SCOPE-AD plans tests to cut costs and improve Alzheimer diagnosis
SCOPE-AD: Sequential cost-aware ordinal-belief planning with energy-based models for diagnostic agents
Artificial IntelligenceComputation and Language
Summary
Diagnosing Alzheimer's disease can involve many costly and time-consuming tests. The authors developed SCOPE-AD, a system that smartly chooses which tests to run and when to stop, saving money and effort. It uses a special model that understands how likely it is for a patient to be healthy, mildly impaired, or have Alzheimer's, updating predictions as new tests come in. Their approach got better accuracy with much less cost compared to always running all tests. This method could help doctors make diagnoses more efficiently and with less burden on patients.
What this means in practice
- •For hospital data teams: Enable clinical workflows to select diagnostic tests dynamically for Alzheimer's patients, reducing costs while maintaining diagnosis accuracy.
- •For health insurance analysts: Implement patient-specific test planning to manage Alzheimer’s diagnosis expenditures and optimize resource allocation.
Tested on one dataset.
Authors
Ziwen Yu, Ivan Koychev, Elizabeth Coulthard, Ting Zhou, Bolin Chen, Dian Hong, Zinuo You, Yujiao Wang, Anthony Mulholland, Qiang Liu
Abstract
Alzheimer's disease (AD) diagnosis requires sequential evidence acquisition under heterogeneous test costs and patient burden. Fixed-modality predictors do not jointly decide which test to acquire or when the available evidence is sufficient for diagnosis. We propose SCOPE-AD (Sequential Cost-Aware Ordinal-Belief Planning with Energy-Based Models for Diagnostic Agents) for cost-aware classification of cognitively normal (CN), mild cognitive impairment (MCI), and AD cases. A mask-aware ordinal model represents uncertainty along the ordered CN--MCI--AD continuum. Retrospective training records provide sampled Bellman targets for an energy-based teacher, whose action distributions are distilled into a Qwen policy. At deployment, the agent selects acquisition or diagnosis actions under availability and budget constraints without access to unacquired values. After each acquisition, the evidence and ordinal belief are updated before the next decision. On ADNI, SCOPE-AD achieves 77.70\% Macro-F1 at an average acquisition cost of \$50.46, exceeding the strongest evaluated baseline by 9.34 percentage points. Full-modality evaluation raises Macro-F1 by only 1.89 points while increasing acquisition cost by 116.7 times. These results support selective acquisition for cost-effective diagnosis.