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

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

7.7K

Machine Learning Models for Sepsis: From Early Detection to Short- and Long-Term Prognosis.

Maria Vittoria Ristori1,2,3, Filippo Ruffini4, Silvia Spoto5

  • 1National PhD Program in One Health Approaches to Infectious Diseases and Life Science Research, Department of Public Health, Experimental and Forensic Medicine, University of Pavia, 27100 Pavia, Italy.

International Journal of Molecular Sciences
|March 28, 2026
PubMed
Summary

Related Concept Videos

Steps in Outbreak Investigation01:18

Steps in Outbreak Investigation

696
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:
696

You might also read

Related Articles

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

Sort by
Same author

NGS and emerging molecular scenarios in chronic myeloproliferative neoplasms: a case of double mutated polycythemia vera.

Annals of hematology·2026
Same author

Can AI applied on MRI reliably predict shunt response in INPH? A comprehensive exploration of deep learning and radiomics approaches using preoperative MRI.

PloS one·2026
Same author

Robotic-Assisted Surgery for Colorectal Cancer Treatment in 2026: An Updated Narrative Review.

Journal of clinical medicine·2026
Same author

Exploratory PET/CT Radiomics for Predicting Early Progression in Locally Advanced Pancreatic Cancer.

Diagnostics (Basel, Switzerland)·2026
Same author

Pancreatic Steatosis as a Risk Phenotype for Pancreatic Ductal Adenocarcinoma: A Narrative Review.

Medicina (Kaunas, Lithuania)·2026
Same author

Inflammation and fibrosis at pancreatic resection margin and their role in post-operative pancreatic fistula development after pancreaticoduodenectomy: a pilot study from a single institution.

Surgery open science·2026
Same journal

Correction: Mahmud et al. Thymoquinone Attenuates NF-κβ Signalling Activation in Retinal Pigment Epithelium Cells Under AMD-Mimicking Conditions. <i>Int. J. Mol. Sci.</i> 2025, <i>26</i>, 11473.

International journal of molecular sciences·2026
Same journal

Correction: Borovikov et al. The Twisting and Untwisting of Actin and Tropomyosin Filaments Are Involved in the Molecular Mechanisms of Muscle Contraction, and Their Disruption Can Result in Muscle Disorders. <i>Int. J. Mol. Sci</i>. 2025, <i>26</i>, 6705.

International journal of molecular sciences·2026
Same journal

Correction: Molagoda et al. Flavonoid Glycosides from <i>Ziziphus jujuba</i> var. <i>inermis</i> (Bunge) Rehder Seeds Inhibit α-Melanocyte-Stimulating Hormone-Mediated Melanogenesis. <i>Int. J. Mol. Sci.</i> 2021, <i>22</i>, 7701.

International journal of molecular sciences·2026
Same journal

Correction: Guo et al. Integrated Transcriptomic and Metabolomic Analysis Reveals the Molecular Regulatory Mechanism of Flavonoid Biosynthesis in Maize Roots Under Lead Stress. <i>Int. J. Mol. Sci.</i> 2024, <i>25</i>, 6050.

International journal of molecular sciences·2026
Same journal

Correction: Chang et al. Improvement of Carbon Tetrachloride-Induced Acute Hepatic Failure by Transplantation of Induced Pluripotent Stem Cells Without Reprogramming Factor c-Myc. <i>Int. J. Mol. Sci.</i> 2012, <i>13</i>, 3598-3617.

International journal of molecular sciences·2026
Same journal

Correction: Pînzariu et al. Gut Microbiota and Short-Chain Fatty Acids: Key Factors in Pediatric Obesity and Therapeutic Targets. <i>Int. J. Mol. Sci.</i> 2025, <i>26</i>, 11503.

International journal of molecular sciences·2026
See all related articles
This summary is machine-generated.

Machine learning models accurately predict sepsis progression and mortality by integrating clinical and biochemical data. These tools offer improved early diagnosis and personalized risk stratification compared to conventional methods.

Area of Science:

  • Critical Care Medicine
  • Computational Biology
  • Biomarkers and Diagnostics

Background:

  • Sepsis is a significant global health challenge, causing high morbidity and mortality.
  • Existing clinical scores and biomarkers have limitations in accurately predicting individual patient outcomes.
  • Machine learning (ML) presents an opportunity to enhance sepsis risk stratification by analyzing complex datasets.

Purpose of the Study:

  • To evaluate the performance of machine learning models in predicting sepsis severity and mortality.
  • To compare ML model performance against conventional methods like logistic regression.
  • To assess the interpretability of ML models using SHAP values for clinical relevance.

Main Methods:

  • Analysis of demographic, clinical, and laboratory data from 477 patients (251 sepsis, 100 septic shock, 126 controls).
Keywords:
Artificial Intelligencebiomarkersclinical decision support systemsexplainable AIprognosisrisk stratification

Related Experiment Videos

Last Updated: Mar 29, 2026

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

7.7K
  • Univariate correlation analyses to identify associations with sepsis severity and mortality.
  • Development and validation of various ML models, with performance measured by AUC-ROC and MCC; interpretability assessed via SHAP.

    • Main Results:

    • Biomarkers (procalcitonin, mid-regional pro-adrenomedullin, lactate) and clinical scores (SOFA, qSOFA) correlated with sepsis severity and mortality.
    • Selected ML models demonstrated superior or comparable performance to logistic regression for predicting sepsis (AUC 0.99), septic shock (AUC 0.96), and mortality (AUC up to 0.90).
    • SHAP analysis confirmed the clinical significance of identified predictors.

    Conclusions:

    • Machine learning models integrating clinical and biochemical data effectively predict sepsis progression and mortality.
    • ML-based tools offer improved accuracy and interpretability for early sepsis diagnosis and personalized risk stratification.
    • External validation is necessary prior to widespread clinical implementation of these ML tools.