Non-invasive arterial blood pressure waveform generation in critically ill patients: A sensor-based deep learning approach

2026-07-15

PRE

Carl Harris

Bright Nnadi

Sampath Rapuri

John Rattray

Francesco Tenore

Ralph Etienne-Cummings

Robert D. Stevens *

DOI：10.1016/j.compbiomed.2026.111861

Original

Original request for help

Save

Abstract

En 中文

• MOSAIC wearable sensors enable non-invasive continuous BP estimation in the ICU. • A CNN/LSTM hybrid model achieved R2=0.732 , MAE=6.42 on ABP waveform prediction. • Split-conformal prediction gave calibrated, value-dependent uncertainty bands. • MOSAIC may reduce reliance on invasive arterial catheterization in the ICU.

Non-invasive arterial blood pressure waveform generation in critically ill patients: A sensor-based deep learning approach

Abstract

Journal

Organization

Cited Papers

Citing Papers