An Artificial Intelligence-Assisted Portable Low-Cost Device for the Rapid Detection of SARS-CoV-2

Abstract

An artificial intelligence-assisted low-cost portable device for the rapid detection of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is presented here. This standalone temperature-controlled device houses tubes designed for conducting reverse transcription loop-mediated isothermal amplification (RT-LAMP) assays. Moreover, the device utilises tubes illuminated by LEDs, an in-built camera, and a small onboard computer with automated image acquisition and processing algorithms. This intelligent device significantly reduces the normal assay run time and removes the subjectivity associated with operator interpretation of colourimetric RT-LAMP results. To further improve this device’s usability, a mobile app has been integrated into the system to control the LAMP assay environment and to visually display the assay results by connecting the device to a smartphone via Bluetooth. This study was undertaken using ~5000 images produced from the ~200 LAMP amplification assays using the prototype device. Synthetic RNA and a small panel of positive and negative SARS-CoV-2 patient samples were assayed for this study. State-of-the-art image processing and artificial intelligence algorithms were applied to these images to analyse them and to select the most efficient algorithm. The template matching algorithm for image extraction and MobileNet CNN architecture for classification results provided 98.0% accuracy with an average run time of 20 min to confirm the endpoint result. Two working points were chosen based on the best compromise between sensitivity and specificity. The high sensitivity point has a sensitivity value of 99.12% and specificity value of 70.8%, while at the high specificity point, the sensitivity is 96.05% and specificity 93.59%. Furthermore, this device provides an efficient and cost-effective platform for non-health professionals to detect not only SARS-CoV-2 but also other pathogens in resource-limited laboratories, factories, airports, schools, universities, and homes.

Development of a loop-mediated isothermal amplification (LAMP)-based electrochemical test for rapid detection of SARS-CoV-2

“… 37 Our electrochemical-RDT developed in this study is designed for detection of SARS-CoV-2 through amplification of the M gene and consequent redox signal generated from pyrophosphate-molybdate reaction in virus positive samples. Our assay has an advantage over the Cod-UNG-rRT-LAMP 11 and CRISPR-based assays 24 , 30 in avoiding multiple temperature-specific incubation steps. MOPCS, the CRISPR/cas12a based photonic detection requires multiple incubation steps to prepare chip and solutions for surface plasmon resonance measurements and the suitability of detection in crude biological fluids has not been tested, thus requiring further optimizations for POC settings.…”

“…However, this test is based on the pH change from a positive LAMP reaction and any changes in pH during extraction process may lead to false positives. 30 In this study we developed an electrochemical-rapid diagnostic test (RDT) which detects an electrical signal generated from oxidation-reduction (redox) reactions of pyrophosphates (produced in a positive RT-LAMP reaction) with sodium molybdate. We optimized our electrochemical-RDT to work with human fluids such as serum and saliva that contains inherent phosphate contaminants.…”

JMM profile: Loop-mediated isothermal amplification (LAMP): for the rapid detection of nucleic acid targets in resource-limited settings

“…The use of OmniAmp polymerase allowed amplification at higher temperatures (66-72 °C), which resulted in 20 % faster detection in comparison to Bst polymerase [22]. Most recently, LAMP has been applied to detect severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) utilizing a portable device that allows wireless communication of detection data to smartphones [5,23,24].…”

A Miniaturized System for Rapid, Isothermal Detection of SARS-CoV-2 in Human and Environmental Samples

“…Many recent studies have successfully developed POC devices that rely on the naked eye to interpret qualitative assay results [14,15] or complex read-out systems to analyze the assay [16,17]. Other recent studies have used a digital camera to evaluate the result of the assay, but rely on the sample being prepared in PCR tubes prior to amplification [6,18,19], or a complex and expensive amplification process such as the use of a centrifugal device, or droplet microfluidics [20,21]. As shown by [19], artificial intelligence (AI) can be used to augment the sensitivity and specificity of LAMP assays, but it requires images to train and classify features and patterns [19].…”

“…Other recent studies have used a digital camera to evaluate the result of the assay, but rely on the sample being prepared in PCR tubes prior to amplification [6,18,19], or a complex and expensive amplification process such as the use of a centrifugal device, or droplet microfluidics [20,21]. As shown by [19], artificial intelligence (AI) can be used to augment the sensitivity and specificity of LAMP assays, but it requires images to train and classify features and patterns [19]. Moving towards a POC device that uses AI to maximize the assay's sensitivity and specificity, system alignment between the integrated camera, the laser, and the droplet becomes critical.…”