{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T06:45:03Z","timestamp":1764744303087,"version":"3.46.0"},"reference-count":61,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Prediction of infection status is critical for effective disease management and timely intervention. Traditional diagnostic methods for Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) are challenged by varying sensitivities and specificities, necessitating the evaluation of advanced statistical approaches. This study evaluated the predictive performance of frequentist logistic regression, Bayesian logistic regression, and a random forest classifier using clinical and demographic predictors to predict PCR positivity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methodology<\/jats:title>\n                    <jats:p>A total of 950 participants were analyzed using three modeling approaches. To address class imbalance, the data were balanced using the Synthetic Minority Oversampling Technique (SMOTE) before training the random forest classifier. Predictors include IgG serostatus, travel history (international and domestic), self-reported symptoms (such as loss of smell, fatigue, sore throat), sex, and age. Three models were developed: (1) frequentist logistic regression; (2) Bayesian logistic regression with a moderately informative Normal (mean\u202f=\u202f1, SD\u202f=\u202f2) prior and a weakly informative Cauchy (0, 2.5) prior; and (3) machine learning (ML) using a random forest classifier. Missing data were minimal (&amp;lt;2%) and handled through imputation, with sensitivity analyses confirming no material impact on model performance. Performance was evaluated using odds ratios, posterior means with credible intervals, and area under the ROC curve (AUC).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Of the 950 participants, 74.8% tested positive for SARS-CoV-2. The frequentist logistic regression identified recent international travel (Odds Ratio\u202f=\u202f4.8), loss of smell (OR\u202f=\u202f2.3), and domestic travel (OR\u202f=\u202f1.5) as the strongest predictors of PCR positivity. The Bayesian model yielded similar posterior estimates, confirming the robustness of these associations across prior assumptions. The random forest classifier achieved the highest discriminative performance (AUC\u202f=\u202f0.947\u20130.963). Notably, age and sex were not significant in the regression models but emerged as influential predictors in the random forest model, suggesting possible nonlinear or interaction effects.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The machine learning approach (random forest) outperformed the logistic regression models in predictive accuracy. Bayesian regression confirmed the reliability of key predictors and allowed quantification of uncertainty. These findings highlight that simple, routinely collected symptom and exposure data can support rapid, resource-conscious screening for SARS-CoV-2, particularly when laboratory testing capacity is limited.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2025.1668477","type":"journal-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T06:40:14Z","timestamp":1764744014000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Comparative analysis of frequentist, Bayesian, and machine learning models for predicting SARS-CoV-2 PCR positivity"],"prefix":"10.3389","volume":"8","author":[{"given":"Francis Chukwuebuka","family":"Ihenetu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chinyere Ihuarulam","family":"Okoro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Makuochukwu Maryann","family":"Ozoude","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emeka H.","family":"Okechukwu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Easter Godwin","family":"Nwokah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,12,3]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"41","DOI":"10.3390\/diseases8040041","article-title":"Newly reported studies on the increase in gastrointestinal symptom prevalence with COVID-19 infection: a comprehensive systematic review and Meta-analysis","volume":"8","author":"Akin","year":"2020","journal-title":"Diseases"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"e88","DOI":"10.1017\/ash.2024.82","article-title":"Prediction model to identify infectious COVID-19 patients in the emergency department","volume":"4","author":"Aung","year":"2024","journal-title":"Antimicrob. Steward. Healthc. Epidemiol."},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2021-050450","article-title":"Importance of sex and gender factors for COVID-19 infection and hospitalisation: a sex-stratified analysis using machine learning in UK biobank data","volume":"12","author":"Azizi","year":"2022","journal-title":"BMJ Open"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"100631","DOI":"10.1016\/j.epidem.2022.100631","article-title":"Symptom-based vs asymptomatic testing for controlling SARS-CoV-2 transmission in low- and middle-income countries: a modelling analysis","volume":"41","author":"Baik","year":"2022","journal-title":"Epidemics"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1038\/s41746-020-0300-0","article-title":"Estimating the efficacy of symptom-based screening for COVID-19","volume":"3","author":"Callahan","year":"2020","journal-title":"Npj Digit. Med."