paper-with-me

홈 › Papers

Confound-leakage: Confound Removal in Machine Learning Leads to Leakage

2022-10-17 · Sami Hamdan, Bradley C. Love, Georg G. von Polier, Susanne Weis, Holger Schwender, Simon B. Eickhoff, Kaustubh R. Patil

Machine learning (ML) approaches to data analysis are now widely adopted in many fields including epidemiology and medicine. To apply these approaches, confounds must first be removed as is commonly done by featurewise removal of their variance by linear regression before applying ML. Here, we show this common approach to confound removal biases ML models, leading to misleading results. Specifically, this common deconfounding approach can leak information such that what are null or moderate effects become amplified to near-perfect prediction when nonlinear ML approaches are subsequently applied. We identify and evaluate possible mechanisms for such confound-leakage and provide practical guidance to mitigate its negative impact. We demonstrate the real-world importance of confound-leakage by analyzing a clinical dataset where accuracy is overestimated for predicting attention deficit hyperactivity disorder (ADHD) with depression as a confound. Our results have wide-reaching implications for implementation and deployment of ML workflows and beg caution against na\"ive use of standard confound removal approaches.

📄 PDF Abstract BibTeX arXiv:2210.09232

Code (1)

juaml/confoundleakage 공식 구현

Tasks

Epidemiology

Methods 이 논문이 사용한 방법론

Linear Regression Linear Regression is a method for modelling a relationship between a dependent variable and independent variables. These models can be fit with numerous approaches. The most…

Similar Papers 제목 키워드 기반

Detecting and Mitigating Treatment Leakage in Text-Based Causal Inference: Distillation and Sensitivity Analysis

2025-12-30 · Adel Daoud, Richard Johansson, Connor T. Jerzak arxiv

Text-based causal inference increasingly employs textual data as proxies for unobserved confounders, yet this approach introduces a previously undertheorized source of bias: treatment leakage. Treatment leakage occurs wh…

Causal Inference

Efficacy of MRI data harmonization in the age of machine learning. A multicenter study across 36 datasets

2022-11-08 · Chiara Marzi, Marco Giannelli, Andrea Barucci, Carlo Tessa 외

Pooling publicly-available MRI data from multiple sites allows to assemble extensive groups of subjects, increase statistical power, and promote data reuse with machine learning techniques. The harmonization of multicent…

Conceptualizing Treatment Leakage in Text-based Causal Inference

2022-05-01 · NAACL 2022 7 · Adel Daoud, Connor T. Jerzak, Richard Johansson

Causal inference methods that control for text-based confounders are becoming increasingly important in the social sciences and other disciplines where text is readily available. However, these methods rely on a critical…

Causal Inference

Conceptualizing Treatment Leakage in Text-based Causal Inference

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Causal inference methods that control for text-based confounders are becoming increasingly important in the social sciences and other disciplines where text is readily available. However, these methods rely on a critical…

Causal Inference

Mitigating Hidden Confounding Effects for Causal Recommendation

2022-05-16 · Xinyuan Zhu, Yang Zhang, Fuli Feng, Xun Yang 외

Recommender systems suffer from confounding biases when there exist confounders affecting both item features and user feedback (e.g., like or not). Existing causal recommendation methods typically assume confounders are …

Multi-Task LearningRecommendation Systems