Prediction of diagnosis and diastolic filling pressure by AI-enhanced cardiac MRI: a modelling study of hospital data

IF 23.8 1区 医学 Q1 MEDICAL INFORMATICS Lancet Digital Health Pub Date : 2024-05-22 DOI:10.1016/S2589-7500(24)00063-3
David Hermann Lehmann MSc , Bruna Gomes MD , Niklas Vetter MD , Olivia Braun MD , Ali Amr MD , Thomas Hilbel MD , Jens Müller MSc , Prof Ulrich Köthe PhD , Christoph Reich MD , Elham Kayvanpour MD , Farbod Sedaghat-Hamedani MD , Manuela Meder MD , Jan Haas PhD , Prof Euan Ashley MD , Prof Wolfgang Rottbauer MD , Dominik Felbel MD , Raffi Bekeredjian MD , Heiko Mahrholdt MD , Prof Andreas Keller PhD , Peter Ong MD , Prof Benjamin Meder MD
{"title":"Prediction of diagnosis and diastolic filling pressure by AI-enhanced cardiac MRI: a modelling study of hospital data","authors":"David Hermann Lehmann MSc ,&nbsp;Bruna Gomes MD ,&nbsp;Niklas Vetter MD ,&nbsp;Olivia Braun MD ,&nbsp;Ali Amr MD ,&nbsp;Thomas Hilbel MD ,&nbsp;Jens Müller MSc ,&nbsp;Prof Ulrich Köthe PhD ,&nbsp;Christoph Reich MD ,&nbsp;Elham Kayvanpour MD ,&nbsp;Farbod Sedaghat-Hamedani MD ,&nbsp;Manuela Meder MD ,&nbsp;Jan Haas PhD ,&nbsp;Prof Euan Ashley MD ,&nbsp;Prof Wolfgang Rottbauer MD ,&nbsp;Dominik Felbel MD ,&nbsp;Raffi Bekeredjian MD ,&nbsp;Heiko Mahrholdt MD ,&nbsp;Prof Andreas Keller PhD ,&nbsp;Peter Ong MD ,&nbsp;Prof Benjamin Meder MD","doi":"10.1016/S2589-7500(24)00063-3","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><p>With increasing numbers of patients and novel drugs for distinct causes of systolic and diastolic heart failure, automated assessment of cardiac function is important. We aimed to provide a non-invasive method to predict diagnosis of patients undergoing cardiac MRI (cMRI) and to obtain left ventricular end-diastolic pressure (LVEDP).</p></div><div><h3>Methods</h3><p>For this modelling study, patients who had undergone cardiac catheterisation at University Hospital Heidelberg (Heidelberg, Germany) between July 15, 2004 and March 16, 2023, were identified, as were individual left ventricular pressure measurements. We used existing patient data from routine cardiac diagnostics. From this initial group, we extracted patients who had been diagnosed with ischaemic cardiomyopathy, dilated cardiomyopathy, hypertrophic cardiomyopathy, or amyloidosis, as well as control individuals with no structural phenotype. Data were pseudonymised and only processed within the university hospital's AI infrastructure. We used the data to build different models to predict either demographic (ie, AI-age and AI-sex), diagnostic (ie, AI-coronary artery disease and AI-cardiomyopathy [AI-CMP]), or functional parameters (ie, AI-LVEDP). We randomly divided our datasets via computer into training, validation, and test datasets. AI-CMP was not compared with other models, but was validated in a prospective setting. Benchmarking was also done.</p></div><div><h3>Findings</h3><p>66 936 patients who had undergone cardiac catheterisation at University Hospital Heidelberg were identified, with more than 183 772 individual left ventricular pressure measurements. We extracted 4390 patients from this initial group, of whom 1131 (25·8%) had been diagnosed with ischaemic cardiomyopathy, 1064 (24·2%) had been diagnosed with dilated cardiomyopathy, 816 (18·6%) had been diagnosed with hypertrophic cardiomyopathy, 202 (4·6%) had been diagnosed with amyloidosis, and 1177 (26·7%) were control individuals with no structural phenotype. The core cohort only included patients with cardiac catherisation and cMRI within 30 days, and emergency cases were excluded. AI-sex was able to predict patient sex with areas under the receiver operating characteristic curves (AUCs) of 0·78 (95% CI 0·77–0·78) and AI-age was able to predict patient age with a mean absolute error of 7·86 years (7·77–7·95), with a Pearson correlation of 0·57 (95% CI 0·56–0·57). The AUCs for the classification tasks ranged between 0·82 (95% CI 0·79–0·84) for ischaemic cardiomyopathy and 0·92 (0·91–0·94) for hypertrophic cardiomyopathy.</p></div><div><h3>Interpretation</h3><p>Our AI models could be easily integrated into clinical practice and provide added value to the information content of cMRI, allowing for disease classification and prediction of diastolic function.</p></div><div><h3>Funding</h3><p>Informatics for Life initiative of the Klaus-Tschira Foundation, German Center for Cardiovascular Research, eCardiology section of the German Cardiac Society, and AI Health Innovation Cluster Heidelberg.</p></div>","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":null,"pages":null},"PeriodicalIF":23.8000,"publicationDate":"2024-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024000633/pdfft?md5=aacaa15001510ec9d45a77812b597e06&pid=1-s2.0-S2589750024000633-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Lancet Digital Health","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2589750024000633","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MEDICAL INFORMATICS","Score":null,"Total":0}
引用次数: 0

