First impressions count: Therapists' impression on patients' motivation and helping alliance predicts psychotherapy dropout (Updated June 20, 2024).

A preprint abstract from osf.io discusses the issue of dropout rates in psychotherapy and the need for accurate predictors to counteract this problem. The study compared logistic regression models with two machine learning algorithms to predict therapy dropout in two large inpatient samples. The results showed that therapy dropout could be predicted with a high level of accuracy using baseline indicators, with patients' motivation and the therapeutic alliance being the most important predictors. The study suggests that interventions targeting patients' motivation and the therapeutic alliance could help reduce therapy dropouts. However, it is important to note that this preprint has not been peer-reviewed. [Extracted from the article]