Low predictive power of clinical features for relapse prediction after antidepressant discontinuation in a naturalistic setting.

ABSTRACT: The risk of relapse after antidepressant medication (ADM) discontinuation is high. Predictors of relapse could guide clinical decision-making, but are yet to be established. We assessed demographic and clinical variables in a longitudinal observational study before antidepressant discontinuation. State-dependent variables were re-assessed either after discontinuation or before discontinuation after a waiting period. Relapse was assessed during 6 months after discontinuation. We applied logistic general linear models in combination with least absolute shrinkage and selection operator and elastic nets to avoid overfitting in order to identify predictors of relapse and estimated their generalisability using cross-validation. The final sample included 104 patients (age: 34.86 (11.1), 77% femal

SUBMITTER: Berwian IM 

PROVIDER: S-EPMC9249776 | biostudies-literature | 2022 Jul

REPOSITORIES: biostudies-literature