Home https://server7.kproxy.com/servlet/redirect.srv/sruj/smyrwpoii/p2/ Health https://server7.kproxy.com/servlet/redirect.srv/sruj/smyrwpoii/p2/ These algorithms could stop the scourge of tuberculosis

These algorithms could stop the scourge of tuberculosis

In some of the most remote and impoverished parts of the world, where there are respiratory diseases and trained medical professionals are afraid to set foot, diagnostics are increasingly being enhanced by artificial intelligence and the Internet.

In less than a minute, a new phone or computer application can scan an X-ray for signs of tuberculosis, Covid-19, and 27 other conditions.

TB, the world’s deadliest infectious disease, claimed nearly 1.4 million lives last year. The app, called qXR, is one of many AI-based tools that have emerged in recent years to screen for and diagnose tuberculosis.

The tools give hope to detect the disease early and reduce the cost of unnecessary laboratory tests. Used on a large scale, they can also spot emerging groups of diseases.

“Of all the AI ​​applications, I think digital interpretation of an image using an algorithm instead of a human radiologist is probably the most remote,” said Madhukar Pai, director of the McGill International Tuberculosis Center in Montreal.

Artificial intelligence cannot replace clinicians, warned Dr. Pai and other experts. But the combination of AI and clinical expertise is proving powerful.

“The machine plus clinician is better than the clinician, and it’s also better than the machine itself,” said Dr. Eric Topol, director of the Scripps Research Translation Institute in San Diego and author of a book on the use of AI in San Diego. medicine.

In India, where approximately a quarter of the world’s TB cases occur, an application is urgently needed that could signal the disease in remote places.

Chinchpada Christian Hospital in Nandurbar, a small town in northwestern India, serves members of the Bhil tribal community, some of whom travel up to 125 miles to visit the center. The hospital with 50 beds has eight doctors and only the most basic medical equipment.

Clearly across the country, Simdega, one of India’s 20 poorest areas, is isolated from the nearest town of Rurkela by nearly five hours of travel on a bumpy road. The tribal population in the area lives in small villages surrounded by dense, evergreen forest. Simdega Medical Center, which has 60 beds and three doctors, is in a clear forest – “literally in the middle of nowhere,” said Dr. George Matthew, director.

The meager staff should manage everything they come across, “from malaria to myocardial infarction to convulsions to head injuries,” Dr. Matthew said. Over the years, he learned to read X-rays, and when he stumbled, he turned to radiologists among his distant friends and former colleagues.

Although Nandurbar and Simdega are more than 800 miles apart, their populations are strikingly similar. Malaria, sickle cell disease and tuberculosis are spreading among them, combined with poverty, reliance on spiritual healers and alcoholism – even among children.

“Tuberculosis is usually ignored and the diagnosis is often delayed,” said Dr. Ashita Singh, head of medicine at Nandurbar Hospital. By the time people arrive at these medical centers, they are often “very, very sick and have never even been examined anywhere else,” she said.

But in some patients, X-rays show signs that are too fine for a layman to detect. “In this group of patients, patients with AI can be very helpful,” said Dr. Singh.

The arrival of the coronavirus and the subsequent blockade cut off these remote hospitals from nearby cities and from radiologists as well. It also further delays and complicates diagnoses of tuberculosis, as both diseases affect the lungs.

A few months ago, both hospitals began using qXR, an application made by the Indian company Qure.ai and subsidized by the Indian government. The application allows the user to scan an X-ray. If it finds evidence of tuberculosis, it assigns the patient a risk assessment. Physicians can then perform confirmatory tests on the highest risk patients.

At the hospital in Nandurbar, the application helped diagnose tuberculosis in 20 patients in October, Dr Singh said.

Applications such as qXR can also be useful in places with a low prevalence of tuberculosis and for routine screening of people with HIV who are at high risk of contracting tuberculosis, as well as for those with other conditions, experts say.

“Most chest X-rays of people suspected of having tuberculosis are read by people who are not remote experts in their interpretation,” said Dr. Richard E. Shayson, a tuberculosis expert at Johns Hopkins University. . “If there was a package of artificial intelligence that could read your X-rays and CT scans in a remote emergency room, that would be a huge, huge improvement.”

qXR is one of the most promising AI-based tuberculosis detection applications. The company that made the application did not realize this potential until a doctor at an Indian hospital suggested it a few years ago.

In studies comparing different AI applications conducted by the Stop TB partnership, all AI applications outperformed experienced human readers, and qXR looked best.

The app identifies tuberculosis with 95 percent accuracy, according to Qure.ai CEO Prashant Varie. But this level of precision is not based on real conditions, which Dr. Topol called a “common problem” in AI-based applications. The tuberculosis program may be less accurate in the United States or Western Europe than in India because the spread of the disease is lower in those places, Dr. Topol added.

The application has been tested only in adults, but is now used in children 6 years and older. Chest x-rays are especially helpful for childhood tuberculosis because about 70 percent of cases in children cannot be confirmed by laboratory tests, said Dr. Sylvia S. Chiang, an expert on childhood tuberculosis at Brown University.

“There is a huge shortage of trained professionals who feel comfortable interpreting children’s chest X-rays,” she said, “so developing and validating computer-assisted X-ray reading technology in children would help greatly.”

Qure.ai said it was testing its application on children in Bangladesh and would release the data early next year. Meanwhile, qXR and other applications will continue to improve because they learn as they go.

“The more X-rays you feed the beast, the better,” said Dr. Pai.

Experts were optimistic that AI-based applications could have a huge impact on TB control, especially in countries like India that do not have medical resources.

“I’m just dreaming of a time when something like this would be available to all the small primary and secondary health care centers in the public sector that are reluctant to take X-rays because they don’t have the confidence to read them,” Dr. Singh said. “If this was to be available to any X-ray center in the province of India, I think we could beat tuberculosis.”

Source link