Clinical trials: Large Language Models
Anxiety Disorders, OCD
Digital Coach to Support Exposure Therapy Homework for Anxious Youth
This study is testing a digital tool called BraveBot for young people who are receiving cognitive behavioral therapy (CBT) for anxiety, OCD, or related problems. BraveBot is a computer program, not a person.
- Trial name
- NCT07666672
- Testing
- BraveBot, Self-Guided Exposure Therapy Homework
- Where
- 3 sites in United States
- Volunteers
- 50 people
- Sponsor
- Massachusetts General Hospital
Ophthalmology, Large Language Models
A Multimodal AI Agent for Ophthalmic Clinical Decision Support
This study is a multicenter randomized controlled trial evaluating the effectiveness and safety of EyeAgent, a multimodal artificial intelligence (AI) agent designed to assist ophthalmologists in clinical decision-making.
- Conditions
- Ophthalmology, Large Language Models, AI Agent, Eye Disease
- Trial name
- NCT07401459
- Testing
- EyeAgent AI system
- Where
- China
- Volunteers
- 300 people, healthy volunteers welcome
- Sponsor
- The Hong Kong Polytechnic University
Peritoneal Dialysis (PD), Large Language Models
A Simulated Case Study of a Peritoneal Dialysis-Specialized Large Language Model Assisting Doctors in Improving Decision-Making in Peritoneal Dialysis Management
This study is a randomized controlled trial based on simulated clinical cases, aiming to establish a standardized evaluation system for PD physicians, to assess the differences in PD management quality between a workflow assisted…
- Trial name
- NCT07724327
- Testing
- Peritoneal dialysis-specialized large language model.
- Where
- China
- Volunteers
- 100 people, healthy volunteers welcome
- Sponsor
- First Affiliated Hospital, Sun Yat-Sen University
Breast Cancer
An AI Model Predicts the Efficacy of Neoadjuvant Chemotherapy for Breast Cancer: a Multicenter, Bidirectional Cohort Study
Neoadjuvant chemotherapy is an important part of the systematic treatment of breast cancer, and it is of great clinical significance to predict the efficacy of neoadjuvant chemotherapy in early stage.
- Trial name
- NCT06510127
- Where
- China
- Volunteers
- 840 people
- Sponsor
- Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University
Rheumatoid Arthritis (RA, Osteoporosis
Generative AI Impact on Rheumatoid Arthritis Complications Diagnosis
Generative AI (GenAI) based on large language models (LLMs) is expected to improve the diagnosis and treatment of autoimmune diseases.
- Conditions
- Rheumatoid Arthritis (RA, Osteoporosis, Osteoarthritis, Interstitial Lung Disease
- Trial name
- NCT07301892
- Testing
- Generative AI prediction report for RA complications
- Where
- China
- Volunteers
- 57 people
- Sponsor
- Guang'anmen Hospital of China Academy of Chinese Medical Sciences
Pulp and Periapical Tissue Disease
Comparative Analysis of Diagnostic Accuracy and Case Difficulty Assessment of Three Large Language Models
This prospective, blinded diagnostic accuracy study aims to compare the performance of three large language models-ChatGPT (GPT-5.5 Pro), Gemini 3.1 Pro, and Claude Opus 4.7-in endodontic diagnosis and case difficulty assessment.
- Trial name
- NCT07732985
- Testing
- ChatGPT (GPT-5.5 Pro), Gemini 3.1 Pro, Claude Opus 4.7
- Volunteers
- 342 people, healthy volunteers welcome
- Sponsor
- Cairo University
Health Communication, Patient Discharge
AI-Assisted Discharge Documents for Children and Families in a Pediatric Emergency Department
This study compared two ways of preparing discharge documents for children and families leaving a pediatric emergency department.
- Trial name
- EA (NCT07874659)
- Testing
- Conventional Discharge Documentation Workflow, LLM-Assisted Discharge Documentation Workflow
- Where
- 2 sites in France
- Volunteers
- 153 people
- Sponsor
- University Hospital, Montpellier
Medical Student
AI-Assisted Learning in Medicine
This multi-center retrospective cohort study investigates the real-world impact of integrating MetaGP-Edu, a proprietary AI tool fine-tuned for medical education, into the undergraduate Internal Medicine curriculum.
