• Ananya Bist
• Darshana Mukundan
• Deepthi N.
• Ifrah Abdul Khadar Ramadurg
• Dr. Asha T.

According to WHO Tuberculosis (TB) is one of the top 10 causes of death globally. Every year millions of people fall prey to this disease and lose their lives. The transmission of this disease occurs at a very high rate as compared to other diseases. Using the model discussed in this paper, the disease can be detected at an early stage which can result in better treatment of the disease. The proposed model performs blood-based diagnosis of tuberculosis using a graph-based approach in conjunction with a novel signature definition and analysis method. It uses statistical techniques in order to find the miRNAs of interest. The approach used here relies on the construction of a reference map of the transcriptional signatures of a large number of subjects, which include both healthy and affected individuals. The signatures are generated using the filtered circulating miRNAs of interest. The construction of the reference map involves the use of Minimum Spanning Tree based clustering. A new patient is diagnosed according to the relative position of their transcriptional signature on the map. The two significant aspects which make this method the preferred choice for large scale applications such as a mass screening tool, point-of-care diagnostics are: it is minimally invasive and remains persistent to lab-to-lab protocol variability, measurement errors and batch effects. This is because the method demands accuracy only in the relative ranking of miRNA species, not in their absolute values.

miRNA, transcriptional signature, biomarker, circulating miRNA

"miRNA based Tuberculosis Diagnosis using Machine Learning Techniques", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.311-314, June 2019, Available :http://www.jetir.org/papers/JETIR1908199.pdf

"miRNA based Tuberculosis Diagnosis using Machine Learning Techniques", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp311-314, June 2019, Available at : http://www.jetir.org/papers/JETIR1908199.pdf