Comparing artificial intelligence based diagnosis with expert results in SARS-COV-2 RT-qPCR

Abstract

Objectives: Reverse transcription and real-time polymerase chain reaction (RT-qPCR) based on the SARS-CoV-2 viral RNA demonstration is the gold standard in diagnosis. Data files obtained from PCR devices should be analysed by a specialist physician and results should be transferred to Laboratory Information Management System (LIMS). CAtenA Smart PCR (Ventura, Ankara, Türkiye) program is a local bioinformatics software that assess PCR data files with artificial intelligence, submits to expert approval and transfers the approved results to LIMS. The aim of this study is to investigate its accuracy and matching success rate with expert analysis. Methods: A total of 9400 RT-qPCR test results studied in Ankara Provincial Health Directorate Public Health Molecular Diagnosis Laboratory were compared with respect to expert evaluation and CAtenA results. Results: It was determined that the preliminary evaluation results of the CAtenA matched 86% of the negative and 90% of the positive results provided by expert analysis. 987 tests which CAtenA determined as inconclusive and suggested repeating PCR were found either negative or positive by expert analysis. A significant difference between positive and negative matching success rates and artificial intelligence (AI) based software overall accuracy was found and associated with the missed tests of the AI. Conclusions: As a result, it was suggested there is a low risk of confirming false positive results without expert analysis and test repetitions would cause losing time along with extra test costs. It was agreed that the PCR analysis used in CAtenA should be improved particularly in terms of test repetitions.