Artificial Intelligence in treating Tuberculosis

The Problem

Tuberculosis (TB) is an infectious disease that typically affects the lungs and has the potential to be of a severe nature. TB is caused by the Mycobacterium tuberculosis bacteria (MTB) and is spread from one another through droplets of sputum released into the air via coughs and sneezes. There are two types, latent and active. Latent TB is when there are no symptoms and though the bacteria is in the body, it remains inactive and isn’t contagious – however it can turn active and hence treatment is still advised to control the spread of TB. Active TB on the other hand is when symptoms of sickness are visible, which can occur in the first few weeks of infection or even years later. Active TB is contagious.

According to the World Health Organisation, TB is the 9th leading cause of death worldwide and the leading cause from a single infectious agent (beating HIV/AIDS). Over 25% of global deaths due to TB are in the African region, especially in Nigeria and South Africa. Tuberculosis is curable and preventable, however there are issues with the current methods available:

  1. Duration of treatment can be very long (over 6 months) and hence patient compliance may fall over the period of the course.
  2. The drugs can be very toxic. Patients may develop severe side effects from the prolonged treatment and dosage.
  3. There is potential for the development of drug-resistance. In some cases, patients can develop resistance to the drugs especially through inappropriate prescription and incomplete dosage treatment. This may then require more intensive treatment options as chemotherapy (for up to 2 years) and costlier and toxic medication. In cases where XDR-TB (Extensively Drug Resistant TB) develops, patients are left without further treatment options. Drug-resistant TB results in a high fatality rate.

These issues around treatment can be especially prevalent in developing countries where infected patients may not have the sufficient access to good health care systems or may not be able to afford the lengthy treatment course. Thus, it may often be found that in such countries, individuals who are carrying TB may not complete their treatment course (which can lead to worse effects and much more expensive treatment) or even put-off treatment entirely (which can lead to the further spreading of the epidemic).

The Solution (Artificial Intelligence)

A team of researchers at the University of California, Los Angeles (UCLA) have used artificial intelligence-driven data analysis to determined the required optimal drug and dosage combinations to treat patients in a shorter period of time and treat them effectively! As opposed to determining a new drug, an approach that is often very expensive and time consuming, the research conducted by this team resulted in determining the best drug-dose combination of 15 drugs currently available to treat TB. They were able to identify 4 such drug-dose combinations that could lead to a 80% drop in the duration of treatment – the team had tested out the results on MTB-infected mice.

After 3 – 5 weeks, these 4 drug-dose combinations were able to cure the mice completely – relapse free. These findings are extremely promising when compared with the control – mice treated following the standard procedure that is currently adopted – which were unable to achieve relapse-free cures in 6 weeks and still had high numbers of bacteria in their lungs.

As the report concludes, all mouse drug-dose treatment courses extrapolate to those that are readily achievable in humans and hence should effective against most TB cases that are multi-drug resistant (MDR-TB) and many that are extensively drug-resistant (XDR-TB). Therefore, these regimens have potential to dramatically reduce the time required for treatment of both drug-sensitive and drug-resistant TB. Further research is still required before clinical trials are initiated.

“If clinical trials confirm that these regimens dramatically shorten the time required to achieve relapse-free cure in humans, then this radically shortened treatment has the potential to improve treatment compliance, decrease the emergence of drug resistance, and decrease the healthcare burden of treating both drug-sensitive and drug-resistant TB.”

Given the aforementioned, it is plausible to assume that the treatment of TB will become much more affordable for populations of the developing world, thereby ensuring a much clearer view of the end of this global epidemic once and for all.



AI Terminator: A Threat to the Environment

MTN Released the First AI-Driven Service for Mobile Money in Africa

First Crypto Collectable offered in F1 Racing Game.

Cryptoverse Rediscovers Bitcoin in Excel


Leave a comment

My Newsletter

Sign Up For Updates & Newsletters

[mc4wp_form id="456"]