As a founder of iDoc.ai the Tuberculosis was one of the diseases I deeply wanted to address in solutions we create and deliver. Early diagnosis is one of the key factors here and thought that working on chest X-rays can be a good starting point.
If we can diagnose Tuberculosis (TB) in time, we can treat and cure it within a short period of time. Having said that it’s still the leading cause of death worldwide with a, especially in developing countries. Worldwide, TB is one of the top 10 causes of death and the leading cause from a single infectious agent (above HIV/AIDS)” We had come a long way through from 1993 when WHO declared TB as a global health emergency.
Tuberculosis (TB) is contagious (a bacterial infection which spreads through the air via a cough, sneeze, etc.) and usually infects lungs but can also impact other organs of the body. It is normally dormant and initially without any symptoms. For 1 in 10, this progresses to active state which if not diagnosed and treated in time can kill 20- 70 per cent of infected people within 10 years.
As per WHO, an estimated 10 million people fell ill with tuberculosis (TB) worldwide in 2019(5.6 million men, 3.2 million women and 1.2 million children). A total of 1.4 million people died from TB in 2019 (including 208000 people with HIV). Worldwide, TB is one of the top 10 causes of death and the leading cause of a single infectious agent (above HIV/AIDS).
The WHO’s End TB strategy goal between 2016 and 2035 is to reduce worldwide TB incidence by 90% and TB mortality by 95%. The areas to focus for countries targeting to reduce their TB burden (by 2035) are digital health care, surveillance, better programme management, professional training and efficient communication. The focus is also on improved access to medical care, especially diagnostic tests.
However, the world health community’s efforts have met with obstacles such as the emergence of multidrug-resistant strains of the disease. A very high percentage of TB patients develop TB resistant strain to the most common anti-TB drug(rifampicin), and more than 80 per cent out of those are also have multidrug-resistant TB. As per WHO, Multidrug-resistant TB (MDR-TB) remains a public health crisis and a health security threat. In 2018, there were estimated half a million new cases with resistance to rifampicin (the most effective first-line drug), of which 78% had MDR-TB.
To identify and monitor such patients and then to control resistant strains of the disease will be the most challenging issue in the developing world for a time to come.
It’s also important to differentiate between active and latent TB. Active TB has a high risk of infectious spread, whereas latent TB has a low risk of such spread. Both forms need treatment, and it takes active radiography for a certain period of time (usually a few months) to distinguish between two types.
There is a bright light at the end of the tunnel though, TB treatment (as per WHO) saved about 58 million lives globally between 2000 and 2018. The treatment success rate for people with TB was 85% in 2017.
Artificial Intelligence is also making deep inroads into TB diagnosis and treatment via deep learning insights into radiology and pathology, thus helping enormously in the early and accurate detection of TB so that required treatment can be provided. iDoc.ai’s (https://idoc.ai/) AI-based solution for detecting TB from chest X-Ray scans is one the example where the power of AI can augment the existing capabilities in radiology. The snippet can be found on https://idoc.ai/pulmonology-itbd/.
1. World Health Organization Global Tuberculosis Report 2018
2. A.C. Nachiappan, K. Rahbar, X. Shi, et al.Pulmonary tuberculosis: role of radiology in diagnosis and management
RadioGraphics, 37 (1) (2017), pp. 52–72
[cited 2019 Jul 6] Available from: