학술논문
Evaluating Time Influence over Performance of Machine-Learning-Based Diagnosis: A Case Study of COVID-19 Pandemic in Brazil.
Document Type
Academic Journal
Author
Marques JG; Department of Informatics and Applied Mathematics, Federal University of Rio Grande do Norte, Natal 59078-970, Brazil.; Guedes LA; Department of Computer Engineering and Automation, Federal University of Rio Grande do Norte, Natal 59078-970, Brazil.; da Costa Abreu MC; Department of Computing, Sheffield Hallam University, Sheffield S9 3TY, UK.
Source
Publisher: MDPI Country of Publication: Switzerland NLM ID: 101238455 Publication Model: Electronic Cited Medium: Internet ISSN: 1660-4601 (Electronic) Linking ISSN: 16604601 NLM ISO Abbreviation: Int J Environ Res Public Health Subsets: MEDLINE
Subject
Language
English
Abstract
Efficiently recognising severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) symptoms enables a quick and accurate diagnosis to be made, and helps in mitigating the spread of the coronavirus disease 2019. However, the emergence of new variants has caused constant changes in the symptoms associate with COVID-19. These constant changes directly impact the performance of machine-learning-based diagnose. In this context, considering the impact of these changes in symptoms over time is necessary for accurate diagnoses. Thus, in this study, we propose a machine-learning-based approach for diagnosing COVID-19 that considers the importance of time in model predictions. Our approach analyses the performance of XGBoost using two different time-based strategies for model training: month-to-month and accumulated strategies. The model was evaluated using known metrics: accuracy, precision, and recall. Furthermore, to explain the impact of feature changes on model prediction, feature importance was measured using the SHAP technique, an XAI technique. We obtained very interesting results: considering time when creating a COVID-19 diagnostic prediction model is advantageous.