An Adaptive Machine Learning Triage Framework for Predicting Alzheimer's Disease Progression

TL;DR

This paper introduces an adaptive machine learning framework that efficiently predicts Alzheimer's disease progression by selectively utilizing costly biomarkers, reducing testing costs while maintaining high accuracy.

Contribution

It proposes a novel two-stage triage framework that balances diagnostic accuracy with testing costs, improving early AD prediction accessibility.

Findings

Achieved 0.929 AUROC with 20% fewer advanced tests.

Comparable performance to models using all features.

Demonstrated interpretability of triage decisions.

Abstract

Accurate predictions of conversion from mild cognitive impairment (MCI) to Alzheimer's disease (AD) can enable effective personalized therapy. While cognitive tests and clinical data are routinely collected, they lack the predictive power of PET scans and CSF biomarker analysis, which are prohibitively expensive to obtain for every patient. To address this cost-accuracy dilemma, we design a two-stage machine learning framework that selectively obtains advanced, costly features based on their predicted "value of information". We apply our framework to predict AD progression for MCI patients using data from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Our framework reduces the need for advanced testing by 20% while achieving a test AUROC of 0.929, comparable to the model that uses both basic and advanced features (AUROC=0.915, p=0.1010). We also provide an example interpretability analysis showing how one may explain the triage decision. Our work presents an interpretable, data-driven framework that optimizes AD diagnostic pathways and balances accuracy with cost, representing a step towards making early, reliable AD prediction more accessible in real-world practice. Future work should consider multiple categories of advanced features and larger-scale validation.