Predicting antidepressant response through early improvement of individual symptoms of depression incorporating baseline characteristics of patients: An individual patient data meta-analysis.

Overall early improvement in depression after commencement of antidepressant treatment could be associated with subsequent response or remission, but its predictive ability is not adequate. We aimed to investigate whether early improvement of individual depressive symptoms and important baseline characteristics of patients including the number of previous depressive episodes and the duration of index episode, better predicts response or remission. We requested pharmaceutical companies in Japan for individual patient data from randomized placebo-controlled trials focusing on the efficacy of second-generation antidepressants. Primary and secondary outcomes were response and remission at week 6, respectively. We compared models that only included improvement in the overall depression severity at week 2 with models that also included improvement in individual symptoms and baseline characteristics, by conducting an individual patient data meta-analysis. We obtained data from three trials comprising 997 participants. For the response outcome, the model incorporating individual symptoms and baseline characteristics demonstrated better predictive values than those in the model including early improvement in overall depression only. However, the area under the receiver operating characteristic curve, and positive and negative predictive values were 0.65, 0.70, and 0.64, respectively, suggesting that 30% and 36% of the participants still had false-negative and false-positive predictions, respectively. For the remission outcome, the corresponding values in the latter model were 0.72, 0.62, and 0.68, respectively. We suggest that clinical judgement on early discontinuation of antidepressant from non-early improvement at week 2 should be carefully made.