Back

Comparing AI and Human Coding of NIH Grant Abstracts to Identify Innovations in Opioid Addiction Treatment

Alkhatib, S. A.; Jiwa, N.; Judd, D.; Luningham, J. M.; Sawyer-Morris, G.; Ulukaya, M.; Molfenter, T.; Taxman, F. S.; Walters, S. T.

2026-02-17 health informatics
10.64898/2026.02.13.26346235 medRxiv
Show abstract

Large language models (LLMs) are increasingly used for qualitative analysis in substance use research, yet their performance relative to human coders remains underexplored. This study compares ChatGPT-4.0 with human coders in identifying and describing the core innovation of NIH grants focused on reducing opioid overdose. A total of 118 NIH HEAL Initiative grant abstracts were independently coded by ChatGPT and humans to generate innovation descriptions, which were then evaluated by both human raters and ChatGPT for depth/detail and relevance/completeness using 5-point Likert scales. Identical instructions were used across all coding and evaluation stages. ChatGPT-generated descriptions were consistently rated higher than human-generated descriptions on both dimensions. Human evaluators rated ChatGPT outputs at an average of 4.47 for both depth/detail and relevance/completeness, compared to 3.33 and 3.24 for human outputs, respectively (F(1,176)=133.9, p<0.001). These findings suggest that LLMs, when carefully prompted, can enhance the efficiency and quality of qualitative research evaluation.

Published in CrimRxiv · not in our set (fewer than 10 published preprints to learn from) · training set

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.