Preliminary study on prediction of hematoma expansion in hypertensive intracerebral hemorrhage based on cranial radiomics

Chuan Ding; Xiaohu Li; Jun Wang; Hongwen Li; Yuping Wang; Changliang Yu; Yaqiong Ge; Haibao Wang; Bin Liu

Return

Preliminary study on prediction of hematoma expansion in hypertensive intracerebral hemorrhage based on cranial radiomics

Author: Chuan Ding ¹ ; Xiaohu Li ¹ ; Jun Wang ¹ ; Hongwen Li ¹ ; Yuping Wang ¹ ; Changliang Yu ¹ ; Yaqiong Ge ² ; Haibao Wang ¹ ; Bin Liu ¹
Author Information

1. Dept of Radiology, The First Afiliated Hospital of Anhui Medical University,Hefei 230022
2. GE Healthcare(China) ,Shanghai 210000
Publication Type:Journal Article
Keywords: cerebral hemorrhage; hematoma enlargement; radiomics; prediction model
From: Acta Universitatis Medicinalis Anhui 2022;57(1):161-164
CountryChina
Language:Chinese
Abstract: Objective :To study the best machine learning method for early prediction of hematoma expansion in hypertensive intracerebral hemorrhage based on head CT plain scan.
Methods :The CT images of 130 patients with cerebral hemorrhage were retrospectively analyzed , and the texture features of the head CT plain scan were extracted. The classifier was trained by selecting the features , and the six classic machine learning methods were crossvalidated to evaluate the stability and performanceof predicting cerebral hemorrhage hematoma expansion.
Results:The prediction performance of support vector machine (SVM⁃Radial) (AUC 0. 714 ± 0. 144 , accuracy 0. 723 ± 0. 109) , generalized linear model ( GLM) prediction performance ( AUC 0. 643 ± 0. 125 , accuracy 0. 587 ± 0. 136) , random forest (RF) prediction performance (AUC 0. 686 ± 0. 128 , accuracy 0. 680 ± 0. 130) , k ⁃nearest neighbor (kNN) prediction performance ( AUC 0. 657 ± 7C 15 , accuracy 0. 639 ± 39 performance 19) , gradient boosting tree algorithm (GBM) Prediction performance ( AUC 0. 718 ± 0. 141 , accuracy 0. 670 ± 0. 126) , neural network (NNet) prediction performance (AUC 0. 659 ± 0. 162 , accuracy 0. 680 ± 0. 130) , in which support vector machines showed high prediction performance , generalized linear model showed low predictive performance.
Conclusion: Among the six machine learning methods based on cranial CT radiomics to predict early hematoma expansion in hypertensive intracerebral hemorrhage , support vector machine (SVM⁃Radial) has the best predictive performance and has potential clinical application value.
Full text:2024120417060874947基于CT放射组学预测高血压性脑出血血肿扩大的研究_丁川.pdf