Registered title, quoted from ClinicalTrials.gov
Validating a Medical AI Fine-Tuning Platform for Major Diseases
An open trial on stomach cancer, registered on ClinicalTrials.gov. Led by Beijing Friendship Hospital; 0 other hospitals on this site are listed as study sites.
Status, phase and start date as registered on ClinicalTrials.gov on 8 Nov 2026; the registry may have changed since. Whether someone can take part is decided by the study team. Not medical advice.
The study team’s contact details are on the registry record. This site does not pass on enquiries.
Hospitals in mainland China listed for this trial 1
Hospitals on this site that the registry record names as lead sponsor or study site, where the site is open. Lead sponsor first, then study sites A–Z.
The record may name more sites, including outside mainland China, and sites can open or close during a trial. Full list of sites on ClinicalTrials.gov
Source: ClinicalTrials.gov record NCT07795645, read on 8 Nov 2026; hospital names matched to this site’s hospital list. How names are matched
Checklist for this trial 1
Only the points this trial’s record answers definitely: the registered age and sex, and criteria lines that state a number, score, stage or named test, quoted word for word. Tick a point once it has been compared with the medical records.
Show the checklist (1 points)Hide the checklist
18 years to Not stated; sex: all
Registered eligibility fields
Ticks stay on this page; they are not saved or sent. Meeting every point is not enough: the study team decides after its own screening. Lines that need the team’s judgement, such as “sufficient organ function”, are not in this list; they are in the full criteria below. Not stated definitely in this record: diagnosis and how it was confirmed; stage or severity, as the trial defines it; earlier treatment; day-to-day activity level; blood tests: counts, liver and kidney function; scans and measurable lesions; other conditions the trial excludes; pregnancy, breastfeeding and contraception.
Questions to ask the study team
Picked from the record by fixed keyword rules (not by AI, not checked by hand) and quoted from ClinicalTrials.gov, NCT07795645, read on 10 Nov 2026.
Registered criteria
Quoted as registered on ClinicalTrials.gov, in English, read on 10 Nov 2026. This site has not checked, shortened or translated them. Meeting the written criteria is not enough: the study team decides after its own screening.
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.
- 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:
- Participant requests to withdraw from the study during the research process
- Investigator determines that the study should be terminated based on consideration of the participant's best interests
Quoted from ClinicalTrials.gov, NCT07795645, participation criteria. Read on 10 Nov 2026.
Where this information comes from
The registry record
ClinicalTrials.gov (US National Library of Medicine), record NCT07795645, read on 8 Nov 2026. A trial has a page here while its overall status is recruiting, not yet recruiting or enrolling by invitation and at least one listed hospital’s site is open. Trials registered only in China’s own registry (ChiCTR) are not included.
Diseases and hospitals
The trial is listed under a disease when this site’s ClinicalTrials.gov search for that disease in China returns it. Sponsor and site names in the record are matched to this site’s hospital list (ROR identifiers, checked aliases). Definitions
What is left out
Names of investigators and contact persons in the record, and anything not in the record. The title and criteria are quoted from the record.