López-Rueda Antonio, Rodríguez-Sánchez María-Ángeles, Serrano Elena, Moreno Javier, Rodríguez Alejandro, Llull Laura, Amaro Sergi, Oleaga Laura
Clinical Informatics Department, Hospital Clínic de Barcelona, Barcelona, Spain.
Radiology Department, Hospital Clínic de Barcelona, Barcelona, Spain.
Eur J Radiol Open. 2024 Dec 1;13:100618. doi: 10.1016/j.ejro.2024.100618. eCollection 2024 Dec.
This study aims to develop a Radiomics-based Supervised Machine-Learning model to predict mortality in patients with spontaneous intracerebral hemorrhage (sICH).
Retrospective analysis of a prospectively collected clinical registry of patients with sICH consecutively admitted at a single academic comprehensive stroke center between January-2016 and April-2018. We conducted an in-depth analysis of 105 radiomic features extracted from 105 patients. Following the identification and handling of missing values, radiomics values were scaled to 0-1 to train different classifiers. The sample was split into 80-20 % training-test and validation cohort in a stratified fashion. Random Forest(RF), K-Nearest Neighbor(KNN), and Support Vector Machine(SVM) classifiers were evaluated, along with several feature selection methods and hyperparameter optimization strategies, to classify the binary outcome of mortality or survival during hospital admission. A tenfold stratified cross-validation method was used to train the models, and average metrics were calculated.
RF, KNN, and SVM, with the "DropOut+SelectKBest" feature selection strategy and no hyperparameter optimization, demonstrated the best performances with the least number of radiomic features and the most simplified models, achieving a sensitivity range between 0.90 and 0.95 and AUC range from 0.97 to 1 on the validation dataset. Regarding the confusion matrix, the SVM model did not predict any false negative test (negative predicted value 1).
Radiomics-based Supervised Machine Learning models can predict mortality during admission in patients with sICH. SVM with the "DropOut+SelectKBest" feature selection strategy and no hyperparameter optimization was the best simplified model to detect mortality during admission in patients with sICH.
本研究旨在开发一种基于放射组学的监督式机器学习模型，以预测自发性脑出血（sICH）患者的死亡率。
对2016年1月至2018年4月期间在单一学术性综合卒中中心连续收治的sICH患者的前瞻性收集临床登记资料进行回顾性分析。我们对从105例患者中提取的105个放射组学特征进行了深入分析。在识别和处理缺失值后，将放射组学值缩放到0-1以训练不同的分类器。样本以分层方式分为80%-20%的训练-测试和验证队列。对随机森林（RF）、K近邻（KNN）和支持向量机（SVM）分类器进行了评估，同时评估了几种特征选择方法和超参数优化策略，以对住院期间死亡率或生存率的二元结局进行分类。采用十折分层交叉验证方法训练模型，并计算平均指标。
采用“DropOut+SelectKBest”特征选择策略且无超参数优化的RF、KNN和SVM，在放射组学特征数量最少且模型最简化的情况下表现最佳，在验证数据集上的灵敏度范围为0.90至0.95，AUC范围为0.97至1。关于混淆矩阵，SVM模型未预测到任何假阴性测试（阴性预测值为1）。
基于放射组学的监督式机器学习模型可以预测sICH患者住院期间的死亡率。采用“DropOut+SelectKBest”特征选择策略且无超参数优化的SVM是检测sICH患者住院期间死亡率的最佳简化模型。
