Surgery is a particularly potent stressor and the detrimental effects of stress on people undergoing any surgery is indisputable.. This paper focusses on developing an automatic presurgery stress detection scheme based on electrodermal activity (EDA). The measurement set up involves a wrist wearable that monitors EDA of a subject continuously in the most non-invasive and unobtrusive manner. Data were collected from 41 subjects (17 females and 24 males, age: 54.8 ± 16.8 years (mean ± SD)), who subsequently underwent different surgical procedures at the Sri Ramakrishna Hospital, Coimbatore, India. A supervised machine learning algorithm that detects motion artifacts in the recorded EDA data was developed. A novel localized supervised learning scheme, based on the adaptive partitioning of the dataset was adopted for stress detection.

This work was published at JBHI 2019.