb skeletal muscle content, determine the skeletal muscle mass test plan for the patient to be diagnosed; according to the skeletal muscle mass test plan for the patient to be diagnosed, obtain the limb skeletal muscle content of the patient to be diagnosed; obtain the basal metabolic rate and grip strength of the patient to be diagnosed; determine the sarcopenia status of the patient to be diagnosed according to the basal metabolic rate, grip strength, limb skeletal muscle content of the patient to be diagnosed and the test data of each target sarcopenia diagnostic exercise; obtain the psychological state test data of the patient to be diagnosed; determine the recommended auxiliary treatment plan for the patient to be diagnosed according to the disease and exercise association map, the basal metabolic rate and nutrition association map, the psychological intervention knowledge map, the basic information of the patient to be diagnosed, the sarcopenia status and the psychological state test data.

[0006] Furthermore, based on the basic information of the patient to be diagnosed and the basic information, exercise test information and sarcopenia status of the multiple sample sarcopenia patients, multiple target sarcopenia diagnostic exercises for the patient to be diagnosed are determined, including: calculating the basic information similarity of the basic information of any two of the sample sarcopenia patients; clustering the multiple sample sarcopenia patients according to the basic information similarity of the basic information of any two of the sample sarcopenia patients to determine multiple patient clusters; for each of the patient clusters, determining the correlation coefficient between each sarcopenia diagnostic exercise and the patient cluster according to the exercise test information and sarcopenia status of the multiple sample sarcopenia patients included in the patient cluster, and determining the multiple sarcopenia diagnostic exercises corresponding to the patient cluster according to the correlation coefficient between each sarcopenia diagnostic exercise and the patient cluster; determining a patient cluster matching the patient to be diagnosed from the multiple patient clusters according to the basic information of the patient to be diagnosed; and determining the multiple target sarcopenia diagnostic exercises for the patient to be diagnosed according to the multiple sarcopenia diagnostic exercises corresponding to the patient cluster matching the patient to be diagnosed.

[0007] Furthermore, the test data of the patient to be diagnosed during each of the target sarcopenia diagnostic exercises is obtained, including: for any one of the patient clusters, when the multiple sarcopenia diagnostic exercises corresponding to the patient cluster include sit-up exercises, obtaining the motion state data of the multiple sample sarcopenia patients included in the patient cluster during the sit-up exercises, wherein the motion state data includes vibration data of multiple sit-up exercise test positions, determining the correlation coefficient of each sit-up exercise test position with the patient cluster according to the motion state data and sarcopenia status of the multiple sample sarcopenia patients included in the patient cluster during the sit-up exercises, and determining the sit-up exercise test position corresponding to the patient cluster according to the correlation coefficient between each sit-up exercise test position and the patient cluster; when the multiple target sarcopenia diagnostic exercises of the patient to be diagnosed include sit-up exercises, obtaining the motion state data of the patient to be diagnosed during the sit-up exercise according to the sit-up exercise test position corresponding to the patient cluster matched with the patient to be diagnosed.

[0008] Furthermore, the test data of the patient to be diagnosed in each of the target sarcopenia diagnostic exercises is obtained, including: for any one of the patient clusters, when the multiple sarcopenia diagnostic exercises corresponding to the patient cluster include a walking speed test, the walking speed test data of the multiple sample sarcopenia patients included in the patient cluster at multiple test distances are obtained, and the correlation coefficient of each of the test distances with the patient cluster is calculated according to the walking speed test data and sarcopenia status of the multiple sample sarcopenia patients included in the patient cluster at multiple test distances, and the test distance corresponding to the patient cluster is determined according to the correlation coefficient of each of the test distances with the patient cluster; when the multiple target sarcopenia diagnostic exercises of the patient to be diagnosed include a walking speed test, the walking speed test data of the patient to be diagnosed is obtained according to the test distance corresponding to the patient cluster matched with the patient to be diagnosed.

[0009] Furthermore, based on the limb skeletal muscle content of the multiple sample sarcopenia patients, a skeletal muscle mass test scheme for the patient to be diagnosed is determined, including: for each of the patient clusters, obtaining ultrasonic test data of the multiple sample sarcopenia patients included in the patient cluster at multiple ultrasonic test positions, calculating the correlation coefficient between each of the ultrasonic test positions and the patient cluster based on the ultrasonic test data and sarcopenia status of the multiple sample sarcopenia patients included in the patient cluster at multiple ultrasonic test positions, and determining the ultrasonic test position corresponding to the patient cluster based on the correlation coefficient between each of the ultrasonic test positions and the patient cluster; determining the skeletal muscle mass test scheme for the patient to be diagnosed based on the ultrasonic test position corresponding to the patient cluster matched with the patient to be diagnosed.

[0010] Furthermore, the sarcopenia status of the patient to be diagnosed is determined based on the basal metabolic rate, grip strength, skeletal muscle content of the limbs and the test data of each target sarcopenia diagnostic exercise of the patient to be diagnosed, including: for each patient cluster, establishing a sarcopenia status judgment standard corresponding to the patient cluster; extracting the vibration characteristics of the sit-up exercise test position of the patient to be diagnosed based on the exercise state data of the patient to be diagnosed during the sit-up exercise; determining the sarcopenia status of the patient to be diagnosed based on the basal metabolic rate, grip strength, skeletal muscle content of the limbs of the patient to be diagnosed, the vibration characteristics of the sit-up exercise test position of the patient to be diagnosed, the walking speed test data and the sarcopenia status judgment standard corresponding to the patient cluster matched with the patient to be diagnosed.

[0011] Furthermore, based on the motion state data of the patient to be diagnosed during the sit-up exercise, the vibration characteristics of the sit-up exercise test position of the patient to be diagnosed are extracted, including: after performing variational modal decomposition on the motion state data of the patient to be diagnosed during the sit-up exercise, the vibration characteristics of the sit-up exercise test position of the patient to be diagnosed are extracted.

[0012] Furthermore, obtaining psychological state test data of the patient to be diagnosed includes: obtaining conversation data between a psychological test dialogue robot and the patient to be diagnosed; and extracting psychological state keywords and emotion types from the conversation data.

