Changes in symptoms and characteristics of COVID-19 patients across different variants: two years study using neural network analysis

(2023) 23:838 Torabi et al. BMC Infectious Diseases https://doi.org/10.1186/s12879-023-08813-9 BMC Infectious Diseases Open Access RESEARCH Changes in symptoms and characteristics of COVID‑19 patients across different variants: two years study using neural network analysis Seyed Hossein Torabi1, Seyed Mohammad Riahi2, Azadeh Ebrahimzadeh3 and Fatemeh Salmani4* Abstract Background Considering the fact that COVID-19 has undergone various changes over time, its symptoms have also varied. The aim of this study is to describe and compare the changes in personal characteristics, symptoms, and underlying conditions of individuals infected with different strains of COVID-19. Methods This descriptive-analytical study was conducted on 46,747 patients who underwent PCR testing during a two-year period from February 22, 2020 to February 23, 2022, in South Khorasan province, Iran. Patient characteristics and symptoms were extracted based on self-report and the information system. The data were analyzed using logistic regression and artificial neural network approaches. The R software was used for analysis and a significance level of 0.05 was considered for the tests. Results Among the 46,747 cases analyzed, 23,239 (49.7%) were male, and the mean age was 51.48 ± 21.41 years. There was a significant difference in symptoms among different variants of the disease (p < 0.001). The factors with a significant positive association were myalgia (OR: 2.04; 95% CI, 1.76 – 2.36), cough (OR: 1.93; 95% CI, 1.68—2.22), and taste or smell disorder (OR: 2.62; 95% CI, 2.1 – 3.28). Additionally, aging was found to increase the likelihood of testing positive across the six periods. Conclusion We found that older age, myalgia, cough and taste/smell disorder are better factors compared to dyspnea or high body temperature, for identifying a COVID-19 patient. As the disease evolved, chills and diarrhea, demonstrated prognostic strength as in Omicron. Keywords SARC-COV-2, COVID-19, Strains, Symptoms, Artificial Neural Network *Correspondence: Fatemeh Salmani 1 School of Medicine, Birjand University of Medical Sciences, Birjand, South Khorasan Province, Iran 2 Epidemiology Department of Family and Community Medicine, School of Medicine Cardiovascular Diseases Research Center, Birjand University of Medical Sciences, Birjand, South Khorasan Province, Iran 3 Department of Infectious Diseases, School of Medicine Infectious Diseases Research Center, Birjand University of Medical Sciences, Birjand, South Khorasan Province, Iran 4 Department of Epidemiology and Biostatistics, School of Health Social Determinants of Health Research Center, Birjand University of Medical Sciences, Birjand, South Khorasan Province, Iran Background In November 2019 a respiratory disease emerged that was later identified to be caused by a new member of the coronaviruses family, a single-stranded RNA virus named SARS-CoV-2 by the International Committee on Taxonomy of Viruses [1, 2]. Since then, the virus that causes COVID-19 has spread to every country in the world [3]. The World Health Organization declared the outbreak a pandemic in February 2020 [4, 5], and the need to break its chain of transmission had become crucial. As SARSCoV-2 replicates, it can undergo mutations, leading to the emergence of different strains [6]. It is well-established © The Author(s) 2023. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated in a credit line to the data. Torabi et al. BMC Infectious Diseases (2023) 23:838 that the epidemiological and clinical features of COVID19 can vary depending on the predominant strain [7]. In the early days of the outbreak, the disease was characterized mostly by cough, fever and dyspnea [8–10], but as the novel infection grew to inflict upon more people in different regions worldwide, other symptoms emerged as significant in diagnosis including rare symptoms such as changes in smell and taste can complicate the diagnosis of the disease [11]. Six main strains were identified in Iran, namely: the initial strain, B.1.36, B.1.1.413, Alpha, Delta and Omicron. Each variant of the disease has presented with different characteristics. For example, the Omicron variant has shown a higher transmissibility compared to other variants [12]. Investigating the evolution of symptom patterns can assist researchers in understanding the virus’s behavior and tracking its progression. There have been studies conducted globally regarding changes in symptom patterns, some of which are referenced in this study [13–16]. The current research conducted within Iranian society, with a substantial number of participants, can provide valuable insights into the evolving symptom patterns within this geographical region. In this study, we aimed at determining the symptoms that predict a positive result on the RT-PCR test in each variant of COVID-19. We took into consideration situations where testing equipment is limited and costly tests need to be reduced. Thus, we only included characteristics observed at admission and did not consider laboratory or other para-clinical findings. This allowed us to identify most probable cases promptly. Our study focused on all variants of COVID-19 that caused an outbreak in Iran, including three Variants of Concern [6]. The goal of our study was to examine the variations in clinical features during periods when different variants were dominant, using artificial intelligence techniques like deep learning and neural network. Methods Study population and data sources In this study 46,747 cases were extracted from the hospital information system from 17 hospitals of South Khorasan province, Iran, from the first case identified in the region on 22 February 2020 to 23 February 2022. Over the period, six different variants, including three Variants of Concern (VOC) [6] made an outbreak in the country. The initial outbreak belonged to the novel coronavirus original strain (designated herein as “the Initial variant”) and dominated from the beginning un (...truncated)