Prediction of severe COVID-19 infection at the time of testing: A machine learning approach

Early and effective detection of severe infection cases during a pandemic can significantly help patient prognosis and resource allocation. We develop a machine learning framework for detecting severe COVID-19 cases at the time of RT-PCR testing. We retrospectively studied 988 patients from a small Canadian province that tested positive for SARS-CoV-2 where 42 (4%) cases were at-risk (i.e., resulted in hospitalization, admission to ICU, or death), and 8 (< 1%) cases resulted in death. The limited information available at the time of RT-PCR testing included age, comorbidities, and patients reported symptoms, totaling 27 features. Vaccination status was unavailable. Due to the severe class imbalance and small dataset size, we formulated the problem of detecting severe COVID as anomaly detection and applied three models: one-class support vector machine (OCSVM), weight-adjusted XGBoost, and weight-adjusted Ad-aBoost. The OCSVM was the best performing model for detecting the deceased cases with an average 95% true positive rate (TPR) and 27.2% false positive rate (FPR). Meanwhile, the XGBoost provided the best performance for detecting the at-risk cases with an average 96.2% TPR and 19% FPR. In addition, we developed a novel extension to SHAP interpretability to explain the outputs from the models. In agreement with conventional knowledge, we found that comorbidities were influential in predicting severity, however, we also found that symptoms were generally more influential, noting that machine learning combines all available data and is not a single-variate statistical analysis.

How effective was Newfoundland & Labrador's travel ban to prevent the spread of COVID-19? An agent-based analysis

BackgroundTo prevent the spread of COVID-19 in Newfoundland & Labrador (NL), NL implemented a wide travel ban in May 2020. We estimate the effectiveness of this travel ban using a customized agent-based simulation (ABS). MethodsWe built an individual-level ABS to simulate the movements and behaviors of every member of the NL population, including arriving and departing travellers. The model considers individual properties (spatial location, age, comorbidities) and movements between environments, as well as age-based disease transmission with pre-symptomatic, symptomatic, and asymptomatic transmission rates. We examine low, medium, and high travel volume, traveller infection rates, and traveller quarantine compliance rates to determine the effect of travellers on COVID spread, and the ability of contact tracing to contain outbreaks. ResultsInfected travellers increased COVID cases by 2-52x (8-96x) times and peak hospitalizations by 2-49x (8-94x), with (without) contact tracing. Although contact tracing was highly effective at reducing spread, it was insufficient to stop outbreaks caused by travellers in even the best-case scenario, and the likelihood of exceeding contact tracing capacity was a concern in most scenarios. Quarantine compliance had only a small impact on COVID spread; travel volume and infection rate drove spread. InterpretationNLs travel ban was likely a critically important intervention to prevent COVID spread. Even a small number of infected travellers can play a significant role in introducing new chains of transmission, resulting in exponential community spread and significant increases in hospitalizations, while outpacing contact tracing capabilities. With the presence of more transmissible variants, e.g., the UK variant, prevention of imported cases is even more critical.