Enhancing Clinical Decision Support and Differential Diagnosis with Knowledge Graphs, and Retrieval Augmented Generation in Generative AI
Abstract
Diagnostic error carries a burden, while unconstrained large language models (LLMs) remain vulnerable to hallucination and weak integration of quantitative laboratory dynamics. We developed a decision-support pipeline combining disease-specific biomarker correlation graphs, ordinary differential equations (ODEs), deep sequence classification, and retrieval-augmented generation (RAG). For 103 disease classes from a full blood count (FBC) repository, biomarker networks were used as coupling matrices to generate 30 trajectories per disease (3,090 total). A one-dimensional convolutional neural network (CNN) and long short-term memory (LSTM) network classified disease trajectories and six dynamical clusters. A constrained GPT-4o-mini RAG layer used a 19-pattern BMJ Best Practice/NICE corpus to generate differential diagnoses evaluated for diagnostic suitability, evidential grounding, and clinical plausibility. Across five random-seed runs, disease-level accuracy was 0.940 ± 0.006 for the CNN (95\% CI 0.933--0.948) and 0.852 ± 0.019 for the LSTM (95\% CI 0.828--0.875); the CNN advantage was 8.87 percentage points (95\% CI 6.47--11.27; t(4)=10.26, p=5.1×10−4; Hedges' g=3.67). Among 100 sampled RAG cases, 96 parsed successfully; evidence was cited in 97.9\%, the true diagnosis was mentioned in 71.9\%, and the composite score was 3.82/5 with a 47.9\% strict pass rate. The central finding was a decoupling between grounding and diagnostic correctness: classifier-correct versus classifier-wrong outputs differed in diagnostic suitability but not evidential grounding. Post-hoc analysis confirmed a 1.02-point diagnostic-score difference (Mann--Whitney p=0.0024; Hedges' g=0.72), whereas grounding differed by only −0.02 points (p=0.839; g=−0.04).
Related
- Epidemiology of Syphilis, Diagnosis, Differential Diagnosis and Treatment: Up-to-Date Knowledge
- Generative AI for Synthetic Medical Image Generation in Oncology: Addressing Data Scarcity in AI-Driven Cancer Diagnosis
- UKB-KG: Knowledge Graph for Integrating and Enhancing Biomedical Insights from the UK Biobank
- IFC-HFlowVAE: A self-enhancing generative framework with structural anchoring for imbalanced clinical data augmentation
- Generative Artificial Intelligence Models in Breast Cancer Diagnosis: A Systematic Review
BibTeX
@misc{feto2026enhancing,
title = {{Enhancing Clinical Decision Support and Differential Diagnosis with Knowledge Graphs, and Retrieval Augmented Generation in Generative AI}},
author = {Henri Feto and Abicumaran Uthamacumaran and Hector Zenil},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.01653},
eprint = {2609.01653},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.01653},
}
RIS
TY - UNPB
TI - Enhancing Clinical Decision Support and Differential Diagnosis with Knowledge Graphs, and Retrieval Augmented Generation in Generative AI
AU - Henri Feto
AU - Abicumaran Uthamacumaran
AU - Hector Zenil
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.01653
UR - https://arxiv.org/abs/2609.01653
AB - Diagnostic error carries a burden, while unconstrained large language models (LLMs) remain vulnerable to hallucination and weak integration of quantitative laboratory dynamics. We developed a decision-support pipeline combining disease-specific biomarker correlation graphs, ordinary differential equations (ODEs), deep sequence classification, and retrieval-augmented generation (RAG). For 103 disease classes from a full blood count (FBC) repository, biomarker networks were used as coupling matrices to generate 30 trajectories per disease (3,090 total). A one-dimensional convolutional neural network (CNN) and long short-term memory (LSTM) network classified disease trajectories and six dynamical clusters. A constrained GPT-4o-mini RAG layer used a 19-pattern BMJ Best Practice/NICE corpus to generate differential diagnoses evaluated for diagnostic suitability, evidential grounding, and clinical plausibility. Across five random-seed runs, disease-level accuracy was 0.940 ± 0.006 for the CNN (95\% CI 0.933--0.948) and 0.852 ± 0.019 for the LSTM (95\% CI 0.828--0.875); the CNN advantage was 8.87 percentage points (95\% CI 6.47--11.27; t(4)=10.26, p=5.1×10^−4; Hedges' g=3.67). Among 100 sampled RAG cases, 96 parsed successfully; evidence was cited in 97.9\%, the true diagnosis was mentioned in 71.9\%, and the composite score was 3.82/5 with a 47.9\% strict pass rate. The central finding was a decoupling between grounding and diagnostic correctness: classifier-correct versus classifier-wrong outputs differed in diagnostic suitability but not evidential grounding. Post-hoc analysis confirmed a 1.02-point diagnostic-score difference (Mann--Whitney p=0.0024; Hedges' g=0.72), whereas grounding differed by only −0.02 points (p=0.839; g=−0.04).
ER -