Daily Mental Stress Prediction Using Heart Rate Variability

Abstract

In this work, an accurate ECG-based daily mental stress level prediction strategy is presented. Multiple support vector machines (SVM) with linear kernel functions are individually trained to predict daily stress levels of women who participated in the OMsignal MyHeart project. In this study, participants are asked to answer a daily survey to determine the quality of their sleep, exercise, valence, control and rumination during the last 24-hour. Using the aforementioned items, a daily stress score was defined to be used as the target value for constructing the stress prediction model. The model is designed to use heart rate variability (HRV) metrics calculated from a 5- minute data window moving over daily ECG recordings. The features including the first five minimum and maximum values of standard deviation of the NN-intervals (SDNN) and root mean square of the successive differences between normal heart beats (RMSSD) as well as heart rate are extracted to represent each individual daily ECG record. The leave-one-out cross-validation method is used to train and validate our user-dependent SVM model. On validation data, an average accuracy of 82.25% is achieved for predicting daily stress scores of the users with sufficient number of daily survey data.