Abstract

Background

With increasing numbers of patients and novel drugs for distinct causes of systolic and diastolic heart failure, automated assessment of cardiac function is important. We aimed to provide a non-invasive method to predict diagnosis of patients undergoing cardiac MRI (cMRI) and to obtain left ventricular end-diastolic pressure (LVEDP).

Methods

For this modelling study, patients who had undergone cardiac catheterisation at University Hospital Heidelberg (Heidelberg, Germany) between July 15, 2004 and March 16, 2023, were identified, as were individual left ventricular pressure measurements. We used existing patient data from routine cardiac diagnostics. From this initial group, we extracted patients who had been diagnosed with ischaemic cardiomyopathy, dilated cardiomyopathy, hypertrophic cardiomyopathy, or amyloidosis, as well as control individuals with no structural phenotype. Data were pseudonymised and only processed within the university hospital's AI infrastructure. We used the data to build different models to predict either demographic (ie, AI-age and AI-sex), diagnostic (ie, AI-coronary artery disease and AI-cardiomyopathy [AI-CMP]), or functional parameters (ie, AI-LVEDP). We randomly divided our datasets via computer into training, validation, and test datasets. AI-CMP was not compared with other models, but was validated in a prospective setting. Benchmarking was also done.

Findings

66 936 patients who had undergone cardiac catheterisation at University Hospital Heidelberg were identified, with more than 183 772 individual left ventricular pressure measurements. We extracted 4390 patients from this initial group, of whom 1131 (25·8%) had been diagnosed with ischaemic cardiomyopathy, 1064 (24·2%) had been diagnosed with dilated cardiomyopathy, 816 (18·6%) had been diagnosed with hypertrophic cardiomyopathy, 202 (4·6%) had been diagnosed with amyloidosis, and 1177 (26·7%) were control individuals with no structural phenotype. The core cohort only included patients with cardiac catherisation and cMRI within 30 days, and emergency cases were excluded. AI-sex was able to predict patient sex with areas under the receiver operating characteristic curves (AUCs) of 0·78 (95% CI 0·77–0·78) and AI-age was able to predict patient age with a mean absolute error of 7·86 years (7·77–7·95), with a Pearson correlation of 0·57 (95% CI 0·56–0·57). The AUCs for the classification tasks ranged between 0·82 (95% CI 0·79–0·84) for ischaemic cardiomyopathy and 0·92 (0·91–0·94) for hypertrophic cardiomyopathy.

Interpretation

Our AI models could be easily integrated into clinical practice and provide added value to the information content of cMRI, allowing for disease classification and prediction of diastolic function.

