Most interesting result: Lots of performance variability across symptoms, but our latent factor model, capturing core symptoms like negative affect & thought, was the overall winner during external validation (light blue bars) and even outperformed the total depression scores!

We developed and compared models predicting early response (4 weeks) to psychotherapy based on: (i) 16 individual depression symptoms, (ii) 4 latent symptom factors for sleep, appetite, motivation and negative affect related symptoms, and (iii) total scores.

Enjoyed the final conference summer of my PhD, presenting some work on the symptom-level predictive modelling of depression treatment response. Thanks to the Computational Psychiatry Conference #CPConf2025 and British Association for Psychopharmacology #BAP for the platform (and poster prize) 😊