{
  "abstract": "Background: Large language models (LLMs) are increasingly being used as clinical support tools, yet their performance in Parkinson's disease (PD) management remains insufficiently characterized.\n\nMethods: We evaluated a general-purpose LLM (Gemini 1.5 Pro) and a medically specialized LLM (OpenEvidence) using 45 synthetic PD vignettes requiring generative assessment and management recommendations. Responses were independently rated by two movement disorders fellows using predefined 5-point Likert scales, with adjudication by a senior specialist when required.\n\nResults: Both models demonstrated generally good performance in clinical assessment, whereas management recommendations were less reliable. A modest numerical advantage was observed for the medically specialized model across assessment, plan, and composite outcomes, although no statistically significant differences were identified. Qualitative analysis showed that clinically relevant errors occurred in both models, predominantly reflecting treatment strategy errors.\n\nConclusions: These findings suggest that, in the specific model versions evaluated, LLMs may support clinical reasoning in PD, but require cautious interpretation, particularly for treatment recommendations.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Neurology and Neurosurgery, Montreal Neurological Institute, McGill University, Montreal, Canada",
    "Montreal Neurological Hospital, McGill University Centre, Montreal, QC, Canada",
    "Integrated Program in Neuroscience, McGill University, Montreal, Canada",
    "Research Institute of the McGill University Health Centre, Montreal, Canada"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Yosef Shechter"
    },
    {
      "affs": [
        0
      ],
      "name": "Raymond Klevor"
    },
    {
      "affs": [
        1,
        2
      ],
      "name": "Trycia Kouchache"
    },
    {
      "affs": [
        0
      ],
      "name": "Sarah Bouhadoun"
    },
    {
      "affs": [
        0,
        3
      ],
      "name": "Ronald B. Postuma"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/b04rmf8w3vrkf.bib",
  "cited_by": 0,
  "doi": "10.1016/j.prdoa.2026.100517",
  "fulltext_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13757504/",
  "id": "b04rmf8w3vrkf",
  "issns": [
    "2590-1125"
  ],
  "landing_url": "https://doi.org/10.1016/j.prdoa.2026.100517",
  "language": "en",
  "licence": "CC-BY-NC-ND-4.0",
  "licence_label": "CC BY-NC-ND 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Original Article"
    ],
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W7161768836",
  "pdf_url": null,
  "pmcid": "PMC13757504",
  "pmid": "43023049",
  "published": "2026-11-02",
  "publisher": "Elsevier",
  "ris": "https://research.draconitic.com/paper/b04rmf8w3vrkf.ris",
  "sources": [
    {
      "first_seen": "2026-11-16T12:23:07Z",
      "native_id": "PMC13757504",
      "source": "pmc",
      "url": "https://doi.org/10.1016/j.prdoa.2026.100517"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2718|Artificial Intelligence in Healthcare and Education",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "Benchmarking general and medical LLM performance in Parkinson's disease management",
  "title_text": "Benchmarking general and medical LLM performance in Parkinson's disease management",
  "type": "peer-reviewed",
  "updated_at": "2026-11-16T12:23:07Z",
  "url": "https://research.draconitic.com/paper/b04rmf8w3vrkf",
  "venue": "Clinical Parkinsonism & Related Disorders",
  "versions": []
}