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.
There's no shortage of fake news going around the internet these days, but how do we become more aware as consumers of what's real and what's not?
"We are hoping to create what you might call a general 'vaccine' against fake news, rather than trying to counter each specific conspiracy or falsehood."
Researchers at the University of Cambridge may have answered just that by developing an online game designed to expose and educate participants to the tactics used by those spreading false information.
"We wanted to see if we could preemptively debunk, or 'pre-bunk', fake news by exposing people to a weak dose of the methods used to create and spread disinformation, so they have a better understanding of how they might be deceived," Dr Sander van der Linden, Director of the Cambridge Social Decision-Making Lab, said in a statement.
"This is a version of what psychologists call 'inoculation theory', with our game working like a psychological vaccination."
In February 2018, van der Linden and his coauthor, Jon Roozenbeek, helped launch the browser game, "Bad News," where players take on the role of "Disinformation and Fake News Tycoon."
They can manipulate news and social media within the game by several different methods, including deploying twitter-bots, photo-shopping evidence, creating fake accounts, and inciting conspiracy theories with the goal of attracting followers and maintaining a "credibility score" for persuasiveness.
In order to gauge the game's effectiveness, players were asked to rate the reliability of a number of real and fake news headlines and tweets both before and after playing. The data from 15,000 players was evaluated, with the results published June 25 in the journal Palgrave Communications.
The results concluded that "the perceived reliability of fake news before playing the game had reduced by an average of 21% after completing it. Yet the game made no difference to how users ranked real news."
Just 15 minutes of playing the game can have a moderate effect on people, which could play a major role on a larger scale.
Additionally, participants who "registered as most susceptible to fake news headlines at the outset benefited most from the 'inoculation,'" according to the study.
Just 15 minutes of playing the game can have a moderate effect on people, which could play a major role on a larger scale when it comes to "building a societal resistance to fake news," according to Dr. van der Linden.
"Research suggests that fake news spreads faster and deeper than the truth, so combating disinformation after-the-fact can be like fighting a losing battle," he said.
"We are hoping to create what you might call a general 'vaccine' against fake news, rather than trying to counter each specific conspiracy or falsehood," Roozenbeek added.
Van der Linden and Roozenbeek's work is an early example of the potential methods to protect people against deception by training them to be more attuned to the methods used to distribute fake news.
"I hope that the positive results give further credence to the new science of prebunking rather than only thinking about traditional debunking. On a larger level, I also hope the game and results inspire a new kind of behavioral science research where we actively engage with people and apply insights from psychological science in the public interest," van der Linden told leapsmag.
"I like the idea that the end result of a scientific theory is a real-world partnership and practical tool that organizations and people can use to guard themselves against online manipulation techniques in a novel and hopefully fun and engaging manner."
Ready to be "inoculated" against fake news? Then play the game for yourself.
What if people could just survive on sunlight like plants?
The admittedly outlandish question occurred to me after reading about how climate change will exacerbate drought, flooding, and worldwide food shortages. Many of these problems could be eliminated if human photosynthesis were possible. Had anyone ever tried it?
Extreme space travel exists at an ethically unique spot that makes human experimentation much more palatable.
I emailed Sidney Pierce, professor emeritus in the Department of Integrative Biology at the University of South Florida, who studies a type of sea slug, Elysia chlorotica, that eats photosynthetic algae, incorporating the algae's key cell structure into itself. It's still a mystery how exactly a slug can operate the part of the cell that converts sunlight into energy, which requires proteins made by genes to function, but the upshot is that the slugs can (and do) live on sunlight in-between feedings.
Pierce says he gets questions about human photosynthesis a couple of times a year, but it almost certainly wouldn't be worth it to try to develop the process in a human. "A high-metabolic rate, large animal like a human could probably not survive on photosynthesis," he wrote to me in an email. "The main reason is a lack of surface area. They would either have to grow leaves or pull a trailer covered with them."