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"E702","DOI":"10.1503\/cmaj.200869","article-title":"Anosmia and dysgeusia associated with SARS-CoV-2 infection: an age-matched case-control study","volume":"192","author":"Carignan","year":"2020","journal-title":"Can. Med. Assoc. J."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1186\/s12859-018-2264-5","article-title":"Random forest versus logistic regression: a large-scale benchmark experiment","volume":"19","author":"Couronn\u00e9","year":"2018","journal-title":"BMC Bioinformatics"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"n208","DOI":"10.1136\/bmj.n208","article-title":"Put to the test: use of rapid testing technologies for covid-19","volume":"372","author":"Crozier","year":"2021","journal-title":"BMJ"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"78","DOI":"10.12720\/jait.11.2.78-83","article-title":"Comparison of statistical logistic regression and randomforest machine learning techniques in predicting diabetes","volume":"11","author":"Daghistani","year":"2020","journal-title":"J. Adv. Inf. Technol."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"306","DOI":"10.3390\/geosciences13100306","article-title":"Na\u00efve and semi-na\u00efve Bayesian classification of landslide susceptibility applied to the Kulekhani River basin in Nepal as a test case","volume":"13","author":"De Smedt","year":"2023","journal-title":"Geosciences"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"e0268119","DOI":"10.1371\/journal.pone.0268119","article-title":"The influence of gender on COVID-19 infections and mortality in Germany: insights from age- and gender-specific modeling of contact rates, infections, and deaths in the early phase of the pandemic","volume":"17","author":"Doerre","year":"2022","journal-title":"PLoS One"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1101\/2020.06.08.20124412","article-title":"An assessment of Bayesian model-averaged logistic regression for intensive-care prognosis","author":"Dybowski","year":"2020","journal-title":"medRxiv"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"e049699","DOI":"10.1136\/bmjopen-2021-049699","article-title":"Assessing the capacity of symptom scores to predict COVID-19 positivity in Nigeria: a national derivation and validation cohort study","volume":"11","author":"Elimian","year":"2021","journal-title":"BMJ Open"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"e1003777","DOI":"10.1371\/journal.pmed.1003777","article-title":"Predictive symptoms for COVID-19 in the community: REACT-1 study of over 1 million people","volume":"18","author":"Elliott","year":"2021","journal-title":"PLoS Med"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"221","DOI":"10.18683\/germs.2021.1259","article-title":"Clinical diagnosis of COVID-19. A multivariate logistic regression analysis of symptoms of COVID-19 at presentation","volume":"11","author":"Fleitas","year":"2021","journal-title":"Germs"},{"key":"ref16","volume-title":"AI model predicts if a COVID-19 test might be positive or not","author":"Galoustian","year":"2022"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1201\/b16018","volume-title":"Bayesian data analysis","author":"Gelman","year":"2013"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1360","DOI":"10.1214\/08-aoas191","article-title":"A weakly informative default prior distribution for logistic and other regression models","volume":"2","author":"Gelman","year":"2008","journal-title":"Ann. Appl. Stat."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"bjaa081","DOI":"10.1093\/chemse\/bjaa081","article-title":"Recent smell loss is the best predictor of COVID-19 among individuals with recent respiratory symptoms","volume":"46","author":"Gerkin","year":"2020","journal-title":"Chem. Senses"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"2976","DOI":"10.1093\/cid\/ciaa599","article-title":"Associations of early COVID-19 cases in San Francisco with domestic and international travel","volume":"71","author":"Gu","year":"2020","journal-title":"Clin. Infect. Dis."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"ciaa1343","DOI":"10.1093\/cid\/ciae121","article-title":"Infectious Diseases Society of America guidelines on the diagnosis of COVID-19: serologic testing","volume":"121","author":"Hayden","year":"2024","journal-title":"Clin. Infect. Dis."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1186\/s12879-022-07627-5","article-title":"Modelling of a triage scoring tool for SARS-COV-2 PCR testing in health-care workers: data from the first German COVID-19 testing unit in Munich","volume":"22","author":"Hohl","year":"2022","journal-title":"BMC Infect. Dis."},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1002\/9781118548387","volume-title":"Applied logistic regression","author":"Hosmer","year":"2013"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"100168","DOI":"10.1016\/j.microb.2024.100168","article-title":"Optimizing diagnosis of pediatric Streptococcus pyogenes infections: a clinical prediction model","volume":"5","author":"Ihenetu","year":"2024","journal-title":"The Microbe"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"2383","DOI":"10.1007\/s42399-021-01059-z","article-title":"False-negative RT-PCR findings and double mutant variant as factors of an overwhelming second wave of COVID-19 in India: an emerging global health disaster","volume":"3","author":"Jindal","year":"2021","journal-title":"SN Compr. Clin. Med."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"9497","DOI":"10.1038\/s41598-022-13775-0","article-title":"A measure to estimate the risk of imported COVID-19 cases and its application for evaluating travel-related control measures","volume":"12","author":"Kang","year":"2022","journal-title":"Sci. Rep."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1186\/s12985-021-01489-0","article-title":"False negative rate of COVID-19 PCR testing: a discordant testing analysis","volume":"18","author":"Kanji","year":"2021","journal-title":"Virol. J."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"2634","DOI":"10.3390\/diagnostics14232634","article-title":"The impact of the SMOTE method on machine learning and ensemble learning performance results in addressing class imbalance in data used for predicting Total testosterone deficiency in type 2 diabetes patients","volume":"14","author":"Kivrak","year":"2024","journal-title":"Diagnostics"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"262","DOI":"10.7326\/m20-1495","article-title":"Variation in false-negative rate of reverse transcriptase polymerase chain reaction-based SARS-CoV-2 tests by time since exposure","volume":"173","author":"Kucirka","year":"2020","journal-title":"Ann. Intern. Med."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"e0235460","DOI":"10.1371\/journal.pone.0235460","article-title":"COVID-19 symptoms predictive of healthcare workers\u2019 SARS-CoV-2 PCR results","volume":"15","author":"Lan","year":"2020","journal-title":"PLoS One"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"31","DOI":"10.31083\/j.fbl2802031","article-title":"A computational approach in the diagnostic process of COVID-19: the missing link between the laboratory and emergency department","volume":"28","author":"Lanzilao","year":"2023","journal-title":"Front. Biosci."},{"key":"ref32","volume-title":"Bayesian logistic regression essentials","author":"Lee","year":"2025"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/j.jss.2022.01.012","article-title":"Machine learning improves prediction over logistic regression on resected Colon Cancer patients","volume":"275","author":"Leonard","year":"2022","journal-title":"J. Surg. Res."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"012010","DOI":"10.1088\/1742-6596\/1725\/1\/012010","article-title":"Bayesian logistic regression and its application for hypothyroid prediction in post-radiation nasopharyngeal cancer patients","volume":"1725","author":"Lukman","year":"2021","journal-title":"J. Phys. Conf. Ser."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"563465","DOI":"10.3389\/fmed.2021.563465","article-title":"A COVID-19 test triage tool, predicting negative results and reducing the testing burden on healthcare systems during a pandemic","volume":"8","author":"Lundon","year":"2021","journal-title":"Front. Med."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"1037","DOI":"10.1038\/s41591-020-0916-2","article-title":"Real-time tracking of self-reported symptoms to predict potential COVID-19","volume":"26","author":"Menni","year":"2020","journal-title":"Nat. Med."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"6568","DOI":"10.1038\/s41598-022-10344-3","article-title":"Risk factors for severe COVID-19 differ by age for hospitalized adults","volume":"12","author":"Molani","year":"2022","journal-title":"Sci. Rep."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"40","DOI":"10.12688\/f1000research.28393.1","article-title":"Anosmia and dysgeusia in SARS-CoV-2 infection: incidence and effects on COVID-19 severity and mortality, and the possible pathobiology mechanisms - a systematic review and meta-analysis","volume":"10","author":"Mutiawati","year":"2021","journal-title":"F1000Res"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"3113119","DOI":"10.1155\/2022\/3113119","article-title":"Symptom-based COVID-19 prognosis through AI-based IoT: a bioinformatics approach","volume":"2022","author":"Pal","year":"2022","journal-title":"Biomed. Res. Int."},{"key":"ref40","volume-title":"Largest study of lingering COVID-19 effects suggests a looming problem","author":"Park","year":"2021"},{"key":"ref41","volume-title":"Testing: a neglected, critical component of the COVID-19 response - the COVID-19 global accountability project: COVID GAP","author":"Parker","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"909","DOI":"10.1016\/j.gastha.2022.07.002","article-title":"Gastrointestinal manifestations of coronavirus disease 2019 across the United States: a multicenter cohort study","volume":"1","author":"Patel","year":"2022","journal-title":"Gastro Hep Advances"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"588711","DOI":"10.3389\/fmed.2020.588711","article-title":"Prevalence, mechanisms, and implications of gastrointestinal symptoms in COVID-19","volume":"7","author":"Perisetti","year":"2020","journal-title":"Front. Med."},{"key":"ref44","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1038\/s41591-020-1123-x","article-title":"Wearable sensor data and self-reported symptoms for COVID-19 detection","volume":"27","author":"Quer","year":"2020","journal-title":"Nat. Med."