药物基因组学驱动的机器学习预测SSRI抗抑郁疗效:多试验重复验证
研究纳入三个试验共1030例接受西酞普兰/艾司西酞普兰治疗的重性抑郁症白人门诊患者,利用功能验证的药物基因组生物标志物联合基线抑郁严重度构建机器学习模型,预测8周缓解与应答。模型在PGRN-AMPS中AUC>0.7(P<0.04),在STAR*D和ISPC中预测准确率>69%(P≤0.07),表明机器学习可实现可重复的SSRI疗效预测。
要点
- 机器学习联合基线抑郁总分与药物基因组SNP可预测SSRI 8周缓解/应答。
- 预测模型在三个独立试验中具有可重复的预测准确性。
- 预测效能:PGRN-AMPS的AUC>0.7(P<0.04),STAR*D与ISPC准确率>69%(P≤0.07)。
核心结论
- 机器学习联合基线抑郁严重度与药物基因组生物标志物可准确且可重复地预测SSRI治疗反应。
研究设计与样本
- 研究纳入1030例接受西酞普兰/艾司西酞普兰治疗的重性抑郁症白人门诊患者,来自PGRN-AMPS(n=398)、STAR*D(n=467)和ISPC(n=165)三个试验。
- 对PGRN-AMPS中与SSRI反应相关的血浆代谢物(5-羟色胺)及基线MDD严重度(犬尿氨酸)进行全基因组关联研究,识别出DEFB1、ERICH3、AHR和TSPAN5中的单核苷酸多态性(SNP)作为预测因子。
- 采用监督机器学习方法,以SNP和基线抑郁总分为训练特征,预测8周缓解和应答。
主要发现
- 在PGRN-AMPS患者中,预测8周缓解和应答的受试者工作特征曲线下面积(AUC)>0.7(P<0.04)。
- 在STAR*D和ISPC中,预测准确率>69%(P≤0.07),与PGRN-AMPS相当。
关键数值与推荐
- PGRN-AMPS中预测8周缓解/应答的AUC>0.7(P<0.04)。
- STAR*D和ISPC中预测准确率>69%(P≤0.07)。
临床怎么用
- 对于拟接受SSRI治疗的重性抑郁症患者,可考虑结合基线抑郁严重度与药物基因组SNP信息进行机器学习预测,辅助评估8周缓解/应答可能性。
局限性
- 研究人群为白人门诊患者,结论外推至其他种族人群需谨慎。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
We set out to determine whether machine learning-based algorithms that included functionally validated pharmacogenomic biomarkers joined with clinical measures could predict selective serotonin reuptake inhibitor (SSRI) remission/response in patients with major depressive disorder (MDD). We studied 1,030 white outpatients with MDD treated with citalopram/escitalopram in the Mayo Clinic Pharmacogenomics Research Network Antidepressant Medication Pharmacogenomic Study (PGRN-AMPS; n = 398), Sequenced Treatment Alternatives to Relieve Depression (STAR*D; n = 467), and International SSRI Pharmacogenomics Consortium (ISPC; n = 165) trials. A genomewide association study for PGRN-AMPS plasma metabolites associated with SSRI response (serotonin) and baseline MDD severity (kynurenine) identified single nucleotide polymorphisms (SNPs) in DEFB1, ERICH3, AHR, and TSPAN5 that we tested as predictors. Supervised machine-learning methods trained using SNPs and total baseline depression scores predicted remission and response at 8 weeks with area under the receiver operating curve (AUC) > 0.7 (P < 0.04) in PGRN-AMPS patients, with comparable prediction accuracies > 69% (P ≤ 0.07) in STAR*D and ISPC. These results demonstrate that machine learning can achieve accurate and, importantly, replicable prediction of SSRI therapy response using total baseline depression severity combined with pharmacogenomic biomarkers.
引用
- Athreya AP, Neavin D, Carrillo-Roa T, et al. Pharmacogenomics-Driven Prediction of Antidepressant Treatment Outcomes: A Machine-Learning Approach With Multi-trial Replication. Clin Pharmacol Ther. 2019. PMID: 31012492. doi:10.1002/cpt.1482
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。