Inexpensive method for the Quantitative Estimation of Hepatitis C Virus RNA in Blood Plasma for Low-Resource Settings Using ML-based Image Intensity Analysis of RT-LAMP Products

Abstract

Hepatitis C Virus (HCV) infection is a severe public health problem with a staggering 3% of the world population infected with HCV. HCV infections become chronic 80% of the total cases. Performing HCV RNA test to initiate treatment in HCV infected patients remains quite challenging, particularly in places with limited resources where it is difficult to carry out molecular testing. In the current study, for the first time, a novel and inexpensive HCV molecular diagnostic approach based on on-chip reverse transcriptase loop-mediated isothermal amplification (RT-LAMP) integrated with image intensity measurement and machine learning based prediction (RT-LAMP-IM-MLP) is developed for rapid, easy-to-use, sensitive, specific and quantitative detection of HCV RNA from blood plasma. Amplified products are visualized under fluorescence excitation and the captured image processed using OpenCV package in Python, followed by training and prediction through a modified random forest algorithm. When tested on plasma samples positive with HCV, Hepatitis A Virus (HAV), or from otherwise healthy individuals, the RT-LAMP-IM-MLP scheme yields 97.1% sensitivity, 96.9% specificity, all at 97% accuracy and as compared to the reference method Real Time PCR based assay (COBAS® TaqMan® HCV assay (Roche diagnostics, US), our assay can detect HCV RNA concentrations as low as 10 IU/mL (60 fg/µL). Further, minimum quantity of dye is used for fluorescence labeling as compared to colorimetric assays. Therefore, the proposed sensitive and specific detection scheme may serve as an inexpensive and reliable point-of-care (POC) test for detecting HCV RNA in clinical samples.