biostudies-literatureSengupta PPNSFBritish Heart FoundationFonds de Recherche du Québec - SantéNational Institutes of HealthWellcome TrustNational Institute of General Medical SciencesCanadian Institutes of Health ResearchNIGMS NIH HHSNational Science Foundation1707-1720https://www.ebi.ac.uk/biostudies/studies/S-EPMC8434951biostudies-literatureUnknown14(9)<h4>Objectives</h4>The authors explored the development and validation of machine-learning models for augmenting the echocardiographic grading of aortic stenosis (AS) severity.<h4>Background</h4>In AS, symptoms and adverse events develop secondarily to valvular obstruction and left ventricular decompensation. The current echocardiographic grading of AS severity focuses on the valve and is limited by diagnostic uncertainty.<h4>Methods</h4>Using echocardiography (ECHO) measurements (ECHO cohort, n = 1,052), we performed patient similarity analysis to derive high-severity and low-severity phenogroups of AS. We subsequently developed a supervised machine-learning classifier and validated its performance with independent markers of disease severity obtained using computed tomography (CT) (CT coJACC. Cardiovascular imagingA Machine-Learning Framework to Identify Distinct Phenotypes of Aortic Stenosis Severity.PMC843495115/JTACH/09/0025U54GM104942-04RG/16/10/32375CH/09/002/26360WT103782AIARE/18/5/34216FS/14/78/310201920920FS/16/19/31982U54 GM104942Shen MTribouilloy CGuzzetti EBing RSengupta PPGay LGCote NMathieu TLacomis JMPibarot PMacron LGun MSechrist JWDweck MRKulkarni HDreyfus JBeaudoin JPawade TACalabria HCKagiyama NNguyen VChin CWLArsenault MTastet LEvangelista ABernier MCavalcante JLRenard CMessika-Zeitoun DClavel MAHamirani YYanamala NArtificial Intelligence for Aortic Stenosis at Risk International ConsortiumNewby DENtalas ILarose EEverett RJenkins WSARajani RPrendergast BShrestha SfalseA Machine-Learning Framework to Identify Distinct Phenotypes of Aortic Stenosis Severity.<h4>Objectives</h4>The authors explored the development and validation of machine-learning models for augmenting the echocardiographic grading of aortic stenosis (AS) severity.<h4>Background</h4>In AS, symptoms and adverse events develop secondarily to valvular obstruction and left ventricular decompensation. The current echocardiographic grading of AS severity focuses on the valve and is limited by diagnostic uncertainty.<h4>Methods</h4>Using echocardiography (ECHO) measurements (ECHO cohort, n = 1,052), we performed patient similarity analysis to derive high-severity and low-severity phenogroups of AS. We subsequently developed a supervised machine-learning classifier and validated its performance with independent markers of disease severity obtained using computed tomography (CT) (CT co2021-01-01T00:00:00Z2021 Sep2025-04-04T09:37:18.703Z2025-04-04T09:37:18.703ZS-EPMC84349513402327310.1016/j.jcmg.2021.03.020