Deep learning with robustness to missing data: A novel approach to the detection of COVID-19
Open Access
- 30 July 2021
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 16 (7) , e0255301
Abstract
In the context of the current global pandemic and the limitations of the RT-PCR test, we propose a novel deep learning architecture, DFCN (Denoising Fully Connected Network). Since medical facilities around the world differ enormously in what laboratory tests or chest imaging may be available, DFCN is designed to be robust to missing input data. An ablation study extensively evaluates the performance benefits of the DFCN as well as its robustness to missing inputs. Data from 1088 patients with confirmed RT-PCR results are obtained from two independent medical facilities. The data includes results from 27 laboratory tests and a chest x-ray scored by a deep learning model. Training and test datasets are taken from different medical facilities. Data is made publicly available. The performance of DFCN in predicting the RT-PCR result is compared with 3 related architectures as well as a Random Forest baseline. All models are trained with varying levels of masked input data to encourage robustness to missing inputs. Missing data is simulated at test time by masking inputs randomly. DFCN outperforms all other models with statistical significance using random subsets of input data with 2-27 available inputs. When all 28 inputs are available DFCN obtains an AUC of 0.924, higher than any other model. Furthermore, with clinically meaningful subsets of parameters consisting of just 6 and 7 inputs respectively, DFCN achieves higher AUCs than any other model, with values of 0.909 and 0.919.Keywords
All Related Versions
Funding Information
- Fondation Botnar
This publication has 29 references indexed in Scilit:
- Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challengesEuropean Heart Journal, 2016
- Deep Residual Learning for Image Recognition2016
- Deep biomarkers of human aging: Application of deep neural networks to biomarker developmentAging, 2016
- Missing Data in Clinical Studies: Issues and MethodsJournal of Clinical Oncology, 2012
- Noise injection for training artificial neural networks: A comparison with weight decay and early stoppingMedical Physics, 2009
- ImageNet: A large-scale hierarchical image database2009
- Random ForestsMachine Learning, 2001
- Noise injection into inputs in back-propagation learningIEEE Transactions on Systems, Man, and Cybernetics, 1992
- Nonlinear principal component analysis using autoassociative neural networksAIChE Journal, 1991
- Comparing the Areas under Two or More Correlated Receiver Operating Characteristic Curves: A Nonparametric ApproachBiometrics, 1988