Screening for Major Depressive Disorder Using a Wearable Ultra-Short-Term HRV Monitor and Signal Quality Indices

• Published in: Sensors (Basel, Switzerland) Vol. 23; no. 8; p. 3867
• Main Authors: Sato, Shohei, Hiratsuka, Takuma, Hasegawa, Kenya, Watanabe, Keisuke, Obara, Yusuke, Kariya, Nobutoshi, Shinba, Toshikazu, Matsui, Takemi
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01.04.2023; MDPI
• Subjects: Accuracy; Adolescent; Adult; Algorithms; autonomic nervous response; Biomarkers; Classification; Depressive Disorder, Major - diagnosis; Diagnostic systems; Electrocardiography; Heart beat; Heart rate; Heart Rate - physiology; Humans; machine learning; Major depressive disorder; Mental depression; Mental disorders; Mental illness; Middle Aged; Motion; Photoplethysmography; Physiology; Regression analysis; Sensitivity; Sensors; Signal quality; signal quality index; Skin; Sleep; Smartphones; Stress; ultra-short-term heart rate variability; Wavelet transforms; Wearable computers; Wearable Electronic Devices; Wearable technology; Wrist; Wristwatches; Young Adult; Japan; United States > US; ultra-short-term heart rate variability; autonomic nervous response; major depressive disorder; photoplethysmography; machine learning; signal quality index
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s23083867

To encourage potential major depressive disorder (MDD) patients to attend diagnostic sessions, we developed a novel MDD screening system based on sleep-induced autonomic nervous responses. The proposed method only requires a wristwatch device to be worn for 24 h. We evaluated heart rate variability (HRV) via wrist photoplethysmography (PPG). However, previous studies have indicated that HRV measurements obtained using wearable devices are susceptible to motion artifacts. We propose a novel method to improve screening accuracy by removing unreliable HRV data (identified on the basis of signal quality indices (SQIs) obtained by PPG sensors). The proposed algorithm enables real-time calculation of signal quality indices in the frequency domain (SQI-FD). A clinical study conducted at Maynds Tower Mental Clinic enrolled 40 MDD patients (mean age, 37.5 ± 8.8 years) diagnosed on the basis of the , and 29 healthy volunteers (mean age, 31.9 ± 13.0 years). Acceleration data were used to identify sleep states, and a linear classification model was trained and tested using HRV and pulse rate data. Ten-fold cross-validation showed a sensitivity of 87.3% (80.3% without SQI-FD data) and specificity of 84.0% (73.3% without SQI-FD data). Thus, SQI-FD drastically improved sensitivity and specificity.