Scholarlink

<p>Aneurysmal subarachnoid hemorrhage (aSAH) is a life-threatening condition, and accurate prediction of functional outcomes is critical for optimizing patient management within the initial 3 days of presentation. However, existing clinical scoring systems and imaging assessments do not fully capture clinical variability in predicting outcomes. We developed a deep learning model integrating pre- and postoperative noncontrast CT (NCCT) imaging with clinical data to predict 3-month modified Rankin Scale (mRS) scores in aSAH patients. Using data from 1850 patients across four hospitals, we constructed and validated five models: preoperative, postoperative, stacking imaging, clinical, and fusion models. The fusion model significantly outperformed the others (all <i>p</i>&lt;0.001), achieving a mean absolute error of 0.79 and an area under the curve of 0.92 in the external test. These findings demonstrate that this integrated deep learning model enables accurate prediction of 3-month outcomes and may serve as a prognostic support tool early in aSAH care.</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

Prediction of functional outcomes in aneurysmal subarachnoid hemorrhage using pre-/postoperative noncontrast CT within 3 days of admission

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年8月24日

查看全文
  • Pengzhan Yin,
  • Jiaqi Wang,
  • Chao Zhang,
  • Yongxiang Tang,
  • Xiankuo Hu,
  • Hongmin Shu,
  • Jun Wang,
  • Bin Liu,
  • Yongqiang Yu,
  • Yunfeng Zhou,
  • Xiaohu Li

摘要

Aneurysmal subarachnoid hemorrhage (aSAH) is a life-threatening condition, and accurate prediction of functional outcomes is critical for optimizing patient management within the initial 3 days of presentation. However, existing clinical scoring systems and imaging assessments do not fully capture clinical variability in predicting outcomes. We developed a deep learning model integrating pre- and postoperative noncontrast CT (NCCT) imaging with clinical data to predict 3-month modified Rankin Scale (mRS) scores in aSAH patients. Using data from 1850 patients across four hospitals, we constructed and validated five models: preoperative, postoperative, stacking imaging, clinical, and fusion models. The fusion model significantly outperformed the others (all p<0.001), achieving a mean absolute error of 0.79 and an area under the curve of 0.92 in the external test. These findings demonstrate that this integrated deep learning model enables accurate prediction of 3-month outcomes and may serve as a prognostic support tool early in aSAH care.