Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Distributed Privacy Preserving Model for the Detection of Alzheimer's Disease

Paul K. Mandal

TL;DR

A HIPAA compliant framework that can train from distributed data, a multimodal vertical federated model for Alzheimer’s disease detection, and a novel distributed architecture that enables collaborative learning across diverse sources of medical data while respecting statutory privacy constraints are introduced.

Abstract

In the era of rapidly advancing medical technologies, the segmentation of medical data has become inevitable, necessitating the development of privacy preserving machine learning algorithms that can train on distributed data. Consolidating sensitive medical data is not always an option particularly due to the stringent privacy regulations imposed by the Health Insurance Portability and Accountability Act (HIPAA). In this paper, I introduce a HIPAA compliant framework that can train from distributed data. I then propose a multimodal vertical federated model for Alzheimer's Disease (AD) detection, a serious neurodegenerative condition that can cause dementia, severely impairing brain function and hindering simple tasks, especially without preventative care. This vertical federated learning (VFL) model offers a distributed architecture that enables collaborative learning across diverse sources of medical data while respecting privacy constraints imposed by HIPAA. The VFL architecture proposed herein offers a novel distributed architecture, enabling collaborative learning across diverse sources of medical data while respecting statutory privacy constraints. By leveraging multiple modalities of data, the robustness and accuracy of AD detection can be enhanced. This model not only contributes to the advancement of federated learning techniques but also holds promise for overcoming the hurdles posed by data segmentation in medical research.

A Distributed Privacy Preserving Model for the Detection of Alzheimer's Disease

TL;DR

A HIPAA compliant framework that can train from distributed data, a multimodal vertical federated model for Alzheimer’s disease detection, and a novel distributed architecture that enables collaborative learning across diverse sources of medical data while respecting statutory privacy constraints are introduced.

Abstract

In the era of rapidly advancing medical technologies, the segmentation of medical data has become inevitable, necessitating the development of privacy preserving machine learning algorithms that can train on distributed data. Consolidating sensitive medical data is not always an option particularly due to the stringent privacy regulations imposed by the Health Insurance Portability and Accountability Act (HIPAA). In this paper, I introduce a HIPAA compliant framework that can train from distributed data. I then propose a multimodal vertical federated model for Alzheimer's Disease (AD) detection, a serious neurodegenerative condition that can cause dementia, severely impairing brain function and hindering simple tasks, especially without preventative care. This vertical federated learning (VFL) model offers a distributed architecture that enables collaborative learning across diverse sources of medical data while respecting privacy constraints imposed by HIPAA. The VFL architecture proposed herein offers a novel distributed architecture, enabling collaborative learning across diverse sources of medical data while respecting statutory privacy constraints. By leveraging multiple modalities of data, the robustness and accuracy of AD detection can be enhanced. This model not only contributes to the advancement of federated learning techniques but also holds promise for overcoming the hurdles posed by data segmentation in medical research.
Paper Structure (12 sections, 7 figures, 2 tables)

This paper contains 12 sections, 7 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Background
  3. What Is Federated Learning?
  4. Horizontal Federated Learning
  5. Clinical Applications for Horizontal Federated Learning
  6. Vertical Federated Learning
  7. Clinical Applications for Vertical Federated Learning
  8. Methods
  9. Dataset and Preprocessing of the Data
  10. Experimental Model
  11. Results
  12. Discussion

Figures (7)

  • Figure 1: A Horizontal Federated Learning architecture for three radiology departments in different institutions to collaboratively train a single model using all of their data without medical record exchange.
  • Figure 2: A Vertical Federated Learning Architecture where Labratory A has protein tests, Imaging Center B has MRI Data, and Hospital C possesses psychiatric assessments. Secure entity alignment occurs before training to ensure that the patients are "aligned" in order to perform the distributed training.
  • Figure 3: A Multimodal Vertical Federated Learning Model for the Diagnosis of Alzheimer's Dementia.
  • Figure 4: Scatter plot of the dataset projected onto two principal components with loading vectors
  • Figure 5: Cross sectional MRI Image
  • ...and 2 more figures