A Transparent Four-Feature Logistic Model for Depression Screening in Assisted-Living Facilities

Depression in older adults is both common and frequently underdiagnosed, especially in assisted-living communities, where it often co-occurs with mild cognitive impairment (MCI), creating a complex and vulnerable clinical landscape. Despite this urgency, scalable, interpretable, and easy-to-administer tools for early screening remain scarce. In this study, we introduce a transparent and lightweight AI-driven screening model that uses only four linguistic features extracted from brief conversational speech, to detect depression with high sensitivity. Trained on the DAIC-WOZ dataset and optimized for deployment in resource constrained settings, our model achieved strong discriminative performance (AUC = 0.760) with a clinically calibrated sensitivity of 92%. Beyond raw accuracy, the model offers insights into how affective language, syntactic complexity, and latent semantic content relate to psychological states. Notably, one semantic feature derived from transformer embeddings, emb_1, appears to capture deeper emotional or cognitive tension not directly expressed through lexical negativity. We propose this component as a potential digital biomarker of cognitive-affective strain, warranting further longitudinal study. Our approach outperforms many more complex models in the literature, yet remains simple enough for real-time, on-device use, marking a step forward in making mental health AI both interpretable and clinically actionable.