Theses and Dissertations

Date of Award

5-1-2026

Document Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Department

Information Systems

First Advisor

Xuan Wang

Second Advisor

Francis Kofi Andoh-Baidoo

Third Advisor

Geng Sun

Abstract

Chronic neurological diseases, particularly Alzheimer's disease and related dementias (ADRDs), pose mounting global healthcare burdens. Despite advances in AI and health information technologies, early detection, precise diagnosis, and effective caregiver support remain elusive. This dissertation proposes innovative AI-enabled analytical frameworks to address these challenges across the full ADRD continuum.

The first essay designs an explainable AI-enabled clinical decision support system (CDSS) using a graph neural network for early AD identification, evaluated through usability studies demonstrating improved risk awareness and clinical engagement. The second essay introduces MADT-RNN, a multi-level attention-based deep transfer recurrent neural network that fuses convolutional and recurrent architectures with hierarchical transfer learning to achieve 98% diagnostic accuracy on longitudinal neuroimaging data. The third essay develops a fine-tuned LLM grounded in online health community (OHC) discussions, embedding dementia-care heuristics and safety filters to deliver empathetic, contextually appropriate caregiver support.

Our findings from the essays of this dissertation advance information systems (IS) literature and clinical practice by demonstrating how patient-centered, interpretable AI artifacts can improve healthcare delivery across the ADRD spectrum.

Comments

Copyright 2026 Gabriel Owusu. All Rights Reserved. https://proquest.com/docview/3371108361

Download

Share

COinS