赵鹏,刘进军

• 1:蚌埠医科大学第一附属医院心血管内科

摘要(Abstract)：

主动脉瓣狭窄具有高发病率、高致残率以及高死亡率的特征，其诊断评估、风险分层及治疗决策过程复杂，传统方法在客观性和个体化方面仍存在一定局限。随着人工智能技术的发展，机器学习逐渐应用于主动脉瓣狭窄的诊疗研究，并显示出良好的应用前景。本文围绕机器学习在主动脉瓣狭窄诊疗中的研究进展进行综述，重点总结其在影像学自动分析、疾病分级与进展预测、临床风险评估以及治疗策略选择和经导管主动脉瓣置换术相关决策支持等方面的应用现状。现有研究表明，机器学习模型在提高影像评估效率、增强风险预测能力和支持精准决策方面具有一定优势。因此，机器学习有望贯穿主动脉瓣狭窄诊疗的全流程，成为传统临床评估的重要补充。然而，其临床转化仍面临数据标准化不足、模型可解释性有限及外部验证证据欠缺等挑战。未来需通过多中心数据整合和方法学优化，推动机器学习在主动脉瓣狭窄诊疗中的规范化应用。

关键词(KeyWords)： 主动脉瓣狭窄;机器学习;临床应用

Abstract:

Keywords:

基金项目(Foundation): 2024年安徽省临床医学研究转化专项项目（202427b10020089）;; 2024年合肥综合性国家科学中心大健康研究院区域性疾病联合研究中心项目（2024bydjk001）;; 2024年度安徽省卫生健康科研项目（AHWJ2024Aa10053）;; 国家科技信息资源综合利用与公共服务中心（STI）数字医疗实验室开放基金（2025STI135）

