Estimating Reliability of Signal Quality of Physiological Data from Data Statistics Itself for Real-time Wearables

Artificial intelligence (AI) algorithms including machine and deep learning relies on proper data for classification and subsequent action. However, real-time unsupervised streaming data might not be reliable, which can lead to reduced accuracy or high error rates. Estimating reliability of signals, such as from wearable sensors for disease monitoring, is thus important but challenging since signals can be noisy and vulnerable to artifacts. In this paper, we propose a novel "Data Reliability Metric (DReM)" and demonstrate the proof-of-concept with two bio signals: electrocardiogram (ECG) and photoplethysmogram (PPG). We explored various statistical features and developed Artificial Neural Network (ANN), Random Forest (RF) and Support Vector Machine (SVM) models to autonomously classify good quality signals from the bad quality signals. Our results demonstrate the performance of the classification with a cross-validation accuracy of 99.7%, sensitivity of 100%, precision of 97% and F-score of 96%. This work demonstrates the potential of DReM to objectively and automatically estimate signal quality in unsupervised real-time settings with low computational requirement suitable for low-power digital signal processing techniques on wearables.