Department of Statistics and Applied Probability, National University of Singapore, 6 Science Drive 2, Singapore 117546.
J Clin Psychiatry. 2010 Nov;71(11):1502-8. doi: 10.4088/JCP.10m06168blu.
There are currently no clinically useful assessments that can reliably predict--early in treatment--whether a particular depressed patient will respond to a particular antidepressant. We explored the possibility of using baseline features and early symptom change to predict which patients will and which patients will not respond to treatment.
Participants were 2,280 outpatients enrolled in the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) study who had complete 16-item Quick Inventory of Depressive Symptomatology-self-report (QIDS-SR16) records at baseline, week 2, and week 6 (primary outcome) of treatment with citalopram. Response was defined as a ≥ 50% reduction in QIDS-SR16 score by week 6. By developing a recursive subsetting algorithm, we used both baseline variables and change in QIDS-SR16 scores from baseline to week 2 to predict response/nonresponse to treatment for as many patients as possible with controlled accuracy, while reserving judgment for the rest.
Baseline variables by themselves were not clinically useful predictors, whereas symptom change from baseline to week 2 identified 280 nonresponders, of which 227 were true nonresponders. By subsetting recursively according to both baseline features and symptom change, we were able to identify 505 nonresponders, of which 403 were true nonresponders, to achieve a clinically meaningful negative predictive value of 0.8, which was upheld in cross-validation analyses.
Recursive subsetting based on baseline features and early symptom change allows predictions of nonresponse that are sufficiently certain for clinicians to spare identified patients from prolonged exposure to ineffective treatment, thereby personalizing depression management and saving time and cost.
clinicaltrials.gov Identifier: NCT00021528.
目前尚无临床上有用的评估方法可以可靠地预测——在治疗早期——特定的抑郁患者是否会对特定的抗抑郁药产生反应。我们探讨了使用基线特征和早期症状变化来预测哪些患者会对治疗有反应，哪些患者不会有反应的可能性。
共有 2280 名参加 Sequenced Treatment Alternatives to Relieve Depression（STAR*D）研究的门诊患者入组，这些患者在基线、治疗第 2 周和第 6 周（主要结局）时使用西酞普兰完成了 16 项简短抑郁症状清单自评版（QIDS-SR16）的完整记录。以 QIDS-SR16 评分在第 6 周时降低≥50%为应答。通过开发递归子集算法，我们使用基线变量和从基线到第 2 周的 QIDS-SR16 评分变化来预测尽可能多的患者对治疗的反应/无反应，同时保留对其余患者的判断。
基线变量本身不是临床有用的预测指标，而从基线到第 2 周的症状变化则确定了 280 名无反应者，其中 227 名是真正的无反应者。通过根据基线特征和症状变化递归子集化，我们能够识别出 505 名无反应者，其中 403 名是真正的无反应者，从而实现了具有临床意义的阴性预测值 0.8，这在交叉验证分析中得到了验证。
基于基线特征和早期症状变化的递归子集化允许对无反应进行足够确定的预测，以便临床医生能够避免将确定的患者暴露于无效的治疗中，从而实现个体化的抑郁症管理并节省时间和成本。
clinicaltrials.gov 标识符：NCT00021528。
