Researchers have developed ROOFS, a Python package designed to assist biomedical researchers in selecting appropriate feature selection methods for biomarker discovery and clinical predictive modeling. The package benchmarks various methods on user data, providing reports on predictive performance, stability, and feature robustness. In a demonstration using data from the PIONeeR clinical trial, ROOFS identified an optimal approach combining Benjamini-Hochberg adjusted p-values from t-tests and logistic regression, which outperformed methods like LASSO. AI
IMPACT Improves reproducibility and translational value of clinical models by standardizing feature selection methods.
RANK_REASON The cluster describes a new research paper and associated software package for feature selection in biomedical research. [lever_c_demoted from research: ic=1 ai=0.7]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
