Habets Philippe C, Thomas Rajat M, Milaneschi Yuri, Jansen Rick, Pool Rene, Peyrot Wouter J, Penninx Brenda W J H, Meijer Onno C, van Wingen Guido A, Vinkers Christiaan H
Department of Anatomy & Neurosciences, Amsterdam University Medical Center, Vrije Universiteit, Amsterdam, the Netherlands; Department of Psychiatry, Amsterdam Neuroscience, Amsterdam University Medical Center, Vrije Universiteit, Amsterdam, the Netherlands; Department of Internal Medicine, section Endocrinology, Leiden University Medical Center, Leiden, the Netherlands.
Department of Anatomy & Neurosciences, Amsterdam University Medical Center, Vrije Universiteit, Amsterdam, the Netherlands.
Biol Psychiatry. 2023 Dec 15;94(12):948-958. doi: 10.1016/j.biopsych.2023.05.024. Epub 2023 Jun 15.
The ability to predict the disease course of individuals with major depressive disorder (MDD) is essential for optimal treatment planning. Here, we used a data-driven machine learning approach to assess the predictive value of different sets of biological data (whole-blood proteomics, lipid metabolomics, transcriptomics, genetics), both separately and added to clinical baseline variables, for the longitudinal prediction of 2-year remission status in MDD at the individual-subject level.
Prediction models were trained and cross-validated in a sample of 643 patients with current MDD (2-year remission n = 325) and subsequently tested for performance in 161 individuals with MDD (2-year remission n = 82).
Proteomics data showed the best unimodal data predictions (area under the receiver operating characteristic curve = 0.68). Adding proteomic to clinical data at baseline significantly improved 2-year MDD remission predictions (area under the receiver operating characteristic curve = 0.63 vs. 0.78, p = .013), while the addition of other omics data to clinical data did not yield significantly improved model performance. Feature importance and enrichment analysis revealed that proteomic analytes were involved in inflammatory response and lipid metabolism, with fibrinogen levels showing the highest variable importance, followed by symptom severity. Machine learning models outperformed psychiatrists' ability to predict 2-year remission status (balanced accuracy = 71% vs. 55%).
This study showed the added predictive value of combining proteomic data, but not other omics data, with clinical data for the prediction of 2-year remission status in MDD. Our results reveal a novel multimodal signature of 2-year MDD remission status that shows clinical potential for individual MDD disease course predictions from baseline measurements.
预测重度抑郁症（MDD）患者的疾病进程对于优化治疗方案至关重要。在此，我们采用数据驱动的机器学习方法，分别评估不同组生物数据（全血蛋白质组学、脂质代谢组学、转录组学、遗传学）以及将这些数据与临床基线变量相结合，在个体水平上对MDD患者2年缓解状态进行纵向预测的价值。
在643例当前患有MDD的患者样本（2年缓解者n = 325）中训练并交叉验证预测模型，随后在161例MDD患者（2年缓解者n = 82）中测试模型性能。
蛋白质组学数据显示出最佳的单峰数据预测效果（受试者工作特征曲线下面积 = 0.68）。在基线时将蛋白质组学数据添加到临床数据中显著改善了对MDD患者2年缓解的预测（受试者工作特征曲线下面积 = 0.63对0.78，p = 0.013），而将其他组学数据添加到临床数据中并未显著提高模型性能。特征重要性和富集分析表明，蛋白质组学分析物参与炎症反应和脂质代谢，纤维蛋白原水平显示出最高的变量重要性，其次是症状严重程度。机器学习模型在预测2年缓解状态方面优于精神科医生的能力（平衡准确率 = 71%对55%）。
本研究表明，将蛋白质组学数据而非其他组学数据与临床数据相结合，对预测MDD患者2年缓解状态具有额外的预测价值。我们的结果揭示了一种新的2年MDD缓解状态的多模式特征，该特征显示了从基线测量预测个体MDD病程的临床潜力。
