Back

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

Malucelli, L.; Alves, G. L. N.; dos Santos, C. M.; Severo, M.; Ribeiro, V. H. A.; de Almeida, B. M. M.; Klosovski, C. C.; Martinez, T. L. d. R.; Scartezini, M.; Figueredo, M. V. M.

2021-10-30 health systems and quality improvement
10.1101/2021.10.29.21264864 medRxiv
Show abstract

Point-of-care testing (POCT) offers several advantages over conventional laboratory testing. Nonetheless, a faster turnaround time, with less invasive procedures, is not enough if not associated with an acceptable level of accuracy. Here, we show the analytical validation behind the Hilab Flow (HiF), a multi-analyte POCT analyzer. HiF quantitative and qualitative tests for 6,175 clinical samples were compared to gold-standard methods from College of American Pathologists accredited laboratories. The compatibility between methods was evaluated in terms of association and clinical agreement. The established approval criteria was a kappa agreement > 0.8. A strong concordance was observed for the 27 analytes tested. Accuracy was greater than 90% for all HiF exams, indicating a good clinical agreement to gold standard laboratory testing. Results indicate that all quantitative and qualitative tests are suitable for POCT and present a reliable performance. HiF stands as a useful tool to aid decision-making in the clinical setting, with potential to contribute to healthcare solutions in diagnostic medicine worldwide.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.