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

Comparing the Survival Analysis of Two or More Groups01:20

Comparing the Survival Analysis of Two or More Groups

329
Survival analysis is a cornerstone of medical research, used to evaluate the time until an event of interest occurs, such as death, disease recurrence, or recovery. Unlike standard statistical methods, survival analysis is particularly adept at handling censored data—instances where the event has not occurred for some participants by the end of the study or remains unobserved. To address these unique challenges, specialized techniques like the Kaplan-Meier estimator, log-rank test, and...
329
Mechanistic Models: Compartment Models in Individual and Population Analysis01:23

Mechanistic Models: Compartment Models in Individual and Population Analysis

95
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...
95
Kaplan-Meier Approach01:24

Kaplan-Meier Approach

292
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,...
292
Assumptions of Survival Analysis01:15

Assumptions of Survival Analysis

209
Survival models analyze the time until one or more events occur, such as death in biological organisms or failure in mechanical systems. These models are widely used across fields like medicine, biology, engineering, and public health to study time-to-event phenomena. To ensure accurate results, survival analysis relies on key assumptions and careful study design.
209
Cancer Survival Analysis01:21

Cancer Survival Analysis

473
Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...
473
Actuarial Approach01:20

Actuarial Approach

143
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,...
143

You might also read

Related Articles

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

Sort by
Same author

Agentic and LLM-Based Multimodal Anomaly Detection: Architectures, Challenges, and Prospects.

Sensors (Basel, Switzerland)·2026
Same author

Cerebral oxygen monitoring during out-of-hospital cardiac arrest: A scoping review.

Resuscitation plus·2025
Same author

The impact of feature combinations on machine learning models for in-hospital mortality prediction.

Scientific reports·2025
Same author

Comparison of correctly and incorrectly classified patients for in-hospital mortality prediction in the intensive care unit.

BMC medical research methodology·2023
Same author

Unsupervised Anomaly Detection for IoT-Based Multivariate Time Series: Existing Solutions, Performance Analysis and Future Directions.

Sensors (Basel, Switzerland)·2023
Same author

Glenoid bone loss in anterior shoulder dislocation: a multicentric study to assess the most reliable imaging method.

La Radiologia medica·2022

Related Experiment Video

Updated: Oct 2, 2025

Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

931

Comparative analysis of explainable machine learning prediction models for hospital mortality.

Eline Stenwig1, Giampiero Salvi2, Pierluigi Salvo Rossi2

  • 1Department of Circulation and Medical Imaging, The Norwegian University of Science and Technology, Trondheim, Norway. eline.stenwig@ntnu.no.

BMC Medical Research Methodology
|February 28, 2022
PubMed
Summary

Machine learning (ML) models for predicting hospital mortality show similar accuracy but differ in how they interpret patient data. Explainable AI methods like SHapley Additive exPlanations (SHAP) are crucial for building trust in clinical decision support tools.

Keywords:
ExplainabilityMachine learningMortality predictionSHAP valueseICU

More Related Videos

An R-Based Landscape Validation of a Competing Risk Model
05:37

An R-Based Landscape Validation of a Competing Risk Model

Published on: September 16, 2022

2.2K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.0K

Related Experiment Videos

Last Updated: Oct 2, 2025

Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

931
An R-Based Landscape Validation of a Competing Risk Model
05:37

An R-Based Landscape Validation of a Competing Risk Model

Published on: September 16, 2022

2.2K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.0K

Area of Science:

  • Healthcare Informatics
  • Artificial Intelligence in Medicine
  • Clinical Decision Support

Background:

  • Machine learning (ML) offers potential for clinical decision support using vast healthcare data.
  • Lack of trust in ML models, due to poor explainability, hinders adoption in healthcare.
  • Transparent ML methods are needed to improve trust and facilitate clinical integration.

Purpose of the Study:

  • To evaluate the explainability and interpretability of different ML models in predicting hospital mortality.
  • To compare the behavior of various ML algorithms using SHapley Additive exPlanations (SHAP) values.
  • To assess the trustworthiness of ML models in a clinical context.

Main Methods:

  • Developed four ML models (random forest, logistic regression, naive Bayes, adaptive boosting) to predict hospital mortality using the eICU database.
  • Utilized SHapley Additive exPlanations (SHAP) values to analyze the internal behavior and feature importance of each model.
  • Employed features similar to those used in the APACHE IV score for model construction.

Main Results:

  • All ML models demonstrated comparable discriminative abilities in predicting hospital mortality.
  • Models largely agreed on overall feature importance but showed significant differences in calibration and individual feature impact.
  • Discrepancies in feature impact often contradicted established medical knowledge.

Conclusions:

  • Different ML algorithms interpret clinical data distinctively, impacting model behavior and trustworthiness.
  • SHapley Additive exPlanations (SHAP) analysis is a valuable tool for enhancing ML model explainability in healthcare.
  • Improving transparency through methods like SHAP can lead to more reliable and trustworthy clinical ML applications.