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

You might also read

Related Articles

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

Sort by
Same author

Harmonization of measurement units: mission impossible or ethical imperative?

Clinical chemistry and laboratory medicine·2026
Same author

The value-based score in laboratory medicine: results of a European pilot study.

Clinical chemistry and laboratory medicine·2026
Same author

Inflammasome Gene Polymorphisms (NLRP3 and NLRC4) and Vitamin D Status in Patients with Multiple Sclerosis.

International journal of molecular sciences·2026
Same author

Analytical Methods for Fluid Biomarkers in Alzheimer's Disease from Discovery to Clinical Implementation.

International journal of molecular sciences·2026
Same author

Albumin decline corroborates physiological prothrombin time prolongation in the elderly.

Diagnosis (Berlin, Germany)·2026
Same author

Characterizing variation in laboratory medicine data: a comparative analysis of standard deviation and coefficient of variation.

Clinical chemistry and laboratory medicine·2026
Same journal

Correction: Confidence Measurement Metrics in Multimodal Large Language Models for Ultrasound-Based Radiology Cases: Comparative Evaluation Study of Self-Reported, Consistency-Based, and Hybrid Methods.

Journal of medical Internet research·2026
Same journal

Centering Equity During Health Technology Innovation: Scoping Review of Methods and Research Adjustments to Promote Inclusive Coproduction.

Journal of medical Internet research·2026
Same journal

Comparative Effectiveness of AI-Assisted Telerehabilitation, Telerehabilitation, In-Person Care, and Usual Care for Chronic Nonspecific Low Back Pain: Bayesian Network Meta-Analysis.

Journal of medical Internet research·2026
Same journal

Effectiveness of WeChat Public Account Intervention Based on the Information-Motivation-Behavioral Skills Model Among College Students With Internet Addiction: Randomized Controlled Trial.

Journal of medical Internet research·2026
Same journal

Are Traditional Registries Becoming Obsolete in the Modern Digital Health Ecosystem?

Journal of medical Internet research·2026
Same journal

Detecting and Preventing Fraudulent Participation in Qualitative Research: Content Analysis of Two Multisite Studies.

Journal of medical Internet research·2026
See all related articles

Related Experiment Video

Updated: May 25, 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

135

Complete Blood Count and Monocyte Distribution Width-Based Machine Learning Algorithms for Sepsis Detection:

Andrea Campagner1, Luisa Agnello2, Anna Carobene3

  • 1IRCCS Ospedale Galeazzi Sant'Ambrogio, Milan, Italy.

Journal of Medical Internet Research
|February 26, 2025
PubMed
Summary
This summary is machine-generated.

Machine learning models combining monocyte distribution width (MDW) and complete blood count parameters show promise for early sepsis detection. These advanced models demonstrate improved generalizability and robustness across diverse clinical settings.

Keywords:
artificial intelligencebiomarkerclinical signsclinical symptomscomplete blood countcontrollable AIdata distributiondetectiondevelopment studydiagnosticearly detectionexternal validationmachine learningmachine learning modelmedical machine learningorganorgan dysfunctionsepsissepsis detectionvalidation study

More Related Videos

Characterization of Human Monocyte Subsets by Whole Blood Flow Cytometry Analysis
09:12

Characterization of Human Monocyte Subsets by Whole Blood Flow Cytometry Analysis

Published on: October 17, 2018

57.5K
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

6.6K

Related Experiment Videos

Last Updated: May 25, 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

135
Characterization of Human Monocyte Subsets by Whole Blood Flow Cytometry Analysis
09:12

Characterization of Human Monocyte Subsets by Whole Blood Flow Cytometry Analysis

Published on: October 17, 2018

57.5K
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

6.6K

Area of Science:

  • Clinical Medicine
  • Biomedical Engineering
  • Artificial Intelligence in Healthcare

Background:

  • Sepsis, a life-threatening organ dysfunction from infection, requires early detection for improved patient outcomes.
  • Monocyte distribution width (MDW) is a recognized sepsis biomarker, but its clinical utility is limited by poor sensitivity and positive predictive value.
  • Existing machine learning (ML) models for sepsis detection often exhibit poor generalization in real-world clinical settings.

Purpose of the Study:

  • To develop and validate ML models for early sepsis detection using MDW and complete blood count (CBC) parameters.
  • To enhance the generalizability and robustness of ML models in diverse clinical environments, addressing out-of-distribution challenges.
  • To leverage controllable AI techniques, including cautious classification and explainable AI, to improve sepsis detection accuracy and model interpretability.

Main Methods:

  • A multicentric study involving 5,344 patients across 5 Italian hospitals to train and externally validate ML models.
  • Models were trained on emergency department data and validated on diverse cohorts (emergency department and intensive care unit) exhibiting various data distribution shifts.
  • Incorporation of controllable AI techniques such as cautious classification and explainable AI to improve model robustness and provide diagnostic insights.

Main Results:

  • Developed ML models achieved high internal validation performance (AUC 0.91-0.98) and consistent external validation results (AUC 0.75-0.95).
  • The models outperformed traditional biomarkers and existing state-of-the-art ML models in sepsis detection across different cohorts.
  • Controllable AI techniques enhanced model performance and facilitated the derivation of interpretable diagnostic rules.

Conclusions:

  • Controllable AI approaches integrating CBC and MDW show significant potential for the early and accurate detection of sepsis.
  • The proposed methodology yields ML models that are more resilient to data distribution shifts, enhancing their clinical applicability.
  • This study highlights a pathway for developing more reliable AI-driven diagnostic tools for critical conditions like sepsis.