{
  "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 $0.940 \\pm 0.006$ for the CNN (95\\% CI 0.933--0.948) and $0.852 \\pm 0.019$ for the LSTM (95\\% CI 0.828--0.875); the CNN advantage was 8.87 percentage points (95\\% CI 6.47--11.27; $t(4)=10.26$, $p=5.1\\times10^{-4}$; 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 ($p=0.839$; $g=-0.04$).",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.01653",
  "author_total": 3,
  "authors": [
    {
      "name": "Henri Feto"
    },
    {
      "name": "Abicumaran Uthamacumaran"
    },
    {
      "name": "Hector Zenil"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/b5tm61fjyhh4e.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.01653",
  "fulltext_url": null,
  "id": "b5tm61fjyhh4e",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.01653",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "q-bio.OT"
    ],
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W7207764905",
  "pdf_url": "https://arxiv.org/pdf/2609.01653",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/b5tm61fjyhh4e.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:21Z",
      "native_id": "2609.01653",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.01653"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2718|Artificial Intelligence in Healthcare and Education",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "Enhancing Clinical Decision Support and Differential Diagnosis with Knowledge Graphs, and Retrieval Augmented Generation in Generative AI",
  "title_text": "Enhancing Clinical Decision Support and Differential Diagnosis with Knowledge Graphs, and Retrieval Augmented Generation in Generative AI",
  "type": "preprint",
  "updated_at": "2026-10-30T12:18:21Z",
  "url": "https://research.draconitic.com/paper/b5tm61fjyhh4e",
  "venue": "arXiv",
  "versions": []
}