false
OasisLMS
Catalog
Current Concepts in Pediatric Critical Care
19: AI and Machine Learning in the PICU
19: AI and Machine Learning in the PICU
Back to course
[Please upgrade your browser to play this video content]
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
×
Please select your language
1
English