- Trial name
- NCT06945159
- Where
- 2 sites in China
- Volunteers
- 1,632 people, healthy volunteers welcome
- Sponsor
- Kang Zhang
Acute Respiratory Distress Syndrome, Pneumonia in Children
Using Artificial Intelligence To Improve Ventilator Settings For Intensive Care Patients
This observational study aims to determine whether an AI-assisted decision support system can improve clinical outcomes for mechanically ventilated pediatric patients (aged 1 month to 18 years) in the PICU, compared to standard…
- Conditions
- Acute Respiratory Distress Syndrome, Pneumonia in Children, Respiratory Failure (Pediatric Patients)
- Trial name
- NCT07592039
- Where
- China
- Volunteers
- 2,000 people
- Sponsor
- Wu Rongzhou
Pulpal and Periapical Diseases
Diagnostic Accuracy of Educated Large Language Models in Endodontic Diagnosis and Case Difficulty Assessment
This diagnostic test accuracy (DTA) study aims to evaluate the diagnostic performance of educated large language models (Educated ChatGPT (GPT-5.5 Pro), Educated Gemini 3.1 Pro, and Educated Claude Opus 4.7) in endodontic…
- Trial name
- NCT07706894
- Testing
- ChatGPT, Gemini, Calude
- Volunteers
- 349 people
- Sponsor
- Cairo University
HCM - Hypertrophic Cardiomyopathy
Automated Reports Generation of Cardiovascular Magnetic Resonance Imaging
The goal of this observational study is to evaluate the accuracy, completeness, and clinical consistency of large language model-generated cardiac magnetic resonance (CMR) imaging reports compared with expert radiologist reports…
- Trial name
- NCT07340762
- Testing
- large lanuage model
- Where
- China
- Volunteers
- 20,000 people, healthy volunteers welcome
- Sponsor
- Chinese Academy of Medical Sciences, Fuwai Hospital
Large Language Model
Evaluating the Acceptability of AI-Personalized Virtual Reality Picture Books for Hospitalized Pediatric Patients
Hospitalization strips pediatric patients of the environments, objects, and people that shape their daily lives. Hospitalized pediatric patients routinely experience painful procedures, psychological distress, boredom, and a…
- Trial name
- LLM-audiobook (NCT07637617)
- Testing
- LLM-audiobook
- Volunteers
- 15 people
- Sponsor
- Stanford University
HIV Infections, Breast Cancer
The MARVIN Chatbots to Provide Information for Different Health Conditions
This research is a continuation of a usability study with the MARVIN chatbot. The investigators aim to adapt the MARVIN chatbot to open it to other health domains (e.g. breast cancer) and populations (e.g. pharmacists).
- Conditions
- HIV Infections, Breast Cancer, Pediatric Emergency Medicine
- Trial name
- NCT05789901
- Testing
- MARVIN, MARVIN-Pharma, MARVINA
- Where
- 2 sites in Canada
- Volunteers
- 400 people, healthy volunteers welcome
- Sponsor
- McGill University Health Centre/Research Institute of the McGill University Health Centre
Spinal Cord Injury
Large Language Models for Epidural Stimulation Electrode Mapping in Spinal Cord Injury
This observational and methodological study aims to compare the performance of large language models in generating electrode contact configuration recommendations for epidural electrical stimulation in spinal cord injury.
- Trial name
- NCT07817238
- Testing
- ChatGPT-4o Large Language Model, Claude Large Language Model, Grok 3 Large Language Model
- Where
- Turkey (Türkiye)
- Volunteers
- 20 people
- Sponsor
- Istanbul Gelisim University
Colorectal Cancer
Evaluating AI and Human Expert Decisions in Colorectal Cancer
The goal of this observational study is to evaluate the decision-making consistency between large language models (LLMs) and expert multidisciplinary teams (MDTs) in adult patients diagnosed with colorectal cancer who underwent…
- Trial name
- NCT07045207
- Testing
- LLM-MDT
- Where
- China
- Volunteers
- 1,500 people
- Sponsor
- Peking University Cancer Hospital & Institute
Pediatric Patients, Pediatric Patients in Hospital Settings
Impact of Conversational Approaches in Pediatric Social Robot-Mediated Interventions
This study examines how different robot dialogue systems (rule-based vs. large language model-based) and content types (emotional support vs.
- Conditions
- Pediatric Patients, Pediatric Patients in Hospital Settings, Hospitalized Children
- Trial name
- PRIA (NCT07389902)
- Testing
- Robot-Mediated Emotional Support Activity, Robot-Mediated Safety Education Activity
- Where
- South Korea
- Volunteers
- 60 people, healthy volunteers welcome
- Sponsor
- Samsung Medical Center
Non-emergency Ocular Diseases
Evaluate the Performance of Large Language Models in Ophthalmologic Patient Consultation
The intelligent image models lack an understanding of diagnostic and treatment logic, and have not considered textual information such as symptoms and signs.
- Trial name
- NCT06824389
- Testing
- Consultation Model of large language model in Ophthalmology Clinics
- Where
- China
- Volunteers
- 172 people, healthy volunteers welcome
- Sponsor
- Zhongshan Ophthalmic Center, Sun Yat-sen University
Healthy Adult
Effectiveness of AI-Assisted Antibiotic Prescribing
This randomized controlled trial aims to evaluate the impact of providing LLM access to physicians on antibiotic prescribing appropriateness, using a composite outcome instrument, the Antibiotic Prescribing Appropriateness Score…
- Trial name
- NCT07833293
- Testing
- ChatGPT
- Where
- Pakistan
- Volunteers
- 50 people, healthy volunteers welcome
- Sponsor
- Lahore University of Management Sciences
Neurology
Physician Diagnosis of Neurologic Cases With Large Language Models
This study is a prospective randomized controlled trial that aims to evaluate whether large language model (LLM) assistance improves physicians' diagnostic performance compared with conventional assistance.
- Trial name
- NCT07344792
- Testing
- LLM assistance
- Where
- 3 sites in China
- Volunteers
- 40 people, healthy volunteers welcome
- Sponsor
- Capital Medical University
Diagnosis
The Impact of Large Language Models on Diagnostic Reasoning Among LLM-Trained Medical Doctors
This study aims to evaluate whether large language model-trained medical doctors demonstrate enhanced diagnostic reasoning performance when utilizing ChatGPT-4o alongside conventional resources compared to using conventional…
- Trial name
- NCT06774612
- Testing
- ChatGPT-4o
- Where
- Pakistan
- Volunteers
- 60 people, healthy volunteers welcome
- Sponsor
- Lahore University of Management Sciences