# Comparative Analysis of Diagnostic Accuracy and Case Difficulty Assessment of Three Large Language Models

> **NCT07732985** · — · NOT_YET_RECRUITING · sponsor: **Cairo University** · enrollment: 342 (estimated)

## Conditions studied

- Pulp and Periapical Tissue Disease

## Interventions

- **DEVICE:** ChatGPT (GPT-5.5 Pro), Gemini 3.1 Pro, Claude Opus 4.7

## Key facts

- **NCT ID:** NCT07732985
- **Lead sponsor:** Cairo University
- **Sponsor class:** OTHER
- **Phase:** —
- **Study type:** OBSERVATIONAL
- **Status:** NOT_YET_RECRUITING
- **Start date:** 2026-09-01
- **Primary completion:** 2026-12
- **Final completion:** 2027-01
- **Target enrollment:** 342 (ESTIMATED)
- **Last updated:** 2026-07-29


## Primary source

ClinicalTrials.gov registry: https://clinicaltrials.gov/study/NCT07732985

## Citation

> US National Library of Medicine, ClinicalTrials.gov registration NCT07732985, "Comparative Analysis of Diagnostic Accuracy and Case Difficulty Assessment of Three Large Language Models". Retrieved via MORVS 2026-10-20 from https://api.morvs.ai/clinical/NCT07732985. Licensed CC0.

---

*[Clinical trials dataset](/datasets/clinical-trials) · CC0 1.0*