Code for "Generalizable deep learning model for early Alzheimer’s disease detection from structural MRIs"

[JBHI 2024] This is a code implementation of the hybrid-granularity ordinal learning proposed in the manuscript "HOPE: Hybrid-granularity Ordinal Prototype Learning for Progression Prediction of Mild Cognitive Impairment".

Alzheimer prediction using Ensemble Transfer Learning

A responsive web application that helps members with Mild Cognitive Impairment keep track of their daily routines. This was a class project in partnership with the Aware Home at Georgia Tech under CS 7470 - Ubiquitous Computing taught by Dr. Thomas Ploetz.

🧠 Detect MCI from EEG/ERP data using standardized datasets, feature pipelines, and robust validation metrics for reproducible research.

Thesis project with title: "Cognitive decline detection using speech features: A machine learning approach"

Listening Between the Lines: An explainable multimodal framework for MCI detection from spontaneous speech. Leverages Selective State Space Models (Mamba) and Gated Fusion to integrate linguistic disfluencies and eGeMAPS biomarkers across multi-corpus benchmarks (Pitt, ADReSS, TAUKADIAL)

Mild Cognitive Impairment Detection from Rey-Osterrieth Complex Figure Copy Drawings using a Contrastive Loss Siamese Neural Network

Reproducible analysis code and aggregated outputs for a VR-based cognitive screening tool with integrated eye tracking (AD, MCI, and controls).

Alzheimer & MCI DeepLearning (CNN) based Diagnosis Model

Open EEG–MCI benchmark in BIDS format with ERP pipelines. Subject-level LOSO validation, reproducible ML/DL baselines, and reports (F1/MCC/AUC).

Task and analysis code for "Linking cognitive integrity to working memory dynamics in the aging human brain"