During the early stages of respiratory virus outbreaks, such as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the efficient utilize of limited nasopharyngeal swabs for rapid and accurate screening is crucial for public health. In this study, we present a methodology that integrates attenuated total reflection-Fourier transform infrared spectroscopy (ATR-FTIR) with the adaptive iteratively reweighted penalized least squares (airPLS) preprocessing algorithm and a channel-wise attention-based partial least squares one-dimensional convolutional neural network (PLS-1D-CNN) model, enabling accurate screening of infected individuals within 10 minutes. Two cohorts of nasopharyngeal swab samples, comprising 126 and 112 samples from suspected SARS-CoV-2 Omicron variant cases, were collected at Beijing You'an Hospital for verification. Given that ATR-FTIR spectra are highly sensitive to variations in experimental conditions, which can affect their quality, we propose a biomolecular importance (BMI) evaluation method to assess signal quality across different conditions, validated by comparing BMI with PLS-GBM and PLS-RF results. For the ATR-FTIR signals in cohort 2, which exhibited a higher BMI, airPLS was utilized for signal preprocessing, followed by the application of the channel-wise attention-based PLS-1D-CNN model for screening. The experimental results demonstrate that our model outperforms recently reported methods in the field of respiratory virus spectrum detection, achieving a recognition screening accuracy of 96.48%, a sensitivity of 96.24%, a specificity of 97.14%, an F1-score of 96.12%, and an AUC of 0.99. It meets the World Health Organization (WHO) recommended criteria for an acceptable product: sensitivity of 95.00% or greater and specificity of 97.00% or greater for testing prior SARS-CoV-2 infection in moderate to high volume scenarios.

SARS-CoV-2, the highly contagious pathogen responsible for the COVID-19 pandemic, has persistent effects that begin four weeks after initial infection and last for an undetermined duration. These chronic effects are more harmful than acute ones. This review explores the long-term impact of the virus on various human organs, including the pulmonary, cardiovascular, neurological, reproductive, gastrointestinal, musculoskeletal, endocrine, and lymphoid systems, particularly in older adults. Regarding diagnosis, RT-PCR is the gold standard for detecting COVID-19, though it requires specialized equipment, skilled personnel, and considerable time to produce results. To address these limitations, artificial intelligence in imaging and microfluidics technologies offers promising alternatives for diagnosing COVID-19 efficiently. Pharmacological and non-pharmacological strategies are effective in mitigating the persistent impacts of COVID-19. These strategies enhance immunity in post-COVID-19 patients by reducing cytokine release syndrome, improving T cell response, and increasing the circulation of activated natural killer and CD8 T cells in blood and tissues. This, in turn, alleviates symptoms such as fever, nausea, fatigue, muscle weakness, and pain. Vaccines, including inactivated viral, live attenuated viral, protein subunit, viral vectored, mRNA, DNA, and nanoparticle vaccines, significantly reduce the adverse long-term effects of the virus. However, no vaccine has been reported to provide lifetime protection against COVID-19. Consequently, protective measures such as physical distancing, mask usage, and hand hygiene remain essential strategies. This review offers a comprehensive understanding of the persistent effects of COVID-19 on individuals of varying ages, along with insights into diagnosis, treatment, vaccination, and future preventative measures against the spread of SARS-CoV-2.

The UK COVID-19 Vocal Audio Dataset is designed for the training and evaluation of machine learning models that classify SARS-CoV-2 infection status or associated respiratory symptoms using vocal audio. The UK Health Security Agency recruited voluntary participants through the national Test and Trace programme and the REACT-1 survey in England from March 2021 to March 2022, during dominant transmission of the Alpha and Delta SARS-CoV-2 variants and some Omicron variant sublineages. Audio recordings of volitional coughs, exhalations, and speech were collected in the 'Speak up to help beat coronavirus' digital survey alongside demographic, self-reported symptom and respiratory condition data, and linked to SARS-CoV-2 test results. The UK COVID-19 Vocal Audio Dataset represents the largest collection of SARS-CoV-2 PCR-referenced audio recordings to date. PCR results were linked to 70,794 of 72,999 participants and 24,155 of 25,776 positive cases. Respiratory symptoms were reported by 45.62% of participants. This dataset has additional potential uses for bioacoustics research, with 11.30% participants reporting asthma, and 27.20% with linked influenza PCR test results.

