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 statistical learning methods on the Gusto database

M Ennis1, G Hinton, D Naylor

  • 1Department of Statistics, University of Toronto, Canada.

Statistics in Medicine
|November 20, 1998
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

Intrauterine Contraception Device Satisfaction and Continuation in an Urban Youth Clinic in British Columbia, Canada: A Longitudinal Survey Study.

Journal of obstetrics and gynaecology Canada : JOGC = Journal d'obstetrique et gynecologie du Canada : JOGC·2025
Same author

Amivantamab plus lazertinib versus osimertinib in first-line EGFR-mutant advanced non-small-cell lung cancer with biomarkers of high-risk disease: a secondary analysis from MARIPOSA.

Annals of oncology : official journal of the European Society for Medical Oncology·2024
Same author

Adult North Star Network (ANSN): Consensus Document for Therapists Working with Adults with Duchenne Muscular Dystrophy (DMD) - Therapy Guidelines.

Journal of neuromuscular diseases·2022
Same author

Colonoscopy skills improvement training improves patient comfort during colonoscopy.

Surgical endoscopy·2021
Same author

Endotoxin-induced cytokine, chemokine and white blood cell profiles of variable stress-responding sheep.

Stress (Amsterdam, Netherlands)·2021
Same author

Short communication: Characterizing ovine serum stress biomarkers during endotoxemia.

Journal of dairy science·2020

Modern machine learning methods were tested for predicting cardiac patient mortality. These advanced techniques did not outperform a simpler logistic regression model in predicting 30-day mortality from patient data.

Area of Science:

  • Cardiology
  • Machine Learning
  • Biostatistics

Background:

  • Predicting 30-day mortality in cardiac patients is crucial for timely intervention.
  • Existing risk prediction models require continuous evaluation with new methodologies.

Purpose of the Study:

  • To evaluate the performance of modern adaptive non-linear learning methods in predicting 30-day mortality.
  • To compare these advanced methods against a established logistic regression model.

Main Methods:

  • Application of a battery of modern, adaptive non-linear learning algorithms.
  • Utilizing a large real-world database of cardiac patient data.
  • Comparative performance analysis of prediction models.

Main Results:

Related Experiment Videos

  • None of the tested non-linear learning methods demonstrated superior performance.
  • The established logistic regression model remained the most effective predictor.

Conclusions:

  • Simple logistic regression models are highly effective for predicting 30-day cardiac mortality.
  • Advanced non-linear methods did not provide significant improvements in this specific clinical prediction task.