{
  "abstract": "Confirmatory labels for Parkinson’s disease (PD), from expert examination or, prospectively, biological assays, are costly, and missed cases and false alarms carry unequal consequences. ClinRisk-LLM is a framework for label-efficient, cost-aware learning from gait and speech signals in which a large language model (LLM) translates a predefined safety specification into a frozen policy setting the positive-class weight of a support vector machine and the priority of potential missed cases for annotation. Cost-sensitive training, risk-aware querying and the LLM policy were ablated on gait (n=165) and speech (n=252) data and benchmarked against post hoc thresholding, a refer-all policy, held-out gait studies and an independent speech cohort. With half of the labels, cost-sensitive active learning reduced the 4:1 asymmetric cost by 34.1% (gait) and 5.7% (speech) relative to standard active learning, at the expense of specificity. ClinRisk-LLM translated the predefined safety specification into a frozen, auditable policy that adjusted risk settings during label acquisition. Component-wise analyses indicated that classifier weighting accounted for most of the observed cost reduction, while the incremental benefit of LLM-guided adaptation varied across datasets and comparison settings. A threshold-tuned symmetric model came within 1.3 cost points for gait, and gait remained roughly level with referring everyone. ClinRisk-LLM reached a gait cost of 47.60 versus 46.10 for fixed cost-sensitive learning; 40 policies generated across three LLMs from a reconstructed specification yielded gait costs of 52.1–75.8. Applications to molecular triage remain prospective. Code and data availability details are provided in the Data Availability Statement.",
  "abstract_shown": true,
  "affiliations": [
    "Faculty of Medicine, Istanbul Atlas University, Istanbul 34408, Türkiye",
    "Department of Software Engineering, Faculty of Engineering and Natural Sciences, Istanbul Atlas University, Istanbul 34408, Türkiye"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Burcu Gülez",
      "orcid": "0000-0002-2939-8388"
    },
    {
      "affs": [
        1
      ],
      "name": "Ali Güneş",
      "orcid": "0000-0003-3116-1184"
    },
    {
      "affs": [
        0
      ],
      "name": "Ersoy Kocabıçak",
      "orcid": "0000-0002-7989-5550"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/fnxy64nk3gft1.bib",
  "cited_by": 0,
  "doi": "10.3390/ijms27219542",
  "fulltext_url": null,
  "id": "fnxy64nk3gft1",
  "issns": [
    "1422-0067"
  ],
  "landing_url": "https://www.mdpi.com/1422-0067/27/21/9542",
  "language": null,
  "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": [
    [
      "openalex",
      "1702|Machine Learning and Algorithms"
    ]
  ],
  "openalex": "W7223960568",
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-25",
  "publisher": "MDPI AG",
  "ris": "https://research.draconitic.com/paper/fnxy64nk3gft1.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:57Z",
      "native_id": "10.3390/ijms27219542",
      "source": "crossref",
      "url": "https://www.mdpi.com/1422-0067/27/21/9542"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "issn:1422-0067",
      "subfield": "general"
    }
  ],
  "title": "LLM-Guided Adaptive Cost Calibration in Active Learning for Parkinson’s Disease Biosignals",
  "title_text": "LLM-Guided Adaptive Cost Calibration in Active Learning for Parkinson’s Disease Biosignals",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:18:57Z",
  "url": "https://research.draconitic.com/paper/fnxy64nk3gft1",
  "venue": "International Journal of Molecular Sciences",
  "versions": []
}