Removing Confounding Factors Associated Weights in Deep Neural Networks Improves the Prediction Accuracy for Healthcare Applications
By Haohan Wang, Zhenglin Wu, Eric P. Xing. 2018
47 citations recorded by the source corpus.
The proliferation of healthcare data has brought the opportunities of applying data-driven approaches, such as machine learning methods, to assist diagnosis. Recently, many deep learning methods have been shown with impressive successes in predicting disease status with raw input data. However, the “black-box” nature of deep learning and the high-reliability requirement of biomedical applications have created new challenges regarding the existence of confounding factors. In this paper, with a brief argument that inappropriate handling of confounding factors will lead to models’ sub-optimal performance in real-world applications, we present an efficient method that can remove the influences of confounding factors such as age or gender to improve the across-cohort prediction accuracy of neural networks. One distinct advantage of our method is that it only requires minimal changes of the baseline model’s architecture so that it can be plugged into most of the existing neu-ral networks. We conduct experiments across CT-scan, MRA, and EEG brain wave with convolutional neural networks and LSTM to verify the efficiency of our method.
Subfields: Artificial Intelligence, Health Informatics
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Cynthia Rudin
- Alina Jade Barnett
- Chaofan Tao
- Tong Wang
- Octavio Loyola-González
- Berk Ustun
- Lesia Semenova
- Peter Hase
In Health Informatics
- Cynthia Rudin
- Octavio Loyola-González
- Timo Speith
- S. Lo Piano
- Adrian Weller
- Mohit Bansal
- Sarah Wiegreffe
- Yuval Pinter
Citations in the corpus
- A case-based interpretable deep learning model for classification of mass lesions in digital mammography (2021, background): “Ways to direct model attention include data augmentation [16, 33, 8], techniques that combat hand-selected confounders [51, 50], techniques that combat learned confounders [58], and an approach where a human critic manually approves the attention map during training [43].”