王可欣,陈明龙

• 1:南京医科大学第一附属医院心血管内科

摘要(Abstract)：

心房颤动（房颤）是临床上最常见的心律失常，目前全球患病人数已超过3700万人。由于房颤会影响患者心功能、认知功能、生活质量，增加脑卒中风险及心血管死亡率，因此，早期预测对降低房颤相关并发症的发生风险、早期干预、改善患者预后至关重要。随着人工智能（AI）技术的迅猛发展，其在医学领域尤其是在心脏病学中的应用也受到广泛关注。近年来，多项研究通过利用各类AI工具分析大量的医疗数据（包括临床信息、影像学参数等），希望可以实现对房颤发生、发展及并发症相关的预测，从而为临床决策和诊治提供依据。然而，尽管取得了一定进展，当前的研究仍面临数据隐私、模型的可解释性、采用参数的准确合理性、参数选择的临床可操作性和可实现性等多方面的挑战。因此，本文旨在回顾AI在房颤预测中的最新研究成果，分析其应用现状，并探讨未来发展方向，以期为相关领域的进一步研究提供参考和启示。

关键词(KeyWords)： 心房颤动;人工智能;预测;心律失常;临床应用

Abstract:

Keywords:

基金项目(Foundation): 四大慢病国家科技部重大专项项目（2024ZD0538800）

作者(Author): 王可欣,陈明龙

参考文献(References)：

• [1] Linz D,Gawalko M,Betz K,et al.Atrial fibrillation:epidemiology,screening and digital health[J].Lancet Reg Health Eur,2024,37:100786.DOI:10.1016/j.lanepe.2023.100786.
• [2]Sanna T,Diener HC,Passman RS,et al.Cryptogenic stroke and underlying atrial fibrillation[J].N Engl J Med,2014,370(26):2478-2486.DOI:10.1056/NEJMoa1313600.
• [3]Pipilas D,Friedman SF,Khurshid S.The use of artificial intelligence to predict the development of atrial fibrillation[J].Curr Cardiol Rep,2023,25(5):381-389.DOI:10.1007/s11886-023-01859-w.
• [4]Alonso A,Krijthe BP,Aspelund T,et al.Simple risk model predicts incidence of atrial fibrillation in a racially and geographically diverse population:the CHARGE-AF consortium[J].J Am Heart Assoc,2013,2(2):e000102.DOI:10.1161/jaha.112.000102.
• [5]Lin JY,Larson J,Schoenberg J,et al.Serial 7-day electrocardiogram patch screening for AF in high-risk older women by the CHARGE-AF score[J].JACC Clin Electrophysiol,2022,8(12):1523-1534.DOI:10.1016/j.jacep.2022.08.024.
• [6]陈韵岱.聚焦高水平人工智能研究,优化心血管介入精准施治[J].中国介入心脏病学杂志,2024,32(1):1-4.DOI:10.3969/j.issn.1004-8812.2024.01.001.
• [7]Christopoulos G,Graff-Radford J,Lopez CL,et al.Artificial intelligence-electrocardiography to predict incident atrialfibrillation:a population-based study[J].Circ Arrhythm Electrophysiol,2020,13(12):e009355.DOI:10.1161/CIRCEP.120.009355.
• [8] Khurshid S,Friedman S,Reeder C,et al.ECG-based de ep learning and clinical risk factors to predict atrial fibrillation[J].Circulation,2022,145(2):122-133.DOI:10.1161/circulationaha.121.057480.
• [9]聂陆经,王玉洁,冯文玖,等.人工智能预测心房颤动导管消融术后复发的研究进展[J].中国心血管病研究,2025,23(1):86-90.DOI:10.3969/j.issn.1672-5301.2025.01.015.
• [10]Miotto R,Wang F,Wang S,et al.Deep learning for healthcare:review,opportunities and challenges[J].Brief Bioinform,2018,19(6):1236-1246.DOI:10.1093/bib/bbx044.
• [11] Isaksen JL,Baumert M,Hermans ANL,et al.Artificial intelligence for the detection,prediction,and management of atrial fibrillation[J].Herzschrittmacherther Elektrophysiol,2022,33(1):34-41.DOI:10.1007/s00399-022-00839-x.
• [12]Tao Y,Zhang D,Tan C,et al.An artificial intelligence-enabled electrocardiogram algorithm for the prediction of left atrial lowvoltage areas in persistent atrial fibrillation[J].J Cardiovasc Electrophysiol,2024,35(9):1849-1858.DOI:10.1111/jce.16373.
• [13] Kany S,R?m?JT,Friedman SF,et al.Integrating clinical,genetic,and electrocardiogram-based artificial intelligence to estimate risk of incident atrial fibrillation[J].medRxiv,2024.DOI:10.1101/2024.08.13.24311944.
• [14]Attia ZI,Noseworthy PA,Lopez-Jimenez F,et al.An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm:a retrospective analysis of outcome prediction[J].Lancet,2019,394(10201):861-867.DOI:10.1016/s0140-6736(19)31721-0.
• [15] Mannhart D,Lischer M,Knecht S,et al.Clinical validation of 5 direct-to-consumer wearable smart devices to detect atrial fibrillation:BASEL wearable study[J].JACC Clin Electrophysiol,2023,9(2):232-242.DOI:10.1016/j.jacep.2022.09.011.
