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: Jul 2, 2026

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

ARDSMLpred: A machine learning model for predicting SCAP-associated ARDS based on MIMIC-IV database.

Xiaohui Zhu1, Zhimu Yuan2, QiuSong Shen3

  • 1Department of Respiratory, The Fourth Affiliated Hospital of Nanjing Medical University, 298 Nanpu Road, Nanjing, 211899, China.

Respiratory Medicine
|May 13, 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 author

Case Report: Metastatic right ventricular tumor and pulmonary embolism from cervical cancer post COVID-19 infection.

Frontiers in immunology·2026
Same author

Epigenetic safety of in vitro maturation in PCOS: genome-wide DNA methylation profiling of cord blood from a randomized controlled trial.

Journal of ovarian research·2026
Same author

Mesoporous silica-triggered aggregation-induced enhanced emission enables ratiometric fluorescence detection of multiple heavy metal ions in water.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2026
Same author

Effectiveness analysis of a multi-track teaching model based on OBE concept in pediatric ophthalmology clinical internship.

BMC medical education·2026
Same author

Composite Ultrasound Score Integrating VExUS Grading and Right Ventricular Function for Predicting 90-Day Heart Failure Rehospitalization: A Single-Center Retrospective Cohort Study.

International journal of general medicine·2026
Same author

The oral microbiome is associated with the diagnosis, prognosis and radiotherapy sensitivity of esophageal cancer.

Journal of translational medicine·2026
Same journal

Eight-week high-intensity inspiratory muscle training improves cardiac autonomic function in COPD: a randomised controlled trial.

Respiratory medicine·2026
Same journal

Respiratory Muscle Strength, Functional Exercise Capacity, and Muscle Oxygenation Differences Between COPD, PRISM, and Healthy Controls.

Respiratory medicine·2026
Same journal

Prediction of therapeutic effect of antifibrotic therapy for idiopathic pulmonary fibrosis using quantitative CT texture analysis.

Respiratory medicine·2026
Same journal

Obesity and Early Sepsis-Associated Acute Respiratory Distress Syndrome: A Prospective Multicenter Study.

Respiratory medicine·2026
Same journal

Adults with congenital lung malformations: A descriptive analysis of an underexplored population.

Respiratory medicine·2026
Same journal

Risk factors and microbiological characteristics of ventilator-associated pneumonia in a Tunisian intensive care unit during the COVID-19 pandemic.

Respiratory medicine·2026
See all related articles
This summary is machine-generated.

This study developed a machine learning model to predict acute respiratory distress syndrome (ARDS) in severe community-acquired pneumonia (SCAP) patients. The XGBoost model demonstrated excellent performance, aiding in early diagnosis and improved patient outcomes.

Area of Science:

  • Critical Care Medicine
  • Machine Learning in Healthcare
  • Respiratory Medicine

Background:

  • Early identification of acute respiratory distress syndrome (ARDS) in severe community-acquired pneumonia (SCAP) is critical for reducing patient morbidity and mortality.
  • Developing accurate prediction models for SCAP-associated ARDS in adult ICU patients is essential.

Purpose of the Study:

  • To develop and validate an optimal prediction model for SCAP-associated ARDS using clinical data and biomarkers.
  • To identify key clinical and laboratory variables predictive of ARDS development in SCAP patients.

Main Methods:

  • Utilized the MIMIC-IV database with 3,807 SCAP patients, randomly split into training (n=2,664) and testing (n=1,143) sets.
  • Employed LASSO regression to select 8 significant variables (Charlson, Lactate, Stroke, Race, AG, ALB, Sepsis, ROX) for model construction.
Keywords:
ARDSMIMIC-IV databaseMachine learningSCAPSCAP-Associated ARDSXGBoost algorithm

Related Experiment Videos

Last Updated: Jul 2, 2026

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

  • Developed and evaluated ten machine learning models, including XGBoost, LGBM, and KNN, assessing performance via ROC curves, calibration plots, and other metrics.

    • Main Results:

    • The XGBoost model achieved an AUROC of 0.9999 in the training set and 0.9466 in the test set.
    • Other models like LGBM and KNNC also showed high performance in the training set, with varying results in the test set.
    • A web calculator (ARDSMLpred) is available for predicting SCAP-associated ARDS in adult ICU patients.

    Conclusions:

    • The XGBoost-based prediction model, utilizing 8 key variables, demonstrates excellent predictive performance for SCAP-associated ARDS in adult ICU patients.
    • This data-driven model can assist clinicians in making timely and accurate diagnoses.
    • The developed prediction tool offers a valuable resource for improving patient care and outcomes.