Analytical Accuracy and Clinical Agreement of a Novel Internet of Things and AI-based Point-of-Care Testing Laboratory

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.