A clinical risk stratification tool for predicting treatment resistance in major depressive disorder.
A clinical risk stratification tool for predicting treatment resistance in major depressive disorder.
复制标题
DOI：
10.1016/j.biopsych.2012.12.007
复制
发表时间：
2013-07-01
影响因子：
10.6
通讯作者：
Perlis, Roy H.
中科院分区：
文献类型：
--
作者：
Perlis, Roy H.
关键词：
及早识别耐药的高危抑郁症患者有助于选择最佳的治疗环境和护理强度。目前，促进这种风险分层的有效工具很少在精神病学实践中使用。数据来自一项多中心抗抑郁剂对严重抑郁障碍的有效性研究的前两个治疗水平，即缓解抑郁的排序治疗替代方案(STAR*D)队列。该队列被分为训练、测试和验证子集。只有临床或社会人口学变量可由自我报告获得，或容易服从自我报告。多变量模型被开发来区分通过第一次或第二次药物治疗试验而达到缓解的个体和那些尽管进行了两次试验而没有达到缓解的个体。Logistic回归模型在训练、测试和验证队列中实现了接收器操作特征曲线(AUC)下的面积超过0.71，并在队列之间保持了良好的校准。使用机器学习方法的三种替代模型--朴素贝叶斯分类器和支持向量机，以及随机森林模型--的性能不太一致。在重度抑郁症和轻度抑郁症之间、男性和女性之间以及初级和专科护理地点之间也观察到了类似的表现。开发了一个基于网络的计算器，它实现了这一工具，并提供了风险的图形估计。使用一个结合了基线社会人口学和临床特征的简单模型，可以估计门诊重度抑郁障碍患者耐药的风险。未来的研究应该检查这种模式在其他临床人群中的表现，以及它在治疗选择或临床试验设计中的实用性。缓解抑郁的序贯治疗替代方案(STAR*D)；NCT00021528；www.star-d.org
Early identification of depressed individuals at high risk for treatment-resistance could be helpful in selecting optimal setting and intensity of care. At present, validated tools to facilitate this risk stratification are rarely used in psychiatric practice. Data were drawn from the first two treatment levels of a multicenter antidepressant effectiveness study in major depressive disorder, the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) cohort. This cohort was divided into training, testing, and validation subsets. Only clinical or sociodemographic variables available by, or readily amenable to, self-report were considered. Multivariate models were developed to discriminate individuals reaching remission with a first or second pharmacologic treatment trial from those not reaching remission despite two trials. A logistic regression model achieved an area under the receiver operating characteristic curve (AUC) exceeding 0.71 in training, testing and validation cohorts, and maintained good calibration across cohorts. Performance of three alternative models using machine learning approaches–a naïve Bayes classifier and a support vector machine, and a random forest model – was less consistent. Similar performance was observed between more and less severe depression, males and females, and primary versus specialty care sites. A web-based calculator was developed which implements this tool and provides graphical estimates of risk. Risk for treatment-resistance among outpatients with major depressive disorder can be estimated using a simple model incorporating baseline sociodemographic and clinical features. Future studies should examine the performance of this model in other clinical populations and its utility in treatment selection or clinical trial design. Sequential Treatment Alternatives to Relieve Depression (STAR*D); NCT00021528; www.star-d.org
登录
查看更多内容
影响因子：
37.8
作者：
Cook, Nancy R.
通讯作者：
Cook, Nancy R.
DOI：
10.1111/j.1532-5415.1968.tb02103.x
发表时间：
1968-01-01
影响因子：
6.3
作者：
LINN, BS;LINN, MW;GUREL, L
通讯作者：
GUREL, L
影响因子：
1.7
作者：
Austin, Peter C.;Lee, Douglas S.;Tu, Jack V.
通讯作者：
Tu, Jack V.
影响因子：
4.8
作者：
Burges, CJC
通讯作者：
Burges, CJC
影响因子：
4.6
作者：
Grove, WM;Lloyd, M
通讯作者：
Lloyd, M