Department of Neurosurgery, The First Medical Center of Chinese PLA General Hospital, Beijing, China.
Department of Neurosurgery, Dongying People's Hospital, Dongying, China.
Brain Behav. 2021 May;11(5):e02085. doi: 10.1002/brb3.2085. Epub 2021 Feb 24.
Spontaneous intracerebral hemorrhage remains a major cause of death and disability throughout the world. We tried to establish accurate long-term outcome prediction models for hypertensive intracerebral hemorrhage (HICH) using CT radiomics and machine learning.
In a retrospective study of 270 patients with HICH between June 2013 and June 2018, CT images and patients' 6-month outcome based on the modified Rankin Scale were collected. Hematomas on CT images were selected as volumes of interests (VOIs), and 1,029 radiomics features of the VOIs were extracted. Based on correlations with patients' outcome, radiomics features underwent dimensionality reduction analyses. Then, the support vector machine (SVM), k-nearest neighbor (KNN), logistic regression (LR), decision tree (DT), random forest (RF), and XGBoost algorithms were applied with the screened features to establish prognostic prediction models of HICH. Accuracies of all models were compared.
Eighteen radiomics features were screened as prognosis-associated radiomics signature of HICH based on the variance threshold, SelectKBest, and least absolute shrinkage and selection operator (LASSO) regression models. Patients were randomly allocated into training (n = 215) and validation (n = 55) sets. Accuracies of all 6 machine learning algorithms in the validation set exceeded 80%. The sensitivity, specificity, and accuracy in the validation set were 93.3%, 92.5%, and 92.7% for the RF model and 92.3%, 88.1%, and 89.1% for the XGBoost model, respectively, which were the best two among all models.
Taking advantage of radiomics and machine learning, we established accurate prognostic prediction models of HICH. The RF model and XGBoost model returned the best accuracies.
自发性脑出血仍然是全世界死亡和残疾的主要原因。我们试图使用 CT 放射组学和机器学习为高血压性脑出血（HICH）建立准确的长期预后预测模型。
在 2013 年 6 月至 2018 年 6 月期间进行的一项回顾性研究中，共纳入了 270 例 HICH 患者，收集了他们的 CT 图像和 6 个月时根据改良 Rankin 量表（mRS）评估的预后结果。在 CT 图像上选择血肿作为感兴趣容积（VOI），并提取了 1029 个 VOI 的放射组学特征。根据与患者预后的相关性，对放射组学特征进行降维分析。然后，应用支持向量机（SVM）、k-最近邻（KNN）、逻辑回归（LR）、决策树（DT）、随机森林（RF）和 XGBoost 算法，结合筛选出的特征，建立 HICH 的预后预测模型。比较了所有模型的准确性。
基于方差阈值、SelectKBest 和最小绝对值收缩和选择算子（LASSO）回归模型，筛选出 18 个与 HICH 预后相关的放射组学特征作为预后相关的放射组学特征。患者被随机分配到训练集（n=215）和验证集（n=55）。在验证集中，所有 6 种机器学习算法的准确率均超过 80%。在验证集中，RF 模型的灵敏度、特异度和准确率分别为 93.3%、92.5%和 92.7%，XGBoost 模型的灵敏度、特异度和准确率分别为 92.3%、88.1%和 89.1%，这两个模型是所有模型中准确率最高的。
利用放射组学和机器学习，我们建立了 HICH 的准确预后预测模型。RF 模型和 XGBoost 模型的准确率最高。
