Covid-19 Automated Diagnosis and Risk Assessment through Metabolomics and Machine Learning.

COVID-19 is still placing a heavy health and financial burden worldwide. Impairment in patient screening and risk management plays a fundamental role on how governments and authorities are directing resources, planning reopening, as well as sanitary countermeasures, especially in regions where poverty is a major component in the equation. An efficient diagnostic method must be highly accurate, while having a cost-effective profile. We combined a machine learning-based algorithm with mass spectrometry to create an expeditious platform that discriminate COVID-19 in plasma samples within minutes, while also providing tools for risk assessment, to assist healthcare professionals in patient management and decision-making. A cross-sectional study enrolled 815 patients (442 COVID-19, 350 controls and 23 COVID-19 suspicious) from three Brazilian epicenters from April to July 2020. We were able to elect and identify 19 molecules related to the disease's pathophysiology and several discriminating features to patient's health-related outcomes. The method applied for COVID-19 diagnosis showed specificity >96% and sensitivity >83%, and specificity >80% and sensitivity >85% during risk assessment, both from blinded data. Our method introduced a new approach for COVID-19 screening, providing the indirect detection of infection through metabolites and contextualizing the findings with the disease's pathophysiology. The pairwise analysis of biomarkers brought robustness to the model developed using machine learning algorithms, transforming this screening approach in a tool with great potential for real-world application.

Efficient detection of Zika virus RNA in patients' blood from the 2016 outbreak in Campinas, Brazil.

Infection with Zika virus (ZIKV), a mosquito-borne flavivirus has been casually linked with increased congenital microcephaly in Brazil from 2015 through 2016. Sensitive and specific diagnosis of patients with Zika fever (ZIKF) remains critical for patient management. We developed a ZIKV NS5 qRT-PCR assay by combining primers described by Balm et al. and a new Taqman probe. The assay was evaluated and compared with another assay described by Lanciotti et al. (ZIKV 1107) using 51 blood and 42 urine samples from 54 suspected ZIKV patients. ZIKV NS5 performed better in terms of sensitivity with more samples detected as ZIKV-positive (n = 37) than ZIKV 1107 (n = 34) for urine, and ZIKV-positive (n = 29) than ZIKV 1107 (n = 26) for blood. Both assays displayed good overall agreement for urine (κappa = 0.770) and blood (κappa = 0.825) samples. Improved availability of validated diagnostic tests, such ZIKV NS5 qRT-PCR, will be critical to ensure adequate and accurate ZIKV diagnosis.