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

Using connectionist modules for decision support.

G Hripcsak1

  • 1Center for Medical Informatics, Columbia University, New York.

Methods of Information in Medicine
|July 1, 1990
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

MAO inhibitory activity of bromo-2-phenylbenzofurans: synthesis, <i>in vitro</i> study, and docking calculations.

MedChemComm·2018
Same author

Estimating summary statistics for electronic health record laboratory data for use in high-throughput phenotyping algorithms.

Journal of biomedical informatics·2018
Same author

Decision Support, Knowledge Representation and Management.

Yearbook of medical informatics·2016
Same author

Health and Clinical Management.

Yearbook of medical informatics·2016
Same author

Systems pharmacology augments drug safety surveillance.

Clinical pharmacology and therapeutics·2015
Same author

Similarity-based modeling applied to signal detection in pharmacovigilance.

CPT: pharmacometrics & systems pharmacology·2014
Same journal

Design and methodological development of a digital clinical safety training programme informed by a national framework: a New Zealand case study.

Methods of information in medicine·2026
Same journal

Panic Prediction from Digital Phenotyping: Subject-Level Cross-Validation Reveals Limited Between-Person Generalization.

Methods of information in medicine·2026
Same journal

Agent-Based Modeling Approach for Population Dynamics of the Biological Vector Aedes Aegypti.

Methods of information in medicine·2026
Same journal

A Statistical Framework for Person-centered Analysis of Digital Service Use in Public Health and Social Care.

Methods of information in medicine·2026
Same journal

Assessing the Quality of Electronic Discharge Summaries: A Cross-Sectional Study Using the Validated Spanish Version of the PDQI-9.

Methods of information in medicine·2026
Same journal

A Knowledge Graph-Driven Hypergeometric Efficacy Prediction Model for Classical Traditional Chinese Herbal Formulas.

Methods of information in medicine·2026
See all related articles

A new connectionist model accurately estimates disease probability using back-propagation modules. This AI model outperforms logistic regression, especially with stepped and normal disease manifestations.

Area of Science:

  • Artificial Intelligence
  • Medical Informatics
  • Computational Neuroscience

Background:

  • Clinical decision support systems (CDSS) are crucial for accurate diagnosis.
  • Traditional models like logistic regression have limitations in handling complex manifestation relationships.
  • Connectionist models offer a potential alternative for improved diagnostic accuracy.

Purpose of the Study:

  • To develop and evaluate a connectionist model for disease probability estimation.
  • To compare the performance of the connectionist model against logistic regression.
  • To assess the model's ability to handle various manifestation types and confidence levels.

Main Methods:

  • A connectionist model was built using multiple back-propagation modules.

Related Experiment Videos

  • The model accepted real-valued manifestations with specified measurement confidence.
  • Training involved 1,000 simulated cases; testing used 30,000 cases.

    • Main Results:

    • The connectionist model achieved a lower standard deviation of residuals (0.046) compared to logistic regression (0.062).
    • The model demonstrated superior performance in estimating posterior disease probability.
    • It fitted stepped and normally distributed manifestations better than linear ones and handled intermediate confidence levels effectively.

    Conclusions:

    • Connectionist models, utilizing back-propagation, show significant promise for enhancing clinical decision support.
    • This AI-driven approach offers improved accuracy in disease probability estimation over traditional methods.
    • The model's flexibility in handling diverse data types and confidence levels supports its clinical utility.