1. Point-of-Care Serodiagnostic Test for Early-Stage Lyme Disease Using a Multiplexed Paper-Based Immunoassay and Machine Learning
- Author
-
Paul M. Arnaboldi, Hyou-Arm Joung, Raymond J. Dattwyler, Derek Tseng, Linghao Zhang, Dino Di Carlo, Zachary S. Ballard, Jing Wu, Elizabeth J. Horn, Omai B. Garner, Aydogan Ozcan, and Hailemariam Teshome
- Subjects
Paper ,Surface Properties ,Point-of-care testing ,General Physics and Astronomy ,02 engineering and technology ,010402 general chemistry ,01 natural sciences ,Machine Learning ,Lyme disease ,Antigen ,Borrelia ,Medicine ,Humans ,General Materials Science ,Borrelia burgdorferi ,Particle Size ,Point of care ,Immunoassay ,Lyme Disease ,biology ,medicine.diagnostic_test ,business.industry ,General Engineering ,021001 nanoscience & nanotechnology ,biology.organism_classification ,medicine.disease ,Telemedicine ,0104 chemical sciences ,Infectious disease (medical specialty) ,Point-of-Care Testing ,Immunology ,0210 nano-technology ,business - Abstract
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 $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.
- Published
- 2019