The Application of Federated Learning in the Detection of Heart Arrhythmias

Session Number

Project ID: CMPS 04

Advisor(s)

Dr. Ravi Madduri, Argonne National Laboratory

Discipline

Computer Science

Start Date

17-4-2024 8:15 AM

End Date

17-4-2024 8:30 AM

Abstract

This study aims to address the pressing need for accessible and accurate detection of heart irregularities amidst the rising prevalence of cardiovascular diseases. Leveraging machine learning's capability to process extensive datasets, the research proposes the development of predictive models for identifying heart rhythm irregularities. However, a significant challenge in healthcare persists: ensuring the security and privacy of patient data. To mitigate this concern, the study adopts Privacy-Preserving Federated Learning, specifically utilizing the Argonne Privacy-Preserving Federated Learning (APPFL) framework. This approach enables collaboration among multiple entities while safeguarding sensitive information. By harnessing Federated Learning, the research seeks to construct a robust model for heart irregularity detection, evaluating its accuracy, efficacy, and scalability. Through this methodology, the study hopes to enhance early detection and intervention for individuals at risk, thereby contributing to proactive healthcare interventions and improved patient outcomes in the realm of cardiovascular health.

Share

COinS
 
Apr 17th, 8:15 AM Apr 17th, 8:30 AM

The Application of Federated Learning in the Detection of Heart Arrhythmias

This study aims to address the pressing need for accessible and accurate detection of heart irregularities amidst the rising prevalence of cardiovascular diseases. Leveraging machine learning's capability to process extensive datasets, the research proposes the development of predictive models for identifying heart rhythm irregularities. However, a significant challenge in healthcare persists: ensuring the security and privacy of patient data. To mitigate this concern, the study adopts Privacy-Preserving Federated Learning, specifically utilizing the Argonne Privacy-Preserving Federated Learning (APPFL) framework. This approach enables collaboration among multiple entities while safeguarding sensitive information. By harnessing Federated Learning, the research seeks to construct a robust model for heart irregularity detection, evaluating its accuracy, efficacy, and scalability. Through this methodology, the study hopes to enhance early detection and intervention for individuals at risk, thereby contributing to proactive healthcare interventions and improved patient outcomes in the realm of cardiovascular health.