Predictive Analytics for Early Detection of COVID-19 by Fuzzy Logic
International Series in Operations Research and Management Science
; 320:45-65, 2022.
Article
in English
| Scopus | ID: covidwho-1756677
ABSTRACT
Today entire world is struggling, and significant cases are rising due to Coronavirus, namely COVID-19. Healthcare providers are busy in clinical trials to investigate the vaccine for this pandemic. If this virus attacks the person, nobody can know that person is going to be tested positive. This virus is spreading through the droplets of one person or dirty hands. The primary task of healthcare providers is to provide diagnostic product services at low costs and accurately diagnose patients. Machine learning methods can use for disease identification because they mainly apply to data and prioritize specific tasks’ outcomes. In this work, a multistage fuzzy rule-based algorithm for detection and CART algorithm is utilizing to produce the fuzzy rules. Implementation results exhibit that the proposed method differentiated the development of the disease prediction accuracy. The integration of these two techniques, multistage fuzzy rules and CART algorithms with unrelated data removal methods, could help predict disease. The proposed system can be helpful for healthcare providers in predicting the early stages of COVID-19. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
Full text:
Available
Collection:
Databases of international organizations
Database:
Scopus
Type of study:
Prognostic study
Language:
English
Journal:
International Series in Operations Research and Management Science
Year:
2022
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS