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

An evaluation of machine-learning methods for predicting pneumonia mortality

G F Cooper1, C F Aliferis, R Ambrosino

  • 1Center for Biomedical Informatics, University of Pittsburgh, PA 15261, USA. gfc@cbmi.upmc.edu

Artificial Intelligence in Medicine
|February 1, 1997
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

Survey of Maternity Unit Guidelines regarding Formula Supplementation of Breastfed Babies.

Irish medical journal·2025
Same author

Sex-Specific Skeletal Muscle Gene Expression Responses to Exercise Reveal Novel Direct Mediators of Insulin Sensitivity Change.

medRxiv : the preprint server for health sciences·2024
Same author

Match loads of university rugby union players between the 2016 and 2018 Varsity Cup competitions.

South African journal of sports medicine·2023
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

A qualitative study of the acceptability of cognitive bias modification for paranoia (CBM-pa) in patients with psychosis.

BMC psychiatry·2019
Same author

Corrigendum to "Efficacy of a social support and problem-solving intervention on heart failure self-care: A pilot study" [Patient Educ. Couns. 101 (2018) 266-275].

Patient education and counseling·2019
Same journal

Real-time EEG-based epileptic seizure prediction using artificial intelligence: A systematic review.

Artificial intelligence in medicine·2026
Same journal

R-peak detection and ECG data compression scheme based on empirical mode decomposition and wavelet transform.

Artificial intelligence in medicine·2026
Same journal

CastNet: A three-channel EEG-based deep learning model for cross-subject depression detection.

Artificial intelligence in medicine·2026
Same journal

State-of-the-art TinyML approaches for colorectal cancer detection: Current advances, challenges, and future directions.

Artificial intelligence in medicine·2026
Same journal

JRadiEvo: A Japanese radiology report generation model enhanced by evolutionary optimization of model merging.

Artificial intelligence in medicine·2026
Same journal

Causally-informed deep learning towards explainable and generalizable outcome prediction in critical care.

Artificial intelligence in medicine·2026
See all related articles

Eight statistical and machine-learning models predict pneumonia patient mortality. Models showed similar accuracy, suggesting potential for paper-based clinical guidelines to aid treatment decisions.

Area of Science:

  • Medical Informatics
  • Computational Statistics
  • Clinical Decision Support

Background:

  • Pneumonia mortality prediction is crucial for patient management.
  • Accurate predictive models can guide treatment decisions (hospital vs. home care).
  • Evaluating model performance requires metrics sensitive to clinical utility.

Purpose of the Study:

  • To apply eight statistical and machine-learning methods for predicting hospital patient mortality from pneumonia.
  • To evaluate the performance of these predictive models using a clinically relevant metric.
  • To identify models suitable for implementation as paper-based clinical guidelines.

Main Methods:

  • Eight distinct statistical and machine-learning models were developed.
  • Models were trained on 9,847 patient cases and validated on 4,352 additional cases.

Related Experiment Videos

  • Performance was assessed using prediction error as a function of predicted survival fraction (0.1-0.6).

    • Main Results:

    • All eight models demonstrated comparable predictive error rates within 1% across the evaluated survival fractions.
    • When predicting ~30% survival, all models achieved an error rate below 1.5%.
    • Model complexity (number of variables/parameters) varied more than predictive accuracy.

    Conclusions:

    • Multiple statistical and machine-learning models exhibit similar, high accuracy in predicting pneumonia patient mortality.
    • The choice of model may depend on implementation feasibility, such as suitability for paper-based guidelines.
    • These models show promise for supporting clinical decisions regarding patient disposition.