Proof-of-Concept: Smartphone- and Cloud-Based Artificial Intelligence Quantitative Analysis System (SCAISY) for...

Area of Science:

• Biotechnology
• Infectious Disease Surveillance
• Artificial Intelligence in Diagnostics

Background:

• Smartphone-based point-of-care testing (POCT) offers advantages over traditional methods, especially in resource-limited settings.
• Accurate quantification of SARS-CoV-2 antibodies is crucial for monitoring vaccine effectiveness and infection-induced immunity.

Purpose of the Study:

• To develop and validate a smartphone- and cloud-based artificial intelligence quantitative analysis system (SCAISY) for rapid analysis of SARS-CoV-2 IgG antibody lateral flow assays.
• To assess the system's accuracy, reproducibility, and correlation with established laboratory methods.

Main Methods:

• SCAISY utilizes smartphone cameras to capture images of lateral flow assay test strips for quantitative antibody analysis.
• The system was tested on over 248 individuals, analyzing antibody level changes related to vaccination and infection status.
• Factors influencing image acquisition, such as lighting and camera angle, were evaluated for consistency.

Main Results:

• SCAISY provided rapid (<60 s) quantitative results with a standard deviation of less than 10% for antibody levels.
• Significant correlations were found between SCAISY results and enzyme-linked immunosorbent assay (ELISA) optical density values (Spearman: 0.59, Pearson: 0.56).
• Optimal image acquisition was achieved between 45° and 90° camera angles, with consistent results across various lighting conditions.

Conclusions:

• SCAISY is a simple, powerful tool for real-time public health surveillance of SARS-CoV-2 antibodies.
• The system accelerates the quantification of antibodies from vaccination or infection, facilitating personal immunity tracking.
• This technology holds promise for enhancing infectious disease monitoring and management globally.