Continuous Cardiac Arrest Prediction in ICU using PPG Foundation Model
This addresses the problem of non-invasive, continuous cardiac arrest prediction for ICU patients, representing an incremental advance by applying foundation models to this specific domain.
The researchers tackled in-hospital cardiac arrest (IHCA) prediction in ICU patients using only single-channel finger photoplethysmography (PPG) signals, achieving an average AUROC of 0.79 over a 24-hour prediction window and peaking at 0.82 one hour before cardiac arrest.
Non-invasive patient monitoring for tracking and predicting adverse acute health events is an emerging area of research. We pursue in-hospital cardiac arrest (IHCA) prediction using only single-channel finger photoplethysmography (PPG) signals. Our proposed two-stage model Feature Extractor-Aggregator Network (FEAN) leverages powerful representations from pre-trained PPG foundation models (PPG-GPT of size up to 1 Billion) stacked with sequential classification models. We propose two FEAN variants ("1H", "FH") which use the latest one-hour and (max) 24-hour history to make decisions respectively. Our study is the first to present IHCA prediction results in ICU patients using only unimodal (continuous PPG signal) waveform deep representations. With our best model, we obtain an average of 0.79 AUROC over 24~h prediction window before CA event onset with our model peaking performance at 0.82 one hour before CA. We also provide a comprehensive analysis of our model through architectural tuning and PaCMAP visualization of patient health trajectory in latent space.