Computerized analysis of facial expression reveals objective indices of blunted facial affect

Blunted affect is associated with severe mental illness, particularly schizophrenia. Mechanisms of blunted affect are poorly understood, potentially due to a lack of phenomenological clarity. Here, we examine clinician rated blunted affect and computerized facial metrics derived from ambulatory video assessment using machine learning. With high predictive accuracy (80-82%), we found that head orientation, eye movement, and facets of mouth movement were associated with clinical ratings of blunted affect. Features denoting larger muscle movements were associated with social cognition (R² = 0.37) and cognition (R² = 0.40). Findings provide potential insights on psychological and pathophysiological contributors to blunted affect.