Integrating knowledge graphs and retrieval-augmented generation to identify clinical pharmacology gaps in infectious disease trial protocols
- 1Artificial Intelligence and Clinical Pharmacology Laboratory, Department of Pharmaceutical Sciences, University at Buffalo, The State University of New York
Abstract
Purpose: Clinical trial protocols contain critical clinical pharmacology information that is often scattered across different sections of these lengthy documents. The purpose was to evaluate whether a retrieval-augmented generation (RAG) protocol review integrated with knowledge graphs (KGs) could be used to obtain clinical pharmacology evidence and identify regulatory gaps.
Methods: Clinical trial protocols were obtained from the Gates Foundation’s publicly available corpus of clinical trials in low- and middle-income countries. The RAG protocol review was used to assess the protocols against Food & Drug Administration (FDA) guidance documents for hepatic impairment, exposure-response, population PK (PopPK), and physiologically based pharmacokinetic modeling (PBPK). Disease-specific KG analyses were conducted for tuberculosis (TB), human immunodeficiency virus (HIV), malaria, and neglected tropical diseases (NTD). KG models connecting studies to drugs, diseases, pharmacologic classes, organ-function exclusions, biomarkers, and pharmacokinetic (PK) parameter features were obtained.
Results: Across 42 unique trials, the KG contained 223 nodes and 376 edges. TB protocols produced the largest disease-specific graph, whereas HIV had the highest frequency of PK studies. Gap analysis showed that hepatic impairment exclusions in TB were more frequent than PK studies. In the multi-guidance evaluation, faithfulness was high, answer relevancy was lower, and the clinical pharmacology metric showed guidance-dependent differences.
Conclusion: The integrated KG-RAG approach can help highlight potential gaps in clinical pharmacology reporting in infectious disease clinical trial protocols.
Related
- Temporal-spatial reasoning over hypergraph knowledge structures for multimodal retrieval-augmented generation
- HalluciGuard-eye: knowledge graph-enhanced retrieval-augmented generation for hallucination detection and mitigation in ophthalmic multimodal large language models
- Enhancing Clinical Decision Support and Differential Diagnosis with Knowledge Graphs, and Retrieval Augmented Generation in Generative AI
- EIN-RECAP: Evidence-Grounded Multi-Agent Summarization and Retrieval of Infectious-Disease Expert Discussions
- How an Infectious Diseases and Clinical Microbiology Clerkship Affects Medical Students' HIV/AIDS Knowledge and Attitudes
BibTeX
@article{waikar2026integrating,
title = {{Integrating knowledge graphs and retrieval-augmented generation to identify clinical pharmacology gaps in infectious disease trial protocols}},
author = {Shreyas Waikar and Murali Ramanathan},
journal = {Frontiers in Pharmacology},
year = {2026},
month = oct,
doi = {10.3389/fphar.2026.1955011},
url = {https://www.frontiersin.org/articles/10.3389/fphar.2026.1955011/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Integrating knowledge graphs and retrieval-augmented generation to identify clinical pharmacology gaps in infectious disease trial protocols
AU - Shreyas Waikar
AU - Murali Ramanathan
PY - 2026
DA - 2026/10/14
JO - Frontiers in Pharmacology
DO - 10.3389/fphar.2026.1955011
UR - https://www.frontiersin.org/articles/10.3389/fphar.2026.1955011/full
AB - Purpose: Clinical trial protocols contain critical clinical pharmacology information that is often scattered across different sections of these lengthy documents. The purpose was to evaluate whether a retrieval-augmented generation (RAG) protocol review integrated with knowledge graphs (KGs) could be used to obtain clinical pharmacology evidence and identify regulatory gaps. Methods: Clinical trial protocols were obtained from the Gates Foundation’s publicly available corpus of clinical trials in low- and middle-income countries. The RAG protocol review was used to assess the protocols against Food & Drug Administration (FDA) guidance documents for hepatic impairment, exposure-response, population PK (PopPK), and physiologically based pharmacokinetic modeling (PBPK). Disease-specific KG analyses were conducted for tuberculosis (TB), human immunodeficiency virus (HIV), malaria, and neglected tropical diseases (NTD). KG models connecting studies to drugs, diseases, pharmacologic classes, organ-function exclusions, biomarkers, and pharmacokinetic (PK) parameter features were obtained. Results: Across 42 unique trials, the KG contained 223 nodes and 376 edges. TB protocols produced the largest disease-specific graph, whereas HIV had the highest frequency of PK studies. Gap analysis showed that hepatic impairment exclusions in TB were more frequent than PK studies. In the multi-guidance evaluation, faithfulness was high, answer relevancy was lower, and the clinical pharmacology metric showed guidance-dependent differences. Conclusion: The integrated KG-RAG approach can help highlight potential gaps in clinical pharmacology reporting in infectious disease clinical trial protocols.
SN - 1663-9812
ER -