[0013] Furthermore, based on the disease and exercise association map, the basal metabolic rate and nutrition association map, the psychological intervention knowledge map, the basic information of the patient to be diagnosed, the sarcopenia status and the psychological state test data, the recommended auxiliary treatment plan for the patient to be diagnosed is determined, including: based on the basic information, sarcopenia status and the psychological state test data of the patient to be diagnosed, determining similar sample sarcopenia patients from the patient cluster matching the patient to be diagnosed; determining the recommended auxiliary treatment plan for the patient to be diagnosed through a plan generation model based on the auxiliary treatment plans of similar sample sarcopenia patients, the disease and exercise association map, the basal metabolic rate and nutrition association map, the psychological intervention knowledge map, the basic information of the patient to be diagnosed, the sarcopenia status and the psychological state test data.

[0014] The present invention provides a sarcopenia auxiliary diagnosis and treatment system, which applies the above-mentioned sarcopenia auxiliary diagnosis and treatment method, including: an information acquisition module, used to obtain basic information, exercise test information, sarcopenia status and limb skeletal muscle content of multiple sample sarcopenia patients, wherein the exercise test information includes test data of the sample sarcopenia patients in multiple sarcopenia diagnostic exercises; a map establishment module, used to establish a disease and exercise association map, a basal metabolic rate and nutrition association map and a psychological intervention knowledge map; the information acquisition module is also used to obtain the basic information of the patient to be diagnosed; an exercise determination module, used to determine multiple target sarcopenia diagnostic exercises for the patient to be diagnosed based on the basic information of the patient to be diagnosed and the basic information and exercise test information of the multiple sample sarcopenia patients; the information acquisition module is also used to obtain the test data of the patient to be diagnosed in each of the target sarcopenia diagnostic exercises; a scheme determination module, used to determine the target sarcopenia diagnostic exercises of the patient to be diagnosed according to the The skeletal muscle content of the limbs of multiple sample sarcopenia patients is used to determine the skeletal muscle mass test plan for the patient to be diagnosed; the information acquisition module is also used to obtain the skeletal muscle content of the limbs of the patient to be diagnosed according to the skeletal muscle mass test plan for the patient to be diagnosed; the information acquisition module is also used to obtain the basal metabolic rate of the patient to be diagnosed; the state determination module is used to determine the sarcopenia state of the patient to be diagnosed according to the basal metabolic rate, skeletal muscle content of the limbs of the patient to be diagnosed and the test data of each target sarcopenia diagnostic exercise; the information acquisition module is also used to obtain the psychological state test data of the patient to be diagnosed; the auxiliary treatment module is used to determine the recommended auxiliary treatment plan for the patient to be diagnosed according to the disease and exercise association map, the basal metabolic rate and nutrition association map, the psychological intervention knowledge map, the basic information of the patient to be diagnosed, the diet and exercise habits, the sarcopenia state and the psychological state test data.

[0015] Compared with the prior art, the sarcopenia auxiliary diagnosis and treatment method and system provided by the present invention have at least the following beneficial effects:

[0016] 1. By collecting the basic information, exercise test information, sarcopenia status and skeletal muscle content of multiple sample sarcopenia patients, a comprehensive database can be constructed. This helps to evaluate the condition of the patient to be diagnosed from multiple dimensions and improve the accuracy of diagnosis. Based on the basic information of the patient to be diagnosed and the comparison with multiple sample patients, the target sarcopenia diagnostic exercise that is more suitable for the individual can be determined, so as to conduct more targeted tests and further ensure the personalization of diagnosis. Through the disease-exercise association map, the basal metabolic rate-nutrition association map and the psychological intervention knowledge map, a more scientific and comprehensive auxiliary treatment plan can be provided for the patient to be diagnosed. These maps are constructed based on a large amount of sample data and can reflect the relationship between the disease and various factors, thereby guiding the formulation of treatment plans. Personalized treatment plans can more effectively target the specific conditions of patients, thereby improving the treatment effect. For example, the patient's exercise ability and preferences can be determined through exercise test data, and a suitable exercise plan can be formulated for them; the patient can be guided to eat a reasonable diet and supplement the required nutrients through the nutrition map. In addition to physical diagnosis and treatment, this method also pays attention to the patient's psychological state. By obtaining psychological state test data, the patient's psychological problems can be discovered in time, and psychological intervention and support can be provided. Personalized treatment plans and psychological support can enhance patients' confidence in treatment and make them more actively cooperate with treatment, thereby improving treatment outcomes and speeding up recovery.

[0017] 2. By calculating the similarity of basic information and matching the patients to be diagnosed with sample sarcopenia patients, the patient cluster that is most similar to the patients to be diagnosed can be found. This helps to provide more personalized diagnostic exercise recommendations for patients to be diagnosed, because similar patients tend to have similar responses to similar diagnostic exercises. Relying on a large amount of sample data, the association between diagnostic exercises and patient status is determined through statistical analysis. This improves the objectivity of decision-making and reduces errors caused by subjective judgment. By determining multiple sarcopenia diagnostic exercises corresponding to each patient cluster, a more targeted sarcopenia diagnostic solution can be provided for patients to be diagnosed. These exercises are verified and highly correlated with the sarcopenia status of specific patient clusters, and are therefore more likely to produce accurate sarcopenia diagnostic data.

