Towards an AI biomedical scientist: Accelerating discoveries in neurodegenerative disease
Bibliographic record
Abstract
Despite major advances in Alzheimer's disease and related diseases (ADRD) research, the translation of discoveries into impactful clinical interventions remains slow. Overwhelming data complexity, fragmented knowledge, and prolonged research cycles hinder progress in understanding and treating neurodegenerative diseases. Artificial intelligence (AI) offers a promising path forward, particularly when developed as a scientist-in-the-loop system that collaborates with researchers throughout the scientific discovery process. This paper introduces the concept of an AI Biomedical Scientist, an intelligent platform designed to support literature synthesis, hypothesis generation, experimental design, and data interpretation. This platform aims to function as a holistic scientific partner, integrating diverse biomedical data and expert reasoning to accelerate discovery. We review commercial and academic efforts and introduce targeted Minimum Viable Products (MVPs) needed for general biomedical research lab utilization of AI, such as robust and accurate tools for literature and data analysis, negative data models, and virtual peer review, with a longer-term vision of foundation models trained directly on biomedical datasets. In AD and neurodegeneration research, such tools are anticipated to deliver efficiency gains ranging from modest improvements in specific research tasks to potential multi-fold accelerations in discovery workflows as systems mature and scale. This review examines the technical foundations, challenges, and anticipated impacts of AI and aims to inform and engage researchers in utilizing these systems to transform biomedical discovery, starting with AD and extending to other complex conditions.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.033 | 0.040 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.001 | 0.005 |
| Scholarly communication | 0.008 | 0.012 |
| Open science | 0.003 | 0.006 |
| Research integrity | 0.004 | 0.004 |
| Insufficient payload (model declined to judge) | 0.004 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".