Demystifying Heart Failure with Mid-Range Ejection Fraction Using Machine Learning

Abstract

Treating Heart Failure (HF) patients with mid-range Ejection Fraction (HFmrEF) is a challenging task due to prognostic uncertainty and transitional behaviour of HFmrEF, often referred to as “grey-area”. In this study, we address the uncertainty of HFmrEF through Machine Learning (ML) by classifying it into two well studied phenotypes: HF with preserved Ejection Fraction and HF with reduced Ejection Fraction, using the data from clinical attributes. We propose a semi-supervised Active Learning based model that uses significantly lesser data to tackle the need of supervised label validation and performs on-par with supervised ML models developed for comparison. We believe the use of proposed ML models can enable experts in making informed data-driven decisions leading to the accurate prognosis of HF patients.