Highlights
RT-PCR followed by CT shows high sensitivity for detecting COVID-19.
Immunological tests should use a combination of IgG and IgM.
The genes E and RdRp present high analytical sensitivity to detect the virus.
Assays for molecular diagnosis should employ 2-target systems.
Studies of diagnostic tests for COVID-19 are of moderate methodological quality.
Objective
This study aimed to implement and evaluate machine learning based-models to predict COVID-19’ diagnosis and disease severity.
Methods
COVID-19 test samples (positive or negative results) from patients who attended a single hospital were evaluated. Patients diagnosed with COVID-19 were categorised according to the severity of the disease. Data were submitted to exploratory analysis (principal component analysis, PCA) to detect outlier samples, recognise patterns, and identify important variables. Based on patients’ laboratory tests results, machine learning models were implemented to predict disease positivity and severity. Artificial neural networks (ANN), decision trees (DT), partial least squares discriminant analysis (PLS-DA), and K nearest neighbour algorithm (KNN) models were used. The four models were validated based on the accuracy (area under the ROC curve).
Results
The first subset of data had 5,643 patient samples (5,086 negatives and 557 positives for COVID-19). The second subset included 557 COVID-19 positive patients. The ANN, DT, PLS-DA, and KNN models allowed the classification of negative and positive samples with >84% accuracy. It was also possible to classify patients with severe and non-severe disease with an accuracy >86%. The following were associated with the prediction of COVID-19 diagnosis and severity: hyperferritinaemia, hypocalcaemia, pulmonary hypoxia, hypoxemia, metabolic and respiratory acidosis, low urinary pH, and high levels of lactate dehydrogenase.
Conclusion
Our analysis shows that all the models could assist in the diagnosis and prediction of COVID-19 severity.
We investigated the predictors of delay in the diagnosis and mortality of patients with COVID-19 in Rio de Janeiro, Brazil. A cohort of 3,656 patients were evaluated (Feb-Apr 2020) and patients’ sociodemographic characteristics, and social development index (SDI) were used as determinant factors of diagnosis delays and mortality. Kaplan-Meier survival analyses, time-dependent Cox regression models, and multivariate logistic regression analyses were conducted. The median time from symptoms onset to diagnosis was eight days (interquartile range [IQR] 7.23-8.99 days). Half of the patients recovered during the evaluated period, and 8.3% died. Mortality rates were higher in men. Delays in diagnosis were associated with male gender (p = 0.015) and patients living in low SDI areas (p < 0.001). The age groups statistically associated with death were: 70-79 years, 80-89 years, and 90-99 years. Delays to diagnosis greater than eight days were also risk factors for death. Delays in diagnosis and risk factors for death from COVID-19 were associated with male gender, age under 60 years, and patients living in regions with lower SDI. Delays superior to eight days to diagnosis increased mortality rates.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.