This paper presents the Coswara dataset, a dataset containing diverse set of respiratory sounds and rich meta-data, recorded between April-2020 and February-2022 from 2635 individuals (1819 SARS-CoV-2 negative, 674 positive, and 142 recovered subjects). The respiratory sounds contained nine sound categories associated with variants of breathing, cough and speech. The rich metadata contained demographic information associated with age, gender and geographic location, as well as the health information relating to the symptoms, pre-existing respiratory ailments, comorbidity and SARS-CoV-2 test status. Our study is the first of its kind to manually annotate the audio quality of the entire dataset (amounting to 65~hours) through manual listening. The paper summarizes the data collection procedure, demographic, symptoms and audio data information. A COVID-19 classifier based on bi-directional long short-term (BLSTM) architecture, is trained and evaluated on the different population sub-groups contained in the dataset to understand the bias/fairness of the model. This enabled the analysis of the impact of gender, geographic location, date of recording, and language proficiency on the COVID-19 detection performance.

Rapid testing is essential to fighting pandemics such as COVID-19, the disease caused by the SARS-CoV-2 virus. Exhaled human breath contains multiple volatile molecules providing powerful potential for non-invasive diagnosis of diverse medical conditions. We investigated breath detection of SARS-CoV-2 infection using cavity-enhanced direct frequency comb spectroscopy (CE-DFCS), a state-of-the-art laser spectroscopic technique capable of a real-time massive collection of broadband molecular absorption features at ro-vibrational quantum state resolution and at parts-per-trillion volume detection sensitivity. Using a total of 170 individual breath samples (83 positive and 87 negative with SARS-CoV-2 based on Reverse Transcription Polymerase Chain Reaction tests), we report excellent discrimination capability for SARS-CoV-2 infection with an area under the Receiver-Operating-Characteristics curve of 0.849(4). Our results support the development of CE-DFCS as an alternative, rapid, non-invasive test for COVID-19 and highlight its remarkable potential for optical diagnoses of diverse biological conditions and disease states.

To identify patients who are hospitalized because of COVID-19 as opposed to those who were admitted for other indications, we compared the performance of different computable phenotype definitions for COVID-19 hospitalizations that use different types of data from the electronic health records (EHR), including structured EHR data elements, provider notes, or a combination of both data types. And conduct a retrospective data analysis utilizing chart review-based validation. Participants are 586 hospitalized individuals who tested positive for SARS-CoV-2 during January 2022. We used natural language processing to incorporate data from provider notes and LASSO regression and Random Forests to fit classification algorithms that incorporated structured EHR data elements, provider notes, or a combination of structured data and provider notes. Results: Based on a chart review, 38% of 586 patients were determined to be hospitalized for reasons other than COVID-19 despite having tested positive for SARS-CoV-2. A classification algorithm that used provider notes had significantly better discrimination than one that used structured EHR data elements (AUROC: 0.894 vs 0.841, p < 0.001), and performed similarly to a model that combined provider notes with structured data elements (AUROC: 0.894 vs 0.893). Assessments of hospital outcome metrics significantly differed based on whether the population included all hospitalized patients who tested positive for SARS-CoV-2 versus those who were determined to have been hospitalized due to COVID-19. This work demonstrates the utility of natural language processing approaches to derive information related to patient hospitalizations in cases where there may be multiple conditions that could serve as the primary indication for hospitalization.

In a recent study posted to the medRxiv* preprint server, an interdisciplinary team of researchers conducted an open, prospective pilot feasibility analysis through artificial intelligence (AI)-based platform to provide clinical decision support on coronavirus disease 2019 (COVID-19) outcomes. Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)-related symptoms and disease course pose an enormous burden on the healthcare facilities. During the COVID-19 pandemic, e-telemonitoring was recommended to reduce the pressure on the over-whelming healthcare systems and limit access to the emergency department (ED). Healthcare big data analysis use is increasing, as represented by the explosion of the internet of medical things (IoMT). This study was designed to estimate the application and integration of a dedicated AI-based support system with the territory and hospital intervention plan during the COVID-19 pandemic.

