Huda Ahsan, Castaño Adam, Niyogi Anindita, Schumacher Jennifer, Stewart Michelle, Bruno Marianna, Hu Mo, Ahmad Faraz S, Deo Rahul C, Shah Sanjiv J
Pfizer, Inc., New York, NY, USA.
Northwestern University Feinberg School of Medicine, Chicago, IL, USA.
Nat Commun. 2021 May 11;12(1):2725. doi: 10.1038/s41467-021-22876-9.
Transthyretin amyloid cardiomyopathy, an often unrecognized cause of heart failure, is now treatable with a transthyretin stabilizer. It is therefore important to identify at-risk patients who can undergo targeted testing for earlier diagnosis and treatment, prior to the development of irreversible heart failure. Here we show that a random forest machine learning model can identify potential wild-type transthyretin amyloid cardiomyopathy using medical claims data. We derive a machine learning model in 1071 cases and 1071 non-amyloid heart failure controls and validate the model in three nationally representative cohorts (9412 cases, 9412 matched controls), and a large, single-center electronic health record-based cohort (261 cases, 39393 controls). We show that the machine learning model performs well in identifying patients with cardiac amyloidosis in the derivation cohort and all four validation cohorts, thereby providing a systematic framework to increase the suspicion of transthyretin cardiac amyloidosis in patients with heart failure.
转甲状腺素蛋白淀粉样心肌病是一种常被忽视的心力衰竭病因，目前可用转甲状腺素蛋白稳定剂进行治疗。因此，在不可逆心力衰竭发生之前，识别出可接受针对性检测以实现早期诊断和治疗的高危患者非常重要。在此，我们表明随机森林机器学习模型可利用医疗理赔数据识别潜在的野生型转甲状腺素蛋白淀粉样心肌病。我们在1071例病例和1071例非淀粉样心力衰竭对照中推导了一个机器学习模型，并在三个具有全国代表性的队列（9412例病例，9412例匹配对照）以及一个基于单中心大型电子健康记录的队列（261例病例，39393例对照）中对该模型进行了验证。我们表明，该机器学习模型在推导队列和所有四个验证队列中识别心脏淀粉样变性患者方面表现良好，从而提供了一个系统性框架，以提高对心力衰竭患者转甲状腺素蛋白心脏淀粉样变性的怀疑。
