Research on an Intelligent Health Recommendation System for Chronic Disease Comorbidity Integrating TCM

Research on an Intelligent Health Preservation Recommendation System for Chronic Disease Comorbidity Based on the Integration of Traditional Chinese Medicine Constitution Database and Multimodal Large Language Models

1. Construct a Traditional Chinese Medicine (TCM) constitution database, clarify the distribution patterns of TCM constitution in populations with comorbid "three-high" conditions (hypertension, hyperlipidemia, and hyperglycemia) and their associations with metabolic indicators. Establish a "constitution-comorbidity-metabolism" relationship model to provide a basis for personalized intervention and the development of an AI platform.
2. Develop the AI-HEALS system by integrating the TCM constitution database with multimodal large language models. This system will generate personalized intervention plans and provide intelligent interactive Q&A capabilities to enhance patient intervention adherence.
3. Evaluate the clinical application effectiveness of the AI-HEALS system, explore the relationship between changes in constitution and intervention outcomes, and validate the TCM intervention pathway of "regulating constitution to promote health." This will provide both theoretical and practical guidance for the dynamic regulation and precise intervention of TCM constitution.

Study Overview

• Status: Not yet recruiting
• Conditions: TCM Constitution Theory
• Intervention / Treatment: Other: Multimodal AI Models

Detailed Description

This project combines Traditional Chinese Medicine (TCM) constitution theory with large language models (LLMs) through interdisciplinary integration, constructing a dynamically empowered intelligent health recommendation system for TCM. It promotes the deep integration of the "treatment based on constitution differentiation" concept with artificial intelligence. The significance of this research is mainly reflected in the following two aspects:

At the theoretical level, this study helps expand the knowledge representation and computational modeling methods of TCM constitution theory within the framework of modern artificial intelligence. It advances the application and transformation of the TCM concept of "preventive treatment" in big data and intelligent reasoning scenarios, provides new perspectives for research on the mechanisms linking TCM constitution and chronic disease comorbidities, and fosters cross-integration between TCM theoretical systems and modern medical information science.

At the practical level, the research relies on real clinical data and multimodal AI models to establish a structured, standardized TCM constitution database. It develops a health education system with individualized identification, intelligent recommendation, and dynamic intervention functions, suitable for personalized management and early warning in populations with chronic disease comorbidities. The project outcomes will help enhance individual health literacy and quality of life, alleviate the burden of chronic diseases, promote the practical application of TCM in primary healthcare services and digital medicine, and demonstrate significant social value and broad prospects for widespread adoption.

• Study Type: Observational
• Enrollment (Estimated): 195

Contacts and Locations

• Study Contact: Name: qingqing liu; Phone Number: 13858089867; Email: qingliuq@zju.edu.cn
• Study Contact Backup: Name: yibo wu; Phone Number: 13758089867; Email: bjmuwuyibo@outlook.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

A standardized survey was conducted using the Classification and Assessment Criteria of Traditional Chinese Medicine Constitution (Standard of the China Association of Chinese Medicine)constitution identification scale. Trained TCM practitioners and nursing staff performed constitution assessment to identify the dominant constitution type and any coexisting constitution types. Additionally, patient basic information, disease diagnosis details, and recent metabolic indicators such as blood pressure, fasting blood glucose, glycosylated hemoglobin, and blood lipid levels were collected.

Description

Inclusion Criteria:

Age ≥ 18 years; Clear diagnosis of hypertension, type 2 diabetes, and hyperlipidemia, and a comorbid condition involving all three diseases; Stable disease condition with no recent acute complications; Capable of completing questionnaires, and willing to provide informed consent to voluntarily participate in the study.

Exclusion Criteria:

Patients in the acute phase of the three high diseases (hypertension, diabetes, hyperlipidemia) or with severe complications (such as acute myocardial infarction or stroke); Patients with other major diseases that may affect constitution assessment or intervention implementation, such as malignant tumors, severe liver or kidney dysfunction, active tuberculosis, or mental illness; Patients who have received systematic Traditional Chinese Medicine treatment (e.g., herbal decoctions or acupuncture) within the past month, which may influence the initial assessment of constitution type; Pregnant or lactating women; Individuals unable to cooperate with measurements, with language communication barriers, or cognitive impairments; Patients participating in other interventional clinical studies.

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Traditional Chinese Medicine (TCM) Constitution Database	Develop the AI-HEALS intelligent intervention platform, equipped with functions such as constitution identification, intelligent recommendations, and interactive Q&A, achieving a Q&A accuracy rate of over 90%.	Observation period: 3 years

Collaborators and Investigators

• Sponsor: The Fourth Affiliated Hospital of Zhejiang University School of Medicine

Study record dates

Study Major Dates

• Study Start (Estimated): December 20, 2025
• Primary Completion (Estimated): December 30, 2028
• Study Completion (Estimated): December 30, 2028

Study Registration Dates

• First Submitted: December 15, 2025
• First Submitted That Met QC Criteria: December 15, 2025
• First Posted (Actual): December 29, 2025

Study Record Updates

• Last Update Posted (Actual): December 29, 2025
• Last Update Submitted That Met QC Criteria: December 15, 2025
• Last Verified: December 1, 2025

More Information

Terms related to this study

• Other Study ID Numbers: KY-2025-295

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No