Scholarlink

Objectives <p>To compare machine learning models using different combinations of clinical and imaging variables for classifying ischemic stroke patients as having an onset-to-imaging (OTI) time within or beyond 4.5 h.</p> Materials and methods <p>We analyzed 993 patients with known OTI time from the MR CLEAN Registry and LATE trial. Data were split into training and test sets (80:20). We developed models using various combinations of variables to classify OTI time, including clinical-radiological information, and variables automatically extracted from segmented ischemic regions on non-contrast CT, such as net water uptake (NWU), lesion volume, and radiomics features. Performance was assessed using the area under the receiver operating characteristic curve (AUC).</p> Results <p>Of 993 patients, 199 (20%) presented beyond 4.5 h. The model including only clinical-radiological scores, and the one including only NWU, achieved an AUC of 0.65. Performance was higher for models that included NWU combined with lesion volume or clinical-radiological scores (AUCs ranging from 0.70 to 0.75). Radiomics-based models achieved the highest performance with AUCs of 0.81, significantly outperforming NWU-based models. Key predictors for identifying patients beyond 4.5 h included homogeneous lesion textures in both core and hypoperfused areas, smaller hypoperfused area volumes, higher core NWU, and lower baseline NIHSS scores.</p> Conclusion <p>We found that radiomics-based models outperform models including NWU measurements for classifying stroke OTI time in this endovascular therapy population. The superior performance suggests that texture, shape, and intensity patterns of ischemic lesions may capture more information about lesion age than single metrics like NWU. External validation in broader stroke populations is needed to establish clinical utility.</p> Key Points <p><Emphasis Type="BoldItalic">Question</Emphasis> <i>Which combinations of clinical and CT-derived variables enable the most accurate classification of stroke onset time within versus beyond 4.5</i> <i>h using machine learning?</i></p> <p><Emphasis Type="BoldItalic">Findings</Emphasis> <i>Models using radiomics features achieved superior accuracy (AUC 0.81) compared to models using net water uptake measurements (AUC 0.65) for onset time classification</i>.</p> <p><Emphasis Type="BoldItalic">Clinical relevance</Emphasis> <i>Automated CT-based radiomics models enable accurate stroke onset time classification without advanced imaging, potentially expanding treatment options for patients with unknown symptom onset times in centers lacking MRI capabilities</i>.</p> Graphical Abstract <p></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

Machine learning models for CT-based classification of ischemic stroke onset time within or beyond 4.5 h: a comparison of approaches

  • 期刊论文

  • 发表日期：

    2025年12月8日

查看全文
  • Laura M. van Poppel,
  • Lucas de Vries,
  • Mahsa Mojtahedi,
  • Manon Kappelhof,
  • Susanne G. H. Olthuis,
  • Robert van Oostenbrugge,
  • Wim H. van Zwam,
  • Pieter Jan van Doormaal,
  • Ludo F. M. Beenen,
  • Yvo B. W. E. M. Roos,
  • Charles B. L. M. Majoie,
  • Henk A. Marquering,
  • Bart J. Emmer

摘要

Objectives

To compare machine learning models using different combinations of clinical and imaging variables for classifying ischemic stroke patients as having an onset-to-imaging (OTI) time within or beyond 4.5 h.

Materials and methods

We analyzed 993 patients with known OTI time from the MR CLEAN Registry and LATE trial. Data were split into training and test sets (80:20). We developed models using various combinations of variables to classify OTI time, including clinical-radiological information, and variables automatically extracted from segmented ischemic regions on non-contrast CT, such as net water uptake (NWU), lesion volume, and radiomics features. Performance was assessed using the area under the receiver operating characteristic curve (AUC).

Results

Of 993 patients, 199 (20%) presented beyond 4.5 h. The model including only clinical-radiological scores, and the one including only NWU, achieved an AUC of 0.65. Performance was higher for models that included NWU combined with lesion volume or clinical-radiological scores (AUCs ranging from 0.70 to 0.75). Radiomics-based models achieved the highest performance with AUCs of 0.81, significantly outperforming NWU-based models. Key predictors for identifying patients beyond 4.5 h included homogeneous lesion textures in both core and hypoperfused areas, smaller hypoperfused area volumes, higher core NWU, and lower baseline NIHSS scores.

Conclusion

We found that radiomics-based models outperform models including NWU measurements for classifying stroke OTI time in this endovascular therapy population. The superior performance suggests that texture, shape, and intensity patterns of ischemic lesions may capture more information about lesion age than single metrics like NWU. External validation in broader stroke populations is needed to establish clinical utility.

Key Points

Question Which combinations of clinical and CT-derived variables enable the most accurate classification of stroke onset time within versus beyond 4.5 h using machine learning?

Findings Models using radiomics features achieved superior accuracy (AUC 0.81) compared to models using net water uptake measurements (AUC 0.65) for onset time classification.

Clinical relevance Automated CT-based radiomics models enable accurate stroke onset time classification without advanced imaging, potentially expanding treatment options for patients with unknown symptom onset times in centers lacking MRI capabilities.

Graphical Abstract