Similarity-based prediction of Ejection Fraction in Heart Failure Patients

TL;DR

This paper introduces FILL, a machine learning method that infers missing patient features from real-world data to predict heart failure types, achieving over 80% precision and outperforming classical models.

Contribution

The study presents a novel feature imputation technique, FILL, that improves classification of heart failure subtypes using incomplete real-world datasets.

Findings

FILL achieves over 80% precision in identifying HFpEF patients.

FILL outperforms logistic regression and random forest models.

Key features include atrial fibrillation and anticoagulant use.

Abstract

Biomedical research is increasingly employing real world evidence (RWE) to foster discoveries of novel clinical phenotypes and to better characterize long term effect of medical treatments. However, due to limitations inherent in the collection process, RWE often lacks key features of patients, particularly when these features cannot be directly encoded using data standards such as ICD-10. Here we propose a novel data-driven statistical machine learning approach, named Feature Imputation via Local Likelihood (FILL), designed to infer missing features by exploiting feature similarity between patients. We test our method using a particularly challenging problem: differentiating heart failure patients with reduced versus preserved ejection fraction (HFrEF and HFpEF respectively). The complexity of the task stems from three aspects: the two share many common characteristics and treatments, only part of the relevant diagnoses may have been recorded, and the information on ejection fraction is often missing from RWE datasets. Despite these difficulties, our method is shown to be capable of inferring heart failure patients with HFpEF with a precision above 80% when considering multiple scenarios across two RWE datasets containing 11,950 and 10,051 heart failure patients. This is an improvement when compared to classical approaches such as logistic regression and random forest which were only able to achieve a precision < 73%. Finally, this approach allows us to analyse which features are commonly associated with HFpEF patients. For example, we found that specific diagnostic codes for atrial fibrillation and personal history of long-term use of anticoagulants are often key in identifying HFpEF patients.