[0018] 3. By analyzing the motion state data (such as vibration data and gait data) of sample sarcopenia patients in sit-up exercise and gait speed test, and correlating them with the sarcopenia status of the patients, it is possible to accurately determine which test positions or test distances are most sensitive and effective for a specific patient cluster. This enables the patient to be diagnosed to choose the most appropriate test position and distance for their personal situation when undergoing the test, thereby improving the accuracy of the diagnosis. By analyzing the ultrasonic test data of sample sarcopenia patients at multiple ultrasonic test positions, and correlating them with the sarcopenia status of the patients, it is possible to determine which ultrasonic test positions are most accurate for a specific patient cluster. This enables the patient to be diagnosed to choose the most appropriate test position for their personal situation when undergoing skeletal muscle mass testing, thereby obtaining more accurate test results. By determining the sit-up exercise test position, gait speed test distance, and ultrasonic test position corresponding to the patient cluster, comprehensive and indiscriminate testing of all patients can be avoided. This not only reduces the testing burden on patients, but also saves medical resources and improves testing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0020] Figure 1 It is a flowchart of a sarcopenia auxiliary diagnosis and treatment method according to some embodiments of this specification;

[0021] Figure 2 This is a module schematic diagram of a sarcopenia auxiliary diagnosis and treatment system shown in some embodiments of this specification. DETAILED DESCRIPTION

[0022] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0023] Figure 1 is a flow chart of a sarcopenia auxiliary diagnosis and treatment method according to some embodiments of this specification, such as Figure 1 As shown, a method for auxiliary diagnosis and treatment of sarcopenia may include the following steps.

[0024] Step 111, obtaining basic information, exercise test information, sarcopenia status and limb skeletal muscle content of multiple sample sarcopenia patients.

[0025] Among them, the exercise test information includes test data of sample sarcopenia patients in various sarcopenia diagnostic exercises.

[0026] Basic information may include the patient's age, gender, weight, height, previous medical history, previous surgical history, previous medication history, nutritional status, eating habits and exercise habits, etc. The basic information of multiple samples of sarcopenia patients can be obtained through questionnaire surveys, case data analysis, instrument examinations, etc.

[0027] Multiple sarcopenia diagnostic exercises may include a stand-and-walk test, a multiple sit-up test, standing with feet together, standing with feet forward and backward, standing on one leg, a gait test, etc. Multiple sarcopenia diagnostic exercises may be determined by a machine learning model based on previous diagnosis cases, or may be determined manually (e.g., by multiple experts).

[0028] The skeletal muscle content of the limbs can be obtained through ultrasound technology, and the speed of ultrasound propagation in the bones can be used to evaluate bone density and muscle mass.

[0029] The sarcopenia status can be used to characterize the severity of sarcopenia in a patient. The sarcopenia status can be represented by a numerical value, and the larger the numerical value, the more severe the sarcopenia status. The sarcopenia status can be evaluated by a machine learning model or manually (e.g., multiple experts).

[0030] Step 112, establishing a disease and exercise association map, a basal metabolic rate and nutrition association map, and a psychological intervention knowledge map.

[0031] The disease-exercise association map is a visualization tool used to show the association between different diseases and specific exercises. This map is usually based on scientific research and clinical data, integrating and displaying various diseases with information such as appropriate exercise methods, exercise intensity, and exercise frequency. In the disease-exercise association map, various diseases are used as nodes, and appropriate exercise methods are used as lines or arrows connecting these nodes. For example, for cardiovascular diseases, the disease-exercise association map records that aerobic exercise (such as walking, jogging, swimming, etc.) has a positive preventive and therapeutic effect on them; for skeletal muscle system diseases such as osteoporosis, the disease-exercise association map records that resistance training and balance training have a positive preventive and therapeutic effect on them. Through the disease-exercise association map, you can intuitively understand the association between different diseases and exercise, so as to choose the appropriate exercise method according to the patient's sarcopenia status.

[0032] The basal metabolic rate and nutrition association map is the basis for the total recommended intake, dietary habits and recommended protein intake calculated based on the basal metabolic rate. The basal metabolic rate and nutrition association map usually includes the following key parts: Basal metabolic rate calculation: The individual's basal metabolic rate is obtained through the individual's basic information (such as age, height, weight, etc.) and the corresponding calculation formula. Total recommended intake: Based on the basal metabolic rate, combined with the individual's activity level and health status, the daily energy intake required is calculated. This total amount is usually 1.2 to 1.5 times the basal metabolic rate to meet the needs of daily activities and light exercise. Dietary habit guidance: Provide personalized dietary habit suggestions based on the individual's basal metabolic rate and the total recommended intake. This includes the type of food, intake, and matching ratio of each meal to ensure nutritional balance and energy balance. Recommended protein intake: Protein is an important nutrient for maintaining muscle mass and promoting metabolism. Calculate the daily protein intake required based on the individual's basal metabolic rate and weight. This intake is usually recommended to be 0.8 to 1.2 grams per kilogram of body weight.

[0033] The psychological intervention knowledge graph is a visualization tool that displays the relationship between psychological intervention methods, techniques, and application fields. It integrates and displays various psychological intervention methods (such as cognitive behavioral therapy, psychodynamic therapy, family therapy, etc.) and their application fields (such as anxiety, depression, sleep disorders, etc.) based on research results and practical experience in the fields of psychology, psychological counseling, and psychotherapy. In the psychological intervention knowledge graph, various psychological intervention methods are used as nodes, and their application fields and effects are used as lines or arrows connecting these nodes. Psychological intervention method nodes represent various different types of psychological intervention methods, such as cognitive behavioral therapy, psychodynamic therapy, family therapy, art therapy, etc. Application field nodes represent different fields where psychological intervention methods are applicable, such as anxiety, depression, sleep disorders, interpersonal relationship problems, etc. Relationship lines connect psychological intervention methods and application fields, indicating the matching relationship between them.

[0034] Step 113, obtaining basic information of the patient to be diagnosed.

[0035] Step 114, based on the basic information of the patient to be diagnosed and the basic information, exercise test information and sarcopenia status of multiple sample sarcopenia patients, determine multiple target sarcopenia diagnostic exercises for the patient to be diagnosed.

[0036] Specifically include:

[0037] Calculate the basic information similarity of any two sample sarcopenia patients;

[0038] According to the similarity of basic information of any two sample sarcopenia patients, multiple sample sarcopenia patients are clustered to determine multiple patient clusters;

[0039] For each patient cluster, according to the exercise test information and sarcopenia status of multiple sample sarcopenia patients included in the patient cluster, determine the correlation coefficient between each sarcopenia diagnostic exercise and the patient cluster, and according to the correlation coefficient between each sarcopenia diagnostic exercise and the patient cluster, determine multiple sarcopenia diagnostic exercises corresponding to the patient cluster;

[0040] According to the basic information of the patient to be diagnosed, a patient cluster matching the patient to be diagnosed is determined from multiple patient clusters;

[0041] According to the multiple sarcopenia diagnostic motions corresponding to the patient cluster matching the patient to be diagnosed, multiple target sarcopenia diagnostic motions of the patient to be diagnosed are determined.

