biodiscvr: Biomarker Discovery Using Composite Value Ratios
Abstract
biodiscvr provides a framework for discovering and evaluating optimised biomarkers defined as ratios of composite values derived from feature sets (e.g., regional measurements from imaging data).The conceptual approach is domain-agnostic, but the current implementation is tailored to Alzheimer's disease (AD) research, reflecting the motivating use cases that guided its development.As such, several preprocessing utilities, expected variable names, and default assumptions correspond to common AD datasets (e.g., cognitive status groupings, amyloid/tau measures, and region-of-interest conventions).
Fields of Study & Subjects
Dementia and Cognitive Impairment Research
Alzheimer's disease research and treatments
Artificial Intelligence in Healthcare
Publication details
- Journal / source
- The Journal of Open Source Software
- Volume
- 11
- Issue
- 119
- Pages
- 9070–9070
- Publication date
- 15 March 2026
- Language
- EN