Abstract Clinical course after first episode psychosis (FEP) is heterogeneous. Subgrouping longitudinal symptom trajectories after FEP would be useful for developing personalized treatment approaches, and being able to predict these trajectories at baseline would facilitate individual-level treatment planning. We utilized k-means clustering to identify distinct clusters of 411 FEP patients based on longitudinal positive and negative symptom patterns. Ridge logistic regression was then used to identify predictors o…