In short: Plants have already exploited the best tricks for subsisting on photosynthesis, and unless we want to look and act like plants, we won't have much success ourselves. Not that it stopped Pierce from trying to develop human photosynthesis technology anyway: "I even tried to sell it to the Navy back in the day," he told me. "Imagine photosynthetic SEALS."
It turns out, however, that while no one is actively trying to create photosynthetic humans, scientists are considering the ways humans might need to change to adapt to future environments, either here on the rapidly changing Earth or on another planet. Rice University biologist Scott Solomon has written an entire book, Future Humans, in which he explores the environmental pressures that are likely to influence human evolution from this point forward. On Earth, Solomon says, infectious disease will remain a major driver of change. As for Mars, the big two are lower gravity and radiation, the latter of which bombards the Martian surface constantly because the planet has no magnetosphere.
Although he considers this example "pretty out there," Solomon says one possible solution to Mars' magnetic assault could leave humans not photosynthetic green, but orange, thanks to pigments called carotenoids that are responsible for the bright hues of pumpkins and carrots.
"Carotenoids protect against radiation," he says. "Usually only plants and microbes can produce carotenoids, but there's at least one kind of insect, a particular type of aphid, that somehow acquired the gene for making carotenoids from a fungus. We don't exactly know how that happened, but now they're orange... I view that as an example of, hey, maybe humans on Mars will evolve new kinds of pigmentation that will protect us from the radiation there."
We could wait for an orange human-producing genetic variation to occur naturally, or with new gene editing techniques such as CRISPR-Cas9, we could just directly give astronauts genetic advantages such as carotenoid-producing skin. This may not be as far-off as it sounds: Extreme space travel exists at an ethically unique spot that makes human experimentation much more palatable. If an astronaut already plans to subject herself to the enormous experiment of traveling to, and maybe living out her days on, a dangerous and faraway planet, do we have any obligation to provide all the protection we can?
Probably the most vocal person trying to figure out what genetic protections might help astronauts is Cornell geneticist Chris Mason. His lab has outlined a 10-phase, 500-year plan for human survival, starting with the comparatively modest goal of establishing which human genes are not amenable to change and should be marked with a "Do not disturb" sign.
To be clear, Mason is not actually modifying human beings. Instead, his lab has studied genes in radiation-resistant bacteria, such as the Deinococcus genus. They've expressed proteins called DSUP from tardigrades, tiny water bears that can survive in space, in human cells. They've looked into p53, a gene that is overexpressed in elephants and seems to protect them from cancer. They also developed a protocol to work on the NASA twin study comparing astronauts Scott Kelly, who spent a year aboard the International Space Station, and his brother Mark, who did not, to find out what effects space tends to have on genes in the first place.
In a talk he gave in December, Mason reported that 8.7 percent of Scott Kelly's genes—mostly those associated with immune function, DNA repair, and bone formation—did not return to normal after the astronaut had been home for six months. "Some of these space genes, we could engineer them, activate them, have them be hyperactive when you go to space," he said in that same talk. "When we think about having the hubris to go to a faraway planet...it seems like an almost impossible idea….but I really like people and I want us to survive for a long time, and this is the first step on the stairwell to survive out of the solar system."
What is the most important ability we could give our future selves through science?
There are others performing studies to figure out what capabilities we might bestow on the future-proof superhuman, but none of them are quite as extreme as photosynthesis (although all of them are useful). At Harvard, geneticist George Church wants to engineer cells to be resistant to viruses, such as the common cold and HIV. At Columbia, synthetic biologist Harris Wang is addressing self-sufficient humans more directly—trying to spur kidney cells to produce amino acids that are normally only available from diet.
But perhaps Future Humans author Scott Solomon has the most radical idea. I asked him a version of the classic What would be your superhero power? question: What does he see as the most important ability we could give our future selves through science?
"The empathy gene," he said. "The ability to put yourself in someone else's shoes and see the world as they see it. I think it would solve a lot of our problems."