[0042] Specifically, the basic information similarity of any two sample sarcopenia patients can be calculated according to the following process:

[0043] S11. Process the missing or abnormal data in the basic information of the two samples of sarcopenia patients, for example, fill in the average value, delete or infer based on the context;

[0044] S12. Standardize data of different dimensions (e.g., age, weight, height) to make them comparable, for example, by converting data of different dimensions into Z scores (i.e., standard scores) or performing normalization;

[0045] S13. For non-numeric data (e.g., gender, medical history, etc.), appropriate coding is required, such as encoding gender as 0 (female) and 1 (male), or encoding medical history as a binary vector, for example, if the disease is present, the corresponding position is 1, and if not, it is 0;

[0046] S14. Calculation of single feature similarity: For numerical data (e.g., age, weight, height), the similarity is calculated using methods such as Euclidean distance or cosine similarity. Euclidean distance and Manhattan distance represent the straight-line distance between two points in n-dimensional space, respectively, while cosine similarity measures the degree of similarity between two vectors in direction. For categorical data (e.g., gender, past medical history, etc.), the similarity is calculated using methods such as Jaccard similarity coefficient or Hamming distance. Jaccard similarity coefficient measures the degree of similarity between two sets, while Hamming distance represents the number of different characters in corresponding positions between two strings of equal length.

[0047] S15. Assign a weight to each feature. The size of the weight can be determined based on the importance of the feature to the diagnosis or treatment of sarcopenia. For example, age, gender, and nutritional status may have higher weights, while certain drugs in the past medication history may have less effect on sarcopenia and therefore have lower weights. The total similarity between the two samples is calculated by weighted summation. That is, the similarity of each feature is multiplied by the corresponding weight, and then all weighted similarities are added together to obtain the total similarity.

[0048] A clustering algorithm (for example, a K-means clustering algorithm, a hierarchical clustering algorithm, etc.) can be used to cluster multiple sample sarcopenia patients according to the similarity of basic information of any two sample sarcopenia patients to determine multiple patient clusters.

[0049] The correlation coefficient between the sarcopenia diagnostic exercise and the patient cluster can be calculated according to the following formula:

[0050]

[0051] in, is the correlation coefficient between the i-th sarcopenia diagnostic exercise and the k-th patient cluster, is the test data of the g-th sample sarcopenia patient in the k-th patient cluster for the i-th sarcopenia diagnostic exercise, is the sarcopenia status of the g-th sample sarcopenia patient included in the k-th patient cluster, is the total number of sample sarcopenia patients included in the kth patient cluster.

[0052] The correlation coefficient of the two sarcopenia diagnostic exercises in the patient cluster can be calculated according to the following formula:

[0053]

[0054] in, is the correlation coefficient of the two sarcopenia diagnostic exercises in the kth patient cluster, The test data of the j-th sarcopenia diagnostic exercise for the g-th sample sarcopenia patient included in the k-th patient cluster.

[0055] Multiple sarcopenia diagnostic exercises corresponding to the patient cluster can be determined according to the following process:

[0056] S21, taking a sarcopenia diagnostic motion having a correlation coefficient with a patient cluster greater than a first correlation coefficient threshold as a candidate sarcopenia diagnostic motion;

[0057] S22, determining whether there are at least two candidate sarcopenia diagnostic movements with correlation coefficients greater than a second correlation coefficient threshold in the patient cluster; if not, executing S23; if so, executing S24;

[0058] S23, using the remaining candidate sarcopenia diagnostic motions as multiple sarcopenia diagnostic motions corresponding to the patient cluster;

[0059] S24, determining whether the number of the remaining candidate sarcopenia diagnostic exercises is greater than the number threshold, if not, executing S23, if yes, executing S25;

[0060] S25. For each candidate sarcopenia diagnostic motion, according to the correlation coefficient of any two candidate sarcopenia diagnostic motions in the patient cluster, calculate the deduplication priority value of the candidate sarcopenia diagnostic motion;

[0061] S26. Remove the candidate sarcopenia diagnostic motion with the largest deduplication priority value from the remaining candidate sarcopenia diagnostic motions, and execute S22.

[0062] The deduplication priority value of the candidate sarcopenia diagnostic motion can be calculated according to the following formula:

[0063]

[0064] in, is the deduplication priority value of the h-th candidate sarcopenia diagnostic motion corresponding to the k-th patient cluster, is the total number of candidate sarcopenia diagnostic motions corresponding to the k-th patient cluster, is the correlation coefficient between the h-th candidate sarcopenia diagnostic motion corresponding to the k-th patient cluster and the n-th candidate sarcopenia diagnostic motion in the patient cluster.

[0065] The basic information similarity between the basic information of the patient to be diagnosed and the basic information corresponding to the cluster center of each patient cluster can be calculated, and the patient cluster whose basic information similarity is greater than the basic information similarity threshold is used as the patient cluster matching the patient to be diagnosed. The method of calculating the basic information similarity between the basic information of the patient to be diagnosed and the basic information corresponding to the cluster center of each patient cluster is similar to the method of calculating the basic information similarity of the basic information of two sample sarcopenia patients, which will not be repeated here.

[0066] If there is only one patient cluster matching the patient to be diagnosed, the multiple sarcopenia diagnostic motions corresponding to the patient cluster are used as the multiple target sarcopenia diagnostic motions of the patient to be diagnosed.

[0067] If there are multiple patient clusters matching the patient to be diagnosed, the multiple sarcopenia diagnostic motions corresponding to the multiple patient clusters matching the patient to be diagnosed are unioned as the multiple target sarcopenia diagnostic motions for the patient to be diagnosed.

[0068] Step 115, obtaining test data of the patient to be diagnosed in each target sarcopenia diagnostic exercise.

