Detection of neurologic changes in critically ill infants using deep learning on video data: a retrospective single center cohort study

Infant alertness and neurologic changes can reflect life-threatening pathology but are assessed by physical exam, which can be intermittent and subjective. Reliable, continuous methods are needed. We hypothesized that our computer vision method to track movement, pose artificial intelligence (AI), c...

Full description

Saved in:
Bibliographic Details
Published in:EClinicalMedicine 2024-12, Vol.78, p.102919, Article 102919
Main Authors: Gleason, Alec, Richter, Florian, Beller, Nathalia, Arivazhagan, Naveen, Feng, Rui, Holmes, Emma, Glicksberg, Benjamin S., Morton, Sarah U., La Vega-Talbott, Maite, Fields, Madeline, Guttmann, Katherine, Nadkarni, Girish N., Richter, Felix
Format: Article
Language:English
Subjects:
Artificial intelligence
Deep learning
Encephalopathy
Neonatology
Sedation
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Infant alertness and neurologic changes can reflect life-threatening pathology but are assessed by physical exam, which can be intermittent and subjective. Reliable, continuous methods are needed. We hypothesized that our computer vision method to track movement, pose artificial intelligence (AI), could predict neurologic changes in the neonatal intensive care unit (NICU). We collected video data linked to electroencephalograms (video-EEG) from infants with corrected age less than 1 year at Mount Sinai Hospital in New York City, a level four urban NICU between February 1, 2021 and December 31, 2022. We trained a deep learning pose recognition algorithm on video feeds, labeling 14 anatomic landmarks in 25 frames/infant. We then trained classifiers on anatomic landmarks to predict cerebral dysfunction, diagnosed from EEG readings by an epileptologist, and sedation, defined by the administration of sedative medications. We built the largest video-EEG dataset to date (282,301 video minutes, 115 infants) sampled from a diverse patient population. Infant pose was accurately predicted in cross-validation, held-out frames, and held-out infants with respective receiver operating characteristic area under the curves (ROC-AUCs) 0.94, 0.83, 0.89. Median movement increased with age and, after accounting for age, was lower with sedative medications and in infants with cerebral dysfunction (all P 
ISSN:2589-5370
2589-5370
DOI:10.1016/j.eclinm.2024.102919