Validity of at-home rapid antigen lateral flow assay and artificial intelligence read to detect SARS-CoV-2

Shannon Richardson; Michael A Kohn; Jenna Bollyky; Julie Parsonnet

doi:10.1016/j.diagmicrobio.2022.115763

Validity of at-home rapid antigen lateral flow assay and artificial intelligence read to detect SARS-CoV-2

Diagn Microbiol Infect Dis. 2022 Nov;104(3):115763. doi: 10.1016/j.diagmicrobio.2022.115763. Epub 2022 Jul 7.

Authors

Shannon Richardson¹, Michael A Kohn², Jenna Bollyky³, Julie Parsonnet⁴

Affiliations

¹ Department of Epidemiology and Population Health, Stanford University School of Medicine, Stanford, CA, USA.
² Department of Emergency Medicine, Stanford University School of Medicine, Stanford, CA, USA.
³ Department of Epidemiology and Population Health, Stanford University School of Medicine, Stanford, CA, USA; Department of Pediatrics, Stanford University School of Medicine, Stanford, CA, USA.
⁴ Department of Epidemiology and Population Health, Stanford University School of Medicine, Stanford, CA, USA; Department of Medicine, Stanford University School of Medicine, Stanford, CA, USA. Electronic address: parsonnt@stanford.edu.

Abstract

Background: The gold standard for COVID-19 diagnosis-reverse-transcriptase polymerase chain reaction (RT-PCR)- is expensive and often slow to yield results whereas lateral flow tests can lack sensitivity.

Methods: We tested a rapid, lateral flow antigen (LFA) assay with artificial intelligence read (LFAIR) in subjects from COVID-19 treatment trials (N = 37; daily tests for 5 days) and from a population-based study (N = 88; single test). LFAIR was compared to RT-PCR from same-day samples.

Results: Using each participant's first sample, LFAIR showed 86.2% sensitivity (95% CI 73.6%-98.8) and 94.3% specificity (88.8%-99.7%) compared to RT-PCR. Adjusting for days since symptom onset and repeat testing, sensitivity was 97.8% (89.9%-99.5%) on the first symptomatic day and decreased with each additional day. Sensitivity improved with artificial intelligence (AI) read (86.2%) compared to the human eye (71.4%).

Conclusion: LFAIR showed improved accuracy compared to LFA alone. particularly early in infection.

Keywords: Artificial intelligence; COVID-19; Diagnostic accuracy; Rapid antigen test; SARS-CoV-2; Validity.

MeSH terms

Antigens, Viral* / analysis
Antigens, Viral* / immunology
Artificial Intelligence*
COVID-19 Nucleic Acid Testing
COVID-19 Serological Testing* / methods
COVID-19 Serological Testing* / standards
COVID-19* / diagnosis
COVID-19* / immunology
COVID-19* / virology
Clinical Trials as Topic
Humans
Reproducibility of Results
SARS-CoV-2* / immunology
SARS-CoV-2* / isolation & purification
Sensitivity and Specificity
Time Factors

Substances

Antigens, Viral