• [16]Kwon S,Hong J,Choi EK,et al.Detection of atrial fibrillation using a ring-type wearable device(CardioTracker)and deep learning analysis of photoplethysmography signals:prospective observational proof-of-concept study[J].J Med Internet Res,2020,22(5):e16443.DOI:10.2196/16443.
• [17]Cremer A,LainéM,Papaioannou G,et al.Increased arterial stiffness is an independent predictor of atrial fibrillation in hypertensive patients[J].J Hypertens,2015,33(10):2150-2155.DOI:10.1097/hj h.0000000000000652.
• [18]Benjamin EJ,Levy D,Vaziri SM,et al.Independent risk factors for atrial fibrillation in a population-based cohort.The Framingham Heart Study[J].JAMA,1994,271(11):840-844.
• [19]Papadopoulou A,Harding D,Slabaugh G,et al.Prediction of atrial fibrillation and stroke using machine learning models in UK Biobank[J].Heliyon,2024,10(7):e28034.DOI:10.1016/j.heliyon.2024.e28034.
• [20] Venkat V,Abdelhalim H,Degroat W,et al.Investigating genes associated with heart failure,atrial fibrillation,and other cardiovascular diseases,and predicting disease using machine learning techniques for translational research and precision medicine[J].Genomics,2023,115(2):110584.DOI:10.1016/j.ygeno.2023.1105 84.
• [21]Bisson A,Lemrini Y,Romiti GF,et al.Prediction of earlydeath after atrial fibrillation diagnosis using a machine learning approach:a French nationwide cohort study[J].Am Heart J,2023,265:191-202.DOI:10.1016/j.ahj.2023.08.006.
• [22] Sekelj S,Sandler B,Johnston E,et al.Detecting undiagnosed atrial fibrillation in UK primary care:validation of a machine learning prediction algorithm in a retrospective cohort study[J].Eur J Prev Cardiol,2021,28(6):598-605.DOI:10.1177/2047487320942338.
• [23]Lu Y,Chen Q,Zhang H,et al.Machine learning models of postoperative atrial fibrillation prediction after cardiac surgery[J].J Cardiothorac Vasc Anesth,2023,37(3):360-366.DOI:10.105 3/j.jvca.2022.11.025.
• [24]Laghari AA,Sun Y,Alhussein M,et al.Deep residual-dense network based on bidirectional recurrent neural network for atrial fibrillation detection[J].Sci Rep,2023,13(1):15109.DOI:10.103 8/s41598-023-40343-x.
• [25] Zhang X,Jiang M,Polat K,et al.Detection of atrial fibrillation from variable-duration ECG signal based on time-adaptive densely network and feature enhancement strategy[J].IEEE J Biomed Health Inform,2023,27(2):944-955.DOI:10.1109/jbhi,2022.3221464.
• [26]Wu H,Sawada T,Goto T,et al.Edge AI model deploy ed for real-time detection of atrial fibrillation risk during sinus rhythm[J].J Clin Med,2024,13(8):2218.DOI:10.3390/jcm13082218.
• [27]Yang Z,Jin A,Li Y,et al.A coordinated adaptive multiscale enhanced spatio-temporal fusion network for multi-lead electrocardiogram arrhythmia detection[J].Sci Rep,2024,14(1):20828.DOI:10.1038/s41598-024-71700-z.
• [28] Rahman MM,Rivolta MW,Vaglio M,et al.Residual-attention deep learning model for atrial fibrillation detection from Holter recordings[J].J Electrocardiol,2025,89:153876.DOI:10.1016/j.jelectrocard.2025.153 876.
• [29] Tiwari P,Colborn KL,Smith DE,et al.Assessment of a machine learning model applied to harmonized electronic health record data for the prediction of incident atrial fibrillation[J].JAMA Netw Open,2020,3(1):e1919396.DOI:10.1001/j amanetworkopen.2019.193 96.
• [30]Kaminski AE,Albus ML,Ball CT,et al.Evaluating atrial fibrillation artificial intelligence for the ED:statistical and clinical implications[J].Am J Emerg Med,2022,57:98-102.DOI:10.1016/j.ajem.2022.04.032.
• [31] Gruwez H,Barthels M,Haemers P,et al.Detecting paroxysmal atrial fibrillation from an electrocardiogram in sinus rhythm:external validation of the AI approach[J].JACC Clin Electrophysiol,2023,9(8 Pt 3):1771-1782.DOI:10.1016/j.jacep.2023.04.008.
