Scholarlink

<p>Implantable neurotechnologies are increasingly used to reduce seizure burden in pediatric&#xa0;epilepsy. Vagus nerve stimulation (VNS), the most common option, is effective for only half of patients, with no means to predict outcome prior to surgery. As a result, many children undergo invasive and costly procedures without benefit. Although T1-weighted magnetic resonance imaging (T1w) is routinely acquired presurgically and may capture structural brain differences relevant to treatment outcome, its high dimensionality relative to sample sizes has limited its utility in predictive modelling. To address this challenge, we present VQ-VNS, a deep representation learning model to predict VNS outcome based on preoperative T1w (<i>n</i> = 263). First, we present data from the largest paediatric VNS cohort (<i>n</i> = 1046), wherein presurgical clinical data could not predict response (AUC 0.54,<i>p</i> &gt; 0.99). Next, VQ-VNS was pretrained on 7433 T1w images to learn compact anatomical representations enabling its classifier to predict VNS response (AUC = 0.73,<i>p</i> = 0.007). Model predictions localized to serotonin-rich brain regions and inferred large-scale disruptions in network connectivity among non-responders. This biologically interpretable predictor based on routine structural imaging improves upon current clinical decision-making.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A deep representation learning model to predict response to vagus nerve stimulation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月7日

查看全文
  • Hrishikesh Suresh,
  • Karim Mithani,
  • Vicki Li,
  • Timur H. Latypov,
  • Nebras M. Warsi,
  • Simeon M. Wong,
  • Lauren Erdman,
  • Jaeyoung Kang,
  • Jurgen Germann,
  • Flavia Venetucci Gouveia,
  • Sebastian C. Coleman,
  • Alexandre Berger,
  • Vann Chau,
  • Shelly Weiss,
  • Carolina Gorodetsky,
  • Elizabeth Donner,
  • Alexander G. Weil,
  • Jignesh Tailor,
  • Taylor J. Abel,
  • Madison Remick,
  • Emefa Akwayena,
  • Dewi Schrader,
  • Robert J. Bollo,
  • Matthew D. Smyth,
  • Diana Aum,
  • Sean M. Lew,
  • Shelly Wang,
  • Toba N. Niazi,
  • Aria Fallah,
  • Jeffrey S. Raskin,
  • Howard L. Weiner,
  • Nisha Gadgil,
  • Gregory W. Albert,
  • Aristides Hadjinicolaou,
  • Philippe Major,
  • Farbod Niazi,
  • Guillaume Theaud,
  • Sami Obaid,
  • Elysa Widjaja,
  • Birgit Ertl-Wagner,
  • Logi Vidarsson,
  • Margot J. Taylor,
  • Alexandre Boutet,
  • James T. Rutka,
  • Melissa A. LoPresti,
  • Puneet Jain,
  • George M. Ibrahim

摘要

Implantable neurotechnologies are increasingly used to reduce seizure burden in pediatric epilepsy. Vagus nerve stimulation (VNS), the most common option, is effective for only half of patients, with no means to predict outcome prior to surgery. As a result, many children undergo invasive and costly procedures without benefit. Although T1-weighted magnetic resonance imaging (T1w) is routinely acquired presurgically and may capture structural brain differences relevant to treatment outcome, its high dimensionality relative to sample sizes has limited its utility in predictive modelling. To address this challenge, we present VQ-VNS, a deep representation learning model to predict VNS outcome based on preoperative T1w (n = 263). First, we present data from the largest paediatric VNS cohort (n = 1046), wherein presurgical clinical data could not predict response (AUC 0.54,p > 0.99). Next, VQ-VNS was pretrained on 7433 T1w images to learn compact anatomical representations enabling its classifier to predict VNS response (AUC = 0.73,p = 0.007). Model predictions localized to serotonin-rich brain regions and inferred large-scale disruptions in network connectivity among non-responders. This biologically interpretable predictor based on routine structural imaging improves upon current clinical decision-making.