Building a Traditional Chinese Medicine Clinical Diagnosis and Treatment Database
- Conditions
- Artificial IntelligenceMedicine, Chinese Traditional
- Interventions
- Other: Observational study, non intervention
- Registration Number
- NCT06525025
- Lead Sponsor
- Fifth Affiliated Hospital, Sun Yat-Sen University
- Brief Summary
Collecting Traditional Chinese Medicine (TCM) clinical diagnosis and treatment data, including doctor-patient dialogues, tongue diagnosis, facial diagnosis, and TCM constitution information, to construct databases for tongue diagnosis, TCM constitution, and doctor-patient dialogues. Based on artificial intelligence technology, engage in research related to the standardization and intelligentization of TCM.
- Detailed Description
The technological principles of large language models align with the empirical medical principles of Traditional Chinese Medicine (TCM), and the rise of large model technology can greatly promote the progress of TCM. However, there is currently a lack of clinical diagnosis and treatment databases with TCM characteristics for training TCM artificial intelligence(AI) large models.
At present, a large-scale tongue image database has not yet been established for modeling common TCM tongue appearances, thereby ensuring the accuracy and consistency of TCM diagnosis and promoting the objective standardization of TCM diagnostic development.
Considering the feedback from the subjects in clinical work that the TCM constitution survey questionnaire has a large volume, takes a long time, and has certain subjective issues, we plan to carry out a large-scale clinical observational study to optimize the process of TCM constitution identification.
Traditional Chinese Medicine (TCM) doctor-patient dialogues and medical record writing are essential entities generated during the TCM diagnosis and treatment process. Assisting in consultation, medical record generation, and treatment plan recommendations based on doctor-patient dialogues have significant clinical and research value. Therefore, we plan to collect a large number of doctor-patient dialogues and outpatient medical records to construct a doctor-patient dialogue database, preparing in advance for optimizing interactive large-scale TCM models.
In summary, the research on constructing a TCM clinical diagnosis and treatment database has important clinical and scientific research value. This will help to improve the standardization and normalization of TCM diagnosis and treatment, and also support the modernization and internationalization of TCM. By applying big data analysis and artificial intelligence technology, it is possible to delve deeper into TCM diagnosis and treatment information, providing richer and more accurate data resources for clinical decision-making and scientific research exploration in TCM.
Recruitment & Eligibility
- Status
- NOT_YET_RECRUITING
- Sex
- All
- Target Recruitment
- 80000
- People who come to the hospital for physical examination and medical treatment；
- Participants voluntarily participate in the study.
- Subjects with difficulty in tongue extension, communication, etc. who cannot cooperate with data collection；
- The researchers determined that there were other factors that may have forced the subjects to terminate the study.
Study & Design
- Study Type
- OBSERVATIONAL
- Study Design
- Not specified
- Arm && Interventions
Group Intervention Description Traditional Chinese Medicine Constitution Data Group Observational study, non intervention Internally, using random allocation, divided into training group and validation group Traditional Chinese Medicine Tongue Image Group Observational study, non intervention Internally, using random allocation, divided into training group and validation group Traditional Chinese Medicine Doctor Patient Dialogue Data Group Observational study, non intervention Data used for fine-tuning traditional Chinese medicine models
- Primary Outcome Measures
Name Time Method Development of a tongue image-based machine learning tool 20 months 1. It is anticipated to enroll 50,000 samples to establish a Traditional Chinese Medicine (TCM) tongue appearance database.
2. The tongue images will undergo quality selection and preprocessing.
3. The tongue images will be manually annotated, with 40% allocated to the training group and 60% to the testing group.
4. For the training group: A TCM tongue appearance model will be constructed based on the manually annotated tongue images.
5. For the testing group: The TCM tongue appearance model will be used to interpret the tongue images.
6. Analyze the consistency between the tongue appearance interpretations by the model built from the training group and the readings by TCM physicians for the testing group's tongue images.
- Secondary Outcome Measures
Name Time Method TCM Constitution Multimodal Model 20 months 1. It is projected to include 20,000 samples to construct a Traditional Chinese Medicine (TCM) constitution database.
2. Of these, 15,000 samples will complete the TCM constitution survey questionnaire and have their tongue and facial diagnosis data collected.
3. Based on the data from step 2, a multimodal TCM constitution assessment model will be constructed.
4. An additional 5,000 samples will be tested, first by completing the multimodal TCM constitution assessment model, and then the TCM constitution survey questionnaire.
5. Analyze the consistency between the readings of the TCM constitution assessment model and the results from the TCM constitution survey questionnaire generation, and treatment plan recommendations, prepare in advance for optimizing interactive large-scale TCM models.