Current Concepts in Pediatric Critical Care-19: AI and Machine Learning in the PICU

Video Transcription

Video Summary

The speaker provides an insight into understanding and developing artificial intelligence (AI) and machine learning (ML) models, particularly in clinical informatics. The focus is on simplifying complex concepts regarding AI and ML, covering essential learning objectives like supervised, unsupervised, and deep learning. The speaker underscores the clinical relevance of these technologies, dwelling on understanding performance metrics and limitations to discern what is beneficial at the bedside. They discuss the workflow of developing prediction models, focusing primarily on supervised learning and emphasizing the importance of external validation to establish model generalizability. The speaker outlines a standard pipeline for ML projects and identifies common pitfalls, particularly in model implementation and real-world application. Through examples involving sepsis recognition and early acute kidney injury models, challenges like data set selection, model overfitting, and sensitivity versus positive predictive value trade-offs are illustrated. The summary emphasizes the gap in translating these models from research to practical clinical use.

Keywords

artificial intelligence

machine learning

clinical informatics

supervised learning

model validation

prediction models

	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.