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

2025-11-10

AI Summary

High-cost biomarker assays hinder clinical deployment of mild cognitive impairment (MCI)–to–Alzheimer’s disease (AD) conversion prediction. Method: We propose a two-stage, interpretable machine learning triage framework that dynamically selects costly features using information value (IV), minimizing expensive testing while preserving predictive accuracy. It integrates routine clinical data with multimodal biomarkers to enable adaptive, progressive feature acquisition. Results: Evaluated on the ADNI dataset, the model achieves an AUROC of 0.929—statistically indistinguishable from the full-feature baseline (p = 0.1010)—while reducing demand for advanced biomarker assays by 20%. Our key contribution is the first integration of IV-driven feature selection into clinical triage, jointly optimizing prediction robustness, interpretability, and cost-effectiveness—thereby enabling feasible, personalized early intervention.

Technology Category

• Machine Learning: Dimensionality Reduction/Feature Selection
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Predicts Alzheimer's progression from mild cognitive impairment
• Reduces need for expensive advanced medical testing
• Balances diagnostic accuracy with cost-effectiveness in healthcare

Innovation

• Two-stage ML framework for Alzheimer's prediction
• Selectively obtains costly features using value prediction
• Reduces advanced testing needs while maintaining accuracy