A diagnosis and treatment path recommendation method based on IBS multidimensional data

Abstract

This invention discloses a treatment pathway recommendation method based on IBS multidimensional data. This invention relates to the field of intelligent diagnosis and treatment technology, and includes the following steps: S1, constructing an IBS treatment plan library. The treatment plan library contains standardized treatment plans corresponding to different diagnostic types and severity levels of IBS. The standardized treatment plan includes at least follow-up recommendations, medication recommendations, probiotic recommendations, and nursing guidance, and each treatment plan is associated with a corresponding IBS multidimensional data feature threshold. This treatment pathway recommendation method based on IBS multidimensional data overcomes the limitations of existing technologies with single-dimensional diagnostic data. It comprehensively integrates four core dimensions: patient symptom data, physical sign data, laboratory test data, and medical history data. Symptom data is obtained through a combination of patient self-reporting and doctor consultation to ensure no omissions; physical sign data relies on professional medical equipment to ensure objectivity; and laboratory test data is obtained synchronously from the hospital's testing system to reduce errors.

Description

Technical Field

[0001] This invention relates to the field of intelligent diagnosis and treatment technology, specifically to a method for recommending treatment pathways based on IBS multidimensional data. Background Technology

[0002] Irritable bowel syndrome (IBS) is a common functional bowel disorder with a complex pathogenesis, related to various factors such as gut microbiota dysbiosis, gastrointestinal motility disorders, and psychological factors. Clinical manifestations are diverse, mainly including abdominal pain, bloating, changes in bowel habits, and abnormal stool characteristics. Furthermore, the severity of symptoms, frequency of attacks, and overall health vary significantly among patients. Currently, the diagnosis and treatment of IBS primarily rely on the physician's clinical experience. Physicians develop treatment plans based on a single or few diagnostic data points combined with their own experience, which has the following limitations: (i) The diagnostic data is too narrow and does not fully integrate the patient’s symptoms, signs, laboratory tests, medical history and other multi-dimensional data, resulting in a lack of comprehensiveness and pertinence in the treatment plan, making it difficult to achieve personalized diagnosis and treatment for each patient. (ii) Existing treatment plans are mostly standardized templates that are not dynamically adjusted according to individual patient differences. Furthermore, the recommendation process lacks quantitative basis, which leads to strong subjectivity and low accuracy, and the treatment plan is prone to not matching the patient's actual condition. (iii) Doctors in primary healthcare institutions have relatively insufficient experience in the diagnosis and treatment of IBS, making it difficult for them to quickly and accurately develop the optimal treatment pathway, resulting in poor treatment outcomes, untimely follow-up examinations, and even delays in diagnosis and treatment. (iv) The treatment plan relies on manual summarization and cannot be optimized in real time based on the patient's treatment feedback and changes in the condition, making it difficult to adapt to the dynamic needs of IBS diagnosis and treatment.