作者(Author): 赵鹏,刘进军

参考文献(References)：

• [1]Carabello BA,Paulus WJ.Aortic stenosis[J].Lancet,2009,373(9667):956-966.DOI:10.1016/s0140-6736(0 9)60211-7.
• [2]Généreux P,Sharma RP,Cubeddu RJ,et al.The mortality burden of untreated aortic stenosis[J].J Am Coll Cardiol,2023,82(22):2101-2109.DOI:10.1016/j.j acc.2023.09.796.
• [3]Ajmone Marsan N,Delgado V,Shah DJ,et al.Valvular heart disease:shifting the focus to the myocardium[J].Eur Heart J,2023,44(1):28-40.DOI:10.109 3/eurheartj/ehac504
• [4]Van Mieghem NM,Deeb GM,S??ndergaard L,et al.Self-expanding transcatheter vs.surgical aortic valve replacement in intermediaterisk patients:5-year outcomes of the SURTAVI randomized clinical trial[J]. JAMA Cardiol,2022,7(10):1000-1008.DOI:10.1001/jamacardio.2022.2695.
• [5]Généreux P,Schwartz A,Oldemeyer JB,et al.Transcatheter aorticvalve replacement for asymptomatic severe aortic steno sis[J].N Engl J Med,2025,3 92(3):217-227.DOI:10.1056/NEJMoa2405 880.
• [6]郑琰莉,苏文星,宋元涛.机器学习在心血管疾病中应用的研究进展[J].中西医结合心脑血管病杂志,2024,22(10):1813-1817.DOI:10.12102/j.issn.1672-1349.2024.10.015.
• [7]Baman JR,Sekhon S,Flaherty JD.What Is Aortic Stenosis?[J].JAMA,2022,327(10):1003.DOI:10.1001/jama.2022.03 32.
• [8]Faggiano P,Frattini S,Zilioli V,et al.Prevalence of comorbidities and associated cardiac diseases in patients with valve aortic stenosis.Potential implications for the decision-making process[J].Int J Cardiol,2012,15 9(2):94-99.DOI:10.1016/j.ijcard.2011.02.026.
• [9] Yang C,Ojha BD,Aranoff ND,et al.Classification of aortic stenosis using conventional machine learning and deep learning methods based on multi-dimensional cardio-mechanical signals[J].Sci Rep,2020,10(1):17521.DOI:10.1038/s41598-020-74519-6.
• [10]Baumgartner H Chair,Hung J Co-Chair,Bermejo J,et al.Recommendations on the echocardiographic assessment of aortic valve stenosis:a focused update from the European Association of Cardiovascular Imaging and the American Society of Echocardiography[J].Eur Heart J Cardiovasc Imaging,2017,18(3):254-275.DOI:10.1093/ehjci/jew335.
• [11]Kovács A,Tokodi M.Refining echocardiographic surveillance of aortic stenosis using machine learning:toward personalized and sustainable follow-up schemes[J].JACC Cardiovasc Imaging,2023,16(6):745-748.DOI:10.1016/j.jcmg.2023.01.019.
• [12] Wessler BS,Huang Z,Long GM Jr,et al.Automated detection of aortic steno sis using machine learning[J].J Am Soc Echocardiogr,2023,36(4):411-420.DOI:10.1016/j.echo.2023.01.006.
• [13]Boulif J,Gerber B,Slimani A,et al.Assessment of ao rtic valve calcium load by multidetector computed tomography.Anatomical validation,impact of scanner settings and incremental diagnostic value[J].J Cardiovasc Comput Tomogr,2017,11(5):360-366.DOI:10.1016/j.jcct.2017.07.004.
• [14]Boulif J,Slimani A,Lazam S,et al.Diagnostic and prognostic accuracy of aortic valve calcium scoring in patients with moderateto-severe aortic stenosis[J].Front Cardiovasc Med,2021,8:673 5 19.DOI:10.3 389/fcvm.2021.673519.
• [15]Kang NG,Suh YJ,Han K,et al.Performance of prediction models for diagno sing severe aortic stenosis based on aortic valve calcium on cardiac computed tomography:incorporation of radiomics and machine learning[J].Korean J Radiol,2021,22(3):334-343.DOI:10.3348/kjr.2020.0099.
• [16]Hesse K,Khanji MY,Aung N,et al.Assessing heterogeneity on cardiovascular magnetic resonance imaging:a novel approach to diagno sis and risk stratification in cardiac diseases[J].Eur Heart J Cardiovasc Imaging,2024,25(4):437-445.DOI:10.1093/ehjci/jead285.
• [17]Kj eldsen EW,Thomas sen JQ,Rasmus sen KL,et al.Cardiovascular risk factors and aortic valve stenosis:towards 10-year absolute risk charts for primary prevention[J].Eur J Prev Cardiol,2025,32(17):1684-1693.DOI:10.1093/eurjpc/zwae177.
• [18]Elias P,Poterucha TJ,Rajaram V,et al.Deep learning electrocardiographic analysis for detection of left-sided valvular heart disease[J].J Am Coll Cardio1,2022,80(6):613-626.DOI:10.1016/j.jacc.2022.05.029.
