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.
Shoot for the Moon: Its Surface Contains a Pot of Gold
Here's a riddle: What do the Moon, nuclear weapons, clean energy of the future, terrorism, and lung disease all have in common?
One goal of India's upcoming space probe is to locate deposits of helium-3 that are worth trillions of dollars.
The answer is helium-3, a gas that's extremely rare on Earth but 100 million times more abundant on the Moon. This past October, the Lockheed Martin corporation announced a concept for a lunar landing craft that may return humans to the Moon in the coming decade, and yesterday China successfully landed the Change-4 probe on the far side of the Moon. Landing inside the Moon's deepest crater, the Chinese achieved a first in space exploration history.
Meanwhile, later this month, India's Chandrayaan-2 space probe will also land on the lunar surface. One of its goals is to locate deposits of helium-3 that are worth trillions of dollars, because it could be a fuel for nuclear fusion energy to generate electricity or propel a rocket.
The standard way that nuclear engineers are trying to achieve sustainable fusion uses fuels that are more plentiful on Earth: deuterium and tritium. But MIT researchers have found that adding small amounts of helium-3 to the mix could make it much more efficient, and thus a viable energy source much sooner that once thought.
Even if fusion is proven practical tomorrow, any kind of nuclear energy involves long waits for power plant construction measured in decades. However, mining helium-3 could be useful now, because of its non-energy applications. A major one is its ability to detect neutrons coming from plutonium that could be used in terrorist attacks. Here's how it works: a small amount of helium-3 is contained within a forensic instrument. When a neutron hits an atom of helium-3, the reaction produces tritium, a proton, and an electrical charge, alerting investigators to the possibility that plutonium is nearby.
Ironically, as global concern about a potential for hidden nuclear material increased in the early 2000s, so did the supply of helium-3 on Earth. That's because helium-3 comes from the decay of tritium, used in thermonuclear warheads (H-bombs). Thousands of such weapons have been dismantled from U.S. and Russian arsenals, making helium-3 available for plutonium detection, research, and other applications--including in the world of healthcare.
Helium-3 can help doctors diagnose lung diseases, since it enables imaging of the lungs in real time.
Helium-3 dramatically improves the ability of doctors to image the lungs in a range of diseases including asthma, chronic obstructive pulmonary disease and emphysema, cystic fibrosis, and bronchopulmonary dysplasia, which happens particularly in premature infants. Specifically, helium-3 is useful in magnetic resonance imaging (MRI), a procedure that creates images from within the body for diagnostic purposes.
But while a standard MRI allows doctors to visualize parts of the body like the heart or brain, it's useless for seeing the lungs. Because lungs are filled with air, which is much less dense than water or fat, effectively no signals are produced that would enable imaging.
To compensate for this problem, a patient can inhale gas that is hyperpolarized –meaning enhanced with special procedures so that the magnetic resonance signals from the lungs are finally readable. This gas is safe to breathe when mixed with enough oxygen to support life. Helium-3 is one such gas that can be hyperpolarized; since it produces such a strong signal, the MRI can literally see the air inside the lungs and in all of the airways, revealing intricate details of the bronchopulmonary tree. And it can do this in real time
The capability to show anatomic details of the lungs and airways, and the ability to display functional imaging as a patient breathes, makes helium-3 MRI far better than the standard method of testing lung function. Called spirometry, this method tells physicians how the lungs function overall, but does not home in on particular areas that may be causing a problem. Plus, spirometry requires patients to follow instructions and hold their breath, so it is not great for testing young children with pulmonary disease.
In recent years, the cost of helium-3 on Earth has skyrocketed.
Over the past several years, researchers have been developing MRI for lung testing using other hyperpolarized gases. The main alternative to helium-3 is xenon-129. Over the years, researchers have learned to overcome certain disadvantages of the latter, such as its potential to put patients to sleep. Since helium-3 provides the strongest signal, though, it is still the best gas for MRI studies in many lung conditions.
But the supply of helium-3 on Earth has been decreasing in recent years, due to the declining rate of dismantling of warheads, just as the Department of Homeland Security has required more and more of the gas for neutron detection. As a result, the cost of the gas has skyrocketed. Less is available now for medical uses – unless, of course, we begin mining it on the moon.
The question is: Are the benefits worth the 239,000-mile trip?
Should Organ Donors Be Paid?
Deanna Santana had assumed that people on organ transplant lists received matches. She didn't know some died while waiting. But in May 2011, after her 17-year-old son, Scott, was killed in a car accident, she learned what a precious gift organ and tissue donation can be.
"I would estimate it cost our family about $4,000 for me to donate a kidney to a stranger."
His heart, lungs, kidneys, liver and pancreas saved five people. His corneas enabled two others to see. And his bones, connective tissues and veins helped 73 individuals.
The donation's impact had a profound effect on his mother as well. In September 2016, she agreed to donate a kidney in a paired exchange of four people making the same sacrifice for four compatible strangers.
She gave up two weeks' worth of paid vacation to recuperate and covered lodging costs for loved ones during her transplant. Eventually, she qualified for state disability for part of her leave, but the compensation was less than her salary as public education and relations manager at Sierra Donor Services, an organ procurement organization in West Sacramento, California.
"I would estimate it cost our family about $4,000 for me to donate a kidney to a stranger," says Santana, 51. Despite the monetary hardship, she "would do it again in a heartbeat."
