Medical AI fine-tuning platform for major diseases

Is this trial a fit for you?

A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.

What this trial studies

This multicenter observational project collects and combines retrospective and prospective medical records from three Beijing hospitals to fine-tune and validate a large medical language model. It builds a big data dataset, a medical knowledge graph, and a platform for fine-tuning the model to support department-specific consultation and diagnostic needs. The study uses inpatient records for training and validation and outpatient records for training, with block randomization to minimize bias. The goal is to standardize services, improve efficiency, and support graded diagnosis and treatment across hospital levels. Data handling and model development are aligned with existing guidelines, literature, and expert resources.

Why it matters

Who can join: the full rules

Inclusion Criteria:

* Retrospective Historical Medical Records: patients with stomach, cardiovascular and cerebrovascular diseases from September 2014 to August 2024 were enrolled.

  (1) Age ≥ 18 years; (2) Diagnosed with any of the following: chronic gastritis, gastric cancer, gastro esophageal reflux, coronary artery disease, or stroke.
* Prospective Historical Medical Records: Patients with stomach, cardiovascular and cerebrovascular diseases from September 2024 and August 2027 are enrolled.Outpatient and emergency records are used for large model training, and inpatient records are used for both training and internal validation. Inpatient records are allocated to the training set and internal validation set at a 3:1 ratio. Block randomization is used to reduce bias. Each sample is assigned a raw random number uniformly distributed between 0 and 1. Under the block design, each block contains 4 samples. Within each block, samples are ranked by the raw random number and assigned a random code from 1 to 4. The randomization schedule is prepared by a statistician on a computer system before the start of the study and printed on opaque, sealed envelopes.

  1. Age ≥ 18 years; (2) Clinically diagnosed with one of the following: chronic gastritis, gastric cancer, gastro esophageal reflux, coronary artery disease, or stroke; (3) Patient or legally authorized representative able to understand the study and provide informed consent; (4) Clinically stable and able to complete the study procedures

Exclusion Criteria:

* Retrospective Historical Medical Records:

  (1) Records with information that cannot be correctly read due to modification or smudging; (2) Examination reports that are smudged or damaged, making them uninterpretable by the large model.
* Prospective Historical Medical Records:

  (1) Severe psychiatric disorders (e.g., depression, mania, epilepsy, schizophrenia); (2) Judged by the investigator to be unable to comply with study procedures; (3) Poor audio quality due to accent or recording issues that prevents accurate data capture; (4) Laboratory or imaging reports that are smudged or damaged, making them uninterpretable by the model
* Withdrawal Criteria:

Prospective Historical Medical Records:

1. Participant requests to withdraw from the study during the research process
2. Investigator determines that the study should be terminated based on consideration of the participant's best interests

Where it's running

• Beijing Friendship Hospital, Capital Medical University
  Beijing, China Recruiting

Study contacts

• Study coordinator: Zhi zheng, Attending surgon
• Email: zhengzhi@ccmu.edu.cn
• Phone: +86-13811132175

Similar studies

Other studies for the same condition or treatment. Recruiting studies are listed first.

• Managing multiple medications in older adults with chronic diseases

  This project will see if taking many different medicines changes the health outlook of people aged 65 and older who have chronic conditions.

  Recruiting Xijing Hospital · Xi'an, Shaanxi · NCT07180368

• Deep phenotyping to explore recovery in young adults after stroke

  This project will test whether a detailed health and sample-collection approach (deep phenotyping) is practical and acceptable for people aged 18–55 who have had a stroke.

  Recruiting The Florey Institute of Neuroscience and Mental Health · Heidelberg, Victoria and 1 other locations · NCT07019493

• Stem cell therapy for chronic stroke recovery

  This study is testing whether using a patient's own stem cells can help people with long-term stroke recovery feel better and improve their daily functioning.

  Recruiting Phase 2 Hokkaido University Hospital · Sapporo, Hokkaido · NCT06752720

• Investigating heart-related side effects of cancer immunotherapy

  This study is testing whether cancer immunotherapy treatments can cause heart problems in patients with certain types of cancer.

  Recruiting Academisch Medisch Centrum - Universiteit van Amsterdam (AMC-UvA) · Amsterdam, North Holland · NCT06519292

• Pharmacy-led intervention to improve medication adherence after hospital discharge

  This study tests a pharmacy-led program to help low-income patients with multiple chronic conditions take their medications correctly after leaving the hospital.

  Recruiting University of Tennessee · Knoxville, Tennessee and 1 other locations · NCT06374277

• Using advanced cardiac imaging to improve treatment for patients with chest pain

  This study is testing if using advanced heart imaging techniques can help people with chest pain get better treatment and feel healthier compared to standard care.

  Recruiting Copenhagen University Hospital, Rigshospitalet · Copenhagen · NCT04709900

How to take part

1. Review the eligibility criteria above with your treating physician.
2. Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
3. Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.