[0069] Preferably, step 115 specifically includes:

[0070] For any patient cluster, when the multiple sarcopenia diagnostic exercises corresponding to the patient cluster include sit-up exercises, obtaining motion state data of multiple sample sarcopenia patients included in the patient cluster during the sit-up exercise, wherein the motion state data includes vibration data of multiple sit-up exercise test positions, determining the correlation coefficient between each sit-up exercise test position and the patient cluster according to the motion state data and sarcopenia status of the multiple sample sarcopenia patients included in the patient cluster during the sit-up exercise, and determining the sit-up exercise test position corresponding to the patient cluster according to the correlation coefficient between each sit-up exercise test position and the patient cluster;

[0071] When multiple target sarcopenia diagnostic exercises for the patient to be diagnosed include sit-up exercises, the exercise state data of the patient to be diagnosed during the sit-up exercise is obtained according to the sit-up exercise test position corresponding to the patient cluster matched with the patient to be diagnosed.

[0072] Specifically, for each sit-up exercise test position, the vibration amplitude corresponding to the sit-up exercise test position can be calculated based on the vibration data of the sit-up exercise test position during the sit-up exercise of the sample sarcopenia patient.

[0073] The correlation coefficient between the sit-up exercise test position and the patient cluster can be calculated according to the following formula:

[0074]

[0075] in, is the correlation coefficient between the e-th sit-up exercise test position and the k-th patient cluster, The vibration amplitude of the e-th sit-up exercise test position during the sit-up exercise of the g-th sample sarcopenia patient included in the k-th patient cluster.

[0076] The sit-up exercise test positions having a correlation coefficient with the patient cluster greater than a third correlation coefficient threshold may be used as the sit-up exercise test positions corresponding to the patient cluster.

[0077] If there is only one patient cluster matching the patient to be diagnosed, the sit-up exercise test position corresponding to the patient cluster is used as the sit-up exercise test position of the patient to be diagnosed.

[0078] If there are multiple patient clusters matching the patient to be diagnosed, the sit-up exercise test positions corresponding to the multiple patient clusters matching the patient to be diagnosed are unioned as the sit-up exercise test position of the patient to be diagnosed.

[0079] Preferably, step 115 specifically includes:

[0080] For any patient cluster, when multiple sarcopenia diagnostic exercises corresponding to the patient cluster include a gait speed test, obtain gait speed test data of multiple sample sarcopenia patients included in the patient cluster at multiple test distances, calculate the correlation coefficient between each test distance and the patient cluster according to the gait speed test data and sarcopenia status of the multiple sample sarcopenia patients included in the patient cluster at multiple test distances, and determine the test distance corresponding to the patient cluster according to the correlation coefficient between each test distance and the patient cluster;

[0081] When multiple target sarcopenia diagnostic exercises of the patient to be diagnosed include a walking speed test, the walking speed test data of the patient to be diagnosed is obtained according to the test distance corresponding to the patient cluster matched with the patient to be diagnosed.

[0082] Specifically, for each test distance (for example, 4 meters, 6 meters, etc.), the average walking speed of the sample sarcopenia patients when performing the walking speed test corresponding to the test distance can be calculated.

[0083] The correlation coefficient between the sit-up exercise test position and the patient cluster was calculated according to the following formula:

[0084]

[0085] in, For the The correlation coefficient between the test distance and the kth patient cluster, The mean walking speed of the g-th sample sarcopenia patient included in the k-th patient cluster during the walking speed test corresponding to the th test distance.

[0086] The test distance with the largest correlation coefficient with the patient cluster can be used as the test distance corresponding to the patient cluster.

[0087] Step 116, determining a skeletal muscle mass testing scheme for the patient to be diagnosed based on the skeletal muscle content of the limbs of multiple samples of sarcopenia patients.

[0088] Specifically include:

[0089] For each patient cluster, ultrasonic test data of multiple sample sarcopenia patients included in the patient cluster at multiple ultrasonic test positions are obtained, and a correlation coefficient between each ultrasonic test position and the patient cluster is calculated based on the ultrasonic test data of multiple sample sarcopenia patients included in the patient cluster at multiple ultrasonic test positions and the sarcopenia status, and the ultrasonic test position corresponding to the patient cluster is determined based on the correlation coefficient between each ultrasonic test position and the patient cluster;

[0090] A skeletal muscle mass testing plan for the patient to be diagnosed is determined according to the ultrasonic testing position corresponding to the patient cluster matched with the patient to be diagnosed.

[0091] Specifically, the ultrasonic test positions are located at the limbs of the sample sarcopenia patient. For each ultrasonic test position, the skeletal muscle mass (kg) corresponding to the ultrasonic test position can be determined according to the ultrasonic test data corresponding to the ultrasonic test position.

[0092] For each patient cluster, the correlation coefficient between the ultrasound test location and the patient cluster can be calculated according to the following formula:

[0093]

[0094] in, is the correlation coefficient between the bth ultrasound test position and the kth patient cluster, The skeletal muscle mass of the g-th sarcopenia patient included in the k-th patient cluster at the th ultrasound test position.

[0095] The ultrasonic test positions whose correlation coefficients with the patient cluster are greater than a fourth correlation coefficient threshold are used as the ultrasonic test positions corresponding to the patient cluster.

[0096] If there is only one patient cluster matching the patient to be diagnosed, the ultrasonic test position corresponding to the patient cluster is used as the ultrasonic test position of the patient to be diagnosed.

[0097] If there are multiple patient clusters matching the patient to be diagnosed, the ultrasonic test positions corresponding to the multiple patient clusters matching the patient to be diagnosed are unioned as the ultrasonic test position of the patient to be diagnosed, and the skeletal muscle mass test plan for the patient to be diagnosed may include the ultrasonic test position of the patient to be diagnosed.

[0098] Step 117, obtaining the skeletal muscle content of the limbs of the patient to be diagnosed according to the skeletal muscle mass testing plan of the patient to be diagnosed.

[0099] Specifically, an ultrasonic test is performed at each ultrasonic test position of the patient to be diagnosed to obtain the skeletal muscle mass at each ultrasonic test position of the patient to be diagnosed as the skeletal muscle content of the limbs of the patient to be diagnosed.

