Privacy Preserving Machine Learning for Electronic Health Records using Federated Learning and Differential Privacy

TL;DR

This paper discusses combining federated learning and differential privacy to develop machine learning models that protect sensitive patient data in electronic health records while enabling data analysis for improved healthcare.

Contribution

It introduces a novel approach integrating federated learning with differential privacy specifically tailored for electronic health records.

Findings

Enhanced privacy protection for sensitive health data

Maintained model accuracy with privacy-preserving techniques

Applicable framework for healthcare data analysis

Abstract

An Electronic Health Record (EHR) is an electronic database used by healthcare providers to store patients' medical records which may include diagnoses, treatments, costs, and other personal information. Machine learning (ML) algorithms can be used to extract and analyze patient data to improve patient care. Patient records contain highly sensitive information, such as social security numbers (SSNs) and residential addresses, which introduces a need to apply privacy-preserving techniques for these ML models using federated learning and differential privacy.