Diagnostic accuracy of a large language model in rheumatology: comparison of physician and ChatGPT-4

Editorial Material Rheumatology

ChatGPT: when artificial intelligence replaces the rheumatologist in medical writing

Frank Verhoeven et al.

Summary: In this article, we discuss the role of artificial intelligence (AI) in scientific article writing, particularly editorials. We asked chatGPT to write an editorial on how AI could potentially replace rheumatologists in editorial writing for the Annals of Rheumatic Diseases. chatGPT's response was diplomatic, acknowledging AI as a tool to assist, rather than replace, rheumatologists. While AI is already used in medicine, particularly in image analysis, its potential applications in scientific article writing could rapidly aid or replace rheumatologists. We also explore the ethical aspects and future role of rheumatologists.

ANNALS OF THE RHEUMATIC DISEASES (2023)

Add to Collection

Letter Medicine, General & Internal

Accuracy of a Generative Artificial Intelligence Model in a Complex Diagnostic Challenge

Zahir Kanjee et al.

Summary: This study evaluates the diagnostic accuracy of the GPT-4 AI model in challenging cases.

JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION (2023)

Add to Collection

Article Medicine, General & Internal

Comparing Physician and Artificial Intelligence Chatbot Responses to Patient Questions Posted to a Public Social Media Forum

John W. Ayers et al.

Summary: The rapid expansion of virtual health care has led to an increase in patient messages and burnout among health care professionals. This study evaluated the ability of an AI chatbot assistant to provide quality and empathetic responses to patient questions, and found that the chatbot performed well in both aspects.

JAMA INTERNAL MEDICINE (2023)

Add to Collection

Editorial Material Rheumatology

The wide range of opportunities for large language models such as ChatGPT in rheumatology

Thomas Hugle

RMD OPEN (2023)

Add to Collection

Article

Trialling a Large Language Model (ChatGPT) in General Practice With the Applied Knowledge Test: Observational Study Demonstrating Opportunities and Limitations in Primary Care

Arun James Thirunavukarasu et al.

JMIR Medical Education (2023)

Add to Collection

Review Biochemistry & Molecular Biology

Large language models in medicine

Arun James Thirunavukarasu et al.

Summary: This review explores the development and application of large language models (LLMs), such as ChatGPT, in clinical settings. LLMs, like ChatGPT, have the potential to improve efficiency and effectiveness in medicine, but their limitations need to be considered. The review serves as a primer for clinicians interested in utilizing LLM technology in healthcare.

NATURE MEDICINE (2023)

Add to Collection

Editorial Material Radiology, Nuclear Medicine & Medical Imaging

Diagnostic Performance of ChatGPT from Patient History and Imaging Findings on the Diagnosis Please Quizzes

Daiju Ueda et al.

RADIOLOGY (2023)

Add to Collection

Article Rheumatology

2022 EULAR points to consider for remote care in rheumatic and musculoskeletal diseases

Annette de Thurah et al.

Summary: This study aims to develop EULAR points to consider for telehealth in the clinical care of people with RMD. Based on a systematic literature review and discussions among a multidisciplinary team, four overarching principles and nine points to consider were formulated. Telehealth can be tailored to patient's needs and preferences and has the potential to improve screening, monitoring, and medication regulation in RMD.

ANNALS OF THE RHEUMATIC DISEASES (2022)

Add to Collection

Editorial Material Rheumatology

The Challenge of Addressing the Rheumatology Workforce Shortage

Eli M. Miloslavsky et al.

JOURNAL OF RHEUMATOLOGY (2022)

Add to Collection

Article Rheumatology

Diagnostic delay stages and pre-diagnostic treatment in patients with suspected rheumatic diseases before special care consultation: results of a multicenter-based study

Franziska Fuchs et al.

Summary: The study investigated diagnostic delays and pre-diagnosis treatment in new patients presenting to rheumatology outpatient clinics. The findings showed persistent diagnostic delays in rheumatology, but current triage strategies effectively lead to earlier appointments for patients with inflammatory rheumatic diseases (IRD). Improvement of triage methods and pre-diagnosis treatment could decrease overall burden of disease in IRD patients.

RHEUMATOLOGY INTERNATIONAL (2022)

Add to Collection

Article Rheumatology

Comparison of physician and artificial intelligence-based symptom checker diagnostic accuracy

Markus Graef et al.

Summary: This study compared the accuracy of an AI-based symptom checker (Ada) to physicians in diagnosing inflammatory rheumatic diseases (IRD). The study found that Ada had higher diagnostic accuracy compared to physicians when considering basic health and symptom-related medical history. These results highlight the potential of using symptom checkers early in the patient journey and the importance of complete patient information for accurate diagnosis.

RHEUMATOLOGY INTERNATIONAL (2022)

Add to Collection

Article Rheumatology

Accuracy, patient-perceived usability, and acceptance of two symptom checkers (Ada and Rheport) in rheumatology: interim results from a randomized controlled crossover trial

Johannes Knitza et al.

Summary: This study evaluated the diagnostic accuracy, patient-perceived usability, and acceptance of two symptom checkers, Ada and Rheport, in the management of inflammatory rheumatic diseases. While the patient acceptance of the symptom checkers was high, their diagnostic accuracy for IRDs was found to be limited.

ARTHRITIS RESEARCH & THERAPY (2021)

Add to Collection

Article Rheumatology

Specialist training quo vadis?

M. Krusche et al.

ZEITSCHRIFT FUR RHEUMATOLOGIE (2019)

Add to Collection

Diagnostic accuracy of a large language model in rheumatology: comparison of physician and ChatGPT-4

Related references

Export Citation

Share Paper