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.
Top Fertility Doctor: Artificially Created Sperm and Eggs "Will Become Normal" One Day
Imagine two men making a baby. Or two women. Or an infertile couple. Or an older woman whose eggs are no longer viable. None of these people could have a baby today without the help of an egg or sperm donor.
Cells scraped from the inside of your cheek could one day be manipulated to become either eggs or sperm.
But in the future, it may be possible for them to reproduce using only their own genetic material, thanks to an emerging technology called IVG, or in vitro gametogenesis.
Researchers are learning how to reprogram adult human cells like skin cells to become lab-created egg and sperm cells, which could then be joined to form an embryo. In other words, cells scraped from the inside of your cheek could one day be manipulated to become either eggs or sperm, no matter your gender or your reproductive fitness.
In 2016, Japanese scientists proved that the concept could be successfully carried out in mice. Now some experts, like Dr. John Zhang, the founder and CEO of New Hope Fertility Center in Manhattan, say it's just "a matter of time" before the method is also made to work in humans.
Such a technological tour de force would upend our most basic assumptions about human reproduction and biology. Combined with techniques like gene editing, these tools could eventually enable prospective parents to have an unprecedented level of choice and control over their children's origins. It's a wildly controversial notion, and an especially timely one now that a Chinese scientist has announced the birth of the first allegedly CRISPR-edited babies. (The claims remain unverified.)
Zhang himself is no stranger to controversy. In 2016, he stunned the world when he announced the birth of a baby conceived using the DNA of three people, a landmark procedure intended to prevent the baby from inheriting a devastating neurological disease. (Zhang went to a clinic in Mexico to carry out the procedure because it is prohibited in the U.S.) Zhang's other achievements to date include helping a 49-year-old woman have a baby using her own eggs and restoring a young woman's fertility through an ovarian tissue transplant surgery.
Zhang recently sat down with our Editor-in-Chief in his New York office overlooking Columbus Circle to discuss the fertility world's latest provocative developments. Here are his top ten insights:
Clearly [gene-editing embryos] will be beneficial to mankind, but it's a matter of how and when the work is done.
1) On a Chinese scientist's claim of creating the first CRISPR-edited babies:
I'm glad that we made a first move toward a clinical application of this technology for mankind. Somebody has to do this. Whether this was a good case or not, there is still time to find out.
Clearly it will be beneficial to mankind, but it's a matter of how and when the work is done. Like any scientific advance, it has to be done in a very responsible way.
Today's response is identical to when the world's first IVF baby was announced in 1978. The major news media didn't take it seriously and thought it was evil, wanted to keep a distance from IVF. Many countries even abandoned IVF, but today you see it is a normal practice. And it took almost 40 years [for the researchers] to win a Nobel Prize.
I think we need more time to understand how this work was done medically, ethically, and let the scientist have the opportunity to present how it was done and let a scientific journal publish the paper. Before these become available, I don't think we should start being upset, scared, or giving harsh criticism.
2) On the international outcry in response to the news:
I feel we are in scientific shock, with many thinking it came too fast, too soon. We all embrace modern technology, but when something really comes along, we fear it. In an old Chinese saying, one of the masters always dreamed of seeing the dragon, and when the dragon really came, he got scared.
Dr. John Zhang, the founder and CEO of New Hope Fertility Center in Manhattan, pictured in his office.
3) On the Western world's perception that Chinese scientists sometimes appear to discount ethics in favor of speedy breakthroughs:
I think this perception is not fair. I don't think China is very casual. It's absolutely not what people think. I don't want people to feel that this case [of CRISPR-edited babies] will mean China has less standards over how human reproduction should be performed. Just because this happened, it doesn't mean in China you can do anything you want.
As far as the regulation of IVF clinics, China is probably the most strictly regulated of any country I know in this world.
4) On China's first public opinion poll gauging attitudes toward gene-edited babies, indicating that more than 60 percent of survey respondents supported using the technology to prevent inherited diseases, but not to enhance traits:
There is a sharp contrast between the general public and the professional world. Being a working health professional and an advocate of scientists working in this field, it is very important to be ethically responsible for what we are doing, but my own feeling is that from time to time we may not take into consideration what the patient needs.
5) On how the three-parent baby is doing today, several years after his birth:
No news is good news.