This Overview, Design Concepts, and Details Protocol (ODD) provides a detailed description of an agent-based model (ABM) that was developed to simulate hospitalizations during the COVID-19 pandemic. Using the descriptions of submodels, provided parameters, and the links to data sources, modelers will be able to replicate the creation and results of this model.

Severe acute respiratory syndrome (SARS), Middle East respiratory syndrome (MERS), and COVID-19 all broke out in recent decades and are caused by different strains of coronavirus (CoV). These viruses are considered to originate from bats and to have been transmitted to humans through intermediate hosts. SARS-CoV was identified in palm civets in wildlife markets and MERS-CoV in dromedary camels ([ 1 ][1]), but the direct source of the COVID-19 causative agent, SARS-CoV-2, is still undetermined. On page 172 of this issue, Oude Munnink et al. ([ 2 ][2]) report an in-depth investigation of SARS-CoV-2 infections in animals and humans working or living in 16 mink farms in the Netherlands. SARS-CoV-2 infections were detected in 66 out of 97 (68%) of the owners, workers, and their close contacts. Some people were infected with viral strains with an animal sequence signature, providing evidence of SARS-CoV-2 spillover back and forth between animals and humans within mink farms. Besides mink, multiple species of wild or domestic animals may also carry SARS-CoV-2 or its related viruses. Experimental infections and binding-affinity assays between the SARS-CoV-2 spike (a surface protein that mediates cell entry) and its receptor, angiotensin-converting enzyme II (ACE2), demonstrate that SARS-CoV-2 has a wide host range ([ 3 ][3]). After the SARS-CoV-2 outbreak, several groups reported SARS-related CoVs in horseshoe bats in China and in pangolins smuggled from South Asian countries, but according to genome sequence comparison, none are directly the progenitor virus of SARS-CoV-2 ([ 4 ][4]). Domestic cats and dogs, as well as tigers in zoos, have also been found to be naturally infected by SARS-CoV-2 from humans, but there is no evidence that they can infect humans, and so they are unlikely to be the source hosts of SARS-CoV-2 ([ 4 ][4], [ 5 ][5]). To date, SARS-CoV-2 infections in mink farms have been reported in eight countries (the Netherlands, Denmark, Spain, France, Sweden, Italy, the United States, and Greece), according to the World Organisation for Animal Health ([ 6 ][6]). In addition to animal-to-human transmission in farms, cold food supplier chains are raising substantial concern. In various cities in China, several small-scale COVID-19 outbreaks caused by virus-contaminated uncooked seafood or pork from overseas countries have been documented. It was found that viral genome signatures in these outbreaks were different from the viral strains present in China ([ 7 ][7], [ 8 ][8]). There is evidence that SARS-CoV-2 can survive up to 3 weeks in meat and on the surface of cold food packages without losing infectivity ([ 7 ][7], [ 8 ][8]). Thus, meat from SARS-CoV-2–infected animals or food packaging contaminated by SARS-CoV-2 could be a source of human infection (see the figure). This raises concerns about public health and agriculture in the prevention and control of SARS-CoV-2. Most SARS-CoV-2–infected animals do not display an obvious clinical syndrome, and infections would be unrecognized without routine diagnosis. The massive mink culling of infected farms is an efficient way to prevent further transmission of the virus. However, it cannot be applied to all domestic animals (if other species are found to be SARS-CoV-2 hosts). Thus, out of caution, extensive and strict quarantine measures should be implemented in all domestic farms with high-density animal populations. Because the virus is able to jump between some animals (such as mink) and humans, similar strategies should be applied to people in key occupations involving animal-human interfaces, such as animal farmers, zookeepers, or people who work in slaughterhouses. Notably, there is limited