{
  "abstract": "Integrating Large Language Models (LLMs) into radiology is often hindered by the inability of monolithic architectures to balance clinical reasoning with pedagogical safety. This study evaluates MedGemma-27B-IT across two specialized agentic frameworks: a clinical \"Radiology Sparring Partner\" and a \"Socratic Teacher\". For clinical decision support, we compared three architectures: Raw (base model output, no prompt), Minimal Prompted (single-shot prompt), and Multi-Agentic, using a 4-stage pipeline for clinical synthesis. Separately, the educational track employs a dual-agent architecture for progressive educational scaffolding. A pooled evaluation of 120 interaction transcripts (10 per architecture with three independent LLM-as-a-judge runs) was finalized using an expert-anchored combined mean approach, anchored via Bühlmann credibility calibration against radiologist-authored references (5 per architecture). Results demonstrate that agentic orchestration outperforms monolithic baselines in high-level reasoning. Most notably, Pathophysiological Logic scores rose from 3.20 (Raw) to 4.14 (Agentic) on a 5-point Likert scale, with a simultaneous reduction in standard deviation from 1.23 to 0.70. While this Proof of Concept (PoC) highlights the advantages of modularity, results remain subject to evaluator formulation bias and a measurable \"latency tax\" inherent in sequential agent hand-offs. Future work will focus on longitudinal clinical validation and optimization of cached memory architectures to refine reasoning depth while mitigating latency.",
  "abstract_shown": true,
  "affiliations": [
    "Cognitive-Systems, Otto-von-Guericke University Magdeburg, Universitätsplatz 2,Magdeburg, Germany",
    "Department of Radiology, Otto-von-Guericke University Magdeburg, Leipziger Str. 44,Magdeburg, Germany",
    "Department of Psychosomatic Medicine and Psychotherapy, Otto-von-Guericke University Magdeburg, Leipziger Str. 44,Magdeburg, Germany"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Schewior Jonas"
    },
    {
      "affs": [
        0
      ],
      "name": "Ashfaq Anwerdeen Mohamed"
    },
    {
      "affs": [
        1
      ],
      "name": "Ertürk Birim"
    },
    {
      "affs": [
        1
      ],
      "name": "Großer Oliver"
    },
    {
      "affs": [
        2
      ],
      "name": "Siegert Ingo"
    },
    {
      "affs": [
        1
      ],
      "name": "Pech Maciej"
    },
    {
      "affs": [
        0
      ],
      "name": "Wendemuth Andreas"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/f261y63gzx710.bib",
  "cited_by": 0,
  "doi": "10.1515/cdbme-2026-0216",
  "fulltext_url": "https://doi.org/10.1515/cdbme-2026-0216",
  "id": "f261y63gzx710",
  "issns": [
    "2364-5504"
  ],
  "landing_url": "https://doi.org/10.1515/cdbme-2026-0216",
  "language": "en",
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "lcc",
      "R"
    ],
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W7215127544",
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-26",
  "publisher": "De Gruyter",
  "ris": "https://research.draconitic.com/paper/f261y63gzx710.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T13:47:21Z",
      "native_id": "8c82d430b0a84dc78a7cbd03f1f5c048",
      "source": "doaj",
      "url": "https://doi.org/10.1515/cdbme-2026-0216"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2718|Artificial Intelligence in Healthcare and Education",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "The Radiology Sparring Partner: A PoC Study of Multi-Agentic Workflows for Clinical Decision Support and Teaching",
  "title_text": "The Radiology Sparring Partner: A PoC Study of Multi-Agentic Workflows for Clinical Decision Support and Teaching",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T13:47:21Z",
  "url": "https://research.draconitic.com/paper/f261y63gzx710",
  "venue": "Current Directions in Biomedical Engineering",
  "versions": []
}