Design of an Efficient, Ease-of-use and Affordable Artificial Intelligence based Nucleic Acid Amplification Diagnosis Technology for Tuberculosis and Multi-drug Resistant Tuberculosis
This addresses the need for affordable and easy-to-use diagnostic tools for tuberculosis in low-resource settings, representing an incremental improvement over existing lab-based technologies.
The paper tackles the problem of diagnosing tuberculosis and multi-drug resistant tuberculosis in low-resource settings by developing a portable, low-cost, machine learning automated NAAT device using smartphone-based fluorescence detection, achieving sensitive detection in qPCR experiments with cDNA concentrations of 40 ng/uL and 200 ng/uL.
Current technologies that facilitate diagnosis for simultaneous detection of Mycobacterium tuberculosis and its resistance to first-line anti-tuberculosis drugs (Isoniazid and Rifampicim) are designed for lab-based settings and are unaffordable for large scale testing implementations. The suitability of a TB diagnosis instrument, generally required in low-resource settings, to be implementable in point-of-care last mile public health centres depends on manufacturing cost, ease-of-use, automation and portability. This paper discusses a portable, low-cost, machine learning automated Nucleic acid amplification testing (NAAT) device that employs the use of a smartphone-based fluorescence detection using novel image processing and chromaticity detection algorithms. To test the instrument, real time polymerase chain reaction (qPCR) experiment on cDNA dilution spanning over two concentrations (40 ng/uL and 200 ng/uL) was performed and sensitive detection of multiplexed positive control assay was verified.