Using Association Rules to Obtain Sets of Prevalent Symptoms throughout the Covid-19 Pandemic
An Analysis of Similarities between Cases of Covid-19 and Unspecified Sars in São Paulo-Brazil
Bibliographic Data
| ID | 15511765 |
|---|---|
| Authors | Julliana Gonçalves Marques (0000-0002-0740-1136, Universidade Federal do Rio Grande do Norte, corresponding author), Bruno M Carvalho (0000-0002-9122-0257, Universidade Federal do Rio Grande do Norte), Luiz Affonso Guedes (0000-0003-2690-1563, Universidade Federal do Rio Grande do Norte), Márjory Da Costa-Abreu (0000-0001-7461-7570, Sheffield Hallam University) |
| Year | 2024 |
| Volume | 21 |
| Issue | 9 |
| Pages | 1164-1164 |
| Publication date | 2024-09-01 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | International Journal of Environmental Research and Public Health (JOURNAL) |
| Journal identifiers | ISSN: 1661-7827 • E-ISSN: 1660-4601 |
| Publisher | Multidisciplinary Digital Publishing Institute (PUBLISHER • CH) |
| DOI | 10.3390/ijerph21091164 |
| PMID | 39338047 |
| OpenAlex | W4402131080 |
| Language | EN |
| References cited | 25 |
The efficient recognition of symptoms in viral infections holds promise for swift and precise diagnosis, thus mitigating health implications and the potential recurrence of infections. COVID-19 presents unique challenges due to various factors influencing diagnosis, especially regarding disease symptoms that closely resemble those of other viral diseases, including other strains of SARS, thus impacting the identification of useful and meaningful symptom patterns as they emerge in infections. Therefore, this study proposes an association rule mining approach, utilising the Apriori algorithm to analyse the similarities between individuals with confirmed SARS-CoV-2 diagnosis and those with unspecified SARS diagnosis. The objective is to investigate, through symptom rules, the presence of COVID-19 patterns among individuals initially not diagnosed with the disease. Experiments were conducted using cases from Brazilian SARS datasets for São Paulo State. Initially, reporting percentage similarities of symptoms in both groups were analysed. Subsequently, the top ten rules from each group were compared. Finally, a search for the top five most frequently occurring positive rules among the unspecified ones, and vice versa, was conducted to identify identical rules, with a particular focus on the presence of positive rules among the rules of individuals initially diagnosed with unspecified SARS
2019-20 coronavirus outbreak · Association (psychology · Association rule learning · Biology · Coronavirus disease 2019 (COVID-19 · Data mining · Disease · Identification (biology · Infectious disease (medical specialty · Outbreak · Pandemic · Pathology · Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2 · Anomaly Detection Techniques and Applications · Computer Science · Data Mining Algorithms and Applications · Imbalanced Data Classification Techniques · Medicine · Psychology · Virology
| Citation velocity | historical |
|---|---|
| Highly cited | No |