GrantCheck—an AI Solution for Guiding Grant Language to New Policy Requirements: Development Study
Bibliographic record
Abstract
BACKGROUND: Academic institutions face increasing challenges in grant writing due to evolving federal and state policies that restrict the use of specific language. Manual review processes are labor-intensive and may delay submissions, highlighting the need for scalable, secure solutions that ensure compliance without compromising scientific integrity. OBJECTIVE: This study aimed to develop a secure, artificial intelligence-powered tool that assists researchers in writing grants consistent with evolving state and federal policy requirements. METHODS: GrantCheck (University of Massachusetts Chan Medical School) was built on a private Amazon Web Services virtual private cloud, integrating a rule-based natural language processing engine with large language models accessed via Amazon Bedrock. A hybrid pipeline detects flagged terms and generates alternative phrasing, with validation steps to prevent hallucinations. A secure web-based front end enables document upload and report retrieval. Usability was assessed using the System Usability Scale. RESULTS: =0.72). Usability testing among 25 faculty and staff yielded a mean System Usability Scale score of 85.9 (SD 13.4), indicating high user satisfaction and strong workflow integration. CONCLUSIONS: GrantCheck demonstrates the feasibility of deploying institutionally hosted, artificial intelligence-driven systems to support compliant and researcher-friendly grant writing. Beyond administrative efficiency, such systems can indirectly safeguard public health research continuity by minimizing grant delays and funding losses caused by language-related policy changes. By maintaining compliance without suppressing scientific rigor or inclusivity, GrantCheck helps protect the pipeline of research that advances biomedical discovery, health equity, and patient outcomes. This capability is particularly relevant for proposals in sensitive domains-such as social determinants of health, behavioral medicine, and community-based research-that are most vulnerable to evolving policy restrictions. As a proof-of-concept development study, our implementation is tailored to one institution's policy environment and security infrastructure, and findings should be interpreted as preliminary rather than universally generalizable.
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 | 0.011 | 0.033 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.013 | 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".