SCCM Resource Library-Predicting Cardiac Arrest in the Pediatric Intensive Care Unit Using Machine Learning

Predicting Cardiac Arrest in the Pediatric Intensive Care Unit Using Machine Learning

Video Transcription

Video Summary

In this video, Adam Kennett discusses his project on predicting cardiac arrest in a pediatric ICU using machine learning. He explains how they collected data from patients in the PICU, including EHR data, vital signs data, and EKG waveform data. They labeled specific time windows before discharge or cardiac arrest as positive or negative for cardiac arrest. They then performed feature engineering on the data to create 166 different features for their models. They trained, validated, and tested their machine learning models, with the XGBoost model performing the best with high sensitivity and specificity. They also generated a risk score for cardiac arrest and found that their models could identify hidden trends in the data indicative of cardiac arrest.

Asset Subtitle

Pediatrics, Cardiovascular, 2023

Asset Caption

Type: star research | Star Research Presentations: Research Enrichment, Adult and Pediatric (SessionID 30002)

Meta Tag

Content Type Presentation

Knowledge Area Pediatrics

Knowledge Area Cardiovascular

Membership Level Professional

Membership Level Select

Tag Pediatrics

Tag Cardiac Arrest

Year 2023

Keywords

predicting cardiac arrest

pediatric ICU

machine learning

EHR data

vital signs data

	Society of Critical Care Medicine 500 Midway Drive Mount Prospect, IL 60056 USA Phone: +1 847 827-6888 Fax: +1 847 439-7226 Email: support@sccm.org	Contact Us About SCCM Newsroom Advertising & Sponsorship DONATE	MySCCM LearnICU Patients & Families Surviving Sepsis Campaign Critical Care Societies Collaborative	GET OUR NEWSLETTER
© Society of Critical Care Medicine. All rights reserved. \| Privacy Statement \| Terms & Conditions The Society of Critical Care Medicine, SCCM, and Critical Care Congress are registered trademarks of the Society of Critical Care Medicine.