• [32]Fiedler L,Roca I,Lorgat F,et al.Characterization of high-density mapping in catheter ablation for persistent atrial fibrillation:results from the Advisor~(TM)HD Grid Mapping Catheter Observational study[J].J Interv Card Electrophysiol,2023,66(6):1411-1421.DOI:10.1007/s10840-022-01442-3.
• [33]Pilichowska-Paszkiet E,Baran J,Sygitowicz G,et al.Noninvasive assessment of left atrial fibrosis.Correlation between echocardiography,biomarkers,and electroanatomical mapping[J].Echocardiography,2018,35(9):1326-1334.DOI:10.1111/echo.14043.
• [34] Chang S,Zhang X,Ge C,et al.Automatic echocardiographic assessment of left atrial function for prediction of low-voltageareas in non-valvular atrial fibrillation[J].Int J Gen Med,2024,17:4493-4506.DOI:10.2147/ijgm.S477499.
• [35]Korsholm K,Berti S,Iriart X,et al.Expert recommendations on cardiac computed tomography for planning transcatheter left atrial appendage occlusion[J].JACC Cardiovasc Interv,2020,13(3):277-292.DOI:10.1016/j.jcin.2019.08.054.
• [36] Kumar S,Suppah M,Niazi O,et al.Left atrial appendage occlusion optimized with artificial intelligence-guided CT preplanning and intra-procedural intracardiac echocardiographic guidance[J].Cardiovasc Revasc Med,2025.DOI:10.1016/j.carrev.2025.03.021.
• [37]Suzuki S,Motogi J,Nakai H,et al.Identifying patients with atrial fibrillation during sinus rhythm on ECG:significance of the labeling in the artificial intelligence algorithm[J].Int J Cardiol Heart Vasc,2022,38:100954.DOI:10.1016/j.ijcha.2022.100954.
• [38] Zhang Y,Xu S,Xing W,et al.Robust artificial intelligence tool for atrial fibrillation diagnosis:novel development approach incorporating both atrial electrograms and surface ECG and evaluation by head-to-head comparison with hospital-based physician ECG readers[J].J Am Heart Assoc,2024,13(3):e032100.DOI:10.1161/jaha.123.032100.
• [39] Ru X,Zhu L,Ma Y,et al.Effect of an artificial intelligenceassisted tool on non-valvular atrial fibrillation anticoagulation management in primary care:protocol for a cluster randomized controlled trial[J].Trials,2022,23(1):316.DOI:10.1186/s13063-022-06250-8.
• [40]Laranjo L,Shaw T,Trivedi R,et al.Coordinating health care with artificial intelligence-supported technology for patients with atrial fibrillation:protocol for a randomized controlled trial[J].JMIR Res Protoc,2022,11(4):e34470.DOI:10.2196/34470.
• [41]Barrett CD,Suzuki Y,Hussein S,et al.Evaluation of quantitative decision-making for rhythm management of atrial fibrillation using tabular Q-learning[J].J Am Heart Assoc,2023,12(9):e028483.DOI:10.1161/jaha.122.028483.
• [42]Chiruvella V,Guddati AK.Ethical issues in patient data ownership[J].Interact J Med Res,2021,10(2):e22269.DOI:10.2196/22269.
• [43] Radanliev P,Santos O,Brandon-Jones A,et al.Ethics and responsible AI deployment[J].Front Artif Intell,2024,7:1377011.DOI:10.3389/frai.2024.1377011.
• [44]Mao L,Xu Z.Differential privacy preservation for continuous release of real-time location data[J].Entropy(Basel),2024,26(2):138.DOI:10.3390/e26020138.
• [45]Munjal K,Bhatia R.A systematic review of homomorphic encryption and its contributions in healthcare industry[J].Complex Intell Systems,2022:1-28.DOI:10.1007/s40747-022-00756-z.
• [46] Jiang B,Guo N,Ge Y,et al.Development and application of artificial intelligence in cardiac imaging[J].Br J Radiol,2020,93(1113):20190812.DOI:10.1259/bjr.20190812.
• [47] Sánchez De La Nava AM,Atienza F,Bermejo J,et al.Artificial intelligence for a personalized diagnosis and treatment of atrial fibrillation[J].Am J Physiol Heart Circ Physiol,2021,320(4):H1337-H1347.DOI:10.1152/ajpheart.00764.2020.