Validation of a Novel IoT and AI based Point-of-Care Testing Laboratory: Analytical Accuracy and Clinical Agreement (preprint)

ABSTRACT Point-of-care testing (POCT) offers several advantages over traditional laboratory testing. Offering less invasive testing with a faster turnaround time is not enough if not associated with an acceptable level of accuracy. Here, we show the analytical validation behind the multi-analyte POCT immunochromatography analyser, Hilab Flow (HiF). Analyses from 4,518 clinical samples were compared to College of American Pathologists accredited laboratories for ten quantitative and thirteen qualitative exams. Compatibility between methods was evaluated in terms of association/correlation and clinical agreement. Strong correlation/ concordance was observed between quantitative (CHOL, HDL-c, TG, HbA1c, Glycemia, 25-Hydroxy Vitamin D, TSH, Uric Acid, Creatinine, Urea) and qualitative methods (COVID-19 IgG/ IgM, Beta-hCG, Syphilis, Anti-HBsAg, Zika IgG/ IgM, Influenza A/B, HIV, HCV, HBsAg, Dengue NS1, COVID-19 Ag, Dengue IgG/ IgM, PSA). Approval criteria was obtaining a kappa agreement > 0.8 or a Pearson correlation > 0.9 depending on the exam. Overall percentage agreement was greater than 95% for all exams, indicating a good clinical agreement to gold-standard laboratory-based tests. Results indicate all exams are suitable for POCT and present a reliable performance. Data support the analyser is a useful tool to aid decision-making at the clinical setting, with potential to contribute with healthcare solutions in diagnostic medicine worldwide.

Time-to-event assessment for the discovery of the proper prognostic value of clinical biomarkers optimized for COVID-19 (preprint)

In the early days of the pandemic, clinical biomarkers for COVID -19 have been investigated to predict patient mortality. A decision tree has been proposed previously comprising three variables, i.e., lactic dehydrogenase (LDH), high-sensitivity C-reactive protein (CRP), and lymphocyte percentage, with more than 90% accuracy in a public cohort. In this work, we highlighted the importance of the cohort made publicly available and complemented the findings by incorporating further evaluation. Results confirmed poor short-term prognosis to abnormal levels of some laboratorial indicators, such as LDH, CRP, lymphocytes, interleukin-6, and procalcitonin. In addition, our findings provide insights into COVID-19 research, such as key levels of fibrin degradation products, which are directly associated with the Dimerized plasmin fragment D and could indicate active coagulation and thrombosis. Still, we highlight here the prognostic value of interleukin-6, a cytokine that induces inflammatory response and may serve as a predictive biomarker.