Sun Y, Koh V, Marimuthu K, et al. - Researchers conducted a retrospective case-control study including individuals (7 to 98 years) presenting at the designated national outbreak screening center and tertiary care hospital in Singapore for SARS-CoV-2 testing from January 26 to February 16, 2020 in order to develop an algorithm for estimating the risk of COVID-19 using demographic, clinical, laboratory and exposure-risk variables ascertainable at presentation. Polymerase chain reaction (PCR) testing of sputum, nasopharyngeal swabs or throat swabs was performed to confirm COVID-19 status. Model development employed Akaike’s information criterion in a stepwise fashion to create logistic regression models, which were then translated into prediction scores. The study population comprised 788 individuals; of these, 54 (6.9%) were SARS-CoV-2 positive and 734 (93.1%) were SARS-CoV-2 negative. All the models incorporating clinical tests (Models 1, 2 and 3) performed well using leave-out-one cross validation. Findings suggest that individuals at high risk of COVID-19 could be identified with rapidly ascertainable clinical and laboratory data. Further, these data may allow prioritization of PCR-testing and containment efforts. For prediction models, basic laboratory test results were essential.