Physician Reasoning on Diagnostic Cases With Large Language Models

Status Completed

Clinical Trial Summary

This study will evaluate the effect of providing access to GPT-4, a large language model, compared to traditional diagnostic decision support tools on performance on case-based diagnostic reasoning tasks.

Clinical Trial Description

Artificial intelligence (AI) technologies, specifically advanced large language models like OpenAI's ChatGPT, have the potential to improve medical decision-making. Although ChatGPT-4 was not developed for its use in medical-specific applications, it has demonstrated promise in various healthcare contexts, including medical note-writing, addressing patient inquiries, and facilitating medical consultation. However, little is known about how ChatGPT augments the clinical reasoning abilities of clinicians. Clinical reasoning is a complex process involving pattern recognition, knowledge application, and probabilistic reasoning. Integrating AI tools like ChatGPT-4 into physician workflows could potentially help reduce clinician workload and decrease the likelihood of missed diagnoses. However, ChatGPT-4 was not developed for the purpose of clinical reasoning nor has it been validated for this purpose. Further, it may be subject to disinformation, including convincing confabulations that may mislead clinicians. If clinicians misuse this tool, it may not improve diagnostic reasoning and could even cause harm. Therefore, it is important to study how clinicians use large language models to augment clinical reasoning prior to routine incorporation into patient care. In this study, we will randomize participants to answer diagnostic cases with or without access to ChatGPT-4. The participants will be asked to give three differential diagnoses for each case, with supporting and opposing findings for each diagnosis. Additionally they will be asked to provide their top diagnosis along with next diagnostic steps. Answers will be graded by independent reviewers blinded to treatment assignment. ;

Study Design

Related Conditions & MeSH terms

Clinical Trial Details

NCT number	NCT06157944
Study type	Interventional
Source	Stanford University
Contact
Status	Completed
Phase	N/A
Start date	November 29, 2023
Completion date	December 30, 2023

View Details

See also
Status	Clinical Trial	Phase
Not yet recruiting	`NCT05845112` - Start Taking Action For TB Diagnosis
Not yet recruiting	`NCT05889312` - Assessing Cancer Treatment Response to Therapy Using 18F-FSPG PET
Completed	`NCT01194557` - Introducing Rapid Diagnostic Tests Into the Private Health Sector	N/A
Completed	`NCT04257955` - COMMUNIcation and Patient Engagement at Diagnosis of PAncreatic CAncer
Recruiting	`NCT05698212` - Proof of Concept Study to Eval MetriDx Lab-developed Test to Identify Endometriosis-specific Bio Markers	Phase 2
Recruiting	`NCT03372330` - Peripheral Artery Disease and Sepsis Outcomes	N/A
Active, not recruiting	`NCT06134011` - A Multi-omics-based Metabolic Typing Study of Gastric Cancer
Recruiting	`NCT06289803` - The Application of Probe Confocal Laser Endomicroscopy in Pancreatic Tumor Surgery	N/A
Not yet recruiting	`NCT06025240` - Expanding the Scope of Post-transplant HLA-specific Antibody Detection and Monitoring in Renal Transplant Recipients
Not yet recruiting	`NCT05464576` - Tumor Staging T of Bladder Tumours: Correlation of MRI and Anatomopathologic Analysis	N/A
Completed	`NCT06185127` - Dexmedetomidine-ketamine Combination Versus Fentanyl-midazolam During Bronchoscopy	Phase 3
Recruiting	`NCT05824442` - Evaluation of a New Multiplex Quantitative PCR Technique for the Diagnosis of Echinococcosis	N/A
Not yet recruiting	`NCT06072820` - Analytical Evaluation of the Endotest® Diagnostic	N/A
Recruiting	`NCT05587114` - Comparision of Various Biomarkers Between Peripheral and Pulmonary Blood
Recruiting	`NCT06230458` - Fractional Exhaled Nitric Oxide (FeNO)- Test as add-on Test in the Diagnostic Work-up of Asthma	N/A
Not yet recruiting	`NCT05947565` - Patient Position and Invasive Urodynamic Study Results in Males	N/A
Not yet recruiting	`NCT05948410` - How Does the Mood of the Patients Change Before and After the Invasive Urodynamic Study?
Not yet recruiting	`NCT04490746` - Identifcation of Biomarkers for Active Pulmonary Tuberculosis
Completed	`NCT03381131` - Chinese Version of Fibromyalgia Criteria and Severity Scales Study
Recruiting	`NCT05992519` - Diagnostic and Translational Values of Point-of-care Blood Eosinophils and Exhaled Nitric Oxide (FeNO) in People Referred by Primary Care for Suspected Asthma