# Sample Selection Bias in Machine Learning for Healthcare

arXiv: https://arxiv.org/abs/2405.07841 · HTML: https://mlsanity.com/paper/2405.07841/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 83 references that are in the map.
- First posted on arXiv 13 May 2024.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Revisiting the Calibration of Modern Neural Networks](https://mlsanity.com/paper/2106.07998/) (2021)
- [A review of domain adaptation without target labels](https://mlsanity.com/paper/1901.05335/) (2019)
- [Machine Learning with a Reject Option: A survey](https://mlsanity.com/paper/2107.11277/) (2021)
- [A Brief Review of Hypernetworks in Deep Learning](https://mlsanity.com/paper/2306.06955/) (2023)
- [ADAPT : Awesome Domain Adaptation Python Toolbox](https://mlsanity.com/paper/2107.03049/) (2021)
- [Dynamic Inter-treatment Information Sharing for Individualized Treatment Effects Estimation](https://mlsanity.com/paper/2305.15984/) (2023)
- [Adversarial De-confounding in Individualised Treatment Effects Estimation](https://mlsanity.com/paper/2210.10530/) (2022)
- [Double machine learning for sample selection models](https://mlsanity.com/paper/2012.00745/) (2020)
- [Weighted Empirical Risk Minimization: Sample Selection Bias Correction based on Importance Sampling](https://mlsanity.com/paper/2002.05145/) (2020)
- [Fair Regression under Sample Selection Bias](https://mlsanity.com/paper/2110.04372/) (2021)
- [A Framework for Understanding Selection Bias in Real-World Healthcare Data](https://mlsanity.com/paper/2304.04652/) (2023)
- [VAT tax gap prediction: a 2-steps Gradient Boosting approach](https://mlsanity.com/paper/1912.03781/) (2019)
- [Sample Selection Bias in Evaluation of Prediction Performance of Causal Models](https://mlsanity.com/paper/2106.01921/) (2021)

## Abstract (arXiv)

While machine learning algorithms hold promise for personalised medicine, their clinical adoption remains limited, partly due to biases that can compromise the reliability of predictions. In this paper, we focus on sample selection bias (SSB), a specific type of bias where the study population is less representative of the target population, leading to biased and potentially harmful decisions. Despite being well-known in the literature, SSB remains scarcely studied in machine learning for healthcare. Moreover, the existing machine learning techniques try to correct the bias mostly by balancing distributions between the study and the target populations, which may result in a loss of predictive performance. To address these problems, our study illustrates the potential risks associated with SSB by examining SSB's impact on the performance of machine learning algorithms. Most importantly, we propose a new research direction for addressing SSB, based on the target population identification rather than the bias correction. Specifically, we propose two independent networks(T-Net) and a multitasking network (MT-Net) for addressing SSB, where one network/task identifies the target subpopulation which is representative of the study population and the second makes predictions for the identified subpopulation. Our empirical results with synthetic and semi-synthetic datasets highlight that SSB can lead to a large drop in the performance of an algorithm for the target population as compared with the study population, as well as a substantial difference in the performance for the target subpopulations that are representative of the selected and the non-selected patients from the study population. Furthermore, our proposed techniques demonstrate robustness across various settings, including different dataset sizes, event rates, and selection rates, outperforming the existing bias correction techniques.