AI-assisted prediction of differential response to antidepressant classes using electronic health records.
AI-assisted prediction of differential response to antidepressant classes using electronic health records.
复制标题
DOI：
10.1038/s41746-023-00817-8
复制
发表时间：
2023-04-26
影响因子：
15.2
通讯作者：
Smoller, Jordan W. W.
中科院分区：
文献类型：
--
作者：
Sheu, Yi-han;Magdamo, Colin;Miller, Matthew;Das, Sudeshna;Blacker, Deborah;Smoller, Jordan W. W.
抗病选择在很大程度上是一个试错过程。我们使用电子健康记录（EHR）数据和人工智能（AI）来预测抗抑郁药开始后4至12周对四种抗抑郁药（SSRI，SNRI，安非他酮和米氮平）的反应。最终数据集包括17，556名患者。预测因子来源于结构化和非结构化EHR数据，模型考虑了预测治疗选择的特征，以最大限度地减少适应症的混淆。通过专家图表审查和AI自动插补获得结局标签。训练了正则化广义线性模型（GLM）、随机森林、梯度提升机（GBM）和深度神经网络（DNN）模型，并比较了它们的性能。使用SHapley加法解释（SHAP）得出预测重要性评分。所有模型均表现出相似的良好预测性能（AUROC ≥ 0.70，AUPRC ≥ 0.68）。该模型可以估计患者之间以及同一患者的抗抑郁药类别之间的差异治疗反应概率。此外，可以生成驱动每个抗抑郁药类别的响应概率的患者特异性因素。我们表明，可以通过人工智能建模从真实世界的EHR数据准确预测抗抑郁药反应，并且我们的方法可以为临床决策支持系统的进一步开发提供信息，以实现更有效的治疗选择。
Antidepressant selection is largely a trial-and-error process. We used electronic health record (EHR) data and artificial intelligence (AI) to predict response to four antidepressants classes (SSRI, SNRI, bupropion, and mirtazapine) 4 to 12 weeks after antidepressant initiation. The final data set comprised 17,556 patients. Predictors were derived from both structured and unstructured EHR data and models accounted for features predictive of treatment selection to minimize confounding by indication. Outcome labels were derived through expert chart review and AI-automated imputation. Regularized generalized linear model (GLM), random forest, gradient boosting machine (GBM), and deep neural network (DNN) models were trained and their performance compared. Predictor importance scores were derived using SHapley Additive exPlanations (SHAP). All models demonstrated similarly good prediction performance (AUROCs ≥ 0.70, AUPRCs ≥ 0.68). The models can estimate differential treatment response probabilities both between patients and between antidepressant classes for the same patient. In addition, patient-specific factors driving response probabilities for each antidepressant class can be generated. We show that antidepressant response can be accurately predicted from real-world EHR data with AI modeling, and our approach could inform further development of clinical decision support systems for more effective treatment selection.
登录
查看更多内容
影响因子：
3.2
作者：
Klöbl M;Gryglewski G;Rischka L;Godbersen GM;Unterholzner J;Reed MB;Michenthaler P;Vanicek T;Winkler-Pjrek E;Hahn A;Kasper S;Lanzenberger R
通讯作者：
Lanzenberger R
影响因子：
3.6
作者：
Lee, Hyun Seo;Baik, Seung Yeon;Lee, Seung-Hwan
通讯作者：
Lee, Seung-Hwan
影响因子：
4.7
作者：
Kohler-Forsberg, Kristin;Jorgensen, Anders;Frokjaer, Vibe Gedsoe
通讯作者：
Frokjaer, Vibe Gedsoe
影响因子：
6.8
作者：
Cohen SE;Zantvoord JB;Wezenberg BN;Bockting CLH;van Wingen GA
通讯作者：
van Wingen GA
影响因子：
13.8
作者：
Hughes, Michael C.;Pradier, Melanie F.;Doshi-Velez, Finale
通讯作者：
Doshi-Velez, Finale