Advancing diagnostic efficacy using a computer vision-assisted lateral flow assay for influenza and SARS-CoV-2 detection

Abstract

Lateral flow assays (LFAs) have emerged as indispensable tools for point-of-care testing during the pandemic era. However, the interpretation of results through unassisted visual inspection by untrained individuals poses inherent limitations. In our study, we propose a novel approach that combines computer vision (CV) and lightweight machine learning (ML) to overcome these limitations and significantly enhance the performance of LFAs. By incorporating CV-assisted analysis into the LFA assay, we achieved a remarkable three-fold improvement in analytical sensitivity for detecting Influenza A and for SARS-CoV-2 detection. The obtained R² values reached approximately 0.95, respectively, demonstrating the effectiveness of our approach. Moreover, the integration of CV techniques with LFAs resulted in a substantial amplification of the colorimetric signal specifically for COVID-19 positive patient samples. Our proposed approach, which incorporates a simple machine learning algorithm, provides substantial enhancements in assay sensitivity, improving diagnostic efficacy and accessibility of point-of-care testing without requiring significant additional resources. Moreover, the simplicity of the machine learning algorithm enables its standalone use on a mobile phone, further enhancing its practicality for point-of-care testing.