Artificial Intelligence is getting better than humans at detecting breast cancer
Since the early 2000s, AI systems have eliminated more than 1.7 million jobs, and that number will only increase as AI improves. Some research estimates that by 2025, AI will eliminate more than 85 million jobs.
But for all the talk about job security, AI is also proving to be a powerful tool in healthcare—specifically, cancer detection. One recently published study has shown that, remarkably, artificial intelligence was able to detect 20 percent more cancers in imaging scans than radiologists alone.
Published in The Lancet Oncology, the study analyzed the scans of 80,000 Swedish women with a moderate hereditary risk of breast cancer who had undergone a mammogram between April 2021 and July 2022. Half of these scans were read by AI and then a radiologist to double-check the findings. The second group of scans was read by two researchers without the help of AI. (Currently, the standard of care across Europe is to have two radiologists analyze a scan before diagnosing a patient with breast cancer.)
The study showed that the AI group detected cancer in 6 out of every 1,000 scans, while the radiologists detected cancer in 5 per 1,000 scans. In other words, AI found 20 percent more cancers than the highly-trained radiologists.
Scientists have been using MRI images (like the ones pictured here) to train artificial intelligence to detect cancers earlier and with more accuracy. Here, MIT's AI system, MIRAI, looks for patterns in a patient's mammograms to detect breast cancer earlier than ever before. news.mit.edu
But even though the AI was better able to pinpoint cancer on an image, it doesn’t mean radiologists will soon be out of a job. Dr. Laura Heacock, a breast radiologist at NYU, said in an interview with CNN that radiologists do much more than simply screening mammograms, and that even well-trained technology can make errors. “These tools work best when paired with highly-trained radiologists who make the final call on your mammogram. Think of it as a tool like a stethoscope for a cardiologist.”
AI is still an emerging technology, but more and more doctors are using them to detect different cancers. For example, researchers at MIT have developed a program called MIRAI, which looks at patterns in patient mammograms across a series of scans and uses an algorithm to model a patient's risk of developing breast cancer over time. The program was "trained" with more than 200,000 breast imaging scans from Massachusetts General Hospital and has been tested on over 100,000 women in different hospitals across the world. According to MIT, MIRAI "has been shown to be more accurate in predicting the risk for developing breast cancer in the short term (over a 3-year period) compared to traditional tools." It has also been able to detect breast cancer up to five years before a patient receives a diagnosis.
The challenges for cancer-detecting AI tools now is not just accuracy. AI tools are also being challenged to perform consistently well across different ages, races, and breast density profiles, particularly given the increased risks that different women face. For example, Black women are 42 percent more likely than white women to die from breast cancer, despite having nearly the same rates of breast cancer as white women. Recently, an FDA-approved AI device for screening breast cancer has come under fire for wrongly detecting cancer in Black patients significantly more often than white patients.
As AI technology improves, radiologists will be able to accurately scan a more diverse set of patients at a larger volume than ever before, potentially saving more lives than ever.
Scientists Are Studying How to Help Dogs Have Longer Lives, in a Bid to Further Our Own
The sad eyes. The wagging tail. The frustrated whine. The excited bark. Dogs know how to get their owners to fork over the food more often.
The extra calories dogs get from feeding patterns now used by many Americans may not be good for them from a health and longevity viewpoint. In research from a large study called the Dog Aging Project, canines fed once a day had better scores on cognition tests and lower odds of developing diseases of organs throughout the body: intestinal tract, mouth and teeth, bones and joints, kidneys and bladder, and liver and pancreas.
Fewer than 1 in 10 dog owners fed their furry friends once daily, while nearly three fourths provided two daily meals.
“Most veterinarians have been led to believe that feeding dogs twice a day is optimal, but this is a relatively new idea that has developed over the past few decades with little supportive evidence from a health standpoint,” said Matt Kaeberlein, PhD, Co-Director of the Dog Aging Project, a professor of pathology and Director of the Healthy Aging and Longevity Research Institute at the University of Washington. Kaeberlein studies basic mechanisms of aging to find ways of extending the healthspan, the number of years of life lived free of disease. It’s not enough to extend the lifespan unless declines in biological function and risks of age-related diseases are also studied, he believes, hence the healthspan.
The Dog Aging Project is studying tens of thousands of dogs living with their owners in the real world, not a biology laboratory. The feeding study is the first of several reports now coming from the project based on owners’ annual reports of demographics, physical activity, environment, dog behavior, diet, medications and supplements, and health status. It has been posted on bioRxiv as it goes through peer review.
“All available evidence suggests that most biological mechanisms of aging in dogs will be conserved in humans. It just happens much faster in dogs.”
“The Dog Aging Project is one of the most exciting in the longevity space,” said David A. Sinclair, professor in the Department of Genetics and co-director of the Paul F. Glenn Center for Biology of Aging Research at Harvard Medical School. “Not only is it important to help our companions live longer and healthier, but because they are like people and share the same environment and many of the lifestyles as their owners, they are the perfect model for human longevity interventions.”
The epigenetic clock — and specifically changes in gene expression resulting from methylation of cytosine and guanine in the DNA — provides the critical connection between aging in dogs and people. “All available evidence suggests that most biological mechanisms of aging in dogs will be conserved in humans,” Kaeberlein said. “It just happens much faster in dogs.” These methylation changes, called the “methylomes,” have been associated with rates of aging in dogs, humans, and also mice.
In a 2020 study young dogs matched with young adults and aged dogs matched with older adults showed the greatest similarities in methylomes. In the Cell Systems report, Tina Wang of the University of California, San Diego, and colleagues wrote that the methylome “can be used to quantitatively translate the age-related physiology experienced by one organism (i.e., a model species like dog) to the age at which physiology in a second organism is most similar (i.e., a second model or humans).” This allows rates of aging in one species to be mapped onto aging in another species, providing “a compelling tool in the quest to understand aging and identify interventions for maximizing healthy lifespan.”
In the Dog Aging Project study, 8% of 24,238 owners fed their dogs once daily, the same as the percentage of owners serving three daily meals. Twice-daily feedings were most common (73%), and just over 1 in 10 owners (11%) “free fed” their dogs by just filling up the bowl whenever it was empty — most likely Rover’s favorite option.
“The notion of breakfast, lunch, and dinner for people in the United States is not based on large studies that compared three meals a day to two meals a day, or to four, “ said Kate E. Creevy, chief veterinary officer with the Dog Aging Project and associate professor at Texas A&M University. “It’s more about what we are accustomed to. Similarly, there are not large population studies comparing outcomes of dogs fed once, twice, or three times a day.”
“We do not recommend that people change their dogs’ diets based on this report,” Creevy emphasized. “It’s important to understand the difference between research that finds associations versus research that finds cause and effect.”
To establish cause and effect, the Dog Aging Project will follow their cohort over many years. Then, Creevy said, “We will be able to determine whether the associations we have found with feeding frequency are causes, or effects, or neither.”
While not yet actionable, the feeding findings fit with biology across a variety of animals, Kaeberlein said, including indicators that better health translates into longer healthspans. He said that caloric restriction and perhaps time-restricted eating or intermittent fasting — all ways that some human diets are structured — can have a positive impact on the biology of aging by allowing the gastrointestinal tract to have time each day to rest and repair itself, just as sleep benefits the brain through rest.
Timing of meals is also related to the concept of ketogenesis, Kaeberlein explained. Without access to glucose, animals switch over to a ketogenic state in which back-up systems produce energy through metabolic pathways that generate ketones. Mice go into this state very quickly, after a few hours or an overnight fast, while people shift to ketogenesis more slowly, from a few hours to up to 36 hours for people on typical Western diets, Kaeberlein said.
Dogs are different. They take at least two days to shift to ketogenesis, suggesting they have evolved to need fewer meals that are spaced out rather than the multiple daily meals plus snacks that people prefer.
As this relates to longevity, Kaeberlein said that a couple of studies show that mice who are fed a ketogenic diet have longer lifespans (years of life regardless of health). “For us, the next step is to analyze the composition of the dogs’ diets or the relationship of multiple daily feedings with obesity,” he said. “Maybe not being obese is related to better health.”
To learn more, the Dog Aging Project needs dogs — lots of dogs! Kaeberlein wants at least 100,000 dogs, including small dogs, large dogs, dogs of all ages. Puppies are needed for the researchers to follow across their lifespan. The project has an excellent website where owners can volunteer to participate.
Nutritional strategies are often not built around sound scientific principles, Kaeberlein said. In human nutrition, people have tried all kinds of diets over the years, including some that were completely wrong. Kaeberlein and his colleagues in the Dog Aging Project want to change that, at least for people’s canine companions, and hopefully, as a result, give dogs added years of healthy life and provide clues for human nutrition.
After that, maybe they can do something about those sad eyes and the frustrated whine.
Podcast: New Solutions to Combat Gluten Sensitivities and Food Allergies
The "Making Sense of Science" podcast features interviews with leading medical and scientific experts about the latest developments and the big ethical and societal questions they raise. This monthly podcast is hosted by journalist Kira Peikoff, founding editor of the award-winning science outlet Leaps.org.
This month, we talk Anat Binur, the CEO of Israeli/U.S.-based biotech company Ukko. Ukko is taking a revolutionary approach to the distressing problem of food allergies and gluten sensitivities: their scientists are designing and engineering proteins that keep the good biophysical properties of the original proteins, while removing the immune-triggering parts that can cause life-threatening allergies. The end goal is proteins that are safe for everyone. Ukko is focusing first on developing a new safe gluten protein for use in baking and a new peanut protein for use as a therapeutic. Their unique platform could theoretically be used for any protein-based allergy, including cats and bees. Hear more in this episode.
Watch the 60-second trailer
Listen to the whole episode
<div id="buzzsprout-player-9950980"></div><script src="https://www.buzzsprout.com/1714953/9950980-solving-food-allergies-with-biotech-company-ukko.js?container_id=buzzsprout-player-9950980&player=small" type="text/javascript" charset="utf-8"></script>
Kira Peikoff was the editor-in-chief of Leaps.org from 2017 to 2021. As a journalist, her work has appeared in The New York Times, Newsweek, Nautilus, Popular Mechanics, The New York Academy of Sciences, and other outlets. She is also the author of four suspense novels that explore controversial issues arising from scientific innovation: Living Proof, No Time to Die, Die Again Tomorrow, and Mother Knows Best. Peikoff holds a B.A. in Journalism from New York University and an M.S. in Bioethics from Columbia University. She lives in New Jersey with her husband and two young sons. Follow her on Twitter @KiraPeikoff.