# SAFS: A Deep Feature Selection Approach for Precision Medicine

## TL;DR

This paper introduces a deep feature selection method using stacked auto-encoders to identify significant risk factors for hypertension-related heart damage in a specific demographic, improving predictive accuracy.

## Contribution

The paper presents a novel deep learning-based feature selection approach tailored for precision medicine, focusing on risk factor assessment for hypertension in African-Americans.

## Key findings

- Improved identification of risk factors for hypertension-related heart damage.
- Enhanced predictive performance over existing methods.
- Effective feature representation using deep auto-encoders.

## Abstract

In this paper, we propose a new deep feature selection method based on deep architecture. Our method uses stacked auto-encoders for feature representation in higher-level abstraction. We developed and applied a novel feature learning approach to a specific precision medicine problem, which focuses on assessing and prioritizing risk factors for hypertension (HTN) in a vulnerable demographic subgroup (African-American). Our approach is to use deep learning to identify significant risk factors affecting left ventricular mass indexed to body surface area (LVMI) as an indicator of heart damage risk. The results show that our feature learning and representation approach leads to better results in comparison with others.