Machine-Learning Score Using Stress CMR for Death Prediction in Patients With Suspected or Known CAD,JACC: Cardiovascular Imaging

当前位置： X-MOL 学术 › JACC Cardiovasc. Imaging › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Machine-Learning Score Using Stress CMR for Death Prediction in Patients With Suspected or Known CAD
JACC: Cardiovascular Imaging ( IF 12.8 ) Pub Date : 2022-07-13 , DOI: 10.1016/j.jcmg.2022.05.007
Théo Pezel ₁ , Francesca Sanguineti ₂ , Philippe Garot ₂ , Thierry Unterseeh ₂ , Stéphane Champagne ₂ , Solenn Toupin ₃ , Stéphane Morisset ₄ , Thomas Hovasse ₂ , Alyssa Faradji ₅ , Tania Ah-Sing ₅ , Martin Nicol ₆ , Lounis Hamzi ₇ , Jean Guillaume Dillinger ₆ , Patrick Henry ₆ , Valérie Bousson ₅ , Jérôme Garot ₂

Affiliation

Cardiovascular Magnetic Resonance Laboratory, Institut Cardiovasculaire Paris Sud, Hôpital Privé Jacques Cartier, Ramsay Santé, Massy, France; Inserm UMRS 942, Service de Cardiologie, Hôpital Lariboisière, Assistance Publique-Hôpitaux de Paris, Université de Paris, Paris, France; Service de Radiologie, Hôpital Lariboisière, Assistance Publique-Hôpitaux de Paris, Université de Paris, Paris, France.
Cardiovascular Magnetic Resonance Laboratory, Institut Cardiovasculaire Paris Sud, Hôpital Privé Jacques Cartier, Ramsay Santé, Massy, France.
Scientific Partnerships, Siemens Healthcare France, Saint-Denis, France.
Independent Biostatistician, Pérouges, France.
Service de Radiologie, Hôpital Lariboisière, Assistance Publique-Hôpitaux de Paris, Université de Paris, Paris, France.
Inserm UMRS 942, Service de Cardiologie, Hôpital Lariboisière, Assistance Publique-Hôpitaux de Paris, Université de Paris, Paris, France.
Cardiovascular Magnetic Resonance Laboratory, Institut Cardiovasculaire Paris Sud, Hôpital Privé Jacques Cartier, Ramsay Santé, Massy, France; Service de Radiologie, Hôpital Lariboisière, Assistance Publique-Hôpitaux de Paris, Université de Paris, Paris, France.

Background

In patients with suspected or known coronary artery disease, traditional prognostic risk assessment is based on a limited selection of clinical and imaging findings. Machine learning (ML) methods can take into account a greater number and complexity of variables.

Objectives

This study sought to investigate the feasibility and accuracy of ML using stress cardiac magnetic resonance (CMR) and clinical data to predict 10-year all-cause mortality in patients with suspected or known coronary artery disease, and compared its performance with existing clinical or CMR scores.

Methods

Between 2008 and 2018, a retrospective cohort study with a median follow-up of 6.0 (IQR: 5.0-8.0) years included all consecutive patients referred for stress CMR. Twenty-three clinical and 11 stress CMR parameters were evaluated. ML involved automated feature selection by random survival forest, model building with a multiple fractional polynomial algorithm, and 5 repetitions of 10-fold stratified cross-validation. The primary outcome was all-cause death based on the electronic National Death Registry. The external validation cohort of the ML score was performed in another center.

Results

Of 31,752 consecutive patients (mean age: 63.7 ± 12.1 years, and 65.7% male), 2,679 (8.4%) died with 206,453 patient-years of follow-up. The ML score (ranging from 0 to 10 points) exhibited a higher area under the curve compared with Clinical and Stress Cardiac Magnetic Resonance score, European Systematic Coronary Risk Estimation score, QRISK3 score, Framingham Risk Score, and stress CMR data alone for prediction of 10-year all-cause mortality (ML score: 0.76 vs Clinical and Stress Cardiac Magnetic Resonance score: 0.68, European Systematic Coronary Risk Estimation score: 0.66, QRISK3 score: 0.64, Framingham Risk Score: 0.63, extent of inducible ischemia: 0.66, extent of late gadolinium enhancement: 0.65; all P < 0.001). The ML score also exhibited a good area under the curve in the external cohort (0.75).

Conclusions

The ML score including clinical and stress CMR data exhibited a higher prognostic value to predict 10-year death compared with all traditional clinical or CMR scores.

中文翻译：

机器学习评分使用 Stress CMR 预测疑似或已知 CAD 患者的死亡

背景

对于疑似或已知冠状动脉疾病的患者，传统的预后风险评估是基于有限的临床和影像学发现选择。机器学习 (ML) 方法可以考虑更多和更复杂的变量。

目标

本研究旨在调查 ML 使用负荷心脏磁共振 (CMR) 和临床数据预测疑似或已知冠心病患者 10 年全因死亡率的可行性和准确性，并将其性能与现有临床或 CMR 进行比较分数。

方法

2008 年至 2018 年间，一项中位随访时间为 6.0（IQR：5.0-8.0）年的回顾性队列研究纳入了所有转诊接受负荷 CMR 的连续患者。评估了 23 个临床和 11 个负荷 CMR 参数。ML 涉及随机生存林的自动特征选择、使用多重分数多项式算法的模型构建以及 5 次重复的 10 倍分层交叉验证。主要结果是基于电子国家死亡登记处的全因死亡。ML 评分的外部验证队列是在另一个中心进行的。

结果

在 31,752 名连续患者（平均年龄：63.7 ± 12.1 岁，65.7% 为男性）中，2,679 名 (8.4%) 患者在 206,453 患者年的随访中死亡。与临床和负荷心脏磁共振评分、欧洲系统冠状动脉风险评估评分、QRISK3 评分、Framingham 风险评分和负荷 CMR 数据相比，ML 评分（范围从 0 到 10 分）显示出更高的曲线下面积用于预测10 年全因死亡率（ML 评分：0.76 vs 临床和负荷心脏磁共振评分：0.68，欧洲系统冠状动脉风险评估评分：0.66，QRISK3 评分：0.64，Framingham 风险评分：0.63，诱导性缺血程度：0.66，晚期钆增强的程度：0.65；所有P < 0.001）。ML 分数在外部队列中也表现出良好的曲线下面积 (0.75)。