Search

Abstract The concept of functional localization within the brain and the associated risk of resecting these areas during removal of infiltrating tumors, such as diffuse gliomas, are well established in neurosurgery. Global efficiency (GE) is a graph theory concept that can be used to simulate connectome disruption following tumor resection. Structural connectivity graphs were created from diffusion tractography obtained from the brains of 80 healthy adults. These graphs were then used to simulate parcellation resection in every gross anatomical region of the cerebrum by identifying every possible combination of adjacent nodes in a graph and then measuring the drop in GE following nodal deletion. Progressive removal of brain parcellations led to patterns of GE decline that were reasonably predictable but had inter-subject differences. Additionally, as expected, there were deletion of some nodes that were worse than others. However, in each lobe examined in every subject, some deletion combinations were worse for GE than removing a greater number of nodes in a different region of the brain. Among certain patients, patterns of common nodes which exhibited worst GE upon removal were identified as “connectotypes”. Given some evidence in the literature linking GE to certain aspects of neuro-cognitive abilities, investigating these connectotypes could potentially mitigate the impact of brain surgery on cognition.

Purpose Current limitations in methodologies used throughout machine-learning to investigate feature importance in boosted tree modelling prevent the effective scaling to datasets with a large number of features, particularly when one is investigating both the magnitude and directionality of various features on the classification into a positive or negative class. This manuscript presents a novel methodology, “Hollow-tree Super” (HOTS), designed to resolve and visualize feature importance in boosted tree models involving a large number of features. Further, this methodology allows for accurate investigation of the directionality and magnitude various features have on classification and incorporates cross-validation to improve the accuracy and validity of the determined features of importance. Methods Using the Iris dataset, we first highlight the characteristics of HOTS by comparing it to other commonly used techniques for feature importance, including Gini Importance, Partial Dependence Plots, and Permutation Importance, and explain how HOTS resolves the weaknesses present in these three strategies for investigating feature importance. We then demonstrate how HOTS can be utilized in high dimensional spaces such as neuroscientific setting, by taking 60 Schizophrenic subjects from the publicly available SchizConnect database and applying the method to determine which regions of the brain were most important for the positive and negative classification of schizophrenia as determined by the positive and negative syndrome scale (PANSS). Results HOTS effectively replicated and supported the findings of feature importance for classification of the Iris dataset when compared to Gini importance, Partial Dependence Plots and Permutation importance, determining ‘petal length’ as the most important feature for positive and negative classification. When applied to the Schizconnect dataset, HOTS was able to resolve from 379 independent features, the top 10 most important features for classification, as well as their directionality for classification and magnitude compared to other features. Cross-validation supported that these same 10 features were consistently used in the decision-making process across multiple trees, and these features were localised primarily to the occipital and parietal cortices, commonly disturbed brain regions in those afflicted with Schizophrenia. Conclusion HOTS effectively overcomes previous challenges of identifying feature importance at scale, and can be utilized across a swathe of disciplines. As computational power and data quantity continues to expand, it is imperative that a methodology is developed that is able to handle the demands of working with large datasets that contain a large number of features. This approach represents a unique way to investigate both the directionality and magnitude of feature importance when working at scale within a boosted tree model that can be easily visualized within commonly used software.