6) On the potentially game-changing research to develop artificial sperm and eggs:
First of all I think that anything that's technically possible, as long as you are not harmful to other people, to other societies, as long as you do it responsibly, and this is a legitimate desire, I think eventually it will become reality.
My research for now is really to try to overcome the very next obstacle in our field, which is how to let a lady age 44 or older have a baby with her own genetic material.
Practically 99 percent of women over age 43 will never make a baby on their own. And after age 47, we usually don't offer donor egg IVF anymore.
But with improved longevity, and quality of life, the lifespan of females continues to increase. In Japan, the average for females is about 89 years old. So for more than half of your life, you will not be able to produce a baby, which is quite significant in the animal kingdom. In most of the animal kingdom, their reproductive life is very much the same as their life, but then you can argue in the animal kingdom unlike a human being, it doesn't take such a long time for them to contribute to the society because once you know how to hunt and look for food, you're done.
"I think this will become a major ethical debate: whether we should let an older lady have a baby at a very late state of her life."
But humans are different. You need to go to college, get certain skills. It takes 20 years to really bring a human being up to become useful to society. That's why the mom and dad are not supposed to have the same reproductive life equal to their real life.
I think this will become a major ethical debate: whether we should let an older lady have a baby at a very late state of her life and leave the future generation in a very vulnerable situation in which they may lack warm caring, proper guidance, and proper education.
7) On using artificial gametes to grant more reproductive choices to gays and lesbians:
I think it is totally possible to have two sperm make a baby, and two eggs make babies.
If we have two guys, one guy to produce eggs, or two girls, one would have to become sperm. Basically you are creating artificial gametes or converting with gametes from sperm to become egg or egg to become a sperm. Which may not necessarily be very difficult. The key is to be able to do nuclear reprogramming.
So why can two sperm not make offspring now? You get exactly half of your genes from each parent. The genes have their own imprinting that say "made in mom," "made in dad." The two sperm would say "made in dad," "made in dad." If I can erase the "made in dad," and say "made in mom," then these sperm can make offspring.
8) On how close science is to creating artificial gametes for clinical use in pregnancies:
It's very hard to say until we accomplish it. It could be very quick. It could be it takes a long time. I don't want to speculate.
"I think these technologies are the solid foundation just like when we designed the computer -- we never thought a computer would become the iPhone."
9) On whether there should be ethical red lines drawn by authorities or whether the decisions should be left to patients and scientists:
I think we cannot believe a hundred percent in the scientist and the patient but it should not be 100 percent authority. It should be coming from the whole of society.
10) On his expectations for the future:
We are living in a very exciting world. I think that all these technologies can really change the way of mankind and also are not just for baby-making. The research, the experience, the mechanism we learn from these technologies, they will shine some great lights into our long-held dream of being a healthy population that is cancer-free and lives a long life, let's say 120 years.
I think these technologies are the solid foundation just like when we designed the computer -- we never thought a computer would become the iPhone. Imagine making a computer 30 years ago, that this little chip will change your life.
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.
Black Participants Are Sorely Absent from Medical Research
After years of suffering from mysterious symptoms, my mother Janice Thomas finally found a doctor who correctly diagnosed her with two autoimmune diseases, Lupus and Sjogren's. Both diseases are more prevalent in the black population than in other races and are often misdiagnosed.
The National Institutes of Health has found that minorities make up less than 10 percent of trial participants.
Like many chronic health conditions, a lack of understanding persists about their causes, individual manifestations, and best treatment strategies.
On the search for relief from chronic pain, my mother started researching options and decided to participate in clinical trials as a way to gain much-needed insights. In return, she received discounted medical testing and has played an active role in finding answers for all.
"When my doctor told me I could get financial or medical benefits from participating in clinical trials for the same test I was already doing, I figured it would be an easy way to get some answers at little to no cost," she says.
As a person of color, her presence in clinical studies is rare. The National Institutes of Health has found that minorities make up less than 10 percent of trial participants.
Without trial participation that is reflective of the general population, pharmaceutical companies and medical professionals are left guessing how various drugs work across racial lines. For example, albuterol, a widely used asthma treatment, was found to have decreased effectiveness for black American and Puerto Rican children. Many high mortality conditions, like cancer, also show different outcomes based on race.
Over the last decade, the pervasive lack of representation has left communities of color demanding higher levels of involvement in the research process. However, no consensus yet exists on how best to achieve this.
