Tamara Thomas

Urban Health Today

A study published in eClinicalMedicine revealed that deep learning with Pose artificial intelligence (AI) might offer a scalable and minimally invasive way for doctors to monitor brain activity and detect potential neurological concerns in babies in the neonatal intensive care unit (NICU). 
Pose AI is a tool that detects and tracks different human movements (poses)  using anatomic landmarks in video data.
A team of clinicians, scientists, and engineers at Mount Sinai trained a deep learning pose-recognition algorithm on video feeds of infants in the neonatal intensive care unit (NICU) to accurately track their movements and identify key neurologic metrics.  
The researchers included video data linked to electroencephalograms (EEGs) of 115 infants at four urban NICUs from  Feb. 1, 2021, to Dec. 31, 2022. In total, the video-EEG was about 282,301 video minutes.
The researchers found that an EEG diagnosis of cerebral dysfunction can be predicted from video data alone. Specifically, they used anatomic landmarks from the video data to predict two critical conditions in infants—sedation and cerebral dysfunction—with high accuracy.
“Although many neonatal intensive care units contain video cameras, to date they do not apply deep learning to monitor patients,” said Dr. Felix Richter, senior author of the paper and Instructor of Newborn Medicine in the Department of Pediatrics at Mount Sinai. “Our study shows that applying an AI algorithm to cameras that continuously monitor infants in the NICU is an effective way to detect neurologic changes early, potentially allowing for faster interventions and better outcomes.”
The researchers emphasized that this approach does not replace the vital role of physicians and nurses in the Neonatal Intensive Care Unit (NICU). Instead, it augments their assessments by offering continuous, real-time data that can be integrated into clinical decision-making.
“We envision a future system where cameras continuously monitor infants in the NICU, with AI providing a neuro-telemetry strip similar to heart rate or respiratory monitoring, with alert for changes in sedation levels or cerebral dysfunction. Clinicians could review videos and AI-generated insights when needed, offering an intuitive and easily interpretable tool for bedside care, ” explained Dr. Richter. 
Source:<a href="https://www.mountsinai.org/about/newsroom/2024/mount-sinai-team-shows-ai-can-detect-serious-neurologic-changes-in-babies-in-the-nicu-using-video-data-alone"> Mount Sinai News</a>
Journal:<a href="https://www.thelancet.com/journals/eclinm/article/PIIS2589-5370(24)00498-X/fulltext"> eClinicalMedicine</a>

Stress-Related Genes May Drive Aggressive Prostate Cancer in Black Men

Prostate Cancer

Rebecca Araujo

Study Highlights Need for Tailored Depression Interventions for Black Adolescents

Mental Health

Lou Portero

Transplant Line Skipping

Public Health

Latest News

AI May Detect Serious Neurologic Changes in Babies in NICU Using Video Analysis

Neurology Diagnostics

A study reveals that deep learning with pose AI can monitor brain activity in NICU infants, enabling early detection of neurological issues through video data analysis.

About Us

Editorial Policy

Contributors & Partners

Contact Us

eNewsletters

Work With Us

Advertising

Career Center

GU Oncology Now

Blood Cancers Today

Cancer Nursing Today

DocWire News

MashupMD

Food Allergy Roundtable Discussions

Allergy

Blood Cancers

— Multiple Myeloma

Breast Cancer

Colorectal Cancer

Pancreatic Cancer

Cancer

Diabetes

Gastroenterology

Heart Failure

Heart Disease Prevention

Heart Health

— Alzheimer’s Disease

Neurology

Autoimmune Disease

Infectious Diseases

Obesity

Pediatrics

Sickle Cell Disease

Digital Health

Dermatology

Pulmonology

Video Insights

Workforce News

More

Gynecologic Cancer

Heart Disease in Women

Menopause

Reproductive Health

Women’s Neurology

Well Woman Today

Roundtables

Podcasts

Conferences

Viewpoints

Subscribe