Application Of Machine Learning Model Based On Multidimensional Data In Intracranial Aneurysms

Section Ⅰ(CharpterⅢ)Rupture Risk Assessment for Intracranial Aneurysm Using Machine Learning on Multidimensional DataBackgroundRuptured intracranial aneurysms are the most common cause of nontraumatic subarachnoid hemorrhage.Assessment of cerebral aneurysm rupture risk is an important task,but it remains challenging.Recent works applying machine learning to rupture risk evaluation presented positive results.Yet they were based on limited aspects of data,and lack of interpretability may limit their use in clinical setting.We aimed to develop interpretable machine learning models on multidimensional data for aneurysm rupture risk assessment.MethodsThe data of 452 cases of intracranial aneurysms in our center from July 2017 to June 2019 were retrospectively analyzed,and 374 of them were finally included in this study according to the discharge criteria.Demographic,medical history,lifestyle behaviors,lipid profile,and morphologies were collected for each patient.Prediction models were derived using machine learning methods(support vector machine,artificial neural network,and XGBoost)and conventional logistic regression.The derived models were compared with the PHASES score method.The Shapley Additive Explanations(SHAP)analysis was applied to improve the interpretability of the best machine learning model and reveal the reasoning behind the predictions made by the model.ResultsThe best machine learning model(XGBoost)achieved an area under the receiver operating characteristic curve of 0.882[95%confidence interval(CI)=0.838-0.927],significantly better than the logistic regression model(0.808;95%CI=0.758-0.858;P=0.002)and the PHASES score method(0.757;95%CI=0.713-0.800;P=0.001).Location,size ratio,and triglyceride level were the three most important features in predicting rupture.Two typical cases were analyzed to demonstrate the interpretability of the model.ConclusionsThis study demonstrated the potential of using machine learning for aneurysm rupture risk assessment.Machine learning models performed better than conventional statistical model and the PHASES score method.The SHAP analysis can improve the interpretability of machine learning models and facilitate their use in a clinical setting.Section Ⅱ(CharpterⅣ)Automated Machine Learning Model Development for Intracranial Aneurysm Treatment Outcome PredictionBackgroundThe prediction of aneurysm treatment outcome can help to optimize treatment strategies.Machine learning has shown positive results in many clinical areas.However,the development of such models requires expertise in machine learning,which is not an easy task for surgeons.The recently emerged automated machine learning(AutoML)has shown promise in making machine learning more accessible to non-computer experts.We aimed to evaluate the feasibility of applying AutoML to develop machine learning models for treatment outcome prediction.MethodsData of intracranial aneurysms receiving endovascular treatment in our center from July 2017 to June 2019 were retrospectively analyzed,and 218 cases of endovascular aneurysms receiving endovascular treatment were included.Statistical prediction model was developed using multivariate logistic regression.Two machine learning(ML)models were also developed.One was developed manually and the other was automatically developed by AutoML.Three models were compared based on their area under the precision-recall curve(AUPRC)and area under the receiver operating characteristic curve(AUROC).ResultsThe mean size of intracranial aneurysm was 5.3 mm.Aneurysm length,aneurysm aneurysm height aneurysm neck diameter,aspect ratio,size ratio,shape,location and treatment were significant independent variables related to treatment outcome.The statistical model showed an AUPRC of 0.432 and AUROC of 0.745.The conventional manually trained ML model showed an improved AUPRC of 0.545 and AUROC of 0.781.The AutoML derived ML model showed the best performance with AUPRC of 0.632 and AUROC of 0.832,significantly better than the other two models.ConclusionsThis study demonstrated the feasibility of using AutoML to develop high quality ML model,which may outperform statistical and manually derived ML models.AutoML could be a useful tool for clinical researchers to apply machine learning in their fields.