University of Groningen, Faculty of Science and Engineering, Groningen Research Institute of Pharmacy, Groningen, the Netherlands.
University of Groningen, University Medical Center Groningen, University Center Psychiatry, Rob Giel Research Center, Interdisciplinary Centre for Psychopathology and Emotion Regulation, the Netherlands.
J Affect Disord. 2023 Aug 1;334:352-357. doi: 10.1016/j.jad.2023.04.111. Epub 2023 May 5.
Limited evidence exists regarding the association between early symptom change and later outcomes of cognitive behavioral therapy (CBT). This study aimed to apply machine learning algorithms to predict continuous treatment outcomes based on pre-treatment predictors and early symptom changes and to uncover whether additional variance could be explained compared to regression methods. Additionally, the study examined early subscale symptom changes to determine the most significant predictors of treatment outcome.
We investigated CBT outcomes in a large naturalistic dataset (N = 1975 depression patients). The sociodemographic profile, pre-treatment predictors, and early symptom change, including total and subscale scores were used to predict the Symptom Questionnaire (SQ)48 score at the 10th session as a continuous outcome. Different machine learners were compared to linear regression.
Early symptom change and baseline symptom score were the only significant predictors. Models with early symptom change explained 22.0 % to 23.3 % more variance than those without early symptom change. Specifically, the baseline total symptom score, and the early symptom score changes of the subscales pertaining to depression and anxiety were the top three predictors of treatment outcome.
Excluded patients with missing treatment outcomes had slightly higher symptom scores at baseline, indicating possible selection bias.
Early symptom change improved the prediction of treatment outcomes. The prediction performance achieved is far from clinical relevance: the best learner could only explain 51.2 % of the variance in outcomes. Compared to linear regression, more sophisticated preprocessing and learning methods did not substantially improve performance.
关于认知行为疗法（CBT）早期症状变化与后期结果之间的关系，证据有限。本研究旨在应用机器学习算法，根据治疗前的预测因素和早期症状变化来预测连续治疗结果，并发现与回归方法相比是否可以解释更多的差异。此外，该研究还检查了早期亚量表症状变化，以确定对治疗结果影响最大的预测因素。
我们在一个大型自然主义数据集（N=1975 例抑郁症患者）中调查了 CBT 结果。社会人口统计学特征、治疗前预测因素和早期症状变化，包括总分和子量表评分，用于预测第 10 次治疗时的症状问卷（SQ）48 评分作为连续结果。将不同的机器学习与线性回归进行比较。
早期症状变化和基线症状评分是唯一显著的预测因素。包含早期症状变化的模型比不包含早期症状变化的模型解释了 22.0%至 23.3%的更多方差。具体来说，基线总症状评分以及抑郁和焦虑相关子量表的早期症状评分变化是治疗结果的前三个预测因素。
排除了未报告治疗结果的患者，他们的基线症状评分略高，表明可能存在选择偏倚。
早期症状变化改善了治疗结果的预测。所达到的预测性能远未达到临床相关性：最佳学习者只能解释 51.2%的结果方差。与线性回归相比，更复杂的预处理和学习方法并没有显著提高性能。