evidence of animal-to-human transmission of SARS-CoV-2 except for mink. Research on whether other domestic animals carry SARS-CoV-2, whether they can transmit it to humans, and factors related to spillover should be conducted. The RNA genome of SARS-CoV-2 seems relatively stable during transmission within human populations, although accumulated mutations have been detected. It is generally accepted that coronaviruses tend to exhibit rapid evolution when jumping to a different species. To keep the replication error rate low, coronaviruses encode several RNA-processing and proofreading enzymes that are thought to increase the fidelity of viral replication. However, viruses tend to have reduced fidelity in favor of adaptation to a new host species ([ 9 ][9]), although the mechanisms underlying this phenomenon are unclear. The coronaviral spike protein is prone to have more mutations because it is the first virus-host interaction protein and thus faces the strongest selection pressure. This molecular evolution can be observed in SARS-CoV genomes, which were under more adaptive pressure in the early stage of the epidemic (palm civet to human) than in later stages (human to human) ([ 10 ][10]). ![Figure][11] Possible SARS-CoV-2 transmission chains Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) spillover likely occurred from bat and/or pangolin (ancestral virus) through unidentified intermediate host animals (direct progenitor virus). Human SARS-CoV-2 strains infect susceptible domestic animals (such as mink) and likely adapt to these species through mutation. The virus can be transmitted from mink back to farm workers and close contacts. SARS-CoV-2 can also be transmitted to humans through contact with contaminated uncooked meat or food packaging. GRAPHIC: MELISSA THOMAS BAUM/ SCIENCE Mutations that occur in SARS-CoV-2 in animals may increase its pathogenesis or transmissibility in humans. Five clusters of SARS-CoV-2 strains were found in mink, each characterized by a specific mink-related variant. In Denmark, the cluster 5 strain of mink SARS-CoV-2 was less immunogenic to COVID-19 patient serum than was human SARS-CoV-2 because of mutations of the spike proteins in the mink strains ([ 11 ][12]). This cluster 5 strain has infected at least 12 people, and the clinical presentation, severity, and transmission among those infected are similar to those of other circulating human SARS-CoV-2 strains ([ 12 ][13]). Currently, there is no evidence that any mutation from mink strains of SARS-CoV-2 escapes neutralization by antibodies designed to target the prevalent human strains. However, considering the possible risk of spillover of SARS-CoV-2 between humans and some animals, it is imperative to closely monitor mutations in the viral genome from infected animals and humans, particularly the genome regions affecting diagnostic tests, antiviral drugs, and vaccine development. It is anticipated that vaccines will allow control of COVID-19. Vaccines have been developed against the current prevalent viral strains and could face challenges if there is continued spillover from animals. The viral genome mutations likely produced during interspecies transmission between animals and humans raise concerns about whether the current vaccines can protect against emerging strains in the future. The extensive sequencing of viral genomes from animals and humans and worldwide data sharing will be central to efforts to monitor the key mutations that could affect vaccine efficacy. Laboratory-based studies should test whether the observed mutations affect key features of the virus, including pathogenesis, immunogenicity, and cross-neutralization. Moreover, preparedness of vaccines based on newly detected variants should be considered in advance. In the long term, vaccination of animals should also be considered to avoid economic losses in agriculture. There has been debate about whether bats or pangolins, which carry coronaviruses with genomes that are ∼90 to 96% similar to human SARS-CoV-2, were the animal source of the first human