There is a new artificial intelligence (AI) interface that’s been in the news lately called ChatGPT. ChatGPT is a language-based AI chatbot that can do many things humans can do. Some tasks it can do better than humans can do. A week or so ago I asked Would You See an AI Doctor?, Saying:
Radiologists sometimes use computer-aided detection (CAD) to interpret mammograms as a backup to human interpretation. Using both a radiologist and CAD together increases accuracy.
Inside a dark room at Bács-Kiskun County Hospital outside Budapest, Dr. Éva Ambrózay, a radiologist with more than two decades of experience, peered at a computer monitor showing a patient’s mammogram.
Two radiologists had previously said the X-ray did not show any signs that the patient had breast cancer. But Dr. Ambrózay was looking closely at several areas of the scan circled in red, which artificial intelligence software had flagged as potentially cancerous.
“This is something,” she said. She soon ordered the woman to be called back for a biopsy, which is taking place within the next week.
Some occupations will always require a human being, whose brain is far more advanced than computer. Other occupations involve tanks that lend themselves to things AI can do well. Whether or not a physician is aided by AI is likely to vary from physician specialty to physician specialty. An early candidate is breast cancer screening.
Advancements in A.I. are beginning to deliver breakthroughs in breast cancer screening by detecting the signs that doctors miss. So far, the technology is showing an impressive ability to spot cancer at least as well as human radiologists, according to early results and radiologists, in what is one of the most tangible signs to date of how A.I. can improve public health.
Hungary has a robust screening program for breast cancer. Five Hungarian hospitals mentioned in the New York Times article perform 35,000 screenings a year. These hospitals began testing AI on breast cancer screenings in 2021 to look for cancer that radiologists may miss. The technology will never replace radiologists but could become an automated algorithm embedded into the machines physicians use to view mammograms. The embedded algorithm would likely be in addition to one or even two radiologists interpreting the scan.
The tool must also show it can produce accurate results on women of all ages, ethnicities and body types. And the technology must prove it can recognize more complex forms of breast cancer and cut down on false-positives that are not cancerous, radiologists said.
Back in 2017 a leading AI researcher told the New York Times that within five years AI would eclipse the skills of a radiologist. Other researchers, such as computer scientist Peter Kecskemethy, knew that was unlikely.
Mr. Kecskemethy grew up in Hungary spending time at one of Budapest’s largest hospitals. His mother was a radiologist, which gave him a firsthand look at the difficulties of finding a small malignancy within an image. Radiologists often spend hours every day in a dark room looking at hundreds of images and making life-altering decisions for patients.
“It’s so easy to miss tiny lesions,” said Dr. Edith Karpati, Mr. Kecskemethy’s mother, who is now a medical product director at Kheiron. “It’s not possible to stay focused.”
Mr. Kecskemethy used 5 million mammograms of patients whose diagnosis was already known to program his machine learning software. That’s a lot of observations from which to train an artificial intelligence algorithm.
From the millions of cases the system is fed, the technology creates a mathematical representation of normal mammograms and those with cancers. With the ability to look at each image in a more granular way than the human eye, it then compares that baseline to find abnormalities in each mammogram.
One radiologist the New York Times interviewed said he used the software to review the most challenging cases of his career, where breast cancer had been missed. In all cases the AI software found the cancer.