Deep Learning-Enhanced Chemiluminescence Vertical Flow Assay for High-Sensitivity Cardiac Troponin I Testing

Area of Science:

• Biomedical Engineering
• Analytical Chemistry
• Medical Diagnostics

Background:

• Point-of-care testing (POCT) requires sensitive and precise biomarker detection.
• Cardiac troponin I (cTnI) is a critical biomarker for diagnosing myocardial infarction.
• Current POCT methods often lack the sensitivity of laboratory-grade assays.

Purpose of the Study:

• To develop a high-sensitivity chemiluminescence vertical flow assay (CL-VFA) for cardiac troponin I (cTnI) detection.
• To integrate advanced sensing, imaging, and deep learning for accurate biomarker quantification.
• To enable accessible and rapid cardiac biomarker testing in diverse healthcare settings.

Main Methods:

• Development of a chemiluminescent paper-based sensor with a polymerized enzyme-based conjugate.
• Utilizing a portable, high-performance chemiluminescence reader.
• Employing a neural network algorithm for cTnI concentration inference from assay data.

Main Results:

• The CL-VFA achieved a detection limit of 0.16 pg mL⁻¹ with <15% coefficient of variation.
• Assay demonstrated a broad dynamic range over six orders of magnitude using 50 µL serum.
• Results correlated strongly with a clinical-grade analyzer in blinded patient sample validation.

Conclusions:

• The CL-VFA system offers an order of magnitude improvement in sensitivity over traditional analyzers.
• This technology enables rapid, low-cost, and precise cTnI quantification for point-of-care cardiac assessment.
• CL-VFA holds significant potential for improving emergency care and healthcare access in underserved regions.