Tipping the Balance: Impact of Class Imbalance Correction on the Performance of Clinical Risk Prediction Models

📅 2026-02-27
📈 Citations: 0
Influential: 0
📄 PDF

career value

181K/year
🤖 AI Summary
The impact of class imbalance correction on model discriminative performance and probability calibration in clinical risk prediction remains unclear. This study systematically evaluates the effects of SMOTE, random oversampling (ROS), and random undersampling (RUS) across ten real-world clinical datasets using a range of linear and nonlinear models. Comprehensive comparisons are conducted using metrics including ROC-AUC, Brier score, and calibration intercept/slope. Results indicate that none of the three resampling methods significantly improve discrimination, yet all consistently degrade probability calibration—evidenced by increased Brier scores (0.029–0.080) and substantial shifts in calibration parameters—revealing systematic distortion in predicted risk estimates. These findings challenge the conventional use of resampling techniques in clinical prediction modeling.

Technology Category

Application Category

📝 Abstract
Objective: ML-based clinical risk prediction models are increasingly used to support decision-making in healthcare. While class-imbalance correction techniques are commonly applied to improve model performance in settings with rare outcomes, their impact on probabilistic calibration remains insufficiently understood. This study evaluated the effect of widely used resampling strategies on both discrimination and calibration across real-world clinical prediction tasks. Methods: Ten clinical datasets spanning diverse medical domains and including 605,842 patients were analyzed. Multiple machine-learning model families, including linear models and several non-linear approaches, were evaluated. Models were trained on the original data and under three commonly used 1:1 class-imbalance correction strategies (SMOTE, RUS, ROS). Performance was assessed on held-out data using discrimination and calibration metrics. Results: Across all datasets and model families, resampling had no positive impact on predictive performance. Changes in the Receiver Operating Characteristic Area Under Curve (ROC-AUC) relative to models trained on the original data were small and inconsistent (ROS: -0.002, p<0.05; RUS: -0.004, p>0.05; SMOTE: -0.01, p<0.05), with no resampling strategy demonstrating a systematic improvement. In contrast, resampling in general degraded the calibration performance. Models trained using imbalance correction exhibited higher Brier scores (0.029 to 0.080, p<0.05), reflecting poorer probabilistic accuracy, and marked deviations in calibration intercept and slope, indicating systematic distortions of predicted risk despite preserved rank-based performance. Conclusion: In a diverse set of real-world clinical prediction tasks, commonly used class-imbalance correction techniques did not provide generalizable improvements in discrimination and were associated with degraded calibration.
Problem

Research questions and friction points this paper is trying to address.

class imbalance
clinical risk prediction
probabilistic calibration
machine learning
resampling
Innovation

Methods, ideas, or system contributions that make the work stand out.

class imbalance
calibration
clinical risk prediction
resampling
probabilistic accuracy
🔎 Similar Papers
A
Amalie Koch Andersen
Medical Informatics and Image Analysis, Department of Health Science and Technology, Aalborg University, Denmark; Medical & Translational Science, Novo Nordisk A/S, Søborg, Denmark
H
Hadi Mehdizavareh
Department of Computer Science, Aalborg University, Aalborg, Denmark
A
Arijit Khan
Department of Computer Science, Aalborg University, Aalborg, Denmark; Department of Computer Science, Bowling Green State University, Bowling Green, Ohio, USA
T
Tobias Becher
Cardiology, Angiology, Haemostaseology, and Medical Intensive Care, Medical Centre Mannheim, Medical Faculty Mannheim, Heidelberg University, Heidelberg, Germany; European Centre for AngioScience (ECAS), German Centre for Cardiovascular Research (DZHK) partner site Heidelberg/Mannheim, and Centre for Cardiovascular Acute Medicine Mannheim (ZKAM), Medical Centre Mannheim, Medical Faculty Mannheim, Heidelberg University, Heidelberg, Germany
S
Simone Britsch
Cardiology, Angiology, Haemostaseology, and Medical Intensive Care, Medical Centre Mannheim, Medical Faculty Mannheim, Heidelberg University, Heidelberg, Germany; European Centre for AngioScience (ECAS), German Centre for Cardiovascular Research (DZHK) partner site Heidelberg/Mannheim, and Centre for Cardiovascular Acute Medicine Mannheim (ZKAM), Medical Centre Mannheim, Medical Faculty Mannheim, Heidelberg University, Heidelberg, Germany
M
Markward Britsch
Cardiology, Angiology, Haemostaseology, and Medical Intensive Care, Medical Centre Mannheim, Medical Faculty Mannheim, Heidelberg University, Heidelberg, Germany; European Centre for AngioScience (ECAS), German Centre for Cardiovascular Research (DZHK) partner site Heidelberg/Mannheim, and Centre for Cardiovascular Acute Medicine Mannheim (ZKAM), Medical Centre Mannheim, Medical Faculty Mannheim, Heidelberg University, Heidelberg, Germany; HMS Analytical Software GmbH, Heidelberg, Germany; Department of Rad
M
Morten Bøttcher
Department of Cardiology, Gødstrup Hospital, Hospitalsparken 15, 7400 Herning, Denmark
S
Simon Winther
Department of Cardiology, Gødstrup Hospital, Hospitalsparken 15, 7400 Herning, Denmark
P
Palle Duun Rohde
Department of Health Science and Technology, Aalborg University, Denmark
M
Morten Hasselstrøm Jensen
Medical Informatics and Image Analysis, Department of Health Science and Technology, Aalborg University, Denmark; Medical & Translational Science, Novo Nordisk A/S, Søborg, Denmark
S
Simon Lebech Cichosz
Medical Informatics and Image Analysis, Department of Health Science and Technology, Aalborg University, Denmark