Predicting Alzheimers Disease Diagnosis Risk over Time with Survival Machine Learning on the ADNI Cohort

TL;DR

This paper explores survival machine learning models to predict the risk and timing of Alzheimer's disease deterioration, demonstrating high predictive accuracy and potential clinical utility.

Contribution

It introduces survival machine learning for predicting both Alzheimer's risk and time to deterioration, showing promising predictive performance.

Findings

Achieved 0.86 C-Index in predictions

Supports clinical use for Alzheimer's risk assessment

Demonstrates effectiveness of survival models in this context

Abstract

The rise of Alzheimers Disease worldwide has prompted a search for efficient tools which can be used to predict deterioration in cognitive decline leading to dementia. In this paper, we explore the potential of survival machine learning as such a tool for building models capable of predicting not only deterioration but also the likely time to deterioration. We demonstrate good predictive ability (0.86 C-Index), lending support to its use in clinical investigation and prediction of Alzheimers Disease risk.