Prediction of new‐onset atrial fibrillation in patients with hypertrophic cardiomyopathy using machine learning

IF 16.9 1区 医学 Q1 CARDIAC & CARDIOVASCULAR SYSTEMS
Ree Lu, Heidi S. Lumish, Kohei Hasegawa, Mathew S. Maurer, Muredach P. Reilly, Shepard D. Weiner, Albree Tower‐Rader, Michael A. Fifer, Yuichi J. Shimada
{"title":"Prediction of new‐onset atrial fibrillation in patients with hypertrophic cardiomyopathy using machine learning","authors":"Ree Lu, Heidi S. Lumish, Kohei Hasegawa, Mathew S. Maurer, Muredach P. Reilly, Shepard D. Weiner, Albree Tower‐Rader, Michael A. Fifer, Yuichi J. Shimada","doi":"10.1002/ejhf.3546","DOIUrl":null,"url":null,"abstract":"AimsAtrial fibrillation (AF) is the most common sustained arrhythmia among patients with hypertrophic cardiomyopathy (HCM), leading to increased symptom burden and risk of thromboembolism. The HCM‐AF score was developed to predict new‐onset AF in patients with HCM, though sensitivity and specificity of this conventional tool are limited. Thus, there is a need for more accurate tools to predict new‐onset AF in HCM. The objective of the present study was to develop a better model to predict new‐onset AF in patients with HCM using machine learning (ML).Methods and resultsIn this prospective, multicentre cohort study, we enrolled 1069 patients with HCM without a prior history of AF. We built a ML model (logistic regression with Lasso regularization) using clinical variables. We developed the ML model using the cohort from one institution (training set) and applied it to an independent cohort from a separate institution (test set). We used the HCM‐AF score as a reference model. We compared the area under the receiver‐operating characteristic curve (AUC) between the ML model and the reference model using the DeLong's test. Median follow‐up time was 2.1 years, with 128 (12%) patients developing new‐onset AF. Using the ML model developed in the training set to predict new‐onset AF, the AUC in the test set was 0.84 (95% confidence interval [CI] 0.77–0.91). The ML model outperformed the reference model (AUC 0.64; 95% CI 0.54–0.73; DeLong's <jats:italic>p</jats:italic> &lt; 0.001). The ML model had higher sensitivity (0.82; 95% CI 0.65–0.93) than that of the reference model (0.67; 95% CI 0.52–0.88). The ML model also had higher specificity (0.76; 95% CI 0.71–0.81) than that of the reference model (0.57; 95% CI 0.41–0.70). Among the most important clinical variables included in the ML‐based model were left atrial volume and diameter, left ventricular outflow tract gradient with exercise stress and at rest, late gadolinium enhancement on cardiac magnetic resonance imaging, peak heart rate during exercise stress, age at diagnosis, positive genotype, diabetes mellitus, and end‐stage renal disease.ConclusionOur ML model showed superior performance compared to the conventional HCM‐AF score for the prediction of new‐onset AF in patients with HCM.","PeriodicalId":164,"journal":{"name":"European Journal of Heart Failure","volume":"41 1","pages":""},"PeriodicalIF":16.9000,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Journal of Heart Failure","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1002/ejhf.3546","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}
引用次数: 0