[0003] Therefore, there is an urgent need for a method that can integrate multidimensional diagnostic data of IBS, combine it with existing treatment plan libraries, and automatically and accurately generate personalized treatment pathways to solve the problems of strong subjectivity, poor targeting, and low efficiency in existing technologies, and improve the standardization and intelligence of IBS diagnosis and treatment. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a diagnostic and treatment pathway recommendation method based on IBS multidimensional data, which solves the problems mentioned in the background section.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a method for recommending treatment pathways based on IBS multidimensional data, comprising the following steps: S1. Construct an IBS treatment plan library, which contains standardized treatment plans corresponding to different diagnostic types and severity levels of IBS. Each standardized treatment plan includes at least follow-up recommendations, medication recommendations, probiotic recommendations, and nursing guidance. Each treatment plan is associated with a corresponding IBS multidimensional data feature threshold. The treatment plan library also has a preset data update mechanism to regularly integrate the latest clinical treatment guidelines, expert consensus, and clinical treatment cases to iteratively optimize the treatment plans and associated feature thresholds in the library. S2. Collect IBS multidimensional diagnostic data from patients. The IBS multidimensional diagnostic data includes at least symptom data, physical sign data, laboratory test data, and medical history data. Symptom data is collected through a combination of patient self-reporting and clinical consultation with doctors. Physical sign data is collected through medical testing equipment. Laboratory test data is obtained synchronously from the hospital's testing system. Medical history data is extracted from the electronic medical record system and supplemented with confirmation from the patient. S3. Preprocess the collected IBS multidimensional diagnostic data, including data cleaning, outlier removal, and data standardization, to obtain standardized diagnostic data. During the data cleaning process, missing values ​​and outliers are marked and processing records are kept. After data standardization, a data standardization report is generated for subsequent tracking and verification of matching results. S4. Match the standardized diagnostic data with the IBS multidimensional data feature thresholds associated with each treatment plan in the treatment plan library, calculate the matching degree using a preset similarity algorithm, and select candidate treatment plans whose matching degree meets the preset threshold; if the matching degree does not reach the preset threshold, select the top 3 treatment plans with the highest matching degree as candidate treatment plans, and generate a matching degree insufficient prompt and manual intervention suggestion. S5. Prioritize candidate treatment options based on matching degree, patient age, complication status, drug allergy history, and underlying diseases, with matching degree having the highest weight, accounting for no less than 60%. Generate and output personalized IBS treatment pathway recommendations based on the ranking results. The recommendations include specific follow-up locations, follow-up times, follow-up items, drug types, drug dosages, drug administration times and methods, probiotic types, probiotic dosages and cycles, and an explanation of the basis for the recommendations, clarifying the matching data and logic corresponding to each recommendation item.

[0006] Preferably, the IBS multidimensional data feature thresholds in step S1 include symptom feature thresholds, sign feature thresholds, laboratory test feature thresholds, and medical history feature thresholds. The symptom features include the frequency and severity of abdominal pain, bloating, diarrhea, constipation, and abnormal defecation characteristics. The laboratory test data include stool routine, blood routine, intestinal flora detection, and inflammatory marker detection data.

[0007] Preferably, the data preprocessing in step S3 specifically includes: removing diagnostic data with a missing value ratio exceeding a preset ratio, supplementing diagnostic data with a missing value ratio below a preset ratio using interpolation; and standardizing numerical diagnostic data using the Z-score standardization method to convert categorical diagnostic data into coded form.

[0008] Preferably, in step S4, the matching process uses a cosine similarity algorithm to calculate the matching degree between standardized diagnostic data and the IBS multidimensional data feature thresholds associated with each treatment plan, and the preset matching degree threshold is not less than 80%.

[0009] Preferably, the priority ranking in step S5 is based on matching degree, patient age, complication status and drug allergy history, with matching degree having the highest weight and accounting for no less than 60%.

[0010] Preferably, the method further includes step S6: updating the output treatment pathway recommendation results in real time, and adjusting the data feature thresholds and priority of candidate treatment plans in the treatment plan library based on the patient's subsequent follow-up data, symptom change data and treatment feedback data.

[0011] Preferably, the medical history data in step S2 includes a history of previous IBS episodes, medication use history, probiotic use history, family medical history, and dietary preference data.

[0012] Preferably, the recommendation results output in step S5 also include dietary guidance and lifestyle adjustment suggestions, wherein the dietary guidance is tailored to different subtypes of IBS and includes a list of food restrictions and recommendations.

[0013] Beneficial effects This invention provides a method for recommending treatment pathways based on IBS multidimensional data. Compared with existing technologies, it has the following advantages: (1) This treatment pathway recommendation method based on IBS multidimensional data breaks through the limitations of single-dimensional diagnostic data in existing technologies. It comprehensively integrates four core dimensions: patient symptom data, physical sign data, laboratory test data, and medical history data. Among them, symptom data is combined with patient self-reporting and doctor consultation to ensure no omissions; physical sign data relies on professional medical equipment to ensure objectivity; laboratory test data is obtained synchronously from the hospital's testing system to reduce errors; and medical history data is extracted from electronic medical records and confirmed by the patient to ensure completeness. Through the deep integration of multidimensional data, it can accurately capture the individual differences of patients, solve the drawbacks of the "one-size-fits-all" standardized template in traditional diagnosis and treatment, realize personalized treatment pathway recommendation for "one patient, one policy", effectively avoid treatment plan deviations caused by one-sided data, significantly improve the treatment effectiveness of IBS patients, and reduce the occurrence of problems such as symptom recurrence and ineffective treatment.