outbreak ([ 4 ][4]). Evolutionary analyses of viral genomes from bats and pangolins indicate that further adaptions, either in animal hosts or in humans, occurred before the virus caused the COVID-19 pandemic ([ 13 ][14]). Therefore, an animal species that has a high population density to allow natural selection and a competent ACE2 protein for SARS-CoV-2—mink, for example—would be a possible host of the direct progenitor of SARS-CoV-2. Another debate concerns the source of SARS-CoV-2 that caused the COVID-19 outbreak at the end of 2019. The current data question the animal origin of SARS-CoV-2 in the seafood market where the early cases were identified in Wuhan, China. Given the finding of SARS-CoV-2 on the surface of imported food packages, contact with contaminated uncooked food could be an important source of SARS-CoV-2 transmission ([ 8 ][8]). Recently, SARS-CoV-2 antibodies were found in human serum samples taken outside of China before the COVID-19 outbreak was detected ([ 14 ][15], [ 15 ][16]), which suggests that SARS-CoV-2 existed for some time before the first cases were described in Wuhan. Retrospective investigations of preoutbreak samples from mink or other susceptible animals, as well as humans, should be conducted to identify the hosts of the direct progenitor virus and to determine when the virus spilled over into humans. 1. [↵][17]1. J. Cui, 2. F. Li, 3. Z. L. Shi , Nat. Rev. Microbiol. 17, 181 (2019). [OpenUrl][18][CrossRef][19][PubMed][20] 2. [↵][21]1. B. B. Oude Munnink et al ., Science 371, 172 (2020). [OpenUrl][22] 3. [↵][23]1. L. Wu et al ., Cell Discov. 6, 68 (2020). [OpenUrl][24] 4. [↵][25]1. B. Hu, 2. H. Guo, 3. P. Zhou, 4. Z. L. Shi , Nat. Rev. Microbiol. 10.1038/s41579-020-00459-7 (2020). 5. [↵][26]1. D. McAloose et al ., mBio 11, e02220-20 (2020). [OpenUrl][27][Abstract/FREE Full Text][28] 6. [↵][29]World Organisation for Animal Health, COVID-19 Portal: Events in Animals (2020); [www.oie.int/en/scientific-expertise/specific-information-and-recommendations/questions-and-answers-on-2019novel-coronavirus/events-in-animals/][30]. 7. [↵][31]1. P. Liu et al ., Biosaf. Health 10.1016/j.bsheal.2020.11.003 (2020). 8. [↵][32]1. J. Han, 2. X. Zhang, 3. S. He, 4. P. Jia , Environ. Chem. Lett. 10.1007/s10311-020-01101-x (2020). 9. [↵][33]1. R. L. Graham, 2. R. S. Baric , J. Virol. 84, 3134 (2010). [OpenUrl][34][Abstract/FREE Full Text][35] 10. [↵][36]Chinese SARS Molecular Epidemiology Consortium, Science 303, 1666 (2004). [OpenUrl][37][Abstract/FREE Full Text][38] 11. [↵][39]European Centre for Disease Prevention and Control, “Rapid Risk Assessment: Detection of New SARS-CoV-2 Variants Related to Mink” (2020); [www.ecdc.europa.eu/sites/default/files/documents/RRA-SARS-CoV-2-in-mink-12-nov-2020.pdf][40]. 12. [↵][41]1. R. Lassauniere et al ., “SARS-CoV-2 spike mutations arising in Danish mink and their spread to humans” (2020); . 13. [↵][42]1. K. G. Andersen, 2. A. Rambaut, 3. W. I. Lipkin, 4. E. C. Holmes, 5. R. F. Garry , Nat. Med. 26, 450 (2020). [OpenUrl][43][CrossRef][44][PubMed][45] 14. [↵][46]1. G. Apolone et al ., Tumori J. 10.1177/0300891620974755 (2020). 15. [↵][47]1. S. V. Basavaraju et al ., Clin. Infect. Dis. ciaa1785 (2020). Acknowledgments: Supported by China National Science Foundation for Excellent Scholars award 81822028 (P.Z.) and Strategic Priority Research Program of the Chinese Academy of Sciences awards XDB29010101 (Z.-L.S.) and XDB29010204 (P.Z.). [1]: #ref-1 [2]: #ref-2 [3]: #ref-3 [4]: #ref-4 [5]: #ref-5 [6]: #ref-6 [7]: #ref-7 [8]: #ref-8 [9]: #ref-9 [10]: #ref-10 [11]: pending:yes [12]: #ref-11 [13]: #ref-12 [14]: #ref-13 [15]: #ref-14 [16]: #ref-15 [17]: #xref-ref-1-1 "View reference 1 in text" [18]: {openurl}?query=rft.jtitle%253DNat.%2BRev.%2BMicrobiol.