Funding

Informatics for Life initiative of the Klaus-Tschira Foundation, German Center for Cardiovascular Research, eCardiology section of the German Cardiac Society, and AI Health Innovation Cluster Heidelberg.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
通过人工智能增强心脏磁共振成像预测诊断结果和舒张期充盈压:医院数据建模研究
背景随着收缩性和舒张性心力衰竭患者人数的增加以及治疗不同病因的新型药物的出现,对心脏功能进行自动评估非常重要。我们的目标是提供一种无创方法来预测接受心脏核磁共振成像(cMRI)的患者的诊断结果,并获得左心室舒张末期压力(LVEDP)。在这项建模研究中,我们确定了 2004 年 7 月 15 日至 2023 年 3 月 16 日期间在海德堡大学医院(德国海德堡)接受过心导管检查的患者,以及单个左心室压力测量值。我们使用了常规心脏诊断中现有的患者数据。从这一初始组中,我们抽取了被诊断为缺血性心肌病、扩张型心肌病、肥厚型心肌病或淀粉样变性的患者,以及无结构表型的对照组患者。数据经过化名处理,仅在大学医院的人工智能基础设施内进行处理。我们利用这些数据建立了不同的模型来预测人口统计学参数(即人工智能-年龄和人工智能-性别)、诊断参数(即人工智能-冠状动脉疾病和人工智能-心肌病 [AI-CMP])或功能参数(即人工智能-LVEDP)。我们通过计算机将数据集随机分为训练数据集、验证数据集和测试数据集。AI-CMP 未与其他模型进行比较,但在前瞻性设置中进行了验证。研究结果66 936 名患者在海德堡大学医院接受了心导管检查,共测量了 183 772 个左心室压力。我们从这一初始群体中提取了 4390 名患者,其中 1131 人(25-8%)被诊断为缺血性心肌病,1064 人(24-2%)被诊断为扩张型心肌病,816 人(18-6%)被诊断为肥厚型心肌病,202 人(4-6%)被诊断为淀粉样变性,1177 人(26-7%)为无结构表型的对照组。核心队列只包括30天内进行过心脏采集和cMRI检查的患者,急诊病例不包括在内。人工智能性别能够预测患者性别,接收者操作特征曲线下面积(AUC)为 0-78(95% CI 0-77-0-78),人工智能年龄能够预测患者年龄,平均绝对误差为 7-86 岁(7-77-7-95),皮尔逊相关性为 0-57(95% CI 0-56-0-57)。缺血性心肌病分类任务的AUC值为0-82(95% CI 0-79-0-84),肥厚型心肌病的AUC值为0-92(0-91-0-94)。释义我们的人工智能模型可以很容易地集成到临床实践中,并为cMRI的信息内容提供附加值,使疾病分类和舒张功能预测成为可能。资助克劳斯-特奇拉基金会生命信息学计划、德国心血管研究中心、德国心脏病学会电子心脏病学分会和海德堡人工智能健康创新集群。
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 去求助
来源期刊
CiteScore
41.20
自引率
1.60%
发文量
232
审稿时长
13 weeks
期刊介绍: The Lancet Digital Health publishes important, innovative, and practice-changing research on any topic connected with digital technology in clinical medicine, public health, and global health. The journal’s open access content crosses subject boundaries, building bridges between health professionals and researchers.By bringing together the most important advances in this multidisciplinary field,The Lancet Digital Health is the most prominent publishing venue in digital health. We publish a range of content types including Articles,Review, Comment, and Correspondence, contributing to promoting digital technologies in health practice worldwide.
期刊最新文献
Artificial intelligence-enabled electrocardiogram for mortality and cardiovascular risk estimation: a model development and validation study COVID-19 testing and reporting behaviours in England across different sociodemographic groups: a population-based study using testing data and data from community prevalence surveillance surveys Fairly evaluating the performance of normative models – Authors' reply Fairly evaluating the performance of normative models Lifting the veil on health datasets
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1