Validation of a COVID-19 self-assessment tool for the prediction of COVID-19 in a primary health care setting in Egypt

Background: As SARS-CoV-2 infection is sweeping the globe, early identification and timely management of infected patients will alleviate unmet health care demands and ultimately control of the disease. Remote COVID-19 self-assessment tools will offer a potential strategy for patient guidance on medical consultation versus home care without requiring direct attention from healthcare professionals. Objective(s): This study aimed to assess the validity and interrater reliability of the initial and modified versions of a COVID-19 self-assessment prediction tool introduced by the Egyptian Ministry of Health and Population (MoHP) early in the epidemic. The scoring tool was released for the public through media outlets for remote self-assessment of SARS-CoV-2 infection connecting patients with the appropriate level of care. Methods: We evaluated the initial score in the analysis of 818 consecutive cases presenting with symptoms suggesting COVID-19 in a single-primary health care clinic in Alexandria during the epidemic in Egypt (mid-February through July). Validity parameters, interrater agreement and accuracy of the score as a triage tool were calculated versus the COVID-19 polymerase chain reaction (PCR) test. Results: A total of 818 patients reporting symptoms potentially attributable to COVID-19 were enrolled. The initial tool correctly identified 296 of 390 COVID-19 PCR +ve cases (sensitivity = 75.9%, specificity = 42.3%, positive predictive value = 54.5%, negative predictive value = 65.8%). The modified versions of the MoHP triage score yielded comparable results albeit with a better accuracy during the late epidemic phase. Recent history of travel [OR (95% CI) = 12.1 (5.0-29.4)] and being a health care worker [OR (95% CI) = 5.8 (2.8-11.9)] were major predictors of SARS-CoV-2 infection in early and late epidemic phases, respectively. On the other hand, direct contact with a respiratory infection case increased the risk of infection by three folds throughout the epidemic period. Conclusion: The tested score has a sufficient predictive value and potential as a triage tool in primary health care settings. Updated implementation of this home-grown tool will improve COVID-19 response at the primary health care level.