Medicine and Health
Mobile sensing-based depression severity assessment in participants with heterogeneous mental health conditions
B. Lamichhane, N. Moukaddam, et al.
Mobile sensing augmented with free-living audio captures sociability signals that improve depression severity assessment across healthy and clinical populations. In a weeklong study with healthy, major depressive disorder, and schizoaffective participants, adding audioband-derived sociability features reduced RMSE from 6.80 to 6.07, boosted five-class F1 from 0.34 to 0.46, and achieved a strong correlation (r=0.76, p<0.001) with reported severity. Research was conducted by Bishal Lamichhane, Nidal Moukaddam, and Ashutosh Sabharwal.
Related Publications
Explore these studies to deepen your understanding of the subject.