But experts suggest that before we can improve black participation in medical studies, key misconceptions must be addressed, such as the false assumption that such patients are unwilling to participate because they distrust scientists.
Jill A. Fisher, a professor in the Center for Bioethics at the University of North Carolina at Chapel Hill, learned in one study that mistrust wasn't the main barrier for black Americans. "There is a lot of evidence that researchers' recruitment of black Americans is generally poorly done, with many black patients simply not asked," Fisher says. "Moreover, the underrepresentation of black Americans is primarily true for efficacy trials - those testing whether an investigational drug might therapeutically benefit patients with specific illnesses."
Without increased minority participation, research will not accurately reflect the diversity of the general population.
Dr. Joyce Balls-Berry, a psychiatric epidemiologist and health educator, agrees that black Americans are often overlooked in the process. One study she conducted found that "enrollment of minorities in clinical trials meant using a variety of culturally appropriate strategies to engage participants," she explained.
To overcome this hurdle, The National Black Church Initiative (NBCI), a faith-based organization made up of 34,000 churches and over 15.7 million African Americans, last year urged the Food and Drug Administration to mandate diversity in all clinical trials before approving a drug or device. However, the FDA declined to implement the mandate, declaring that they don't have the authority to regulate diversity in clinical trials.
"African Americans have not been successfully incorporated into the advancement of medicine and research technologies as legitimate and natural born citizens of this country," admonishes NBCI's president Rev. Anthony Evans.
His words conjure a reminder of the medical system's insidious history for people of color. The most infamous incident is the Tuskegee syphilis scandal, in which white government doctors perpetrated harmful experiments on hundreds of unsuspecting black men for forty years, until the research was shut down in the early 1970s.
Today, in the second decade of twenty-first century, the pernicious narrative that blacks are outsiders in science and medicine must be challenged, says Dr. Danielle N. Lee, assistant professor of biological sciences at Southern Illinois University. And having majority white participants in clinical trials only furthers the notion that "whiteness" is the default.
According to Lee, black individuals often see themselves disconnected from scientific and medical processes. "One of the critiques with science and medical research is that communities of color, and black communities in particular, regard ourselves as outsiders of science," Lee says. "We are othered."
Without increased minority participation, research will not accurately reflect the diversity of the general population.
"We are all human, but we are different, and yes, even different populations of people require modified medical responses," she points out.
Another obstacle is that many trials have health requirements that exclude black Americans, like not wanting individuals who have high blood pressure or a history of stroke. Considering that this group faces health disparities at a higher rate than whites, this eliminates eligibility for millions of potential participants.
One way to increase the diversity in sample participation without an FDA mandate is to include more black Americans in both volunteer and clinical roles during the research process to increase accountability in treatment, education, and advocacy.
"When more of us participate in clinical trials, we help build out the basic data sets that account for health disparities from the start, not after the fact," Lee says. She also suggests that researchers involve black patient representatives throughout the clinical trial process, from the study design to the interpretation of results.
"This allows for the black community to give insight on how to increase trial enrollment and help reduce stigma," she explains.
Thankfully, partnerships are popping up like the one between The Howard University's Cancer Center and Driver, a platform that connects cancer patients to treatment and trials. These sorts of targeted and culturally tailored efforts allow black patients to receive assistance from well-respected organizations.
Some observers suggest that the federal government and pharmaceutical industries must step up to address the gap.
However, some experts say that the black community should not be held solely responsible for solving a problem it did not cause. Instead, some observers suggest that the federal government and pharmaceutical industries must step up to address the gap.
According to Balls-Berry, socioeconomic barriers like transportation, time off work, and childcare related to trial participation must be removed. "These are real-world issues and yet many times researchers have not included these things in their budgets."
When asked to comment, a spokesperson for BIO, the world's largest biotech trade association, emailed the following statement:
"BIO believes that that our members' products and services should address the needs of a diverse population, and enhancing participation in clinical trials by a diverse patient population is a priority for BIO and our member companies. By investing in patient education to improve awareness of clinical trial opportunities, we can reduce disparities in clinical research to better reflect the country's changing demographics."
For my mother, the patient suffering from autoimmune disease, the need for broad participation in medical research is clear. "Without clinical trials, we would have less diagnosis and solutions to diseases," she says. "I think it's an underutilized resource."