Hierarchical Variable Importance with Statistical Control for Medical Data-Based Prediction
This addresses interpretability challenges in medical imaging for clinicians, though it is incremental as it builds on existing model-agnostic methods.
The authors tackled the problem of low power in model-agnostic variable importance methods for highly correlated medical imaging data by introducing Hierarchical-CPI, which groups variables hierarchically and controls family-wise error rates, demonstrating effectiveness in neuroimaging datasets for dementia classification and EEG analysis.
Recent advances in machine learning have greatly expanded the repertoire of predictive methods for medical imaging. However, the interpretability of complex models remains a challenge, which limits their utility in medical applications. Recently, model-agnostic methods have been proposed to measure conditional variable importance and accommodate complex non-linear models. However, they often lack power when dealing with highly correlated data, a common problem in medical imaging. We introduce Hierarchical-CPI, a model-agnostic variable importance measure that frames the inference problem as the discovery of groups of variables that are jointly predictive of the outcome. By exploring subgroups along a hierarchical tree, it remains computationally tractable, yet also enjoys explicit family-wise error rate control. Moreover, we address the issue of vanishing conditional importance under high correlation with a tree-based importance allocation mechanism. We benchmarked Hierarchical-CPI against state-of-the-art variable importance methods. Its effectiveness is demonstrated in two neuroimaging datasets: classifying dementia diagnoses from MRI data (ADNI dataset) and analyzing the Berger effect on EEG data (TDBRAIN dataset), identifying biologically plausible variables.