[0014] (2) This treatment pathway recommendation method based on IBS multidimensional data, based on a pre-set IBS treatment plan library and a standardized similarity matching algorithm, can automatically complete the preprocessing of patients' multidimensional diagnostic data, the matching calculation with treatment plans, the priority ranking of candidate plans, and the generation of the final treatment pathway. The entire process does not require doctors to manually screen, calculate, and adjust plans, greatly reducing the workload of doctors. Especially in view of the current situation where doctors in primary healthcare institutions have relatively insufficient experience in IBS diagnosis and treatment, this method can provide them with scientific and standardized auxiliary decision support, helping them to quickly and accurately formulate the optimal treatment pathway, avoiding problems such as treatment delays and unreasonable plans due to lack of experience; at the same time, the automated process also reduces the error of human subjective judgment, ensures the standardization and normalization of the diagnosis and treatment process, effectively improves the efficiency of IBS diagnosis and treatment in medical institutions at all levels, shortens patients' waiting time, and improves patients' medical experience.

[0015] (3) The treatment pathway recommendation method based on IBS multidimensional data regularly integrates the latest IBS clinical treatment guidelines, expert consensus and clinical treatment cases through a preset fixed-cycle update mechanism. It iteratively optimizes the treatment plans and associated multidimensional data feature thresholds in the treatment plan library, and retains complete update records for easy traceability and review. In addition, it supports real-time dynamic adjustment of the treatment pathway based on the patient's subsequent follow-up data, symptom change data and treatment feedback data. It can optimize the priority of the treatment plan in a timely manner according to the improvement, aggravation or new symptoms of the patient's condition, and even supplement new adaptation plans. It completely solves the drawbacks of the existing technology that the treatment plan is fixed and cannot adapt to the dynamic needs of IBS diagnosis and treatment, and ensures that the recommended treatment pathway is always consistent with the latest clinical diagnosis and treatment standards and the patient's real-time condition, thereby improving the scientific nature and timeliness of diagnosis and treatment.

[0016] (4) This treatment pathway recommendation method based on IBS multidimensional data does not rely on complex medical equipment and high-end medical resources. It can be flexibly applied to medical institutions at all levels, whether it is a tertiary hospital, a community health service center, or a primary township health center. For experienced specialists, this method can serve as an auxiliary decision-making tool to further improve the accuracy and efficiency of diagnosis and treatment. For less experienced primary care physicians, this method can provide standardized and regulated diagnosis and treatment guidance to help them quickly improve their IBS diagnosis and treatment level. At the same time, the personalized recommendation feature of this method can be adapted to patients of different ages, different IBS subtypes, different disease severity, and different underlying diseases, covering various IBS diagnosis and treatment scenarios. It can effectively promote the standardization and intelligent development of IBS diagnosis and treatment, and has extremely high practical value and broad prospects for promotion. Attached Figure Description

[0017] Figure 1The present invention provides a flowchart of a diagnostic and treatment pathway recommendation method based on IBS multidimensional data. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] This invention provides a technical solution: a method for recommending treatment pathways based on IBS multidimensional data, specifically including the following steps: S1. Construct an IBS treatment protocol database We collect clinical diagnosis and treatment data, guidelines, expert consensus, and clinical cases related to IBS to construct a standardized IBS treatment protocol library. This library includes not only different IBS diagnostic types (e.g., IBS-diarrhea, IBS-constipation, IBS-mixed), but also standardized treatment protocols corresponding to different severity levels (mild, moderate, and severe) within each diagnostic type. Each treatment protocol is associated with specific IBS multidimensional data feature thresholds to ensure accurate matching between treatment protocols and diagnostic data, achieving a proper correspondence between disease severity and treatment protocols.

[0020] Meanwhile, the treatment protocol database has a well-established data update mechanism with a fixed update cycle (e.g., every 3 months). It integrates the latest clinical treatment guidelines, expert consensus, and clinical cases to optimize and adjust existing treatment protocols in the database, add new treatment protocols, and update the IBS multidimensional data feature thresholds associated with each protocol, ensuring the timeliness, scientific validity, and practicality of the database. The update process retains update records, including update content, update basis, and update time, for easy traceability and review later.

