Experts gather in Denmark to discuss AI role in TB fight

When Fred Ebil, a technical school instructor from Lira district, started treatment for drug-resistant tuberculosis five years ago, he faced a lot of psychological torture because of being told to stay away from other people, as the disease he was suffering from was highly infectious.

“I was swallowing very many drugs per every day. As if that was not enough, people started treating me like an outcast, and this psychologically tortured me. People had been told not to come near me or else they got infected,” he says.

Ebil, however, says he used to look forward to a visit by a health worker because that was the only time he felt encouraged by a fellow human being.

“The health workers would counsel and encourage me to take the drugs. The mental stress would ease whenever they came around,” he adds.

After healing from the disease, Ebil says people continued to segregate and stigmatise him. It was against this background that he started Fellowship of TB Survivors, a non-government organisation to offer counselling and psychological support to patients of tuberculosis so that they do not endure the mental stress that he faced.

Ebil’s experience is a lesson that as the medical world adopts digital tools, especially artificial intelligence AI, the personal touch between healthcare providers and patients remains crucial in the provision of TB treatment and prevention.

Experiences of people in Ebil’s shoes and their healthcare providers will form the basis of discussions at the forthcoming World Conference on Lung Health slated for November 18-21 at Copenhagen, Denmark.

Among the topics to be explored will be the real opportunities and challenges AI brings to the TB fight -- from transforming diagnostics to reshaping drug discovery.

Among the speakers will be Keymanthri Moodley from Stellenbosch University in South Africa, Prof. Justin Denholm from Australia, Dr Karuna Devi Sagili from the Netherlands, among others.

Artificial Intelligence in TB care

Uganda has a high TB burden and is among the worst 30 countries. According to the Ministry of Health, the disease claimed 41,000 lives in 2023, with 94,100 infections. Statistics also indicate that at least 30 people in Uganda die every day due to TB.

Currently, efforts are underway to end the disease in the country by 2030. One of the solutions that has been fronted against the problem is the rapid adoption of AI in treatment and prevention.

For example, many public health facilities are dumping the old time-consuming and expensive technology and adopting digital X-ray machines, which rapidly diagnose tuberculosis in the communities.

The portable and AI-powered machines are cheaper, offer high image quality, low radiation, automated interpretation and can easily be carried to remote communities, making them effective in detection and control of the spread of TB.

Because of their effectiveness, both the Government and donor communities are deploying them to health facilities across the country.

On May 13, health minister Jane Ruth Aceng received 48 digital X-ray machines valued at sh18b from the US Ambassador, William Popp. The minister said the machines would be vital in Uganda’s quest to end TB by 2030.

“We received 48 X-ray machines, 33 TB-LAMP platforms and 33 tricycles from the US Government to enhance Uganda’s TB response. The innovative "Mobile X-LAMP" (portable digital X-ray + CAD & TB-LAMP) will revolutionise community screening. We are grateful to the US Government,” she said.

Use of AI in control and prevention of TB in Africa

Uganda is not alone in adopting the use of AI to fight TB. In the Central African Republic, experts have created an AI-based high-resolution predictive model that maps TB spread, after which precise interventions can be made.

Developed early this month, the project was a collaboration between The Union, the National Tuberculosis Programme of the Central African Republic and Epcon, a company that uses AI to quantify health risks in specific regions and population groups.

Dr Kobto Ghislain Koura, lead author of the study and director of the TB Department at The Union, said: “For too long, communities have suffered because we’ve been reacting to TB rather than anticipating it. AI allows us to shift from passive surveillance to proactive intervention.”

According to a statement from the Union, the approach could be scaled and used in other low-resource settings, especially developing countries.

"This tool has the potential to reshape how we approach TB surveillance in countries where the disease is most prevalent. It helps us go beyond what is visible and detect where the disease may be silently spreading,” Dr Koura added.

According to the statement, the team created a digital map of the city, dividing it into 100 by 100 metre grids. They trained the AI model to predict TB positivity rates in each area by using publicly available data, such as population density, access to clean water, and distance from TB clinics.