Alzheimer Diagnosis Optimization with Machine Learning and Quantum Machine Learning

Overview

This project explores a hybrid ML-QML pipeline for early detection of Alzheimer’s disease from neuroimaging data. Classical machine learning handles feature extraction and baseline performance, while quantum models are evaluated as complementary models for the optimization and encoding stages.

Why it matters

Neuroimaging datasets are high-dimensional and imbalanced, which makes them a natural test case for hybrid approaches. The goal is not to claim quantum advantage, but to measure carefully where hybrid ML-QML methods can genuinely help compared to a strong classical baseline.

Outcome

The proposal “Optimization of Alzheimer’s Diagnostic Analysis using Machine Learning and Quantum Machine Learning Fusion on Complex Neuroimaging Data” was selected for research funding under the Student Creativity Program (PKM - AMLI), and I received Best Presenter (1st Winner) in Room 10 at the progress report presentation. The hybrid ML-QML fusion model was developed in Python.