文献速递医学人工智能与信息学临床试验与 GCP基础与转化研究

人机协作实时共管癫痫:基于大语言模型的设备平台

Human-artificial intelligence collaboration for comanaging epilepsy in real time.
PubMed 文献 · Nat Med · 2026-10-13

作者开发住院原型平台,将头皮和颅内脑电图经安全大语言模型AI与智能手机应用双向通信,处理睡眠、用药、认知和发作概率等生物标志物并记录反馈以重训发作检测器。在13例视频脑电监测患者中验证,模拟显示仅凭患者反馈即可提升检测精确度。

要点

  • 平台连接头皮/颅内脑电与安全大语言模型AI,经手机应用双向沟通。
  • AI处理睡眠、用药、认知和发作概率等标志物,记录症状并反馈重训检测器。
  • 13例视频脑电监测患者验证,模拟中患者反馈提升检测精确度。

核心结论

  • 该人机协作平台可在住院环境下实时与癫痫患者沟通并利用反馈改进发作检测。

研究设计与样本

  • 住院原型设备平台,连接头皮和颅内脑电至安全的大语言模型AI,经智能手机应用双向通信。
  • 在13例因癫痫接受视频脑电监测的患者中验证(头皮n=11,颅内n=2)。

主要发现

  • AI处理睡眠、用药、认知和发作概率等生物标志物,通知患者临床事件和趋势,记录症状和反应。
  • AI利用患者反馈重训发作检测器,减少误报。
  • 在伪前瞻性模拟中,仅凭患者反馈、无需专家干预,发作检测器精确度即得到提升。

临床怎么用

  • 该系统被提出作为可扩展、有安全保障的医疗设备平台,可快速适应癫痫及其他疾病中患者和提供者的需求。

局限性

  • 验证为住院原型和伪前瞻性模拟,非真实世界前瞻性研究。
  • 样本量13例,头皮11例、颅内2例。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

One-third of the world's 70 million people with epilepsy have seizures uncontrolled by medication, and implantable devices are a promising treatment. These devices can detect impending seizures, missed medication and impaired cognition, but, like most medical devices, they cannot share this information with patients in real time. This is a missed opportunity for devices to learn from clinical events and teach patients how their behaviors affect their health. Here we present a device platform that converses with patients to help them manage their epilepsy. The inpatient prototype links scalp and intracranial electroencephalography (EEG) to a secure, large language model-based artificial intelligence (AI) that communicates bidirectionally through a smartphone app. The AI processes biomarkers of sleep, medication, cognition and seizure probability, notifies patients of clinical events and trends, records symptoms and responses, and uses their feedback to retrain its seizure detector, reducing false alarms. We validated this platform in 13 patients who are undergoing video-EEG monitoring for epilepsy (scalp, n = 11; intracranial, n = 2). In a pseudoprospective simulation, seizure detectors improved precision from patient feedback alone, without expert intervention. We propose this system as a scalable, safeguarded platform for medical devices that can rapidly adapt to patient and provider needs across epilepsy and other medical conditions.

来源:Nat Med,查看原文。版权归原作者所有。

引用

  1. Goldblum Z, Shi H, Xu Z, et al. Human-artificial intelligence collaboration for comanaging epilepsy in real time. Nat Med. 2026. PMID: 42869994. doi:10.1038/s41591-026-04680-4

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。