Abstract：
OBJECTIVE: To construct a clinical noncontrastive computed tomography (NCCT) deep learning joint model for predicting early hematoma expansion (HE) after cerebral hemorrhage (sICH) and evaluate its predictive performance.
METHODS: All 254 patients with primary cerebral hemorrhage from January 2017 to December 2022 in the General Hospital of the Western Theater Command were included. According to the criteria of hematoma enlargement exceeding 33% or the volume exceeding 6 ml, the patients were divided into the HE group and the hematoma non-enlargement (NHE) group. Multiple models and the 10-fold cross-validation method were used to screen the most valuable features and model the probability of predicting HE. The area under the curve (AUC) was used to analyze the prediction efficiency of each model for HE.
RESULTS: They were randomly divided into a training set of 204 cases in an 8:2 ratio and 50 cases of the test set. The clinical imaging deep feature joint model (22 features) predicted the area under the curve of HE as follows: clinical Navie Bayes model AUC 0.779, traditional radiology logistic regression (LR) model AUC 0.818, deep learning LR model AUC 0.873, and clinical NCCT deep learning multilayer perceptron model AUC 0.921.
CONCLUSIONS: The combined clinical imaging deep learning model has a high predictive effect for early HE in sICH patients, which is helpful for clinical individualized assessment of the risk of early HE in sICH patients.
METHODS: All 254 patients with primary cerebral hemorrhage from January 2017 to December 2022 in the General Hospital of the Western Theater Command were included. According to the criteria of hematoma enlargement exceeding 33% or the volume exceeding 6 ml, the patients were divided into the HE group and the hematoma non-enlargement (NHE) group. Multiple models and the 10-fold cross-validation method were used to screen the most valuable features and model the probability of predicting HE. The area under the curve (AUC) was used to analyze the prediction efficiency of each model for HE.
RESULTS: They were randomly divided into a training set of 204 cases in an 8:2 ratio and 50 cases of the test set. The clinical imaging deep feature joint model (22 features) predicted the area under the curve of HE as follows: clinical Navie Bayes model AUC 0.779, traditional radiology logistic regression (LR) model AUC 0.818, deep learning LR model AUC 0.873, and clinical NCCT deep learning multilayer perceptron model AUC 0.921.
CONCLUSIONS: The combined clinical imaging deep learning model has a high predictive effect for early HE in sICH patients, which is helpful for clinical individualized assessment of the risk of early HE in sICH patients.
摘要：
目的：构建脑出血（sICH）后早期血肿扩大（HE）的临床非对比计算机断层扫描（NCCT）深度学习联合模型，并评估其预测性能。
方法：纳入2017年1月至2022年12月西部战区总医院收治的254例原发性脑出血患者。根据血肿扩大超过33%或体积超过6ml的标准，将患者分为HE组和血肿未扩大（NHE）组。使用多个模型和10倍交叉验证方法来筛选最有价值的特征并建模预测HE的概率。曲线下面积(AUC)用于分析各模型对HE的预测效率。
结果：将他们以8：2的比例随机分为204例训练集和50例测试集。临床影像学深层特征联合模型(22个特征)预测HE曲线下面积如下:临床NavieBayes模型AUC0.779,传统放射学逻辑回归(LR)模型AUC0.818,深度学习LR模型AUC0.873,临床NCCT深度学习多层感知器模型AUC0.921。
结论：联合临床影像学深度学习模型对sICH患者早期HE有较高的预测作用，有助于临床个体化评估sICH患者早期HE的风险。
方法：纳入2017年1月至2022年12月西部战区总医院收治的254例原发性脑出血患者。根据血肿扩大超过33%或体积超过6ml的标准，将患者分为HE组和血肿未扩大（NHE）组。使用多个模型和10倍交叉验证方法来筛选最有价值的特征并建模预测HE的概率。曲线下面积(AUC)用于分析各模型对HE的预测效率。
结果：将他们以8：2的比例随机分为204例训练集和50例测试集。临床影像学深层特征联合模型(22个特征)预测HE曲线下面积如下:临床NavieBayes模型AUC0.779,传统放射学逻辑回归(LR)模型AUC0.818,深度学习LR模型AUC0.873,临床NCCT深度学习多层感知器模型AUC0.921。
结论：联合临床影像学深度学习模型对sICH患者早期HE有较高的预测作用，有助于临床个体化评估sICH患者早期HE的风险。
