Machine learning is the key to diagnose COVID-19: a proof of concept study
Cedric Gangloff, Sonia Rafi , Guillaume Bouzillé , Louis Soulat , Marc Cuggia
Received date: 30th October 2020
Background: Two tests are currently available to diagnose COVID-19: chest-CT and RT-PCR. These tests are sub-optimal when they are used independently but their combination on every suspected COVID-19 patient requires considerables resources. The potential contribution of machine learning in this situation has not been evaluated. The objective of this study was to develop and evaluate machine learning models to diagnose COVID-19 among post-emergency hospitalized patients. Methods: All post-emergency hospitalized adults patients admitted in our academic hospital between 2020/03/20 and 2020/05/05 and explored for COVID-19 were included in the study. Three types of machine learning models were created: logistic regressions, random forests, and neural networks. Each type of model was trained to diagnose COVID-19 with different sets of variables. Area under the ROC curve was the primary outcome to evaluate model’s performances. Results: 536 patients were included in the study: 106 in the COVID group, 430 in the NOT-COVID group. AUC of chest-CT increased from 0.778 to 0.889 with the contribution of machine learning. Similarly, AUC of RT-PCR increased from 0.852 to 0.929 with machine learning. Conclusions: After generalization, machine learning models will allow to increase chest-CT and RT-PCR performances to diagnose COVID-19.
This is an abstract of a preprint hosted on a preprint server, which is currently undergoing peer review at Scientific Reports. The findings have yet to be thoroughly evaluated, nor has a decision on ultimate publication been made. Therefore, the results reported should not be considered conclusive, and these findings should not be used to inform clinical practice, or public health policy, or be promoted as verified information.