%26rft.volume%253D17%26rft.spage%253D181%26rft_id%253Dinfo%253Adoi%252F10.1038%252Fs41579-018-0118-9%26rft_id%253Dinfo%253Apmid%252F30531947%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [19]: /lookup/external-ref?access_num=10.1038/s41579-018-0118-9&link_type=DOI [20]: /lookup/external-ref?access_num=30531947&link_type=MED&atom=%2Fsci%2F371%2F6525%2F120.atom [21]: #xref-ref-2-1 "View reference 2 in text" [22]: {openurl}?query=rft.jtitle%253DScience%26rft.volume%253D371%26rft.spage%253D172%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [23]: #xref-ref-3-1 "View reference 3 in text" [24]: {openurl}?query=rft.jtitle%253DCell%2BDiscov.%26rft.volume%253D6%26rft.spage%253D68%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [25]: #xref-ref-4-1 "View reference 4 in text" [26]: #xref-ref-5-1 "View reference 5 in text" [27]: {openurl}?query=rft.jtitle%253DmBio%26rft_id%253Dinfo%253Adoi%252F10.1128%252FmBio.02220-20%26rft_id%253Dinfo%253Apmid%252F33051368%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [28]: /lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6NDoibWJpbyI7czo1OiJyZXNpZCI7czoxNDoiMTEvNS9lMDIyMjAtMjAiO3M6NDoiYXRvbSI7czoyMjoiL3NjaS8zNzEvNjUyNS8xMjAuYXRvbSI7fXM6ODoiZnJhZ21lbnQiO3M6MDoiIjt9 [29]: #xref-ref-6-1 "View reference 6 in text" [30]: http://www.oie.int/en/scientific-expertise/specific-information-and-recommendations/questions-and-answers-on-2019novel-coronavirus/events-in-animals/ [31]: #xref-ref-7-1 "View reference 7 in text" [32]: #xref-ref-8-1 "View reference 8 in text" [33]: #xref-ref-9-1 "View reference 9 in text" [34]: {openurl}?query=rft.jtitle%253DJ.%2BVirol.%26rft_id%253Dinfo%253Adoi%252F10.1128%252FJVI.01394-09%26rft_id%253Dinfo%253Apmid%252F19906932%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [35]: /lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6MzoianZpIjtzOjU6InJlc2lkIjtzOjk6Ijg0LzcvMzEzNCI7czo0OiJhdG9tIjtzOjIyOiIvc2NpLzM3MS82NTI1LzEyMC5hdG9tIjt9czo4OiJmcmFnbWVudCI7czowOiIiO30= [36]: #xref-ref-10-1 "View reference 10 in text" [37]: {openurl}?query=rft.jtitle%253DScience%26rft_id%253Dinfo%253Adoi%252F10.1126%252Fscience.1092002%26rft_id%253Dinfo%253Apmid%252F14752165%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [38]: /lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6Mzoic2NpIjtzOjU6InJlc2lkIjtzOjEzOiIzMDMvNTY2NC8xNjY2IjtzOjQ6ImF0b20iO3M6MjI6Ii9zY2kvMzcxLzY1MjUvMTIwLmF0b20iO31zOjg6ImZyYWdtZW50IjtzOjA6IiI7fQ== [39]: #xref-ref-11-1 "View reference 11 in text" [40]: http://www.ecdc.europa.eu/sites/default/files/documents/RRA-SARS-CoV-2-in-mink-12-nov-2020.pdf [41]: #xref-ref-12-1 "View reference 12 in text" [42]: #xref-ref-13-1 "View reference 13 in text" [43]: {openurl}?query=rft.jtitle%253DNat.%2BMed.%26rft.volume%253D26%26rft.spage%253D450%26rft_id%253Dinfo%253Adoi%252F10.1038%252Fs41591-020-0820-9%26rft_id%253Dinfo%253Apmid%252Fhttp%253A%252F%252Fwww.n%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [44]: /lookup/external-ref?access_num=10.1038/s41591-020-0820-9&link_type=DOI [45]: /lookup/external-ref?access_num=http://www.n&link_type=MED&atom=%2Fsci%2F371%2F6525%2F120.atom [46]: #xref-ref-14-1 "View reference 14 in text" [47]: #xref-ref-15-1 "View reference 15 in text"

Distinguishing COVID-19 from other flu-like illnesses can be difficult due to ambiguous symptoms and still an initial experience of doctors. Whereas, it is crucial to filter out those sick patients who do not need to be tested for SARS-CoV-2 infection, especially in the event of the overwhelming increase in disease. As a part of the presented research, logistic regression and XGBoost classifiers, that allow for effective screening of patients for COVID-19, were generated. Each of the methods was tuned to achieve an assumed acceptable threshold of negative predictive values during classification. Additionally, an explanation of the obtained classification models was presented. The explanation enables the users to understand what was the basis of the decision made by the model. The obtained classification models provided the basis for the DECODE service (decode.polsl.pl), which can serve as support in screening patients with COVID-19 disease. Moreover, the data set constituting the basis for the analyses performed is made available to the research community. This data set consisting of more than 3,000 examples is based on questionnaires collected at a hospital in Poland.