While some contend it's exploitative to entice organ donors and their families with compensation, others maintain they should be rewarded for extending their generosity while risking complications and recovering from donation surgery. But many agree on one point: The focus should be less on paying donors and more on removing financial barriers that may discourage interested prospects from doing a good deed.
"There's significant potential risk associated with donating a kidney, some of which we're continuing to learn," says transplant surgeon Matthew Cooper, a board member of the National Kidney Foundation and co-chair of its Transplant Task Force.
Although most kidneys are removed laparoscopically, reducing hospitalization and recuperation time, complications can occur. The risks include wound and urinary tract infections, pneumonia, blood clots, injury to local nerves causing decreased sensation in the hip or thigh, acute blood loss requiring transfusion and even death, Cooper says.
"We think that donation is a cost-neutral opportunity. It, in fact, is not."
Meanwhile, from a financial standpoint, estimates have found it costs a kidney donor in the United States an average of $3,000 to navigate the entire transplant process, which may include time off from work, travel to and from the hospital, accommodations, food and child care expenses.
"We think that donation is a cost-neutral opportunity. It, in fact, is not," says Cooper, who is also Director of Kidney and Pancreas Transplantation at MedStar Georgetown Transplant Institute in Washington, D.C.
The National Organ Transplant Act of 1984 makes it illegal to sell human organs but did not prohibit payment for the donation of human plasma, sperm and egg cells.
Unlike plasma, sperm and eggs cells—which are "renewable resources"—a kidney is irreplaceable, says John J. Friedewald, a nephrologist who is medical director of kidney transplantation at Northwestern Memorial Hospital in Chicago.
Offering some sort of incentives could lessen the overall burden on donors while benefiting many more potential recipients. "We can eliminate the people waiting on the list and dying, at least for kidneys," Friedewald says.
On the other hand, incentives may influence an individual to the point that the donation is made purely for monetary gain. "It's a delicate balance," he explains, "because so much of the transplant system has been built on altruism."
That's where doing away with the "disincentives" comes into the equation. Compensating donors for the costs they endure would be a reasonable compromise, Friedewald says.
Depending on the state, living donors may deduct up to $10,000 from their adjusted gross income under the Organ Donation Tax Deduction Act for the year in which the transplantation occurs. "Human organ" applies to all or part of a liver, pancreas, kidney, intestine, lung or bone marrow. The subtracted modification may be claimed for only unreimbursed travel and lodging expenses and lost wages.
For some or many donors, the tax credit doesn't go far enough in offsetting their losses, but they often take it in stride, says Chaya Lipschutz, a Brooklyn, N.Y.-based matchmaker for donors and recipients, who launched the website KidneyMitzvah.com in 2009.
Seeking compensation for lost wages "is extremely rare" in her experience. "In all the years of doing this," she recalls, "I only had two people who donated a kidney who needed to get paid for lost wages." She finds it "pretty amazing that mostly all who contact don't ask."
Lipschutz, an Orthodox Jew, has walked in a donor's shoes. In September 2005, at age 48, she donated a kidney to a stranger after coming across an ad in a weekly Jewish newspaper. The ad stated: "Please help save a Jewish life—New Jersey mother of two in dire need of kidney—Whoever saves one life from Israel it is as if they saved an entire nation."
To make matches, Lipschutz posts in various online groups in the United States and Israel. Donors in Israel may receive "refunds" for loss of earnings, travel expenses, psychological treatment, recovery leave, and insurance. They also qualify for visits to national parks and nature reserves without entrance fees, Lipschutz says.
"There has been an attempt to figure out what would constitute fair compensation without the appearance that people are selling their organs or their loved ones' organs."
Kidneys can be procured from healthy living donors or patients who have undergone circulatory or brain death.
"The real dilemma arises with payment for living donation, which would favor poorer individuals to donate who would not necessarily do so," says Dr. Cheryl L. Kunis, a New York-based nephrologist whose practice consists primarily of kidney transplant recipients. "In addition, such payment for living donation has not demonstrated to improve a donor's socioeconomic status globally."
Living kidney donation has the highest success rate. But organs from young and previously healthy individuals who die in accidents or from overdoses, especially in the opioid epidemic, often work just as well as kidneys from cadaveric donors who succumb to trauma, Kunis says.
In these tragic circumstances, she notes that the decision to donate is often left to an individual's grieving family members when a living will isn't available. A payment toward funeral expenses, for instance, could tip their decision in favor of organ donation.
A similar scenario presents when a patient with a beating heart is on the verge of dying, and the family is unsure about consenting to organ donation, says Jonathan D. Moreno, a professor in the department of medical ethics and health policy at the University of Pennsylvania.
"There has been an attempt to figure out what would constitute fair compensation," he says, "without the appearance that people are selling their organs or their loved ones' organs."
The overarching concern remains the same: Compensating organ donors could lead to exploitation of socioeconomically disadvantaged groups. "What's likely to finally resolve" this bioethics debate, Moreno foresees, "is patient-compatible organs grown in pigs as the basic science of xenotransplants (between species) seems to be progressing."
Cooper, the transplant surgeon at Georgetown, believes more potential donors would come forward if financial barriers weren't an issue. Of the ones who end up giving a part of themselves, with or without reimbursement, "the overwhelming majority look back upon it as an extremely positive experience," he says. After all, "they're lifesavers. They should be celebrated."