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

Steps in Outbreak Investigation01:18

Steps in Outbreak Investigation

233
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
233
Kaplan-Meier Approach01:24

Kaplan-Meier Approach

288
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,...
288
Mechanistic Models: Compartment Models in Individual and Population Analysis01:23

Mechanistic Models: Compartment Models in Individual and Population Analysis

89
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
89

You might also read

Related Articles

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

Sort by
Same author

Clinical outcomes of anemia in patients with spontaneous coronary artery dissection: a retrospective cohort analysis.

Journal of thrombosis and thrombolysis·2026
Same author

Access and Reimbursement for Artificial Intelligence in Radiology: Taiwan's Perspective.

Korean journal of radiology·2026
Same author

Coronary Bifurcation PCI-Part I: Fundamentals.

Journal of cardiovascular development and disease·2025
Same author

In-Hospital Mortality Among Patients Undergoing Percutaneous Pericardiocentesis for Pericardial Effusion with and Without Malignancy.

Current oncology (Toronto, Ont.)·2025
Same author

Global uptake of GLP-1 receptor agonists in obese, non-diabetic patients with cardiovascular disease.

European heart journal. Quality of care & clinical outcomes·2025
Same author

A national analysis of obstructive sleep apnea in patients undergoing transcatheter aortic valve replacement.

Sleep & breathing = Schlaf & Atmung·2025

Related Experiment Video

Updated: Sep 27, 2025

A Data-Driven Approach to Quantifying Immune States in Sepsis
07:42

A Data-Driven Approach to Quantifying Immune States in Sepsis

Published on: February 7, 2025

323

Predicting Sepsis Mortality in a Population-Based National Database: Machine Learning Approach.

James Yeongjun Park1, Tzu-Chun Hsu2, Jiun-Ruey Hu3

  • 1Department of Biostatistics, Harvard TH Chan School of Public Health, Boston, MA, United States.

Journal of Medical Internet Research
|April 13, 2022
PubMed
Summary

Machine learning (ML) models significantly outperformed traditional logistic regression in predicting sepsis mortality using administrative data. These advanced ML approaches offer improved accuracy for identifying at-risk patients and guiding clinical care.

Keywords:
SuperLearnermachine learningmortalitysepsis

More Related Videos

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

213
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

7.2K

Related Experiment Videos

Last Updated: Sep 27, 2025

A Data-Driven Approach to Quantifying Immune States in Sepsis
07:42

A Data-Driven Approach to Quantifying Immune States in Sepsis

Published on: February 7, 2025

323
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

213
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

7.2K

Area of Science:

  • Medical Informatics
  • Clinical Prediction Models
  • Health Services Research

Background:

  • Machine learning (ML) has shown promise in point-of-care sepsis prognostication.
  • ML has not been extensively applied to predict sepsis mortality within large administrative databases.
  • This study addresses the gap by evaluating ML algorithms for sepsis mortality prediction in administrative data.

Purpose of the Study:

  • To assess the performance of common ML algorithms in predicting in-hospital mortality for adult sepsis patients.
  • To compare the predictive accuracy of ML models against a conventional logistic regression approach.
  • To determine if ML can enhance the prediction of sepsis-related mortality using administrative health data.

Main Methods:

  • Utilized the US National Inpatient Sample (2010-2013) for training four ML models: regularized logistic regression, random forest, gradient-boosted decision tree, and deep neural network.
  • Compared ML models against a Super Learner ensemble model and a baseline logistic regression model.
  • Evaluated model performance using area under the receiver operating characteristic curve (AUC), confusion matrices, and net reclassification improvement on 2014 data.

Main Results:

  • All four ML models demonstrated superior discriminative ability compared to the reference logistic regression (AUC 0.786).
  • Specific ML models achieved AUCs ranging from 0.878 to 0.893, significantly outperforming the baseline (P<.001).
  • ML models also showed significant improvements in sensitivity, specificity, positive predictive value, and negative predictive value.

Conclusions:

  • Machine learning algorithms significantly enhance the prediction of in-hospital mortality for sepsis patients in the US.
  • These validated ML models can improve clinical decision-making and risk stratification.
  • Further research and validation could lead to more accurate risk-standardized mortality rate comparisons and inform policy on sepsis care disparities.