{
  "abstract": "Introduction: Pharmacotherapy optimization in multimorbid patients is increasingly complex due to polypharmacy, fragmented data, expanding electronic health records, and workforce constraints. Conventional clinical decision support systems remain largely rule-based and often fail to adequately incorporate patient-specific context. While artificial intelligence offers new opportunities, stand-alone models remain insufficiently reliable for high-risk pharmacotherapy decision support.\n\nAim: To develop a relevance-driven, clinician-supervised hybrid AI framework for pharmacotherapy optimization.\n\nMethod: Using a design science-informed approach, an interdisciplinary research group developed a conceptual framework for AI-supported pharmacotherapy optimization. Framework development was informed by prior feasibility work, published literature, clinical practice requirements, and iterative interdisciplinary discussions. Hybrid AI was defined as the combination of retrieval-augmented generation, deterministic safety rules, and large language model reasoning.\n\nResults: Seven design principles were identified, including decomposition of clinical activities, relevance-based prioritization, hybrid reasoning under clinician oversight, integration of patient goals, transparency of evidence sources, longitudinal optimization within a governed closed loop, and evaluation as a design requirement. These principles informed a conceptual architecture integrating structured clinical data, patient preferences, longitudinal patient information, and evidence retrieval within a clinician-governed decision-support framework.\n\nConclusion: The proposed framework conceptualizes AI as a relevance-structuring, clinician-governed decision-support layer rather than an autonomous decision-maker. By combining hybrid reasoning, patient-specific context, and professional oversight, it provides a conceptual foundation for future development, implementation, and evaluation of AI-supported pharmacotherapy systems.",
  "abstract_shown": true,
  "affiliations": [
    "Institute of Pharmacy, Pharmaceutical Biology and Clinical Pharmacy, Paracelsus Medical University, Strubergasse 15, 5020 Salzburg, Austria",
    "Center of Public Health and Health Services Research, Paracelsus Medical University, Strubergasse 21, 5020 Salzburg, Austria",
    "Vorarlberg Institute for Vascular Investigation and Treatment (VIVIT), Carinagasse 47, 6800 Feldkirch, Austria",
    "Institute for Process Management and Digital Transformation (IPD), FH Münster, Corrensstraße 25, 48149 Münster, Germany",
    "University of Applied Sciences of Upper Austria, Softwarepark 11, 4232 Hagenberg, Austria",
    "Faculty of Medicine, Division of Pharmacy, University of Pristina, Str. Bulevardi I Dëshmorëve, 10000 Prishtina, Republic of Kosovo"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 9,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Olaf Rose",
      "orcid": "0000-0003-1681-4909"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Stephanie Clemens",
      "orcid": "0000-0002-8788-9329"
    },
    {
      "affs": [
        2
      ],
      "name": "Andreas Leiherer",
      "orcid": "0000-0003-3776-5704"
    },
    {
      "affs": [
        3
      ],
      "name": "Michael Bücker"
    },
    {
      "affs": [
        3
      ],
      "name": "Finn Petersson"
    },
    {
      "affs": [
        4
      ],
      "name": "Gerald Lirk"
    },
    {
      "affs": [
        0
      ],
      "name": "Christopher Mosch"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Johanna Pachmayr"
    },
    {
      "affs": [
        5
      ],
      "name": "Kreshnik Hoti",
      "orcid": "0000-0001-7652-6074"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/a1a64mfc9z2ns.bib",
  "cited_by": 1,
  "doi": "10.1007/s11096-026-02205-0",
  "fulltext_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13731693/",
  "id": "a1a64mfc9z2ns",
  "issns": [
    "2210-7703",
    "2210-7711"
  ],
  "landing_url": "https://doi.org/10.1007/s11096-026-02205-0",
  "language": "en",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Research"
    ],
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W7203864728",
  "pdf_url": "https://link.springer.com/content/pdf/10.1007/s11096-026-02205-0.pdf",
  "pmcid": "PMC13731693",
  "pmid": "42627626",
  "published": "2026-08-21",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/a1a64mfc9z2ns.ris",
  "sources": [
    {
      "first_seen": "2026-11-08T12:21:50Z",
      "native_id": "PMC13731693",
      "source": "pmc",
      "url": "https://doi.org/10.1007/s11096-026-02205-0"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2718|Artificial Intelligence in Healthcare and Education",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "Development of a hybrid artificial intelligence framework for pharmacotherapy optimization",
  "title_text": "Development of a hybrid artificial intelligence framework for pharmacotherapy optimization",
  "type": "peer-reviewed",
  "updated_at": "2026-11-08T12:21:50Z",
  "url": "https://research.draconitic.com/paper/a1a64mfc9z2ns",
  "venue": "International Journal of Clinical Pharmacy",
  "versions": []
}