AI for Alzheimer’s: NLP-Based Detection and LLM Comprehension

My research focuses on the use of AI in identifying Alzheimer’s disease and evaluating the ability of large language models (LLMs) to comprehend the speech of Alzheimer’s patients. I am supervised by Professor Dean Ho, Head of the Department of Biomedical Engineering at the National University of Singapore.

I am working on two research papers.

PAPER #1 SUMMARY (Submitting for publication)

My research investigates the use of transformer-based natural language processing (NLP) models to support early detection of Alzheimer’s disease by analyzing speech and language patterns. By fine-tuning models on clinical transcripts, the study examines how specific linguistic features—such as pauses and disfluencies—can serve as biomarkers of cognitive decline. The goal is to identify both effective models and meaningful linguistic indicators to improve diagnostic support tools in clinical settings.

Emergent Misalignment in LLMs

PAPER #2 SUMMARY (In progress)

My current research is focused on emergent misalignment and alignment side effects in coding-focused large language models.

CERTIFICATIONS

I have completed the CITI Program courses required by the National University of Singapore: Health Information Privacy and Security (HIPS) - Basic Course and Good Clinical Practice - Basic Course.