[0100] Step 118, obtaining the basal metabolic rate and grip strength of the patient to be diagnosed.

[0101] Specifically, a bioelectrical impedance analyzer can be used to stick electrodes on the wrists and ankles of the subject, and the body's fat and muscle ratio can be estimated by measuring resistance, and then the basal metabolic rate can be calculated. A standard handgrip dynamometer can be used to measure the grip strength of the patient to be diagnosed. Instruct the patient to sit or stand, and adjust the handle of the handgrip dynamometer to a suitable position according to the size of the patient's palm to facilitate the patient's grip. Instruct the patient to squeeze the handle slowly and evenly until it is fully gripped. The screen value of the handgrip dynamometer is continuously refreshed and increased as the patient exerts force until the maximum peak value appears and remains stable. Record this peak value as the patient's grip strength value.

[0102] Step 119, determining the sarcopenia status of the patient to be diagnosed based on the patient's basal metabolic rate, grip strength, limb skeletal muscle content, and test data of each target sarcopenia diagnostic exercise.

[0103] Specifically include:

[0104] For each patient cluster, establish the criteria for judging the sarcopenia status corresponding to the patient cluster;

[0105] Extracting vibration characteristics of a sit-up exercise test position of the patient to be diagnosed according to the motion state data of the patient to be diagnosed during the sit-up exercise;

[0106] The sarcopenia status of the patient to be diagnosed is determined based on the basal metabolic rate, grip strength, skeletal muscle content of the limbs, vibration characteristics of the sit-up exercise test position of the patient to be diagnosed, walking speed test data, and the sarcopenia status judgment criteria corresponding to the patient cluster matching the patient to be diagnosed.

[0107] For example, 1. Basal metabolic rate:

[0108] Normal range: Determine a normal basal metabolic rate range based on factors such as the patient's age, gender, height and weight.

[0109] Judgment criteria: If the patient's basal metabolic rate is lower than the normal range and exists at the same time as other symptoms of sarcopenia (such as decreased muscle mass), it may indicate sarcopenia.

[0110] 2. Grip strength:

[0111] Normal range: grip strength greater than 25kg for men and greater than 18kg for women.

[0112] Judgment criteria: If the patient's grip strength is lower than the normal range and exists simultaneously with other symptoms of sarcopenia (such as decreased muscle strength), it may indicate sarcopenia.

[0113] 3. Limb skeletal muscle content:

[0114] Judgment criteria: If the patient's limb skeletal muscle content is lower than the normal range (such as the skeletal muscle mass index SMI for men is lower than 8.87kg / m² and for women is lower than 6.42kg / m²), and other symptoms of sarcopenia (such as decreased muscle mass and decreased muscle function) exist at the same time, it may indicate sarcopenia.

[0115] 4. Vibration characteristics of the sit-up exercise test position:

[0116] Judgment criteria: If the patient's vibration characteristics show obvious muscle weakness or decreased coordination, and coexist with other symptoms of sarcopenia (such as muscle dysfunction), it may indicate sarcopenia.

[0117] 5. Pace test data:

[0118] Judgment criteria: If the patient's walking speed is lower than the normal range (such as walking speed less than 0.8m / s) and exists at the same time as other symptoms of sarcopenia (such as weakened muscle strength and decreased muscle function), it may indicate sarcopenia.

[0119] As an example only, for each patient cluster, a corresponding sarcopenia status assessment model can be established. The sarcopenia status of the patient to be diagnosed can be determined based on the sarcopenia status assessment model corresponding to the patient cluster matched with the patient to be diagnosed, the basal metabolic rate, grip strength, skeletal muscle content of the limbs, vibration characteristics of the sit-up exercise test position of the patient to be diagnosed, and walking speed test data of the patient to be diagnosed. The sarcopenia status assessment model can be a convolutional neural network (CNN) model.

[0120] Preferably, after performing variational modal decomposition on the motion state data of the patient to be diagnosed during the sit-up exercise, the vibration characteristics of the sit-up exercise test position of the patient to be diagnosed are extracted, for example, the center frequency of each modal component, time domain characteristics and frequency domain characteristics.

[0121] Step 120, obtaining psychological status test data of the patient to be diagnosed.

[0122] Psychological conditions include depression, anxiety, etc.

[0123] In some embodiments, step 120 specifically includes:

[0124] Obtaining conversation data between the psychological test conversation robot and the patient to be diagnosed;

[0125] Extract psychological state keywords and emotion types from conversation data.

[0126] Specifically, the psychological state evaluation model can be used to extract psychological state keywords and emotion types from the conversation data to determine the psychological state of the patient to be diagnosed, wherein the psychological state evaluation model can be a convolutional neural network model.

[0127] Step 121, determine the recommended auxiliary treatment plan for the patient to be diagnosed based on the disease and exercise association map, the basal metabolic rate and nutrition association map, the psychological intervention knowledge map, the basic information of the patient to be diagnosed, the diet and exercise habits, the sarcopenia status and the psychological status test data.

[0128] Specifically include:

[0129] According to the basic information, sarcopenia status and psychological status test data of the patient to be diagnosed, similar sample sarcopenia patients are identified from the patient clusters matched with the patient to be diagnosed;

[0130] The solution generation model determines the recommended auxiliary treatment plan for the patient to be diagnosed based on the auxiliary treatment plan of similar sample sarcopenia patients, the disease and exercise association map, the basal metabolic rate and nutrition association map, the psychological intervention knowledge map, the basic information of the patient to be diagnosed, the diet and exercise habits, the sarcopenia status and the psychological status test data. Among them, the solution generation model can be a convolutional neural network model.

[0131] Figure 2 is a module schematic diagram of a sarcopenia auxiliary diagnosis and treatment system according to some embodiments of this specification, such as Figure 2 As shown, a sarcopenia auxiliary diagnosis and treatment system may include an information acquisition module, a map establishment module, an exercise determination module, a plan determination module, a state determination module and an auxiliary treatment module.

