Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Pierpaolo Giordano1, Melissa D'Ambrosio2, Mateo Banushaj2

  • 1Università "Magna Græcia" di Catanzaro.

Recenti Progressi in Medicina
|November 17, 2024
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A prospective multimethod investigation of cancer-related pain integrating clinical data and machine learning: results from the RUGGI Study.

Journal of anesthesia, analgesia and critical care·2026
Same author

A personalized iodine delivery rate-based injection protocol in coronary angiography on photon-counting CT.

European radiology·2026
Same author

Identifying novel drug targets with computational precision.

Advances in pharmacology (San Diego, Calif.)·2025
Same author

Recenti progressi in medicina·2023
Same author

Western Mediterranean coastal waters--monitoring PCBs and pesticides accumulation in Mytilus galloprovincialis by active mussel watching: the Mytilos project.

Journal of environmental monitoring : JEM·2010

This review explores ChatGPT's use in clinical decision support. While promising for diagnosis and triage, it requires medical adaptation and human oversight due to limitations in complex cases and potential inaccuracies.

Area of Science:

  • Artificial Intelligence in Medicine
  • Clinical Decision Support Systems
  • Natural Language Processing in Healthcare

Background:

  • The integration of artificial intelligence (AI), specifically large language models like ChatGPT, into clinical workflows is rapidly evolving.
  • Evaluating the efficacy and safety of AI tools for clinical decision support is crucial for responsible adoption.
  • Existing literature needs synthesis to understand ChatGPT's current capabilities and limitations in diverse medical applications.

Purpose of the Study:

  • To conduct a scoping review on the state-of-the-art applications of ChatGPT in clinical decision support.
  • To assess ChatGPT's performance metrics, including accuracy, sensitivity, speed, and reliability, across various clinical contexts.
  • To identify current limitations and ethical considerations associated with using ChatGPT in healthcare.

Related Experiment Videos

Main Methods:

  • A comprehensive literature search was conducted to identify relevant research articles.
  • Articles were screened for retrieval and eligibility based on predefined criteria.
  • A total of 50 articles were included in this scoping review from an initial pool of 225.

Main Results:

  • ChatGPT demonstrates strong diagnostic capabilities with complete data but falters with incomplete or ambiguous information.
  • Differential diagnosis performance is inconsistent, particularly in complex clinical scenarios.
  • Treatment recommendations show good sensitivity but lack personalization and necessitate human supervision.
  • Triage accuracy is high for hospitalization decisions, yet specificity for safe discharges is lower.
  • Surgical support is effective for planning but lacks real-time adaptability during procedures without human intervention.

Conclusions:

  • ChatGPT shows significant potential for augmenting clinical decision-making but faces substantial current limitations.
  • Key challenges include the need for medical-specific fine-tuning and the risk of generating erroneous or misleading information (hallucinations).
  • Addressing ethical, legal, and safety concerns is paramount before widespread clinical implementation.