{
  "abstract": "In medicine, the laborious annotation process poses a significant limitation to the creation of large labelled datasets, a challenge that is particularly pronounced for medical video data, where numerous frames require expert annotation. Weakly supervised approaches, such as Multiple Instance Learning (MIL), offer a promising solution by leveraging only video-level labels rather than frame-by-frame annotations. In this work, we tailor a top-k MIL-based approach to medical video data to detect and localise facial motor tics in videos of patients diagnosed with Gilles de la Tourette Syndrome (GTS). Our adaptations include a score-driven top-k instance selection strategy that accounts for variability in tic occurrence between subjects. This enables the effective exploitation of large unlabelled datasets by incorporating weak labels where available. Evaluated against state-of-the-art MIL models, the proposed approach achieves the highest instance-level tic detection performance, with an area under the curve of 86.73 %. These results demonstrate that facial motor tics in videos of individuals with GTS can be effectively localised using only weak video-level annotations, highlighting the potential of the proposed approach for future clinical applications.",
  "abstract_shown": true,
  "affiliations": [
    "German Research Center for Artificial Intelligence, Lübeck, Germany",
    "Institute of Systems Motor Science, University of Luebeck, Lübeck, Germany",
    "Department of Neurology, University Hospital Medical Center Schleswig-Holstein, Lübeck, Germany",
    "Cognitive Neurophysiology, Department of Child and Adolescent Psychiatry, Faculty of Medicine, TU Dresden, Dresden, Germany",
    "Cognitive Psychology, Faculty of Psychology, Shandong Normal University, Jinan, China",
    "Fraunhofer Research Institution for Individualized and Cell-Based Medical Engineering (IMTE), Lübeck, Germany",
    "Section for Clinical Research IT (SKFIT), Institute of Medical Biometry and Statistics, University of Luebeck, Lübeck, Germany",
    "Institute of Medical Informatics, University of Luebeck, Lübeck, Germany"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 9,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Nele Sophie Brügge",
      "orcid": "0009-0006-2039-423X"
    },
    {
      "affs": [
        0
      ],
      "name": "Frédéric Li",
      "orcid": "0000-0003-2110-4207"
    },
    {
      "affs": [
        1
      ],
      "name": "Ronja Schappert",
      "orcid": "0000-0002-4738-5310"
    },
    {
      "affs": [
        1,
        2
      ],
      "name": "Gesine Marie Sallandt"
    },
    {
      "affs": [
        3,
        4
      ],
      "name": "Christian Beste",
      "orcid": "0000-0002-2989-9561"
    },
    {
      "affs": [
        5,
        6
      ],
      "name": "Sebastian Fudickar",
      "orcid": "0000-0002-3553-5131"
    },
    {
      "affs": [
        0,
        7
      ],
      "name": "Marcin Grzegorzek",
      "orcid": "0000-0003-4877-8287"
    },
    {
      "affs": [
        1
      ],
      "name": "Alexander Münchau",
      "orcid": "0000-0002-3219-2284"
    },
    {
      "affs": [
        0,
        7
      ],
      "name": "Heinz Handels",
      "orcid": "0000-0002-3499-4328"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/dsavj0vm6p63s.bib",
  "cited_by": 0,
  "doi": "10.1007/s41666-026-00233-z",
  "fulltext_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13719929/?tool=EBI",
  "id": "dsavj0vm6p63s",
  "issns": [
    "2509-4971",
    "2509-498X"
  ],
  "landing_url": "https://europepmc.org/article/PMC/PMC13719929",
  "language": "eng",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Research"
    ],
    [
      "openalex",
      "3203|Obsessive-Compulsive Spectrum Disorders"
    ]
  ],
  "openalex": "W7171813995",
  "pdf_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13719929/pdf/?tool=EBI",
  "pmcid": "PMC13719929",
  "pmid": "42964513",
  "published": "2026-07-30",
  "publisher": "Springer",
  "ris": "https://research.draconitic.com/paper/dsavj0vm6p63s.ris",
  "sources": [
    {
      "first_seen": "2026-10-31T12:21:45Z",
      "native_id": "PMC:PMC13719929",
      "source": "europepmc",
      "url": "https://europepmc.org/article/PMC/PMC13719929"
    },
    {
      "first_seen": "2026-11-02T12:23:48Z",
      "native_id": "PMC13719929",
      "source": "pmc",
      "url": "https://doi.org/10.1007/s41666-026-00233-z"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:3203|Obsessive-Compulsive Spectrum Disorders",
      "subfield": "psychiatry"
    }
  ],
  "title": "Weakly-Supervised Detection of Facial Motor Tics in Video Data Using Score-Driven Top-k Multiple Instance Learning",
  "title_text": "Weakly-Supervised Detection of Facial Motor Tics in Video Data Using Score-Driven Top-k Multiple Instance Learning",
  "type": "peer-reviewed",
  "updated_at": "2026-11-03T12:20:54Z",
  "url": "https://research.draconitic.com/paper/dsavj0vm6p63s",
  "venue": "Journal of healthcare informatics research",
  "versions": []
}