[0021] The standardized treatment plan includes at least the following: follow-up recommendations (specifying the location, time, and items to be examined), medication recommendations (type, dosage, timing, and method of administration), probiotic recommendations (probiotic strain, dosage, and duration of use), and nursing guidance. The multidimensional data characteristic thresholds for IBS include symptom characteristic thresholds (e.g., abdominal pain ≥3 times per week, abdominal distension duration ≥2 days / week), physical sign characteristic thresholds, laboratory test characteristic thresholds (e.g., beneficial bacteria percentage ≤30% in fecal microbiota, inflammatory marker levels above normal), and medical history characteristic thresholds (e.g., a history of IBS episodes ≥6 months). Furthermore, the treatment plan database supports dynamic updates, allowing for the addition of new treatment plans and adjustments to characteristic thresholds based on the latest clinical guidelines, treatment experience, and patient feedback, ensuring the database's timeliness and practicality.

[0022] S2. Collect IBS multidimensional diagnostic data from patients. A multi-channel integrated data collection approach is adopted to ensure the comprehensiveness, accuracy, and completeness of patients' IBS multidimensional diagnostic data. The specific collection methods are as follows: Symptom data is collected through a combination of patient self-reporting (based on a dedicated reporting interface with clearly defined reporting items and filling specifications) and doctor's clinical consultation, avoiding symptom omissions or description errors caused by a single collection method; Physical sign data is collected through professional medical testing equipment (such as abdominal ultrasound, weighing scales, etc.) to ensure data objectivity; Laboratory test data is directly and synchronously obtained from the hospital's testing system to reduce manual entry errors; Medical history data is extracted from the electronic medical record system and supplemented and confirmed by doctors in conjunction with the patient's oral account to ensure the completeness of the medical history data, especially key information such as details of past IBS attacks and medication use.

[0023] (1) Symptom data: frequency, severity and duration of abdominal pain, bloating, diarrhea, constipation and abnormal stool characteristics (such as watery stool and hard stool); (2) Physical signs: location of abdominal tenderness, degree of abdominal distension, weight changes, etc.; (3) Laboratory test data: routine stool test, routine blood test, intestinal flora test, inflammatory marker (such as C-reactive protein) test, liver and kidney function test, etc.; (4) Medical history data: history of previous IBS attacks, history of medication use, history of probiotic use, family medical history, dietary preferences (such as whether they often eat spicy or cold foods), mental and psychological state (such as anxiety or depression).

[0024] S3. Preprocessing IBS multidimensional diagnostic data Because the collected multidimensional diagnostic data may contain missing values, outliers, and inconsistent data formats, it needs to undergo standardized preprocessing to ensure data usability, lay the foundation for subsequent matching calculations, and retain preprocessing records for easy traceability and verification of subsequent matching results. The specific preprocessing steps are as follows: (1) Data cleaning: Remove diagnostic data with a missing value ratio exceeding the preset ratio (e.g., 30%). For data with a missing value ratio lower than the preset ratio, use linear interpolation, mean interpolation, or other methods to supplement missing values ​​to avoid the impact of missing data on the matching results. At the same time, clearly mark all missing values ​​and outliers, keep cleaning records, and explain the reasons for missing / outliers and the handling methods. (2) Outlier removal: Identify and remove outlier data (such as outliers that are significantly outside the normal range in laboratory tests) using methods such as box plots and Z-scores to ensure the authenticity of the data; (3) Data standardization: The Z-score standardization method is used to standardize numerical diagnostic data (such as laboratory test results and symptom frequency) and convert the data into standardized data with a mean of 0 and a standard deviation of 1 to eliminate the influence of different dimensions of data; for categorical diagnostic data (such as IBS subtypes and drug allergy history), one-hot coding and other methods are used to convert them into a computable coding form; after standardization, a data standardization report is generated to clarify the standardization process, parameters and results of each dimension of data for subsequent verification and traceability of matching results.