• [19]Lin YT,Lin CS,Tsai CS,et al.Comprehensive clinical application analysis of artificial intelligence-enabled electrocardiograms for screening multiple valvular heart diseases[J].Aging(Albany NY),2024,16(10):8717-8731.DOI:10.18632/aging.205835.
• [20] Tokodi M,Shah R,Jamthikar A,et al.Deep learning mo del of diastolic dysfunction risk stratifies the progression of early-stage aortic steno sis[J].JACC Cardiovasc Imaging,2025,18(2):150-165.DOI:10.1016/j.jcmg.2024.07.017.
• [21]Sánchez-Puente A,Dorado-Díaz PI,Sampedro-Gómez J,et al.Machine learning to optimize the echocardiographic follow-up of aortic stenosis[J].JACC Cardiovasc Imaging,2023,16(6):733-744.DOI:DOI:10.1016/j.jcmg.2022.12.008.
• [22]Aquino GJ,Abadia AF,Scho epf UJ,et al.Coronary CT fractio nal flow reserve before transcatheter aortic valve replacement:clinical outcomes[J].Radiology,2022,302(1):50-58.DOI:10.1148/radiol.2021210160.
• [23]Wang J,Wang K,Yu Y,et al.Self-improving generative foundation model for synthetic medical image generation and clinical applications[J].Nat Med,2025,31(2):609-617.DOI:10.1038/s41591-024-03359-y.
• [24]Tsushima T,Al-Kindi S,Nadeem F,et al.Machine learning algorithms for prediction of permanent pacemaker implantation after transcatheter aortic valve replacement[J].Circ Arrhythm Electrophysiol,2021,14(3):e008941.DOI:10.1161/circep.120.008941.
• [25]Zhang G,Liu R,Pu M,et al.Biomechanical identification of high-risk patients requiring permanent pacemaker after transcatheter aortic valve replacement[J].Front Bioeng Biotechnol,2021,9:615090.DOI:10.33 8 9/fbioe.2021.615090.
• [26]Asheghan MM,Javadikasgari H,Attary T,et al.Predicting one-year left ventricular mass index regression following transcatheter aortic valve replacement in patients with severe aortic stenosis:a new era is coming[J].Front Cardiovasc Med,2023,10:1130152.DOI:10.3389/fcvm.2023.1130152.
• [27]Lertsanguansinchai P,Chokesuwattanaskul R,Petchlorlian A,et al.Machine learning-based predictive risk models for 30-day and1-year mortality in severe aortic stenosis patients undergoing transcatheter aortic valve implantation[J].Int J Cardiol,2023,374:20-26.DOI:10.1016/j.ijcard.2022.12.023.
• [28]Danilov VV,Klyshnikov KY,Gerget OM,et al.Aortography keypoint tracking for transcatheter aortic valve implantation based on multi-task learning[J].Front Cardiovasc Med,2021,8:697737.DOI:10.3389/fcvm.2021.697737.
• [29]Mohammadyari P,Vieceli Dalla Sega F,Fortini F,et al.Deep-learning survival analysis for patients with calcific aortic valve disease undergoing valve replacement[J].Sci Rep,2024,14(1):10902.DOI:10.1038/s415 98-024-61685-0.
• [30]Kilic A,Goyal A,Miller JK,et al.Performance of a machine learning algorithm in predicting outcomes of aortic valve replacement[J].Ann Thorac Surg,2021,111(2):503-5 10.DOI:10.1016/j.athoracsur.2020.05.107.
• [31]Astudillo P,Mortier P,Bosmans J,et al.Enabling automated device size selection for transcatheter aortic valve implantation[J].J Interv Cardiol,2019,2019:3591314.DOI:10.1155/2019/3591314.
• [32]Fan J,Liu Q,Dai H,et al.Daily physical activity measured by wearable smartwatch for patients undergoing transcatheter aortic valve replacement:insights from the SMART TAVR study[J].Circ Cardiovasc Qual Outcomes,2024,17(1):e010066.DOI:10.1161/CIRCOUTCOMES.123.010066.
• [33]Gerke S,Babic B,Evgeniou T,et al.The need for a system view to regulate artificial intelligence/machine learning-based software as medical device[J].NPJ Digit Med,2020,3:53.DOI:10.1038/s41746-020-0262-2.
• [34]El Arab RA,Al Moosa OA.Systematic review of cost effectiveness and budget impact of artificial intelligence in healthcare[J].NPJ Digit Med,2025,8(1):548.DOI:10.1038/s41746-025-01722-y.
• [35] Godoy Junior CA,Boverhof BJ,Rutten-van M??lken MPMH,et al.Technological maturity and cost-effectiveness of medical AI:a systematic review of health economic evaluations[J].Value Health,2026,29(5):896-904.DOI:10.1016/j.jval.2026.01.014.