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

A comparison of two computer-based prognostic systems for AIDS

L Ohno-Machado1, M A Musen

  • 1Section on Medical Informatics, Stanford University School of Medicine, CA 94305, USA.

Proceedings. Symposium on Computer Applications in Medical Care
|January 1, 1995
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

Training in Health Informatics in Brazil.

Yearbook of medical informatics·2016
Same author

Challenges in Medical Informatics. A Discipline Coming of Age.

Yearbook of medical informatics·2016
Same author

Challenges for Medical Informatics as an Academic Discipline: Workshop Report.

Yearbook of medical informatics·2016
Same author

Creating a Common Data Model for Comparative Effectiveness with the Observational Medical Outcomes Partnership.

Applied clinical informatics·2015
Same author

Health IT and clinical decision support systems: human factors and successful adoption.

Journal of the American Medical Informatics Association : JAMIA·2014
Same author

"Big data" and the electronic health record.

Yearbook of medical informatics·2014

Both Cox and neural network models accurately predicted deaths in people with AIDS (Acquired Immunodeficiency Syndrome) but struggled with first-year survival predictions. The Cox model offered prognostic variable insights, while neural networks provided flexibility for varied datasets.

Area of Science:

  • Medical Prognostics
  • Biostatistics
  • Machine Learning in Healthcare

Background:

  • Accurate prognostic tools are crucial for managing Acquired Immunodeficiency Syndrome (AIDS).
  • Comparing statistical and machine learning models aids in selecting optimal predictive methods.

Purpose of the Study:

  • To compare the prognostic performance of a Cox proportional hazards model and a neural network model for AIDS patient survival.
  • To evaluate the accuracy of these models in predicting mortality at various intervals post-AIDS diagnosis.

Main Methods:

  • Utilized data from 588 AIDS patients in the ATHOS project, California.
  • Employed a 10-fold cross-validation approach for training and testing both Cox and neural network models.
  • Assessed prognostic accuracy using metrics like sensitivity, specificity, and predictive values for 1-year, 2-year, and 3-year survival.

Related Experiment Videos

Main Results:

  • Both models accurately predicted the number of deaths at different time intervals.
  • Individualized 2- and 3-year survival predictions were reasonable, but 1-year predictions lacked reliability for both models.
  • No significant performance difference was observed between the Cox model and the neural network model.

Conclusions:

  • While both models showed limitations in predicting short-term survival, they offer valuable prognostic insights.
  • The Cox model provides interpretability regarding influential prognostic variables.
  • Neural networks offer a viable alternative when Cox model assumptions may not be met, enhancing prognostic modeling flexibility for AIDS cohorts.