[0025] S4. Matching and screening diagnostic data with treatment plans The preprocessed standardized diagnostic data is matched against the IBS multidimensional data feature thresholds associated with each treatment plan in the treatment plan library to screen candidate treatment plans that match the patient's condition. This invention uses a cosine similarity algorithm to calculate the matching degree; the closer the cosine similarity is to 1, the higher the matching degree between the diagnostic data and the treatment plan. The specific calculation process is as follows: Simultaneously, a preset matching threshold (preferably not less than 80%) is set, and treatment plans with a cosine similarity ≥ the preset threshold are selected as candidate treatment plans. If the matching degree of all treatment plans does not reach the preset threshold, the top 3 treatment plans with the highest matching degree are selected as candidate plans, and an insufficient matching degree prompt is automatically generated, clarifying the matching degree value of each candidate plan and the differences from the patient's diagnostic data. At the same time, manual intervention suggestions are given to remind doctors to further adjust the plan based on clinical experience.

[0026] Let the standardized diagnostic data vector be... ,in For the first Standardized data in 10 dimensions; the feature threshold vector associated with a certain treatment plan is... ,in For the first The feature thresholds of each dimension are used to determine the cosine similarity between the two. The calculation formula is: ; Set a preset matching threshold (preferably not less than 80%), and select treatment plans with a cosine similarity ≥ the preset threshold as candidate treatment plans; if there is no treatment plan with a matching degree reaching the preset threshold, select the top 3 treatment plans with the highest matching degree as candidate plans and mark them as "requires further confirmation by doctor".

[0027] S5. Ranking of candidate treatment options and output of recommendation results The selected candidate treatment plans are prioritized and ranked based on a comprehensive consideration of matching degree, individual patient differences, and treatment safety. The specific weighting is as follows: matching degree weight ≥60%, patient age (with appropriate increase in weight for elderly and pediatric patients), complication status (patients with complications are given priority for safer plans), history of drug allergies (plans containing allergenic drugs are excluded), and underlying diseases (patients with underlying diseases such as hypertension and diabetes are given priority for plans with no conflicts and few side effects) weight ≤40% to ensure the scientific and reasonableness of the ranking results.

[0028] Based on the ranking results, personalized IBS treatment pathway recommendations are generated. The output should include at least: specific follow-up locations (e.g., designated hospital gastroenterology department, community health service center), follow-up times (e.g., follow-up in 1 week, follow-up in 1 month), follow-up items (e.g., gut microbiota testing, stool routine); medication type, dosage, administration time and method; probiotic type, dosage and duration of use. To improve the interpretability of the recommendations, an explanation of the basis for the recommendations is included, clearly stating the patient matching data, characteristic thresholds and matching logic for each recommendation, allowing doctors and patients to clearly understand the reasons for the recommendations, facilitating doctor-patient communication and plan confirmation. In addition, dietary guidance (e.g., avoiding spicy and cold foods, increasing dietary fiber intake) and lifestyle adjustment suggestions (e.g., regular sleep schedule, avoiding staying up late, appropriate exercise) can be provided to help patients better cooperate with treatment.

[0029] To improve the adaptability and accuracy of treatment pathways, this method also supports real-time updates. It collects subsequent patient follow-up data, symptom change data (such as symptom relief and new symptoms), and treatment feedback data (such as adverse drug reactions and treatment effects). After preprocessing this data, it re-matches it with the treatment protocol database, adjusts the priority of candidate treatment protocols, and even adds new treatment protocols, achieving dynamic optimization of the treatment pathway and ensuring that the treatment plan always remains consistent with changes in the patient's condition.

[0030] Furthermore, any content not described in detail in this specification is existing technology known to those skilled in the art.

