Fig. 1: Unsupervised ML and Aortic valve stenosis. | npj Cardiovascular Health

Fig. 1: Unsupervised ML and Aortic valve stenosis.

From: Phenotyping valvular heart diseases using the lens of unsupervised machine learning: a scoping review

Fig. 1

Unsupervised ML and Aortic valve stenosis. By incorporating multiple clinical and echocardiographic parameters into ML models, high risk phenotypes were identified such as low LV ejection fraction, LV mass, increased age, low flow-low gradient variant, high burden of co-morbidities as well as characteristics of echo Doppler data. Bi-ventricular remodeling presenting pulmonary hypertension, IVC dilatation, and reduction in LV systolic function were associated with poor outcomes post TAVR.

Back to article page