Jove
Visualize
Contact Us

Related Concept Videos

Prediction Intervals01:03

Prediction Intervals

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. 
The...
Survival Tree01:19

Survival Tree

Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a survival tree begins...
End Point Prediction: Gran Plot01:07

End Point Prediction: Gran Plot

A Gran plot is used to predict the equivalence volume or endpoint of a potentiometric or acid-base titration without reaching the endpoint. Typically, titration data is collected as a function of the titrant's volume up to a point less than the equivalence volume and then transformed into a linear format. The straight line is extended to the x-axis, indicating the necessary titrant volume to achieve the equivalence point.
For potentiometric titration, the Gran plot is created by plotting the...
Sensitivity, Specificity, and Predicted Value01:13

Sensitivity, Specificity, and Predicted Value

In healthcare diagnostics, laboratory tests play a crucial role in identifying and diagnosing a wide range of medical conditions. However, interpreting test results is not always straightforward. An abnormal test result does not always confirm the presence of a disease, just as a normal result does not guarantee its absence. To assess the reliability of these diagnostic tools, healthcare practitioners rely on two key statistical indicators: sensitivity and specificity.
Sensitivity is the...

You might also read

Related Articles

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

Sort by
Same author

Discrepancies between self-reported alcohol use and breathalyzer results and factors associated with blood alcohol concentration positivity among road traffic injury patients in Cameroon.

Addiction (Abingdon, England)·2026
Same author

Data-adaptive identification of effect modifiers through stochastic shift interventions and cross-validated targeted learning.

Biostatistics (Oxford, England)·2026
Same author

What is the Incidence of Early Antibody Formation after Resuscitation of Hemorrhage? A Comparison of RH(D)+ Whole Blood and RH(D)- Red Blood Cells in 3,531 Trauma Patients.

Annals of surgery·2026
Same author

An in vivo assessment of green plasma: The potential hemostatic superiority of a currently discarded blood product.

The journal of trauma and acute care surgery·2026
Same author

Executing balanced resuscitation in bleeding combat casualties: Good versus good enough?

The journal of trauma and acute care surgery·2026
Same author

Long-term patterns of health services utilization after hospitalization for COPD. A nationwide registry-based study from Norway.

Respiratory medicine·2026
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

Time-dependent prediction and evaluation of variable importance using superlearning in high-dimensional clinical

Alan Hubbard1, Ivan Diaz Munoz, Anna Decker

  • 1School of Public Health, University of California-Berkeley, Berkeley, California 94720, USA. hubbard@berkeley.edu

The Journal of Trauma and Acute Care Surgery
|June 20, 2013
PubMed
Summary

SuperLearner (SL) models offer superior time-dependent prediction of patient outcomes compared to traditional methods. This machine learning approach identifies key clinical variables influencing mortality over time, improving prognostic accuracy.

Related Experiment Videos

Area of Science:

  • Medical Informatics
  • Machine Learning in Healthcare
  • Biostatistics

Background:

  • Outcome prediction after injury is challenging due to model misspecification and uncertainty.
  • Traditional single-time point regression models offer limited value for continuous outcome prediction.
  • Machine learning techniques like SuperLearner (SL) can provide iterative predictions and variable importance evaluation.

Purpose of the Study:

  • To compare the predictive accuracy of SuperLearner (SL) against standard logistic regression for time-dependent mortality prediction.
  • To evaluate the utility of SL in identifying time-specific predictors of mortality.
  • To assess the dynamic nature of variable importance in predicting patient outcomes.

Main Methods:

  • Utilized the PROMMTT dataset, including 980 patients with complete clinical and outcome data.
  • Employed both naive stepwise logistic regression and SuperLearner (SL) techniques for time-dependent mortality prediction.
  • Applied cross-validation to prevent overfitting and select optimal predictor combinations for SL models.
  • Generated interval-specific variable importance measures (VIM) using SL to identify key mortality drivers.

Main Results:

  • SuperLearner (SL) demonstrated superior prediction accuracy across all time intervals compared to the naive approach.
  • Cross-validated prediction correlations for SL ranged from 0.789 to 0.819 across different time intervals.
  • The variable importance measures (VIM) for mortality significantly changed at each time point, indicating dynamic predictor roles.

Conclusions:

  • SuperLearner (SL) technique provides more accurate time-dependent outcome predictions from complex data than standard models.
  • SL-derived variable importance measures offer insights into time-specific drivers of patient outcomes and potential interventions.
  • This automated approach dynamically adapts to patient trajectories, optimizing prognostic accuracy over time.