治疗前奖赏任务脑激活模式预测个体抗抑郁药反应:EMBARC随机临床试验关键结果
研究基于EMBARC试验222例患者,在基线进行奖赏处理任务功能磁共振成像后随机接受舍曲林8周(n=106)或安慰剂8周(n=116),舍曲林无反应者(n=37)换用安非他酮8周。深度学习模型预测舍曲林组汉密尔顿抑郁量表变化R2为48%(95%CI 33%-61%,p<10-3),需治疗人数(NNT)为4.86;安慰剂组R2为28%(95%CI 15%-42%,p<10-3),NNT为2.95;安非他酮组R2为34%(95%CI 10%-59%,p<10-3),NNT为1.68。
要点
- 舍曲林预测模型R2=48%(95%CI 33%-61%,p<10-3),预测反应的NNT=4.86。
- 安慰剂模型R2=28%(95%CI 15%-42%,p<10-3),预测反应的NNT=2.95。
- 安非他酮模型R2=34%(95%CI 10%-59%,p<10-3),预测反应的NNT=1.68。
核心结论
- 奖赏处理测量与深度学习可预测抗抑郁药结局,并形成多模态治疗生物标志物。
研究设计与样本
- EMBARC研究纳入222例患者,基线进行奖赏处理任务功能磁共振成像,随机接受舍曲林8周(n=106)或安慰剂8周(n=116),舍曲林无反应者(n=37)换用安非他酮8周。
- 使用奖赏处理、临床测量和人口学数据训练治疗特异性深度学习模型,结局指标为汉密尔顿抑郁量表变化。
主要发现
- 舍曲林模型预测汉密尔顿抑郁量表变化的R2为48%(95%CI 33%-61%,p<10-3),预测反应的NNT为4.86。
- 安慰剂模型R2为28%(95%CI 15%-42%,p<10-3),预测反应的NNT为2.95。
- 安非他酮模型R2为34%(95%CI 10%-59%,p<10-3),预测反应的NNT为1.68。
- 舍曲林预测涉及前额叶皮层和小脑 crus 1,安非他酮预测涉及扣带皮层、尾状核、眶额皮层和 crus 1。
关键数值与推荐
- 舍曲林预测模型R2=48%(95%CI 33%-61%,p<10-3),NNT=4.86。
- 安慰剂预测模型R2=28%(95%CI 15%-42%,p<10-3),NNT=2.95。
- 安非他酮预测模型R2=34%(95%CI 10%-59%,p<10-3),NNT=1.68。
临床怎么用
- 原文未据此给出临床推荐。
局限性
- 原文未报告局限性。
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
BACKGROUND: The lack of biomarkers to inform antidepressant selection is a key challenge in personalized depression treatment. This work identifies candidate biomarkers by building deep learning predictors of individual treatment outcomes using reward processing measures from functional magnetic resonance imaging, clinical assessments, and demographics. METHODS: Participants in the EMBARC (Establishing Moderators and Biosignatures of Antidepressant Response in Clinical Care) study (n = 222) underwent reward processing task-based functional magnetic resonance imaging at baseline and were randomized to 8 weeks of sertraline (n = 106) or placebo (n = 116). Subsequently, sertraline nonresponders (n = 37) switched to 8 weeks of bupropion. The change in Hamilton Depression Rating Scale was measured after treatment. Reward processing, clinical measurements, and demographics were used to train treatment-specific deep learning models. RESULTS: The predictive model for sertraline achieved R2 of 48% (95% CI, 33%-61%; p < 10-3) in predicting the change in Hamilton Depression Rating Scale and number-needed-to-treat (NNT) of 4.86 participants in predicting response. The placebo model achieved R2 of 28% (95% CI, 15%-42%; p < 10-3) and NNT of 2.95 in predicting response. The bupropion model achieved R2 of 34% (95% CI, 10%-59%, p < 10-3) and NNT of 1.68 in predicting response. Brain regions where reward processing activity was predictive included the prefrontal cortex and cerebellar crus 1 for sertraline and the cingulate cortex, caudate, orbitofrontal cortex, and crus 1 for bupropion. CONCLUSIONS: These findings demonstrate the utility of reward processing measurements and deep learning to predict antidepressant outcomes and to form multimodal treatment biomarkers.
引用
- Nguyen KP, Chin Fatt C, Treacher A, et al. Patterns of Pretreatment Reward Task Brain Activation Predict Individual Antidepressant Response: Key Results From the EMBARC Randomized Clinical Trial. Biol Psychiatry. 2021. PMID: 34916068. doi:10.1016/j.biopsych.2021.09.011
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。