Tuberculosis: Advances in Diagnostics and Treatment
The World Health Organization’s “End TB Strategy” aims to achieve a 90% reduction in tuberculosis deaths and an 80% reduction in incidence by 2030; this calls for innovative approaches to counteract the high burden of disease through a two-prong strategy of early detection coupled with appropriate, timely treatment.
Artificial intelligence (AI) and machine learning are two remarkable technological breakthroughs that could revolutionize the management of tuberculosis. Examples of these technological advances include recognition of tubercle bacilli and abnormal chest radiograph recognition through the artificial neural networks. AI can learn to correlate massive amounts of data, which can be translated into clinically significant results. Another approach that has become promising is the development of virtual directly observed treatment (VDOT) via video, in areas with broadband internet and affordable devices that reach even remote places with tuberculosis patients. VDOT and drone drug delivery allow the treatment of tuberculosis in areas with minimal resources.
KeywordsTuberculosis Artificial intelligence Machine learning Deep learning Artificial neural network Smear microscopy Tuberculous pleural effusion Chest x-ray Computer aided programs Host-directed therapy Immunomodulation Drug resistance Virtually observed therapy
Conflict of Interest
The authors report no conflicts of interest.
- 2.WHO. Global tuberculosis report 2018.Google Scholar
- 6.FrontlineSolvers. Training an artificial neural network – intro 2019 [21 Jan 2019]. Available from: https://www.solver.com/training-artificial-neural-network-intro.
- 8.Murray PR, Rosenthal KS, Pfaller MA. Medical microbiology. Elsevier Health Sciences; 2015, Philadelphia, PAGoogle Scholar
- 13.Aeonase, Clinical Results [Internet]. 2013 [cited 28 Oct 2018]. Available from: http://www.enose.nl/clinical-results/tuberculosis/.
- 31.Kobayashi H, Ohkubo M, Narita A, Marasinghe JC, Murao K, Matsumoto T, et al. A method for evaluating the performance of computer-aided detection of pulmonary nodules in lung cancer CT screening: detection limit for nodule size and density. Br J Radiol. 2017;90(1070):20160313.PubMedCrossRefPubMedCentralGoogle Scholar
- 37.Nahid P, Dorman SE, Alipanah N, Barry PM, Brozek JL, Cattamanchi A, et al. Official American Thoracic Society/Centers for Disease Control and Prevention/Infectious Diseases Society of America Clinical Practice Guidelines: Treatment of Drug-Susceptible Tuberculosis. Clin Infect Dis. 2016;63(7):e147–e95.PubMedPubMedCentralCrossRefGoogle Scholar
- 41.Low A, Gavriilidis G, Larke N, MR BL, Drouin O, Stover J, et al. Incidence of opportunistic infections and the impact of antiretroviral therapy among HIV-infected adults in low- and middle-income countries: a systematic review and meta-analysis. Clin Infect Dis. 2016;62(12):1595–603.PubMedPubMedCentralCrossRefGoogle Scholar
- 52.Small P. DrOTS: Drone Observed Therapy System: Stony Brook University. Available from: https://www.stonybrook.edu/commcms/ghi/projects/drots.php.
- 53.Frontieres MS. Innovating to reach remote TB patients and improve access to treatment 2014 [18 Dec 2018]. Available from: https://www.msf.org/papua-new-guinea-innovating-reach-remote-tb-patients-and-improve-access-treatment.
- 54.Unicef. Child given world’s first drone-delivered vaccine in Vanuatu – UNICEF 2018 [18 Dec 2018]. Available from: https://www.unicef.org/press-releases/child-given-worlds-first-drone-delivered-vaccine-vanuatu-unicef.