Depression is heterogeneous with variable response to treatment. This study used unsupervised machine learning to cluster patients receiving escitalopram therapy into distinct response trajectory groups. Using data from the CAN-BIND-1 trial, the algorithm identified three clusters representing non-responders, responders, and remitters. Subjective mood state and anhedonia emerged as core features of response with escitalopram.
This study reveals distinct response trajectories to escitalopram treatment in depression by applying unsupervised machine learning to clinical data. The findings highlight that subjective mood and anhedonia are central to treatment response, while other symptom domains show more variable patterns.