[0132] The information acquisition module can be used to obtain basic information, exercise test information, sarcopenia status and skeletal muscle content of multiple sample sarcopenia patients, wherein the exercise test information includes test data of sample sarcopenia patients in multiple sarcopenia diagnostic exercises.

[0133] The map building module can be used to build disease and exercise association maps, basal metabolic rate and nutrition association maps, and psychological intervention knowledge maps.

[0134] The information acquisition module can also be used to obtain basic information of the patient to be diagnosed;

[0135] The exercise determination module can be used to determine multiple target sarcopenia diagnostic exercises for the patient to be diagnosed based on the basic information of the patient to be diagnosed and the basic information and exercise test information of multiple sample sarcopenia patients.

[0136] The information acquisition module can also be used to obtain test data of the patient to be diagnosed in each target sarcopenia diagnostic exercise.

[0137] The scheme determination module can be used to determine the skeletal muscle mass testing scheme for the patient to be diagnosed based on the skeletal muscle content of the limbs of multiple samples of sarcopenia patients.

[0138] The information acquisition module can also be used to obtain the skeletal muscle content of the limbs of the patient to be diagnosed according to the skeletal muscle mass test plan of the patient to be diagnosed.

[0139] The information acquisition module can also be used to obtain the basal metabolic rate of the patient to be diagnosed.

[0140] The state determination module can be used to determine the sarcopenia state of the patient to be diagnosed based on the basal metabolic rate, skeletal muscle content of the limbs and test data of each target sarcopenia diagnostic exercise of the patient to be diagnosed.

[0141] The information acquisition module can also be used to obtain psychological status test data of the patient to be diagnosed.

[0142] The auxiliary treatment module can be used to determine the recommended auxiliary treatment plan for the patient to be diagnosed based on the disease and exercise association map, the basal metabolic rate and nutrition association map, the psychological intervention knowledge map, the basic information of the patient to be diagnosed, the diet and exercise habits, the sarcopenia status and the psychological status test data.

[0143] A sarcopenia auxiliary diagnosis and treatment system can be used to execute a sarcopenia auxiliary diagnosis and treatment method. For more descriptions of a sarcopenia auxiliary diagnosis and treatment system, please refer to the relevant descriptions of a sarcopenia auxiliary diagnosis and treatment method, which will not be repeated here.

[0144] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A method for auxiliary diagnosis and treatment of sarcopenia, characterized in that: include: Obtaining basic information, exercise test information, sarcopenia status, and limb skeletal muscle content of multiple sample sarcopenia patients, wherein the exercise test information includes test data of the sample sarcopenia patients in multiple sarcopenia diagnostic exercises; Establish disease-exercise correlation maps, basal metabolic rate-nutrition correlation maps, and psychological intervention knowledge maps; Obtain basic information of patients to be diagnosed; Determining a plurality of target sarcopenia diagnostic exercises for the patient to be diagnosed based on the basic information of the patient to be diagnosed and the basic information, exercise test information, and sarcopenia status of the plurality of sample sarcopenia patients; Acquire test data of the patient to be diagnosed in each of the target sarcopenia diagnostic exercises; Determining a skeletal muscle mass testing scheme for the patient to be diagnosed based on the limb skeletal muscle content of the multiple sample sarcopenia patients; According to the skeletal muscle mass testing scheme of the patient to be diagnosed, obtaining the skeletal muscle content of the limbs of the patient to be diagnosed; Obtaining the basal metabolic rate and grip strength of the patient to be diagnosed; Determining the sarcopenia status of the patient to be diagnosed according to the basal metabolic rate, grip strength, skeletal muscle content of the limbs of the patient to be diagnosed and the test data of each target sarcopenia diagnostic exercise; Acquiring psychological status test data of the patient to be diagnosed; Determine a recommended auxiliary treatment plan for the patient to be diagnosed based on the disease and exercise association map, the basal metabolic rate and nutrition association map, the psychological intervention knowledge map, the basic information of the patient to be diagnosed, the diet and exercise habits, the sarcopenia status and the psychological status test data; Based on the basic information of the patient to be diagnosed and the basic information, exercise test information and sarcopenia status of the multiple sample sarcopenia patients, multiple target sarcopenia diagnostic exercises for the patient to be diagnosed are determined, including: Calculate the basic information similarity of the basic information of any two of the sample sarcopenia patients; Clustering the multiple sample sarcopenia patients according to the basic information similarity of the basic information of any two of the sample sarcopenia patients to determine multiple patient clusters; For each of the patient clusters, determining a correlation coefficient between each sarcopenia diagnostic exercise and the patient cluster according to exercise test information and sarcopenia status of a plurality of sample sarcopenia patients included in the patient cluster, and determining a plurality of sarcopenia diagnostic exercises corresponding to the patient cluster according to the correlation coefficient between each sarcopenia diagnostic exercise and the patient cluster; Determining a patient cluster matching the patient to be diagnosed from the multiple patient clusters according to the basic information of the patient to be diagnosed; Determining a plurality of target sarcopenia diagnostic movements of the patient to be diagnosed according to a plurality of sarcopenia diagnostic movements corresponding to a patient cluster matched with the patient to be diagnosed; Acquiring test data of the patient to be diagnosed in each target sarcopenia diagnostic exercise, including: For any one of the patient clusters, when the multiple sarcopenia diagnostic exercises corresponding to the patient cluster include sit-up exercises, obtaining motion state data of the multiple sample sarcopenia patients included in the patient cluster during the sit-up exercises, wherein the motion state data includes vibration data of multiple sit-up exercise test positions, determining the correlation coefficient between each sit-up exercise test position and the patient cluster according to the motion state data and sarcopenia status of the multiple sample sarcopenia patients included in the patient cluster during the sit-up exercises, and determining the sit-up exercise test position corresponding to the patient cluster according to the correlation coefficient between each sit-up exercise test position and the patient cluster; When the multiple target sarcopenia diagnostic exercises of the patient to be diagnosed include sit-up exercise, acquiring the exercise state data of the patient to be diagnosed during the sit-up exercise according to the sit-up exercise test position corresponding to the patient cluster matched with the patient to be diagnosed; Acquiring test data of the patient to be diagnosed in each target sarcopenia diagnostic exercise, including: For any one of the patient clusters, when the multiple sarcopenia diagnostic exercises corresponding to the patient cluster include a gait test, obtaining gait test data of multiple sample sarcopenia patients included in the patient cluster at multiple test distances, calculating the correlation coefficient between each of the test distances and the patient cluster according to the gait test data and sarcopenia status of the multiple sample sarcopenia patients included in the patient cluster at multiple test distances, and determining the test distance corresponding to the patient cluster according to the correlation coefficient between each of the test distances and the patient cluster; When the multiple target sarcopenia diagnostic exercises of the patient to be diagnosed include a walking speed test, acquiring walking speed test data of the patient to be diagnosed according to a test distance corresponding to a patient cluster matched with the patient to be diagnosed; According to the limb skeletal muscle contents of the multiple sample sarcopenia patients, a skeletal muscle mass testing scheme for the patient to be diagnosed is determined, comprising: For each of the patient clusters, ultrasonic test data of a plurality of sample sarcopenia patients included in the patient cluster at a plurality of ultrasonic test positions are obtained; based on the ultrasonic test data of the plurality of sample sarcopenia patients included in the patient cluster at a plurality of ultrasonic test positions and the sarcopenia status, a correlation coefficient between each of the ultrasonic test positions and the patient cluster is calculated; based on the correlation coefficient between each of the ultrasonic test positions and the patient cluster, an ultrasonic test position corresponding to the patient cluster is determined; Determining a skeletal muscle mass test scheme for the patient to be diagnosed according to the ultrasonic test position corresponding to the patient cluster matched with the patient to be diagnosed; According to the disease and exercise association map, the basal metabolic rate and nutrition association map, the psychological intervention knowledge map, the basic information of the patient to be diagnosed, the diet and exercise habits, the sarcopenia status and the psychological status test data, the recommended auxiliary treatment plan for the patient to be diagnosed is determined, including: Determine similar sample sarcopenia patients from a patient cluster matched with the patient to be diagnosed according to the basic information, sarcopenia status and psychological status test data of the patient to be diagnosed; The recommended auxiliary treatment plan for the patient to be diagnosed is determined through the plan generation model based on the auxiliary treatment plans of similar sample sarcopenia patients, the disease and exercise association map, the basal metabolic rate and nutrition association map, the psychological intervention knowledge map, the basic information of the patient to be diagnosed, the diet and exercise habits, the sarcopenia status and the psychological status test data.

