Pulse.

a daily field guide to health research that matters

◆ Console

‹ Mon · 13 Apr 2026
Promising but preliminary

Non-invasive classification of coronary perfusion pressure during CPR using smartphone-based skin video and deep learning.

AI analyzing phone video during CPR could guide chest compressions without invasive monitoring, making emergency resuscitation more effective.

A deep learning model applied to smartphone-captured skin video enabled non-invasive real-time classification of coronary perfusion pressure during CPR, potentially enabling hemodynamic guidance without invasive arterial lines. This represents a near-term implementable AI diagnostic tool for emergency cardiac care.

What the study was

Study design
Validation study
Population
CPR patients; smartphone video-based hemodynamic assessment
Category
Diagnostics
Maturity
Exploratory
Journal
Computer Methods and Programs in Biomedicine

Why it surfaced

Unsolicited find: novel AI application enabling non-invasive hemodynamic assessment during CPR via smartphone; unexpected intersection of AI diagnostics and emergency care.

A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.