AI Transforms TB Diagnosis in Resource-Limited Areas

Published Date : 7/11/2025 

Artificial intelligence is transforming tuberculosis diagnosis, providing quick and accurate results in regions with a shortage of radiologists. 

On a Thursday morning last month, the Boniaba Community Health Center in Mali was conducting a tuberculosis (TB) screening. Notably, there was no doctor in sight. Yet, a mother plagued by coughing received a diagnosis in a matter of seconds: She was positive for TB.

A few years ago, she would have been fortunate to find a screening nearby, and even then, she would have had to wait a week or two for a sputum test to be sent to a lab and for results to come back. The difference now? A mobile x-ray machine and an AI algorithm are detecting TB. This AI algorithm is essentially a computer program trained on a large dataset.

TB is the world's top infectious disease killer, with 3,500 people dying of it each day, resulting in more than 1.2 million deaths annually. The numbers are increasing, and one of the major hurdles in tackling this epidemic has been the global shortage of radiologists to diagnose this bacterial infection that usually affects the lungs.

“There are countries in which there are less than five radiologists. It's like a disaster. And, even if you have some, they will always be in the capitals,” says Dr. Lucica Ditiu, executive director of the Stop TB Partnership, an advocacy organization. Now, she says, over 80 low- and middle-income countries are turning to AI to screen people for TB.

“It is revolutionary,” Ditiu emphasizes. For example, a nomadic population in Nigeria is benefiting from this technology. “You're in the middle of nowhere. There are these guys. There's cattle. There is dust and nothing else. And they are doing these x-rays with AI. It's unreal,” Ditiu explains, noting that her organization was among the pioneers in developing this technology eight years ago.

The AI models are also being used in refugee camps in Chad. “There are no radiologists. So who gets to look at the [x-ray] and say: 'Is there a problem here or not?' Well, actually, AI does,” says Peter Sands, the executive director of the Global Fund to Fight AIDS, TB and Malaria, which has invested close to $200 million into AI-enabled TB screenings in the past four years. “It's brilliant.”

Proponents say they are glimpsing the future, where AI accelerates the world's ability to detect and control diseases in some of the hardest-to-reach pockets of society. Others urge caution, saying more regulations and guardrails are necessary to protect patients in low- and middle-income countries.

At the Boniaba Community Health Center, the mother is one of dozens of people who get an x-ray from a mobile x-ray machine set up by Diakité Lancine. He is not a doctor but has been trained to take x-rays. The image he captures is sent directly to his computer, where the AI model reads it and provides a score based on how much it thinks the image looks like TB. It also generates a picture of the person's lungs that looks almost like a heat map.

“The blue there is nothing bad, but whenever you see the red — the red means this part is not good,” explains Lancine on the morning he screens the mother.

Lancine works for the local nonprofit ARCAD Santé PLUS and conducts TB screenings around the West African country, arriving with just a few bags — for his mobile x-ray machine, his computer, and a battery pack in case there's no electricity. As soon as the mother's screening comes back with several red patches, he collects a sputum sample to send to the lab for confirmation. Then he tells her to go home quickly and bring her five kids back so he can check them too. TB spreads through the air when someone with active TB coughs, laughs, or talks, making it easily transmissible in households.

Almost instantly, AI tells them: Three of her kids appear to have TB. Soon, Lancine says, they'll start on a six-month course of antibiotics to treat the TB.

“Having AI makes a big difference,” says Bassy Keita, the program officer at ARCAD Santé PLUS, which has received support from the Global Fund. He explains that producing sputum samples was often hard for kids — it requires coughing up mucus from deep in the lungs. Since AI screenings were introduced, they've been able to rapidly weed out the people who do not have any indication of TB on their x-rays and only do sputum samples for those who the AI model shows could have TB. Since incorporating AI into their screenings, they've cut the number of sputum samples by about half.

As a professor and computer scientist at MIT, Regina Barzilay has spent years building AI models to detect breast cancer and lung cancer. When a hospital in Sri Lanka told her it couldn't afford to buy off-the-shelf AI models for TB screenings, she agreed to build one for them. As she got to work this past year, she immediately understood why TB is at the vanguard of global health challenges with AI solutions.

“You can see TB. TB is visual. You have an x-ray. You have a label which says whether they have it or not — and you just train the model,” Barzilay says, adding that it only took her a few months and less than $50,000 to make her model. “It's straightforward, very cheap, very fast to develop.”

Unlike the equipment needed for mammograms or blood tests, x-ray machines for TB are widely available in low-resource settings. And it doesn't take much training for someone to use it. Plus, Ditiu adds, the need is huge. In 2023, there were 10.8 million new cases of TB, up from 10.1 million in 2020, according to the WHO, with the vast majority of cases in low- and middle-income countries.

Ditiu believes TB is only the start. Some of the AI models used for TB can already diagnose other conditions, including lung cancer, pneumonia, and certain cardiovascular issues. Barzilay predicts that in many low-income countries, AI will soon be integrated into health care systems to address a wide range of health issues.

However, the rapid adoption of AI in healthcare also raises concerns about regulation and patient protection. Advocates and experts agree that while the potential benefits are immense, ensuring the accuracy, reliability, and ethical use of AI in healthcare is crucial. As the technology continues to evolve, it is essential to establish robust guidelines and oversight to safeguard patients and maintain the integrity of healthcare systems in low- and middle-income countries. 

Frequently Asked Questions (FAQS): 

Q: What is the primary advantage of using AI for TB diagnosis?

A: The primary advantage of using AI for TB diagnosis is the speed and accuracy of results, allowing for quick identification and treatment of the disease in regions with a shortage of radiologists.

Q: How does AI detect TB in x-ray images?

A: AI detects TB by analyzing x-ray images and identifying signs of TB, such as abnormalities in the lungs. It produces a heat map with red and blue areas to indicate potential TB presence.

Q: What is the impact of AI on TB diagnosis in low- and middle-income countries?

A: AI significantly improves TB diagnosis in low- and middle-income countries by providing a cost-effective and efficient solution, reducing the need for trained radiologists and speeding up the diagnostic process.

Q: How does the AI model for TB diagnosis work?

A: The AI model for TB diagnosis is trained on a large dataset of x-ray images. It learns to identify patterns and abnormalities that indicate TB, providing a score and a heat map of the lungs.

Q: What are the potential future applications of AI in healthcare?

A: The potential future applications of AI in healthcare include diagnosing other conditions such as lung cancer, pneumonia, and cardiovascular issues, as well as integrating into broader healthcare systems to improve overall patient care. 

More Related Topics :