In Biomedical physics & engineering express
Although applying machine learning (ML) algorithms to rupture risk assessment of intracranial aneurysms (IA) has yielded promising results, the opaqueness of some ML methods has limited their clinical translation. We present the first explainability comparison of six commonly used ML algorithms: multivariate logistic regression (LR), support vector machine (SVM), random forest (RF), extreme gradient boosting (XGBoost), multi-layer perceptron neural network (MLPNN), and Bayesian additive regression trees (BART). A total of 128 IAs with known rupture status were selected for this study. The ML-based classification used two anatomical features, nine hemodynamic parameters, and thirteen morphologic variables. We utilized permutation feature importance, local interpretable model-agnostic explanations (LIME), and SHapley Additive exPlanations (SHAP) algorithms to explain and analyze 6 ML algorithms. All models performed comparably: LR area under curve (AUC) were 0.71; SVM AUC was 0.76; RF AUC was 0.73; XGBoost AUC was 0.78; MLPNN AUC was 0.73; BART AUC was 0.73. Our interpretability analysis demonstrated consistent results across methods, i.e., the utility of the top 12 features was broadly consistent. Furthermore, contributions of 7 important features (aneurysm area, aneurysm location, aneurysm type, wall shear stress maximum during systole, size ratio between aneurysm width and parent vessel diameter, (parent) vessel diameter, one standard deviation among time-averaged low shear area) were nearly the same. This research suggests that ML classifiers can provide explainable predictions consistent with general domain knowledge concerning IA rupture. With the improved understanding of ML algorithms, clinicians' trust in ML algorithms will be enhanced, accelerating their clinical translation.
Mu Nan, Rezaeitaleshmahalleh Mostafa, Lyu Zonghan, Wang Min, Tang Jinshan, Strother C M, Gemmete Joseph J, Pandey Aditya, Jiang Jingfeng None
2023-Jan-10
Computational Fluid Dynamics, Intracranial Aneurysm, Machine Learning
