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

Artificial intelligence in medical diagnosis.

P Szolovits1, R S Patil, W B Schwartz

  • 1Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge.

Annals of Internal Medicine
|January 1, 1988
PubMed
Summary

Researchers developed artificial intelligence (AI) programs for computer-aided diagnosis that simulate expert reasoning. While not yet clinically useful, AI development has overcome many challenges, paving the way for future advancements.

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

An Efficient and Chemistry Independent Analysis to Quantify Resistive and Capacitive Loss Contributions to Battery Degradation.

Scientific reports·2019
Same author

Mesenteric Fibromatosis.

Kathmandu University medical journal (KUMJ)·2018
Same author

Chronic Benign Pemphigus of Hailey and Hailiey.

Indian journal of dermatology and venereology·2017
Same author

Predicting early psychiatric readmission with natural language processing of narrative discharge summaries.

Translational psychiatry·2016
Same author

The Harvard-MIT-NEMC Research Training Program in Medical Informatics.

Yearbook of medical informatics·2016
Same author

Molecular Markers of Secondary Organic Aerosol in Mumbai, India.

Environmental science & technology·2016

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Medicine
  • Clinical Decision Support Systems

Background:

  • Conventional computer-aided diagnosis (CAD) systems face inherent limitations.
  • Previous attempts to create clinically useful AI for diagnosis have faced significant challenges.
  • The development of effective artificial intelligence (AI) programs for medical diagnosis has been a long-standing goal.

Purpose of the Study:

  • To explore strategies for developing advanced AI programs that overcome limitations in conventional CAD.
  • To investigate the incorporation of expert human reasoning and pathophysiologic understanding into diagnostic AI.
  • To assess the progress and remaining challenges in achieving expert-level AI performance in medical diagnosis.

Main Methods:

Related Experiment Videos

  • Development of AI programs simulating expert human reasoning.
  • Implementation of strategies to limit the number of hypotheses considered by AI.
  • Incorporation of pathophysiologic reasoning to analyze complex cases with interacting disorders.
  • Design of AI prototypes capable of explaining diagnostic conclusions in understandable medical terms.

    • Main Results:

    • Many challenges impeding the creation of effective AI diagnostic programs have been addressed.
    • Strategies for hypothesis limitation and pathophysiologic reasoning have been successfully developed.
    • AI prototypes can now analyze complex cases and provide explainable conclusions.

    Conclusions:

    • Significant progress has been made in developing AI for medical diagnosis, particularly in simulating expert reasoning and handling complex cases.
    • Current AI prototypes demonstrate improved capabilities but have not yet reached expert performance levels.
    • Further extensive research and development are required to achieve expert-level AI performance in clinical settings.