1700660192 Artificial intelligence is supposed to detect tuberculosis in a prison

Artificial intelligence is supposed to detect tuberculosis in a prison in Mozambique

In the courtyard of a maximum-security prison in Maputo, Mozambique, a man with a shaved head and an orange T-shirt with the word “inmate” crossed out waits patiently, his chest resting on a large white tablet hanging vertically.

• Also read: ‘It can destroy a life’: American teenagers fall victim to fake nude photos created by AI

Behind him, a nurse presses the button on the portable lung.

AI enables precise and instant reading of the radio signal without requiring the expertise of a doctor.

“It’s real time, we have the results in less than five minutes,” explains the nurse.

Artificial intelligence is supposed to detect tuberculosis in a prison in Mozambique

AFP

The image soon appears on the screen of a technician installed a few meters away, accompanied by a diagnosis: “Radiological signs suggestive of tuberculosis – negative,” the computer displays.

The test is part of a pilot project to screen inmates in three prisons in the Mozambican capital, run by Stop TB, a United Nations-backed organization.

Artificial intelligence is supposed to detect tuberculosis in a prison in Mozambique

AFP

Overcrowded prisons are a breeding ground for tuberculosis, the world’s second deadliest disease after Covid, which infected more than 10 million people and killed 1.3 million in 2022, according to the WHO.

Almost one in four people who contracted the disease last year lived in Africa. Around 120,000 cases have been registered in Mozambique, with a population of 32 million.

Early diagnosis helps save lives and stop the spread because while chronic cough is a hallmark of tuberculosis, some carriers show no symptoms.

This is particularly true in prison, where tuberculosis spreads through the air and crowded cells provide a breeding ground.

According to the United Nations, Mozambique’s prisons were about 50% over capacity in 2022.

“Science fiction”

The portable X-ray machine uses AI to improve traditional diagnosis by being faster than skin or blood tests that need to be analyzed in the laboratory. In addition, it does not require patients to travel and eliminates the need for radiologists, which may be rare in rural areas or poor countries, explains Suvanand Sahu, deputy director of Stop TB.

“It’s a major technological advance,” he enthuses.

In the provincial prison in Maputo, the capital of Mozambique, prisoners who tested positive are quarantined behind a rusty metal door.

Artificial intelligence is supposed to detect tuberculosis in a prison in Mozambique

AFP

Inside, a dozen men wearing masks sit on mattresses on the floor while clothes, blankets and other belongings hang from a rope tied between two faded blue pillars. Serious cases are taken to the infirmary.

“It’s not easy to see your comrades stretching out and playing, but you have to accept that I’m sick,” admits Kennet Fortune, who has been incarcerated for 10 years on drug charges, pointing to the trees in the prison’s courtyard.

He tested positive for tuberculosis and is currently undergoing treatment that could last months. “When the time comes, I will come out.”

Earlier this month, a WHO report found that deaths from tuberculosis fell worldwide in 2022, a sign of progress in eradicating the disease.

And over the same period, 7.5 million people were newly diagnosed, the highest number since the WHO began monitoring tuberculosis in 1995.

Stop TB’s Mr Sahu hopes the success of pilot projects like the one in Mozambique will help secure funding to expand the use of AI and portable radios to defeat the disease.

“If I had said at a meeting just a few years ago that we could take X-ray images anywhere that could be read by a machine without the use of radiologists, I would have been told to write a science fiction novel.” he smiles.