Machine learning-augmented loop-mediated isothermal amplification-enabled point-of-care for Mpox-specific detection

Abstract

Mpox can cause serious infections in humans as a zoonotic disease. In recent years, the need for effective and rapid diagnostic methods has increased due to the epidemic potential and rapid spread risk of Mpox. In this study, a low-cost, rapid, and portable loop-mediated isothermal amplification (LAMP)-enabled point-of-care (PoC) platform is developed for the diagnosis of Mpox. The LAMP test is optimized for the specific detection of Mpox virus and showed high sensitivity with a limit of detection value of 2.76 x 103 copies/mu L at a dilution level of 10-7. The LAMP device detects fluorescence signals through its integrated optical reading system and enables easy monitoring of test results via a mobile phone. Additionally, a machine learning pipeline is implemented to analyze infrared temperature profiles recorded during the reaction. Using an ensemble learning model trained on simulated and experimental data, the system estimates thermal conductivity changes, which show a strong correlation with different template DNA concentrations. These findings indicate that the developed platform can be used as an effective diagnostic tool in field environments for early detection of infectious diseases such as Mpox.