Abstract

AimsAtrial fibrillation (AF) is the most common sustained arrhythmia among patients with hypertrophic cardiomyopathy (HCM), leading to increased symptom burden and risk of thromboembolism. The HCM‐AF score was developed to predict new‐onset AF in patients with HCM, though sensitivity and specificity of this conventional tool are limited. Thus, there is a need for more accurate tools to predict new‐onset AF in HCM. The objective of the present study was to develop a better model to predict new‐onset AF in patients with HCM using machine learning (ML).Methods and resultsIn this prospective, multicentre cohort study, we enrolled 1069 patients with HCM without a prior history of AF. We built a ML model (logistic regression with Lasso regularization) using clinical variables. We developed the ML model using the cohort from one institution (training set) and applied it to an independent cohort from a separate institution (test set). We used the HCM‐AF score as a reference model. We compared the area under the receiver‐operating characteristic curve (AUC) between the ML model and the reference model using the DeLong's test. Median follow‐up time was 2.1 years, with 128 (12%) patients developing new‐onset AF. Using the ML model developed in the training set to predict new‐onset AF, the AUC in the test set was 0.84 (95% confidence interval [CI] 0.77–0.91). The ML model outperformed the reference model (AUC 0.64; 95% CI 0.54–0.73; DeLong's p < 0.001). The ML model had higher sensitivity (0.82; 95% CI 0.65–0.93) than that of the reference model (0.67; 95% CI 0.52–0.88). The ML model also had higher specificity (0.76; 95% CI 0.71–0.81) than that of the reference model (0.57; 95% CI 0.41–0.70). Among the most important clinical variables included in the ML‐based model were left atrial volume and diameter, left ventricular outflow tract gradient with exercise stress and at rest, late gadolinium enhancement on cardiac magnetic resonance imaging, peak heart rate during exercise stress, age at diagnosis, positive genotype, diabetes mellitus, and end‐stage renal disease.ConclusionOur ML model showed superior performance compared to the conventional HCM‐AF score for the prediction of new‐onset AF in patients with HCM.
利用机器学习预测肥厚性心肌病患者新发心房颤动
目的房颤(AF)是肥厚性心肌病(HCM)患者中最常见的持续性心律失常,导致症状负担增加和血栓栓塞的风险。HCM - AF评分用于预测HCM患者的新发房颤,尽管这种传统工具的敏感性和特异性有限。因此,需要更准确的工具来预测HCM患者新发房颤。本研究的目的是利用机器学习(ML)建立一个更好的模型来预测HCM患者新发房颤。方法和结果在这项前瞻性、多中心队列研究中,我们招募了1069例无房颤病史的HCM患者。我们使用临床变量建立了ML模型(Lasso正则化logistic回归)。我们使用来自一个机构(训练集)的队列开发ML模型,并将其应用于来自一个单独机构(测试集)的独立队列。我们使用HCM - AF评分作为参考模型。我们使用DeLong’s检验比较了ML模型和参考模型的受试者工作特征曲线下面积(AUC)。中位随访时间为2.1年,128例(12%)患者发展为新发AF。使用训练集中开发的ML模型来预测新发AF,测试集中的AUC为0.84(95%可信区间[CI] 0.77-0.91)。ML模型优于参考模型(AUC 0.64;95% ci 0.54-0.73;德隆的p <;0.001)。ML模型灵敏度较高(0.82;95% CI 0.65-0.93)比参考模型(0.67;95% ci 0.52-0.88)。ML模型也具有更高的特异性(0.76;95% CI 0.71-0.81)比参考模型(0.57;95% ci 0.41-0.70)。在以ML为基础的模型中,最重要的临床变量包括左心房容积和直径、运动应激和静止时的左心室流出道梯度、心脏磁共振成像晚期钆增强、运动应激时的心率峰值、诊断年龄、阳性基因型、糖尿病和终末期肾病。结论与传统的HCM - AF评分相比,我们的ML模型在预测HCM患者新发房颤方面表现优于HCM - AF评分。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
European Journal of Heart Failure
European Journal of Heart Failure 医学-心血管系统
CiteScore
27.30
自引率
11.50%
发文量
365
审稿时长
1 months
期刊介绍: European Journal of Heart Failure is an international journal dedicated to advancing knowledge in the field of heart failure management. The journal publishes reviews and editorials aimed at improving understanding, prevention, investigation, and treatment of heart failure. It covers various disciplines such as molecular and cellular biology, pathology, physiology, electrophysiology, pharmacology, clinical sciences, social sciences, and population sciences. The journal welcomes submissions of manuscripts on basic, clinical, and population sciences, as well as original contributions on nursing, care of the elderly, primary care, health economics, and other related specialist fields. It is published monthly and has a readership that includes cardiologists, emergency room physicians, intensivists, internists, general physicians, cardiac nurses, diabetologists, epidemiologists, basic scientists focusing on cardiovascular research, and those working in rehabilitation. The journal is abstracted and indexed in various databases such as Academic Search, Embase, MEDLINE/PubMed, and Science Citation Index.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信