DeepQuest: A Knowledge-Gap-Driven AI Scientist for Alzheimer's Research
Researchers introduce DeepQuest, an AI scientist framework that turns unresolved questions from Alzheimer's disease literature into traceable, testable hypotheses. It prioritizes hypotheses using data-feasibility screening and groupwise Elo ranking, then couples iterative experimentation with two-level auditing of experimental reliability and knowledge contribution. On OASIS-3, DeepQuest generated 42 feasible hypotheses and outperformed baselines in 14 of 15 evaluator-dimension comparisons across three language-model reviewers. The authors report a 95.24% audit-assessed scientific finding rate, with representative associations supported in independent ADNI and AIBL cohorts.
It presents a concrete research-agent framework with an auditing method and quantitative evaluation for automating traceable scientific discovery in Alzheimer's research.
Comments & Questions (0)
No comments yet
Be the first to comment!