},{"key":"ref45","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1007\/s10115-011-0465-6","article-title":"SMOTE-RSB *: a hybrid preprocessing approach based on oversampling and undersampling for high imbalanced data-sets using SMOTE and rough sets theory","volume":"33","author":"Ramentol","year":"2011","journal-title":"Knowl. Inf. Syst."},{"key":"ref46","doi-asserted-by":"publisher","first-page":"14892","DOI":"10.1038\/s41598-024-63707-3","article-title":"Comparing machine learning screening approaches using clinical data and cytokine profiles for COVID-19 in resource-limited and resource-abundant settings","volume":"14","author":"Rashidi","year":"2024","journal-title":"Sci. Rep."},{"key":"ref47","doi-asserted-by":"publisher","first-page":"852998","DOI":"10.3389\/fmed.2022.852998","article-title":"Is there less alteration of smell sensation in patients with omicron SARS-CoV-2 variant infection?","volume":"9","author":"Rodriguez-Sevilla","year":"2022","journal-title":"Front. Med."},{"key":"ref48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.9734\/ajpas\/2023\/v22i3483","article-title":"Determination of recent in-migrants in Yogyakarta using Bayesian regression logistics","volume":"22","author":"Rohmah","year":"2023","journal-title":"Asian J. Probab. Stat."},{"key":"ref49","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1016\/j.rgmxen.2020.04.001","article-title":"Beware: gastrointestinal symptoms can be a manifestation of COVID-19","volume":"85","author":"Schmulson","year":"2020","journal-title":"Revista de Gastroenterolog\u00eda de M\u00e9xico (English Edition)."},{"key":"ref50","doi-asserted-by":"publisher","first-page":"1159","DOI":"10.1007\/s10654-022-00919-9","article-title":"A population-based cohort study of sex and risk of severe outcomes in covid-19","volume":"37","author":"Sieurin","year":"2022","journal-title":"Eur. J. Epidemiol."},{"key":"ref51","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1186\/s12911-022-02057-4","article-title":"Comparison of machine learning methods with logistic regression analysis in creating predictive models for risk of critical in-hospital events in COVID-19 patients on hospital admission","volume":"22","author":"Sievering","year":"2022","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"ref52","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1186\/s12911-025-02955-3","article-title":"Comparing conventional and Bayesian workflows for clinical outcome prediction modelling with an exemplar cohort study of severe COVID-19 infection incorporating clinical biomarker test results","volume":"25","author":"Sullivan","year":"2025","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"ref53","doi-asserted-by":"publisher","first-page":"17851","DOI":"10.1038\/s41598-025-00873-y","article-title":"Optimizing credit card fraud detection with random forests and SMOTE","volume":"15","author":"Sundaravadivel","year":"2025","journal-title":"Sci. Rep."},{"key":"ref54","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1093\/labmed\/lmaa111","article-title":"Machine learning prediction of SARS-CoV-2 polymerase chain reaction results with routine blood tests","volume":"52","author":"Tschoellitsch","year":"2020","journal-title":"Lab. Med."},{"key":"ref55","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1038\/s41579-020-00461-z","article-title":"Considerations for diagnostic COVID-19 tests","volume":"19","author":"Vandenberg","year":"2020","journal-title":"Nat. Rev. Microbiol."},{"key":"ref56","volume-title":"Prior choice recommendations","author":"Vehtari","year":"2025"},{"key":"ref57","doi-asserted-by":"publisher","first-page":"116027","DOI":"10.1016\/j.diagmicrobio.2023.116027","article-title":"Rapid antigen tests for SARS-CoV-2 - a synopsis of the medical evidence","volume":"107","author":"Wertenauer","year":"2023","journal-title":"Diagn. Microbiol. Infect. Dis."},{"key":"ref58","doi-asserted-by":"publisher","first-page":"2000568","DOI":"10.2807\/1560-7917.ES.2020.25.50.2000568","article-title":"Estimating the false-negative test probability of SARS-CoV-2 by RT-PCR","volume":"25","author":"Wikramaratna","year":"2020","journal-title":"Euro Surveill."},{"key":"ref59","doi-asserted-by":"publisher","first-page":"94","DOI":"10.53433\/yyufbed.837533","article-title":"A Bayesian approach to binary logistic regression model with application to OECD data","volume":"26","author":"Yilmaz","year":"2021","journal-title":"Y\u00fcz\u00fcnc\u00fc Y\u0131l \u00dcniversitesi Fen Bilimleri Enstit\u00fcs\u00fc Dergisi"},{"key":"ref60","doi-asserted-by":"publisher","first-page":"13913","DOI":"10.1038\/s41598-021-93126-7","article-title":"Prediction of individual COVID-19 diagnosis using baseline demographics and lab data","volume":"11","author":"Zhang","year":"2021","journal-title":"Sci. Rep."},{"key":"ref61","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-020-00372-6","article-title":"Machine learning-based prediction of COVID-19 diagnosis based on symptoms","volume":"4","author":"Zoabi","year":"2021","journal-title":"NPJ Digit. Med."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1668477\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T06:40:16Z","timestamp":1764744016000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1668477\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":61,"alternative-id":["10.3389\/frai.2025.1668477"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1668477","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,3]]},"article-number":"1668477"}}