Deep Learning with robustness to missing data: A novel approach to the detection of COVID-19

TL;DR

This paper introduces DFCN, a deep learning model designed to accurately detect COVID-19 from incomplete medical data, demonstrating superior robustness and performance across various missing data scenarios.

Contribution

The paper presents a novel DFCN architecture that is robust to missing input data, outperforming existing models in COVID-19 detection with incomplete datasets.

Findings

DFCN achieves an AUC of 0.924 with all inputs available.

DFCN outperforms other models with fewer inputs, achieving high AUCs of 0.909 and 0.919 with 6 and 7 inputs.

The model maintains high performance even with significant missing data.

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.