Improved Photoplethysmography-Based Four-Stage Sleep Classification with Explainable AI-Driven Machine Learning

Single-sensor-based multistage sleep classification is a challenging task to acquire the accuracy of traditional polysomnography (PSG). Feature engineering is the key factor in improving the accuracy of any measurement based on machine learning with a single sensor. However, too many features increase the complexity of the model and training time. To address this challenge, explainable Artificial Intelligence (XAI) is used in several machine learning classifiers to determine the most explainable features of single-sensor-based (PPG) data for a lightweight model. This study demonstrated substantial improvements in prediction accuracy 75.54% for 4-stage sleep classification utilizing 42 PPG data variables. With a simpler AI model and a single low-cost PPG sensor, our adaptive approach shows promise for accurately staging sleep. This may simplify the detection and treatment of sleep disorders, potentially allowing for at-home solutions.