Point-of-Care Serodiagnostic Test for Early-Stage Lyme Disease Using a Multiplexed Paper-Based Immunoassay and Machine Learning

• Published in: ACS nano Vol. 14; no. 1; pp. 229 - 240
• Main Authors: Joung, Hyou-Arm, Ballard, Zachary S, Wu, Jing, Tseng, Derek K, Teshome, Hailemariam, Zhang, Linghao, Horn, Elizabeth J, Arnaboldi, Paul M, Dattwyler, Raymond J, Garner, Omai B, Di Carlo, Dino, Ozcan, Aydogan
• Format: Journal Article
• Language: English
• Published: United States American Chemical Society 28.01.2020
• Subjects: Humans; Immunoassay; Lyme Disease - blood; Lyme Disease - diagnosis; Lyme Disease - immunology; Machine Learning; Particle Size; Point-of-Care Testing; Surface Properties; Telemedicine; point-of-care testing; Lyme disease; paper-based immunoassay; machine learning; multiplexed immunoassay
• ISSN: 1936-0851; 1936-086X; 1936-086X
• DOI: 10.1021/acsnano.9b08151

Caused by the tick-borne spirochete Borrelia burgdorferi, Lyme disease (LD) is the most common vector-borne infectious disease in North America and Europe. Though timely diagnosis and treatment are effective in preventing disease progression, current tests are insensitive in early stage LD, with a sensitivity of <50%. Additionally, the serological testing currently recommended by the U.S. Center for Disease Control has high costs (>$400/test) and extended sample-to-answer timelines (>24 h). To address these challenges, we created a cost-effective and rapid point-of-care (POC) test for early-stage LD that assays for antibodies specific to seven Borrelia antigens and a synthetic peptide in a paper-based multiplexed vertical flow assay (xVFA). We trained a deep-learning-based diagnostic algorithm to select an optimal subset of antigen/peptide targets and then blindly tested our xVFA using human samples (N (+) = 42, N (−) = 54), achieving an area-under-the-curve (AUC), sensitivity, and specificity of 0.950, 90.5%, and 87.0%, respectively, outperforming previous LD POC tests. With batch-specific standardization and threshold tuning, the specificity of our blind-testing performance improved to 96.3%, with an AUC and sensitivity of 0.963 and 85.7%, respectively.