Toward Camera-PRV-Based Early Warning in Hospital ICU: A Pilot Study

In the Intensive Care Unit (ICU), monitoring a patient’s heart rate variability (HRV) can provide vital information regarding the physiological status and autonomic nervous system, serving as a potential metric for detecting adverse events in ICU. Although camera-based remote photoplethysmography (rPPG) has shown to be effective for heart rate monitoring in clinical environments, it remains insufficient research on utilizing rPPG-derived pulse rate variability (PRV) for monitoring autonomic nervous system (ANS) changes of ICU patients. In addition, the agreement between HRV and PRV is controversial, especially for ICU patients with multiple concurrent diseases. This study aims to validate the accuracy of camera-PRV measurements by analyzing eight HRV/PRV parameters from subjects with different health conditions, further discussing its feasibility as an early-warning tool. The accuracy of rPPG-derived PRV was comparable to that of contact-PPG and has high correlations with Electrocardiogram. Combined with machine learning algorithms, the system was able to accurately differentiate between healthy subjects and ICU patients (accuracy = 0.86, F1 score = 0.83, sensitivity = 0.79, specificity = 0.79). Furthermore, the system demonstrated good reliability in classifying subjects with different health status and ages. However, it could not effectively correspond to the APACHE II score when classifying ICU patients with different severities based on HRV/PRV. Because the APACHE II scoring system evaluates the changes in the patient’s ANS as well as a variety of confounding factors, of which the HRV/PRV parameters represent only a portion. In summary, the camera-PRV system was able to provide the individual physiological tracking and coarse-level modeling of the group health status. It is expected to achieve a more comprehensive health status assessment by integrating more vital signs in the future.