Don't predict if you cannot interpret: investigating the clinical viability of facial movements for machine-learning assisted diagnostics of bipolar disorder

Background: Numerous studies have explored the possibility of developing automatic detection pipelines that can seamlessly diagnose patients with bipolar disorder (BD) and other mental illnesses. Such novel diagnostic tools increasingly rely on data sources, such as facial movements, whose relationships to BD have yet to be fully elucidated. As such, these detection pipelines offer limited clinical value, despite promising performance estimates. A vital next step toward achieving clinically reliable models is to conduct granular interpretability analyses to determine which subsets of facial movements are responsible for determining patient or control class membership. Materials and Methods: In this work, we rely on facial movements encoded as Action Units (AUs) of 32 participants recorded while watching emotional film clips. Our objective is to delineate the specific facial micro-movements responsible for the differences between patients with BD and controls by applying the interpretable Fisher’s Linear Discriminant Analysis (LDA) in a binary, supervised classification design. Results: We report how the movement of brow lowering (AU4) differentiates patients from controls with AUROC scores up to 69%. Conclusions: Our exploratory study argues for the necessity of devising inherently interpretable machine learning models for the clinical domain. Furthermore, we critically discuss the implications of identifying AU4 as a key discriminative feature and assess the clinical value of specific facial movements for the diagnostic process.