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 Video

Updated: Mar 29, 2026

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

580

Responsible AI for Sepsis Prediction: Bridging the Gap Between Machine Learning Performance and Clinical Trust.

Thiago Q Oliveira1, Leandro A Carvalho2, Flávio R C Sousa2

  • 1Department of Computer Science, Federal Institute of Ceará, Fortaleza 60040-531, CE, Brazil.

Journal of Clinical Medicine
|March 28, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same journal

Evidence-Based Clinical Recommendations for the Appropriate Use of Diagnostic Tests in Pediatric Allergology: Focus on Asthma, Rhinoconjunctivitis, and Keratoconjunctivitis Vernal.

Journal of clinical medicine·2026
Same journal

Surgical and Transcatheter Approach of a Failed Mitral Valve Repair: A Comprehensive Review on Selecting the Most Suitable Approach.

Journal of clinical medicine·2026
Same journal

Hybrid Metaheuristic Feature Selection for Breast Cancer Detection in Digital Mammography: A Feasibility Study with Nested Validation, Benchmarking, and External Stress Testing.

Journal of clinical medicine·2026
Same journal

Identity Transformation and the Role of Accountability in Recovery from Problematic Pornography Use: A Phenomenological-Hermeneutical Study.

Journal of clinical medicine·2026
Same journal

Does Early Surgical Treatment in Degenerative Cervical Myelopathy Have a Favorable Clinical Outcome and Impact on Quality of Life?

Journal of clinical medicine·2026
Same journal

Shear Wave Elastography in Musculoskeletal Imaging: A Narrative Review.

Journal of clinical medicine·2026
This summary is machine-generated.

Machine learning models can predict sepsis outcomes like mortality in intensive care units (ICUs). XGBoost showed the best performance, but explainability is key for doctor trust.

Area of Science:

  • Artificial Intelligence
  • Medical Informatics
  • Clinical Prediction Models

Background:

  • Sepsis is a major cause of death in intensive care units (ICUs).
  • Accurate, fair, and transparent machine learning (ML) models are crucial for clinical decision-making.
  • Responsible AI principles are essential for developing trustworthy clinical prediction tools.

Purpose of the Study:

  • To evaluate various ML architectures for predicting sepsis-related clinical outcomes.
  • To assess the performance of different AI algorithms in a clinical setting.
  • To ensure responsible AI principles are integrated into model development and evaluation.

Main Methods:

  • Utilized the MIMIC-IV database (version 3.1) for model training and validation.
  • Compared Logistic Regression, XGBoost, LightGBM, LSTM networks, and Transformer models.
Keywords:
MIMIC-IVartificial intelligenceintensive care unitmachine learningresponsible artificial intelligencesepsis

Related Experiment Videos

Last Updated: Mar 29, 2026

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

580
  • Predicted hospital mortality, length of stay, and septic shock onset.
  • Employed Shapley Additive Explanations (SHAP) for model interpretability.

    • Main Results:

    • XGBoost achieved superior predictive performance, especially for hospital mortality (AUROC 0.874).
    • The model outperformed LSTM networks, Transformers, and linear baselines.
    • Variable importance analysis confirmed the clinical relevance of the XGBoost model's predictions.

    Conclusions:

    • XGBoost and ensemble algorithms show strong predictive capabilities for sepsis prognosis.
    • Clinical adoption of these models requires robust explainability mechanisms.
    • Building trust among physicians is paramount for the successful integration of AI in sepsis care.