Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic, Rochester, MN, USA.
Department of Translational Research Psychiatry, Max Planck Institute of Psychiatry, Munich, Germany.
Neuropsychopharmacology. 2021 Jun;46(7):1272-1282. doi: 10.1038/s41386-020-00943-x. Epub 2021 Jan 15.
Heterogeneity in the clinical presentation of major depressive disorder and response to antidepressants limits clinicians' ability to accurately predict a specific patient's eventual response to therapy. Validated depressive symptom profiles may be an important tool for identifying poor outcomes early in the course of treatment. To derive these symptom profiles, we first examined data from 947 depressed subjects treated with selective serotonin reuptake inhibitors (SSRIs) to delineate the heterogeneity of antidepressant response using probabilistic graphical models (PGMs). We then used unsupervised machine learning to identify specific depressive symptoms and thresholds of improvement that were predictive of antidepressant response by 4 weeks for a patient to achieve remission, response, or nonresponse by 8 weeks. Four depressive symptoms (depressed mood, guilt feelings and delusion, work and activities and psychic anxiety) and specific thresholds of change in each at 4 weeks predicted eventual outcome at 8 weeks to SSRI therapy with an average accuracy of 77% (p = 5.5E-08). The same four symptoms and prognostic thresholds derived from patients treated with SSRIs correctly predicted outcomes in 72% (p = 1.25E-05) of 1996 patients treated with other antidepressants in both inpatient and outpatient settings in independent publicly-available datasets. These predictive accuracies were higher than the accuracy of 53% for predicting SSRI response achieved using approaches that (i) incorporated only baseline clinical and sociodemographic factors, or (ii) used 4-week nonresponse status to predict likely outcomes at 8 weeks. The present findings suggest that PGMs providing interpretable predictions have the potential to enhance clinical treatment of depression and reduce the time burden associated with trials of ineffective antidepressants. Prospective trials examining this approach are forthcoming.
重性抑郁障碍的临床表现存在异质性，抗抑郁药的反应也存在异质性，这限制了临床医生准确预测特定患者治疗最终反应的能力。经验证的抑郁症状谱可能是早期识别治疗过程中不良结局的重要工具。为了得出这些症状谱，我们首先使用概率图模型（PGM）检查了 947 名接受选择性 5-羟色胺再摄取抑制剂（SSRIs）治疗的抑郁患者的数据，以描绘抗抑郁反应的异质性。然后，我们使用无监督机器学习来识别特定的抑郁症状和改善阈值，这些症状和改善阈值在 4 周时可预测患者在 8 周时达到缓解、反应或无反应的可能性。4 种抑郁症状（心境低落、罪恶感和妄想、工作和活动以及精神焦虑）和每个症状在 4 周时的特定变化阈值可预测 8 周时 SSRI 治疗的最终结局，平均准确率为 77%（p=5.5E-08）。从接受 SSRIs 治疗的患者中得出的相同 4 种症状和预后阈值正确预测了在两个独立的公开可用数据集（包括住院和门诊环境中接受其他抗抑郁药治疗的 1996 名患者）中，72%（p=1.25E-05）患者的结局。这些预测准确率高于仅使用基线临床和社会人口统计学因素（i）或使用 4 周无反应状态预测 8 周可能结局（ii）的方法预测 SSRI 反应的准确率 53%。目前的研究结果表明，提供可解释预测的 PGM 有可能增强对抑郁症的临床治疗并减少与无效抗抑郁药试验相关的时间负担。即将进行前瞻性试验来检验这种方法。
