The value of radiomics-based hyperdense middle cerebral artery sign in predicting hemorrhagic transformation in acute ischemic stroke patients undergoing endovascular treatment
2024

Predicting Hemorrhagic Transformation in Stroke Patients Using Radiomics

Sample size: 118 publication 10 minutes Evidence: moderate

Author Information

Author(s): Gong Chundan, Liu Yun, Ma Wei, Jing Yang, Liu Li, Huang Yan, Yang Jinlin, Feng Chen, Fang Yuan, Fang Weidong

Primary Institution: The First Affiliated Hospital of Chongqing Medical University

Hypothesis

Can a model based on hyperdense middle cerebral artery sign (HMCAS) radiomics features predict hemorrhagic transformation in acute ischemic stroke patients undergoing endovascular treatment?

Conclusion

HMCAS-based radiomics is expected to be a reliable tool for predicting hemorrhagic transformation risk in acute ischemic stroke patients after endovascular treatment.

Supporting Evidence

  • 71 out of 118 patients developed hemorrhagic transformation after treatment.
  • The combined model showed improved predictive performance with an AUC of 0.911.
  • ASPECTS was identified as the only independent predictor among various clinical and radiological variables.

Takeaway

Doctors can use special imaging techniques to better predict if stroke patients will have complications after treatment.

Methodology

A retrospective study was conducted on patients with acute ischemic stroke who underwent endovascular treatment, using radiomics features from non-contrast CT scans to develop predictive models.

Potential Biases

Data selection bias may affect the results due to the retrospective nature of the study.

Limitations

The study is retrospective, has a small sample size, and lacks independent external validation.

Participant Demographics

Patients were adults aged 18 and older with acute anterior circulation large vessel occlusion.

Statistical Information

P-Value

0.039

Confidence Interval

95% CI 0.797–0.935

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.3389/fneur.2024.1492089

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication