{
  "abstract": "High-performance brain-computer interfaces (BCIs) rely on stable neural representations, yet brain functional impairments inherently disrupt canonical encoding, creating a fundamental decoding paradox. Conventional data-driven approaches struggle to bridge this gap because of pathological data scarcity and heterogeneity. Here, we propose to leverage healthy neural priors and introduce Pathology-Aware Consensus Training (PACT), a paradigm embedding biophysical constraints into healthy neural recordings to guide neural decoding. In a gesture classification task using high-density electrocorticography from patients with gliomas infiltrating the motor cortex, PACT improved the accuracy by more than 10%, effectively restoring the distorted semantic geometry of motor commands and realigning them with healthy canonical representations (correlation increase: r = 0.66 to r = 0.94). Mechanistically, PACT induced an emergent \"inverse weighting\" strategy: The model autonomously suppresses high-power pathological noise while reanchoring spatial attention to functional compensatory regions. This study provides a proof of concept for improving decoding in compromised networks by harnessing healthy neural dynamics, laying the theoretical foundation for future BCI deployments in clinical populations.",
  "abstract_shown": true,
  "affiliations": [
    "National Clinical Research Center for Geriatric, West China Hospital of Sichuan University, Chengdu 610017, Sichuan, China.",
    "Med-X Center for Manufacturing, Sichuan University, Chengdu 610017, Sichuan, China.",
    "Department of Neurosurgery, West China Hospital of Sichuan University, No. 37 Guo Xue Xiang, Chengdu 610041, China.",
    "Laboratory for Neuro- and Psychophysiology, Department of Neurosciences, KU Leuven, Leuven 3000, Belgium.",
    "Department of Bioengineering, Imperial College of Science, Technology and Medicine, London SW7 2AZ, UK."
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 12,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Yihan Wu",
      "orcid": "0000-0003-2856-3203"
    },
    {
      "affs": [
        2
      ],
      "name": "Tao Chang",
      "orcid": "0000-0001-9050-8032"
    },
    {
      "affs": [
        2
      ],
      "name": "Siliang Chen",
      "orcid": "0000-0001-9598-5882"
    },
    {
      "affs": [
        2
      ],
      "name": "Yuxin Quan",
      "orcid": "0009-0003-0421-2254"
    },
    {
      "affs": [
        3
      ],
      "name": "Qiang Sun",
      "orcid": "0000-0002-1125-4706"
    },
    {
      "affs": [
        3
      ],
      "name": "Marc M. Van Hulle",
      "orcid": "0000-0003-1060-7044"
    },
    {
      "affs": [
        2
      ],
      "name": "Yanhui Liu",
      "orcid": "0000-0002-3722-3334"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Ning Jiang",
      "orcid": "0000-0003-1579-3114"
    },
    {
      "affs": [
        4
      ],
      "name": "Dario Farina",
      "orcid": "0000-0002-7883-2697"
    },
    {
      "affs": [
        2
      ],
      "name": "Yuan Yang",
      "orcid": "0000-0002-5724-6541"
    },
    {
      "affs": [
        2
      ],
      "name": "Qing Mao",
      "orcid": "0000-0001-6227-0397"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Jiayuan He",
      "orcid": "0000-0001-9915-2108"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/6bbqb96cmsa3b.bib",
  "cited_by": 0,
  "doi": "10.1126/sciadv.adx5564",
  "fulltext_url": "https://europepmc.org/articles/PMC13693691",
  "id": "6bbqb96cmsa3b",
  "issns": [
    "2375-2548"
  ],
  "landing_url": "https://www.science.org/doi/10.1126/sciadv.adx5564",
  "language": "eng",
  "licence": "CC-BY-NC",
  "licence_label": "CC BY-NC",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2805|EEG and Brain-Computer Interfaces"
    ]
  ],
  "openalex": "W7223383702",
  "pdf_url": "https://europepmc.org/articles/PMC13693691?pdf=render",
  "pmcid": "PMC13693691",
  "pmid": "42913013",
  "published": "2026-10-23",
  "publisher": "American Association for the Advancement of Science (AAAS)",
  "ris": "https://research.draconitic.com/paper/6bbqb96cmsa3b.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:41Z",
      "native_id": "10.1126/sciadv.adx5564",
      "source": "crossref",
      "url": "https://www.science.org/doi/10.1126/sciadv.adx5564"
    },
    {
      "first_seen": "2026-10-30T12:20:10Z",
      "native_id": "MED:42913013",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42913013"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "openalex:2805|EEG and Brain-Computer Interfaces",
      "subfield": "neuroscience"
    }
  ],
  "title": "Biophysically constrained learning from healthy neural priors improves motor decoding in pathological cortical networks",
  "title_text": "Biophysically constrained learning from healthy neural priors improves motor decoding in pathological cortical networks",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:20:10Z",
  "url": "https://research.draconitic.com/paper/6bbqb96cmsa3b",
  "venue": "Science Advances",
  "versions": []
}