{
  "abstract": "One-third of the world's 70 million people with epilepsy have seizures that are not controlled by medication; and implantable devices are an exciting option for treatment. These devices improve seizure control and can detect impending attacks, missed medication, and impaired cognition. Unfortunately, they have no way to share this information with their hosts in real-time - a limitation common to most medical devices. This is a missed opportunity for implants and wearables to learn from patients, focus on what matters most to them, and teach them how their behavior affects their health. Here, we present a device platform that converses with patients and learns to co-manage epilepsy. The inpatient prototype links scalp and intracranial EEG (electroencephalograms) to secure large language models that communicate freely and bidirectionally with their hosts through a smartphone app. An AI agent ingests biomarkers of sleep, medication level, cognition, and seizure risk extracted from brain activity. It converses with patients to inform them of clinical events and physiological trends, records their symptoms, responses, and behaviors, and automatically retrains itself to improve performance. Both patients and the AI agent can initiate conversations to teach each other and personalize interactions. We demonstrate this platform in 13 patients undergoing inpatient video-EEG monitoring for epilepsy and validate its performance. Algorithms for detecting seizures optimized their precision over several days without expert intervention - in contrast to the months of iterative, in-person physician programming currently required. Patients responded positively to messages regarding sleep, cognition, and seizure risk while rating the system as highly usable. The platform includes several safeguards, including a system for further algorithm fine-tuning using efficient expert review, and features that ensure data security and regulate communication content. Further work will link other biosensors to measure behavior, improve performance, and optimize therapeutic stimulation. We propose this system as a scalable platform for medical devices that can rapidly adapt to patient and provider needs; one that is broadly adaptable to improving care for many medical conditions.",
  "abstract_shown": true,
  "affiliations": [
    "Center for Health, Devices and Technology, University of Pennsylvania, Philadelphia, PA, USA. zackgold@engineering.upenn.edu",
    "Center for Neuroengineering and Therapeutics, University of Pennsylvania, Philadelphia, PA, USA. zackgold@engineering.upenn.edu",
    "Department of Bioengineering, School of Engineering and Applied Science, University of Pennsylvania, Philadelphia, PA, USA. zackgold@engineering.upenn.edu",
    "Center for Neuroengineering and Therapeutics, University of Pennsylvania, Philadelphia, PA, USA",
    "Department of Bioengineering, School of Engineering and Applied Science, University of Pennsylvania, Philadelphia, PA, USA",
    "Penn Medicine, University of Pennsylvania, Philadelphia, PA, USA",
    "Center for Healthcare Transformation and Innovation, University of Pennsylvania, Philadelphia, PA, USA",
    "Department of Neurology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA",
    "Department of Neuroscience, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA",
    "Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania, Philadelphia, PA, USA",
    "Center for Health, Devices and Technology, University of Pennsylvania, Philadelphia, PA, USA. littb@upenn.edu",
    "Center for Neuroengineering and Therapeutics, University of Pennsylvania, Philadelphia, PA, USA. littb@upenn.edu",
    "Department of Bioengineering, School of Engineering and Applied Science, University of Pennsylvania, Philadelphia, PA, USA. littb@upenn.edu",
    "Department of Neurology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA. littb@upenn.edu"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 17,
  "authors": [
    {
      "affs": [
        0,
        1,
        2
      ],
      "name": "Zack Goldblum",
      "orcid": "0000-0003-2803-7051"
    },
    {
      "affs": [
        3,
        4
      ],
      "name": "Haoer Shi",
      "orcid": "0009-0000-5273-8371"
    },
    {
      "affs": [
        3,
        4
      ],
      "name": "Zhongchuan Xu",
      "orcid": "0009-0009-5965-0802"
    },
    {
      "affs": [
        3,
        4
      ],
      "name": "William K.S. Ojemann",
      "orcid": "0009-0007-5166-536X"
    },
    {
      "affs": [
        3,
        4
      ],
      "name": "Carlos A. Aguila",
      "orcid": "0009-0003-9460-3549"
    },
    {
      "affs": [
        5
      ],
      "name": "Kevin W. Long",
      "orcid": "0000-0001-8881-2481"
    },
    {
      "affs": [
        6,
        3,
        7
      ],
      "name": "Kevin Xie",
      "orcid": "0000-0003-1849-2085"
    },
    {
      "affs": [
        3,
        8
      ],
      "name": "Kerry C. Nix",
      "orcid": "0000-0001-6595-0021"
    },
    {
      "affs": [
        3,
        4
      ],
      "name": "Katherine G. Walsh",
      "orcid": "0000-0002-4459-5507"
    },
    {
      "affs": [
        3,
        4
      ],
      "name": "Ellie Chang"
    },
    {
      "affs": [
        3
      ],
      "name": "Sarah B. Lavelle",
      "orcid": "0009-0000-8704-9445"
    },
    {
      "affs": [
        3
      ],
      "name": "Brandon Bach"
    },
    {
      "affs": [
        3,
        7
      ],
      "name": "Kathryn A. Davis",
      "orcid": "0000-0002-7020-6480"
    },
    {
      "affs": [
        3,
        9,
        7
      ],
      "name": "Nishant Sinha",
      "orcid": "0000-0002-2090-4889"
    },
    {
      "affs": [
        3,
        4,
        7
      ],
      "name": "Lauren H. Hammer",
      "orcid": "0000-0002-4045-490X"
    },
    {
      "affs": [
        3,
        7
      ],
      "name": "Erin C. Conrad",
      "orcid": "0000-0001-8910-1817"
    },
    {
      "affs": [
        10,
        11,
        12,
        13
      ],
      "name": "Brian Litt",
      "orcid": "0000-0003-2732-6927"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5v1g2j85q4v34.bib",
  "cited_by": 5,
  "doi": "10.1038/s41591-026-04680-4",
  "fulltext_url": null,
  "id": "5v1g2j85q4v34",
  "issns": [
    "1078-8956",
    "1546-170X",
    "1744-7933"
  ],
  "landing_url": "https://doi.org/10.1038/s41591-026-04680-4",
  "language": "en",
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2805|EEG and Brain-Computer Interfaces"
    ]
  ],
  "openalex": "W7221720041",
  "pdf_url": "https://www.nature.com/articles/s41591-026-04680-4.pdf",
  "pmcid": "PMC12870640",
  "pmid": "41646755",
  "published": "2026-10-13",
  "publisher": "Nature Portfolio",
  "ris": "https://research.draconitic.com/paper/5v1g2j85q4v34.ris",
  "sources": [
    {
      "first_seen": "2026-11-06T13:20:36Z",
      "native_id": "W7221720041",
      "source": "openalex",
      "url": "https://doi.org/10.1038/s41591-026-04680-4"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "openalex:2805|EEG and Brain-Computer Interfaces",
      "subfield": "neuroscience"
    }
  ],
  "title": "Human–artificial intelligence collaboration for comanaging epilepsy in real time",
  "title_text": "Human–artificial intelligence collaboration for comanaging epilepsy in real time",
  "type": "peer-reviewed",
  "updated_at": "2026-11-10T13:21:11Z",
  "url": "https://research.draconitic.com/paper/5v1g2j85q4v34",
  "venue": "Nature Medicine",
  "versions": []
}