[0031] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0032] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for recommending a diagnosis and treatment path based on IBS multidimensional data, characterized by, Includes the following steps: S1. Construct an IBS treatment plan library, which contains standardized treatment plans corresponding to different diagnostic types and severity levels of IBS. Each standardized treatment plan includes at least follow-up recommendations, medication recommendations, probiotic recommendations, and nursing guidance. Each treatment plan is associated with a corresponding IBS multidimensional data feature threshold. The treatment plan library also has a preset data update mechanism to regularly integrate the latest clinical treatment guidelines, expert consensus, and clinical treatment cases to iteratively optimize the treatment plans and associated feature thresholds in the library. S2. Collect IBS multidimensional diagnostic data from patients. The IBS multidimensional diagnostic data includes at least symptom data, physical sign data, laboratory test data, and medical history data. Symptom data is collected through a combination of patient self-reporting and clinical consultation with doctors. Physical sign data is collected through medical testing equipment. Laboratory test data is obtained synchronously from the hospital's testing system. Medical history data is extracted from the electronic medical record system and supplemented with confirmation from the patient. S3. Preprocess the collected IBS multidimensional diagnostic data, including data cleaning, outlier removal, and data standardization, to obtain standardized diagnostic data. During the data cleaning process, missing values ​​and outliers are marked and processing records are kept. After data standardization, a data standardization report is generated for subsequent tracking and verification of matching results. S4. Match the standardized diagnostic data with the IBS multidimensional data feature thresholds associated with each treatment plan in the treatment plan library, calculate the matching degree using a preset similarity algorithm, and select candidate treatment plans whose matching degree meets the preset threshold; if the matching degree does not reach the preset threshold, select the top 3 treatment plans with the highest matching degree as candidate treatment plans, and generate a matching degree insufficient prompt and manual intervention suggestion. S5. Prioritize candidate treatment options based on matching degree, patient age, complication status, drug allergy history, and underlying diseases, with matching degree having the highest weight, accounting for no less than 60%. Generate and output personalized IBS treatment pathway recommendations based on the ranking results. The recommendations include specific follow-up locations, follow-up times, follow-up items, drug types, drug dosages, drug administration times and methods, probiotic types, probiotic dosages and cycles, and an explanation of the basis for the recommendations, clarifying the matching data and logic corresponding to each recommendation item.

2. The method for recommending treatment pathways based on IBS multidimensional data according to claim 1, characterized in that, The IBS multidimensional data feature thresholds mentioned in step S1 include symptom feature thresholds, sign feature thresholds, laboratory test feature thresholds, and medical history feature thresholds. The symptom features include the frequency and severity of abdominal pain, bloating, diarrhea, constipation, and abnormal defecation characteristics. The laboratory test data include stool routine, blood routine, intestinal flora detection, and inflammatory marker detection data.

3. The method for recommending treatment pathways based on IBS multidimensional data according to claim 1, characterized in that, The data preprocessing in step S3 specifically includes: removing diagnostic data with a missing value ratio exceeding a preset proportion, supplementing diagnostic data with a missing value ratio below a preset proportion using interpolation, and standardizing numerical diagnostic data using the Z-score standardization method to convert categorical diagnostic data into coded form.

4. The method for recommending treatment pathways based on IBS multidimensional data according to claim 1, characterized in that, In step S4, the matching process uses a cosine similarity algorithm to calculate the matching degree between standardized diagnostic data and the IBS multidimensional data feature thresholds associated with each treatment plan. The preset matching degree threshold is not less than 80%.

5. The method for recommending treatment pathways based on IBS multidimensional data according to claim 1, characterized in that, The priority ranking in step S5 is based on matching degree, patient age, complication status and drug allergy history, with matching degree having the highest weight, accounting for no less than 60%.

6. The method for recommending treatment pathways based on IBS multidimensional data according to claim 1, characterized in that, It also includes step S6: updating the output treatment pathway recommendation results in real time, and adjusting the data feature thresholds and priority of candidate treatment plans in the treatment plan library based on the patient's subsequent follow-up data, symptom change data and treatment feedback data.

7. The method for recommending treatment pathways based on IBS multidimensional data according to claim 1, characterized in that, The medical history data mentioned in step S2 includes previous IBS episodes, medication history, probiotic history, family medical history, and dietary preference data.

8. The method for recommending treatment pathways based on IBS multidimensional data according to claim 1, characterized in that, The recommendations output in step S5 also include dietary guidance and lifestyle adjustment suggestions. The dietary guidance provides differentiated food taboos and recommendation lists for different IBS subtypes.

Images