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

Human causal discovery from observational data

A I Hashem1, G F Cooper

  • 1Section of Medical Informatics & Learning Research, University of Pittsburgh, PA 15260, USA.

Proceedings : a Conference of the American Medical Informatics Association. AMIA Fall Symposium
|January 1, 1996
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

State Board of Health: Report of Special Committee upon the Most Effectual Means of Preventing Small-Pox in Georgia.

Atlanta medical and surgical journal·2022
Same author

Identifying the ingredients of hydrous arc magmas: insights from Mt Lamington, Papua New Guinea.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2019
Same author

Knowledge Processing and Decision Support Systems.

Yearbook of medical informatics·2016
Same author

Synthesis and characterization of nanosilver-silicone hydrogel composites for inhibition of bacteria growth.

Contact lens & anterior eye : the journal of the British Contact Lens Association·2016
Same author

St. George's Hospital.

British medical journal·2010
Same author

St. George's Hospital.

British medical journal·2010
Same journal

Identification of findings suspicious for breast cancer based on natural language processing of mammogram reports.

Proceedings : a conference of the American Medical Informatics Association. AMIA Fall Symposium·1997
Same journal

Searching for information on the Internet using the UMLS and Medical World Search.

Proceedings : a conference of the American Medical Informatics Association. AMIA Fall Symposium·1997
Same journal

Text structures in medical text processing: empirical evidence and a text understanding prototype.

Proceedings : a conference of the American Medical Informatics Association. AMIA Fall Symposium·1997
Same journal

A natural language parsing system for encoding admitting diagnoses.

Proceedings : a conference of the American Medical Informatics Association. AMIA Fall Symposium·1997
Same journal

Meeting clinician information needs by integrating access to the medical record and knowledge resources via the Web.

Proceedings : a conference of the American Medical Informatics Association. AMIA Fall Symposium·1997
Same journal

Electronic forms: benefits drawbacks of a World Wide Web-based approach to data entry.

Proceedings : a conference of the American Medical Informatics Association. AMIA Fall Symposium·1997
See all related articles

Medical students struggled to identify causal links in patient data using Bayesian belief networks. However, they excelled at detecting the absence of a causal relationship, suggesting combined human-computer approaches for causal discovery.

Area of Science:

  • Medical Education
  • Causal Inference
  • Artificial Intelligence

Background:

  • Bayesian belief networks (BBNs) offer a framework for modeling causality.
  • Understanding causal relationships is crucial for medical diagnosis and treatment.

Purpose of the Study:

  • To evaluate medical students' proficiency in discovering causal relationships from observational data.
  • To assess the effectiveness of BBNs as a model for causal discovery in a medical context.

Main Methods:

  • Nine datasets were generated using simulated causal belief networks.
  • Twenty medical students analyzed these datasets to identify underlying causal structures.
  • Performance metrics were used to quantify the accuracy of causal relationship discovery.

Related Experiment Videos

Main Results:

  • Participants demonstrated poor overall performance in identifying causal relationships.
  • A notable exception was the accurate detection of the absence of causal links.
  • Success rates varied across different network complexities.

Conclusions:

  • Medical students face challenges in inferring causality from observational data.
  • Human-computer collaboration shows promise for enhancing causal discovery in medicine.
  • Further research is needed to improve AI-assisted diagnostic reasoning.