2. The method for auxiliary diagnosis and treatment of sarcopenia according to claim 1, characterized in that: Determining the sarcopenia status of the patient to be diagnosed according to the basal metabolic rate, grip strength, skeletal muscle content of the limbs of the patient to be diagnosed and the test data of each target sarcopenia diagnostic exercise, including: For each of the patient clusters, establishing a sarcopenia status judgment standard corresponding to the patient cluster; Extracting vibration characteristics of a sit-up exercise test position of the patient to be diagnosed according to the motion state data of the patient to be diagnosed during the sit-up exercise; The sarcopenia status of the patient to be diagnosed is determined based on the basal metabolic rate, grip strength, limb skeletal muscle content of the patient to be diagnosed, the vibration characteristics of the sit-up exercise test position of the patient to be diagnosed, the walking speed test data, and the sarcopenia status judgment criteria corresponding to the patient cluster matching the patient to be diagnosed.

3. The method for auxiliary diagnosis and treatment of sarcopenia according to claim 2, characterized in that: Extracting vibration characteristics of a sit-up exercise test position of the patient to be diagnosed according to the movement state data of the patient to be diagnosed during the sit-up exercise, including: After performing variational modal decomposition on the motion state data of the patient to be diagnosed during the sit-up exercise, the vibration characteristics of the sit-up exercise test position of the patient to be diagnosed are extracted.

4. The method for auxiliary diagnosis and treatment of sarcopenia according to claim 1, characterized in that: Acquiring psychological status test data of the patient to be diagnosed, including: Acquire conversation data between the psychological test conversation robot and the patient to be diagnosed; Psychological state keywords and emotion types are extracted from the conversation data.

5. A sarcopenia auxiliary diagnosis and treatment system, characterized in that: A sarcopenia auxiliary diagnosis and treatment method according to any one of claims 1 to 4, comprising: An information acquisition module, used to obtain basic information, exercise test information, sarcopenia status and skeletal muscle content of multiple sample sarcopenia patients, wherein the exercise test information includes test data of the sample sarcopenia patients in multiple sarcopenia diagnostic exercises; A map building module, which is used to build a disease-exercise association map, a basal metabolic rate-nutrition association map, and a psychological intervention knowledge map; The information acquisition module is also used to obtain basic information of the patient to be diagnosed; An exercise determination module, used to determine a plurality of target sarcopenia diagnostic exercises for the patient to be diagnosed based on the basic information of the patient to be diagnosed and the basic information and exercise test information of the plurality of sample sarcopenia patients; The information acquisition module is also used to obtain test data of the patient to be diagnosed in each target sarcopenia diagnostic exercise; A scheme determination module, used for determining a skeletal muscle mass test scheme for the patient to be diagnosed according to the limb skeletal muscle content of the multiple sample sarcopenia patients; The information acquisition module is also used to obtain the skeletal muscle content of the limbs of the patient to be diagnosed according to the skeletal muscle mass test plan of the patient to be diagnosed; The information acquisition module is also used to obtain the basal metabolic rate of the patient to be diagnosed; A state determination module, for determining the sarcopenia state of the patient to be diagnosed according to the basal metabolic rate, skeletal muscle content of the limbs of the patient to be diagnosed and the test data of each target sarcopenia diagnostic exercise; The information acquisition module is also used to obtain psychological state test data of the patient to be diagnosed; The auxiliary treatment module is used to determine the recommended auxiliary treatment plan for the patient to be diagnosed based on the disease and exercise association map, the basal metabolic rate and nutrition association map, the psychological intervention knowledge map, the basic information of the patient to be diagnosed, the diet and exercise habits, the sarcopenia status and the psychological status test data.

Images