Using AI language models to help diagnose and recommend treatments for urologic conditions
Evaluation of AI Large Models for Diagnosis and Treatment in Real-World Cases: Multicenter Retrospective Study
This project will test whether three AI language models (ChatGPT, Gemini, DeepSeek) can accurately recognize urologic diseases and suggest diagnoses and treatments from archived hospital records of adult patients.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 800 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | First Affiliated Hospital of Fujian Medical University Academic / other |
| Locations | 1 site (Fuzhou) |
| Trial ID | NCT07378358 on ClinicalTrials.gov |
What this trial studies
This multicenter retrospective project will run three large language models—ChatGPT, Gemini, and DeepSeek—on 800 archived inpatient urology records from four tertiary hospitals to compare model outputs to documented diagnoses and treatment plans. Model-generated disease recognition, preliminary diagnoses, and treatment recommendations will be compared against the original clinical records and discharge decisions to measure accuracy and applicability. Data will be anonymized and used with prior patient or legal representative consent, and cases with missing core information will be excluded. The aim is to map strengths and limitations of LLM-based decision support in real-world clinical documentation.
Who should consider this trial
Good fit: Ideal candidates are adult patients (18+) whose complete inpatient urology medical records from the participating hospitals are archived and available with consent.
Not a fit: Patients without complete medical records, those under 18, or cases with complex individualized needs not captured in records are unlikely to benefit.
Why it matters
Potential benefit: If successful, these AI models could provide faster, more consistent decision support for clinicians, potentially improving diagnosis and treatment planning in urology.
How similar studies have performed: Early research shows LLMs can perform well on some diagnostic and clinical reasoning tasks, but real-world retrospective validations are limited and results have been mixed.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * The case data is sourced from the four hospitals involved in the study, with complete and authentic diagnosis and treatment records. * Patients must be 18 years or older, with no gender restrictions. * Complete medical records, including the following core information: patient' s basic information, present illness history, past medical history, physical examination, and auxiliary examinations (including laboratory and imaging tests). * A clear discharge diagnosis and treatment plan (including therapeutic measures and follow-up arrangements). * Medical records have been archived, with objective and accurate information that has not been altered. * The patient or their legal representative has provided informed consent, agreeing to the use of their anonymized medical data for research analysis. Exclusion Criteria: * Medical records with significant missing information, such as key clinical details (present illness history, diagnostic or treatment records, etc.). * Cases where the diagnosis or treatment plan is unclear, or where treatment has not been fully completed for an initial diagnosis. * Cases where the primary diagnosis is not urological. * Cases with major errors or inconsistencies in the records that could affect further assessment. * Medical records in special formats or images that are not readable (e.g., handwritten notes, non-standard documentation). * Patients who have not signed the informed consent form or who refuse to allow their medical data to be used for research.
Where this trial is running
Fuzhou
- The First Affiliated Hospital of Fujian Medical University — Fuzhou, China (Recruiting)
Study contacts
- Study coordinator: Ning Xu
- Email: drxun@fjmu.edu.cn
- Phone: +86-13235907575
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.