MICHEL MARTIN, HOST:
Tuberculosis is the world's deadliest infectious disease. More than 3,000 people around the world die from TB every day, and many tuberculosis patients live in low-income countries with limited access to health care. Now artificial intelligence is being used where medical specialists are not available, part of a trend that some experts say will change the future of global health. NPR's Gabrielle Emanuel reports.
GABRIELLE EMANUEL, BYLINE: Carrying an X-ray machine and a computer, Diakite Lancine (ph) travels around Mali in West Africa, going from clinic to clinic. He's a technician for a local nonprofit, ARCAD Sante PLUS. On a recent morning, he called me as he headed into a community health center.
DIAKITE LANCINE: Outside, there is a lot of people. They're coming from everywhere.
EMANUEL: One of the people is a mother. She's coughing a lot. And like the others in line, she's here to see if she has TB. She stands in front of Lancine's X-ray machine. He snaps an image and almost instantly it's read by AI. His computer displays a picture that looks like a heat map where blue is good and red is bad.
LANCINE: Where you see the red, the red means this part is not good, it's not good.
EMANUEL: AI says the mom has TB. Lancine gets a sputum sample to send to a lab to confirm. Then he quickly sends the mom home to get her kids so he can test them, too. Three of the five kids also have TB. Soon they'll start a six-month course of antibiotics. Lancine says this technology has revolutionized their approach because instead of taking a week or two to get an answer, they get one instantly and without a doctor in the room. Peter Sands heads the Global Fund, a multibillion-dollar effort to tackle TB and other diseases.
PETER SANDS: We're talking about situations like refugee camps in Chad. There are no radiologists. So who gets to look at the thing and say, is there a problem here or not? Well, actually, AI does. It's brilliant.
EMANUEL: In the past four years, the Global Fund has put almost $200 million into AI-enabled TB screenings. Sands points to a significant increase in the number of TB cases detected in that time. At MIT, Professor Regina Barzilay builds these AI models. She's predicting AI will be widely adopted in low-income countries, where there's a shortage of doctors and specialists.
REGINA BARZILAY: AI is going to be adopted much more faster in developing countries because they have serious unmet need.
EMANUEL: But some are urging caution. Erwin John Carpio is with the Philippines College of Radiology. He says many high-income countries, like the U.S., have regulations and guardrails for using AI in health. In the U.K., he says, if an AI model misses a diagnosis, it's officially reported. But that's not the case for many low- and middle-income countries, like the Philippines.
ERWIN JOHN CARPIO: In our country, since we don't have the laws in place yet, vendors are not required to provide information like that.
EMANUEL: Carpio says, because each population is a bit different, the AI model must be calibrated to fit the local context. And, he says, there should be continual quality control checks.
CARPIO: You're going to need a computer scientist, a data scientist, an AI engineer. You're going to need an entire team of experts.
EMANUEL: The program used by the clinic in Mali does have those human experts backing it up. Under those circumstances, Carpio admits AI can do a good job with health screenings. But he doesn't want our enthusiasm for the technology to race ahead of our vigilance in making sure we use it responsibly.
Gabrielle Emanuel, NPR News.
(SOUNDBITE OF BROKEN SOCIAL SCENE'S "GUILTY CUBICLES") Transcript provided by NPR, Copyright NPR.
NPR transcripts are created on a rush deadline by an NPR contractor. This text may not be in its final form and may be updated or revised in the future. Accuracy and availability may vary. The authoritative record of NPR鈥檚 programming is the audio record.
