Simulation on GUSTO-I data shows class imbalance corrections fail to boost discrimination and impair calibration plus stability in clinical prediction models.
A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
PCA and k-means on NHANES data identified four reproductive phenotypes in U.S. women aged 20-44, with one fragile subgroup showing 77.5% early multimorbidity prevalence; XGBoost improved discrimination over logistic regression but had worse calibration.
citing papers explorer
-
Class Imbalance Corrections Failed to Enhance Discrimination, Model Calibration, and Prediction Stability: An Empirical Simulation Study Based on Clinical Dataset
Simulation on GUSTO-I data shows class imbalance corrections fail to boost discrimination and impair calibration plus stability in clinical prediction models.
-
AI-Derived Reproductive Phenotypes and Explainable ML for Concurrent Early Multimorbidity in U.S. Women: NHANES 2017-March 2020
PCA and k-means on NHANES data identified four reproductive phenotypes in U.S. women aged 20-44, with one fragile subgroup showing 77.5% early multimorbidity prevalence; XGBoost improved discrimination over logistic regression but had worse calibration.