Harnessing XGBoost for Robust Biomarker Selection of Obsessive-Compulsive Disorder (OCD) from Adolescent Brain Cognitive Development (ABCD) data
This work addresses biomarker selection for OCD in adolescents using ABCD data, but it is incremental as it applies existing methods to a new dataset without major methodological breakthroughs.
The study tackled the problem of predicting obsessive-compulsive disorder scales from highly correlated neuroimaging data by evaluating machine learning models like logistic regression, elastic networks, random forests, and XGBoost, finding that XGBoost best handles multicollinearity and identifies predictive features.
This study evaluates the performance of various supervised machine learning models in analyzing highly correlated neural signaling data from the Adolescent Brain Cognitive Development (ABCD) Study, with a focus on predicting obsessive-compulsive disorder scales. We simulated a dataset to mimic the correlation structures commonly found in imaging data and evaluated logistic regression, elastic networks, random forests, and XGBoost on their ability to handle multicollinearity and accurately identify predictive features. Our study aims to guide the selection of appropriate machine learning methods for processing neuroimaging data, highlighting models that best capture underlying signals in high feature correlations and prioritize clinically relevant features associated with Obsessive-Compulsive Disorder (OCD).