Distinction of COVID-19 and Analysis on Symptoms and Hospitalization Time
These authors contributed equally.
- DOI
- 10.2991/aebmr.k.220307.076How to use a DOI?
- Keywords
- COVID-19; Distinction; Analysis; Machine learning
- Abstract
This paper aims to use the machine learning model to distinguish more precisely whether the patients get COVID-19 or not and analyze symptoms and hospitalization time of the patients. We use CNN to test the hypothesis: we can find from their X-rays that whether the patients get COVID-19. The result showed a 95 percent accuracy indicates that it can be found who are infected with COVID-19 from the model easily. It suggests that X-ray is an important and accurate indicator to find COVID-19 since respectively, X-rays results from patients with COVID-19 and normal people differ significantly. In addition, after the analysis of symptoms and time of staying in hospital, we found that patients were not likely to had no symptoms or experiencing and who had one of the symptoms accounted for the largest group of patients. The symptoms or experiencing they behaved had exact combinations rather than randomly combined, like someone may have fever, tiredness and dry-cough at the same time but he cannot have fever, dry-cough and difficulty-in-breathing simultaneously. What is more, the result also showed that the elder the patients, the longer they stayed in hospitals. The CNN model used in this study has higher accuracy. In addition, the result can help the hospitals effectively avoid the over concentration of medical resources and allocate them reasonably.
- Copyright
- © 2022 The Authors. Published by Atlantis Press International B.V.
- Open Access
- This is an open access article under the CC BY-NC license.
Cite this article
TY - CONF AU - Xiran Gao AU - Guang Ni AU - Jingyuan Zhang AU - Xiaoning Zhao PY - 2022 DA - 2022/03/26 TI - Distinction of COVID-19 and Analysis on Symptoms and Hospitalization Time BT - Proceedings of the 2022 7th International Conference on Financial Innovation and Economic Development (ICFIED 2022) PB - Atlantis Press SP - 471 EP - 480 SN - 2352-5428 UR - https://doi.org/10.2991/aebmr.k.220307.076 DO - 10.2991/aebmr.k.220307.076 ID - Gao2022 ER -