Deep learning on resting electrocardiogram to identify impaired heart rate recovery.
Deep learning on resting electrocardiogram to identify impaired heart rate recovery.
复制标题
DOI：
10.1016/j.cvdhj.2022.06.001
复制
发表时间：
2022-08
影响因子：
--
通讯作者：
Ho, Jennifer E.
中科院分区：
文献类型：
--
作者：
Diamant, Nathaniel;Di Achille, Paolo;Weng, Lu-Chen;Lau, Emily S.;Khurshid, Shaan;Friedman, Samuel;Reeder, Christopher;Singh, Pulkit;Wang, Xin;Sarma, Gopal;Ghadessi, Mercedeh;Mielke, Johanna;Elci, Eren;Kryukov, Ivan;Eilken, Hanna M.;Derix, Andrea;Ellinor, Patrick T.;Anderson, Christopher D.;Philippakis, Anthony A.;Batra, Puneet;Lubitz, Steven A.;Ho, Jennifer E.
运动后心率恢复(HRR)是反映心脏自主神经功能的重要指标，HRR异常与不良结局相关。我们假设，对静息心电轨迹的深入学习可能会识别出HRR受损的个体。我们训练了一个深度学习模型(卷积神经网络)，以便在接受运动测试的英国生物库参与者中，根据静息心电波形(HRRpred)来推断HRR。我们使用COX模型检验了HRRpred与心血管疾病的相关性，并在全基因组关联分析中研究了HRRpred的遗传结构。在56,793名受试者(平均年龄57岁，51%为女性)中，HRRpred模型与实际HRR呈中等相关(r=0.48，95%可信区间[CI]0.47-0.48)。在中位数10年的随访中，我们观察到2060例糖尿病(DM)事件，862例心力衰竭事件，2065例死亡。较高的HRRpred与较低的糖尿病(危险比[HR]0.79/1标准差变化，95%CI为0.76-0.83)、心力衰竭(HR为0.89，95%CI为0.83-0.95)和死亡(HR为0.83，95%CI为0.79-0.86)相关。在考虑静息心率后，HRRpred与糖尿病发病率和全因死亡率的相关性相似。HRRpred的遗传决定因素包括已知的心率、心脏传导系统、心肌病和代谢性状基因座。使用静息心电图对HRR的深度学习评估独立于未来的临床结果，包括新发糖尿病和全因死亡率。根据静息心电图推断运动后的心率反应可能具有潜在的临床意义，对预防策略的影响值得进一步研究。
Postexercise heart rate recovery (HRR) is an important indicator of cardiac autonomic function and abnormal HRR is associated with adverse outcomes. We hypothesized that deep learning on resting electrocardiogram (ECG) tracings may identify individuals with impaired HRR. We trained a deep learning model (convolutional neural network) to infer HRR based on resting ECG waveforms (HRRpred) among UK Biobank participants who had undergone exercise testing. We examined the association of HRRpred with incident cardiovascular disease using Cox models, and investigated the genetic architecture of HRRpred in genome-wide association analysis. Among 56,793 individuals (mean age 57 years, 51% women), the HRRpred model was moderately correlated with actual HRR (r = 0.48, 95% confidence interval [CI] 0.47–0.48). Over a median follow-up of 10 years, we observed 2060 incident diabetes mellitus (DM) events, 862 heart failure events, and 2065 deaths. Higher HRRpred was associated with lower risk of DM (hazard ratio [HR] 0.79 per 1 standard deviation change, 95% CI 0.76–0.83), heart failure (HR 0.89, 95% CI 0.83–0.95), and death (HR 0.83, 95% CI 0.79–0.86). After accounting for resting heart rate, the association of HRRpred with incident DM and all-cause mortality were similar. Genetic determinants of HRRpred included known heart rate, cardiac conduction system, cardiomyopathy, and metabolic trait loci. Deep learning–derived estimates of HRR using resting ECG independently associated with future clinical outcomes, including new-onset DM and all-cause mortality. Inferring postexercise heart rate response from a resting ECG may have potential clinical implications and impact on preventive strategies warrants future study.
登录
查看更多内容
影响因子：
37.8
作者：
Khurshid S;Friedman S;Reeder C;Di Achille P;Diamant N;Singh P;Harrington LX;Wang X;Al-Alusi MA;Sarma G;Foulkes AS;Ellinor PT;Anderson CD;Ho JE;Philippakis AA;Batra P;Lubitz SA
通讯作者：
Lubitz SA
影响因子：
64.8
作者：
Bycroft C;Freeman C;Petkova D;Band G;Elliott LT;Sharp K;Motyer A;Vukcevic D;Delaneau O;O'Connell J;Cortes A;Welsh S;Young A;Effingham M;McVean G;Leslie S;Allen N;Donnelly P;Marchini J
通讯作者：
Marchini J
影响因子：
30.8
作者：
Mahajan A;Taliun D;Thurner M;Robertson NR;Torres JM;Rayner NW;Payne AJ;Steinthorsdottir V;Scott RA;Grarup N;Cook JP;Schmidt EM;Wuttke M;Sarnowski C;Mägi R;Nano J;Gieger C;Trompet S;Lecoeur C;Preuss MH;Prins BP;Guo X;Bielak LF;Below JE;Bowden DW;Chambers JC;Kim YJ;Ng MCY;Petty LE;Sim X;Zhang W;Bennett AJ;Bork-Jensen J;Brummett CM;Canouil M;Ec Kardt KU;Fischer K;Kardia SLR;Kronenberg F;Läll K;Liu CT;Locke AE;Luan J;Ntalla I;Nylander V;Schönherr S;Schurmann C;Yengo L;Bottinger EP;Brandslund I;Christensen C;Dedoussis G;Florez JC;Ford I;Franco OH;Frayling TM;Giedraitis V;Hackinger S;Hattersley AT;Herder C;Ikram MA;Ingelsson M;Jørgensen ME;Jørgensen T;Kriebel J;Kuusisto J;Ligthart S;Lindgren CM;Linneberg A;Lyssenko V;Mamakou V;Meitinger T;Mohlke KL;Morris AD;Nadkarni G;Pankow JS;Peters A;Sattar N;Stančáková A;Strauch K;Taylor KD;Thorand B;Thorleifsson G;Thorsteinsdottir U;Tuomilehto J;Witte DR;Dupuis J;Peyser PA;Zeggini E;Loos RJF;Froguel P;Ingelsson E;Lind L;Groop L;Laakso M;Collins FS;Jukema JW;Palmer CNA;Grallert H;Metspalu A;Dehghan A;Köttgen A;Abecasis GR;Meigs JB;Rotter JI;Marchini J;Pedersen O;Hansen T;Langenberg C;Wareham NJ;Stefansson K;Gloyn AL;Morris AP;Boehnke M;McCarthy MI
通讯作者：
McCarthy MI
影响因子：
3
作者：
Kubrychtova, Vera;Olson, Thomas P.;Johnson, Bruce D.
通讯作者：
Johnson, Bruce D.
影响因子：
2
作者：
Pencina, MJ;D'Agostino, RB
通讯作者：
D'Agostino, RB