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 Concept Videos

Kaplan-Meier Approach01:24

Kaplan-Meier Approach

770
The Kaplan-Meier estimator is a non-parametric method used to estimate the survival function from time-to-event data. In medical research, it is frequently employed to measure the proportion of patients surviving for a certain period after treatment. This estimator is fundamental in analyzing time-to-event data, making it indispensable in clinical trials, epidemiological studies, and reliability engineering. By estimating survival probabilities, researchers can evaluate treatment effectiveness,...
770
Prediction Intervals01:03

Prediction Intervals

3.6K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y. 
3.6K
Actuarial Approach01:20

Actuarial Approach

385
The actuarial approach, a statistical method originally developed for life insurance risk assessment, is widely used to calculate survival rates in clinical and population studies. This method accounts for participants lost to follow-up or those who die from causes unrelated to the study, ensuring a more accurate representation of survival probabilities.
Consider the example of a high-risk surgical procedure with significant early-stage mortality. A two-year clinical study is conducted,...
385

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Towards a Unified Theory for Semiparametric Data Fusion with Individual-Level Data.

Annals of statistics·2026
Same author

Household Transmission of Enterovirus D68, Washington and Oregon, United States, 2022-2024.

Emerging infectious diseases·2026
Same author

Cost-Effectiveness Analyses for Sequential Multiple Assignment Randomized Trials.

Statistics in medicine·2026
Same author

An approach to nonparametric inference on the causal dose-response function.

Journal of causal inference·2026
Same author

A megastudy of behavioral interventions to promote frequent HIV testing among adults at high risk of HIV infection in Kenya and Uganda: study protocol for a randomized controlled trial.

Trials·2026
Same author

Influenza household transmission and genomic diversity in the United States: A prospective cohort study, 2022-2024.

The Journal of infection·2026

Related Experiment Videos

Mortality prediction in intensive care units with the Super ICU Learner Algorithm (SICULA): a population-based study.

Romain Pirracchio1, Maya L Petersen2, Marco Carone3

  • 1Division of Biostatistics, School of Public Health, University of California, Berkeley, CA, USA; Service de Biostatistique et Information Médicale, Unité INSERM 1153, Equipe ECSTRA, Hôpital Saint Louis, Paris, France; Service d'Anesthésie-Réanimation, Hôpital Européen Georges Pompidou, Paris, France.

The Lancet. Respiratory Medicine
|December 4, 2014
PubMed
Summary

The Super ICU Learner Algorithm (SICULA) demonstrates superior performance in predicting intensive care unit patient mortality compared to existing scoring systems. This machine learning approach offers improved accuracy and calibration for better clinical decision-making.

Related Experiment Videos

Area of Science:

  • Critical Care Medicine
  • Machine Learning Applications in Healthcare
  • Biostatistics and Predictive Modeling

Background:

  • Accurate mortality prediction in intensive care units (ICUs) remains a significant clinical challenge.
  • Existing severity scores often exhibit inadequate calibration, limiting their reliability.
  • Ensemble machine learning techniques, like Super ICU Learner Algorithm (SICULA), show promise for enhancing prediction performance.

Purpose of the Study:

  • To develop and evaluate a novel mortality prediction algorithm for ICU patients using the Super Learner ensemble method.
  • To compare the performance of the Super Learner algorithm against established scoring systems such as SAPS-II, APACHE-II, and SOFA.

Main Methods:

  • Utilized the Multiparameter Intelligent Monitoring in Intensive Care II (MIMIC-II) database (v26) for model development (2001-2008).
  • Assessed calibration, discrimination, and risk classification of the Super Learner against SAPS-II, APACHE-II, and SOFA using cross-validation.
  • Externally validated the Super Learner model on a separate ICU dataset (Hôpital Européen Georges-Pompidou, Paris) from 2013-2014.

Main Results:

  • The Super Learner algorithm achieved a higher Area Under the Receiver Operating Characteristic Curve (AUROC) compared to SAPS-II and SOFA (0.88 vs. 0.78 and 0.71, respectively).
  • Super Learner demonstrated superior calibration properties and strong performance on the external validation dataset (AUROC 0.94).
  • The model predicted hospital mortality with an average probability of 0.12-0.13, outperforming SAPS-II (0.30) and SOFA (0.12) in predictive accuracy.

Conclusions:

  • The Super Learner algorithm offers significantly improved performance for predicting hospital mortality in ICU patients compared to conventional scoring systems.
  • The enhanced predictive accuracy and calibration of Super Learner can aid clinicians in risk stratification and patient management.
  • A user-friendly online implementation of the Super Learner score is available to facilitate clinical adoption and validation.