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.
Science's dream of creating perfect custom organs on demand as soon as a patient needs one is still a long way off. But tiny versions are already serving as useful research tools and stepping stones toward full-fledged replacements.
Although organoids cannot yet replace kidneys, they are invaluable tools for research.
The Lowdown
Australian researchers have grown hundreds of mini human kidneys in the past few years. Known as organoids, they function much like their full-grown counterparts, minus a few features due to a lack of blood supply.
Cultivated in a petri dish, these kidneys are still a shadow of their human counterparts. They grow no larger than one-sixth of an inch in diameter; fully developed organs are up to five inches in length. They contain no more than a few dozen nephrons, the kidney's individual blood-filtering unit, whereas a fully-grown kidney has about 1 million nephrons. And the dish variety live for just a few weeks.
An organoid kidney created by the Murdoch Children's Institute in Melbourne, Australia.
Photo Credit: Shahnaz Khan.
But Melissa Little, head of the kidney research laboratory at the Murdoch Children's Institute in Melbourne, says these organoids are invaluable tools for research. Although renal failure is rare in children, more than half of those who suffer from such a disorder inherited it.
The mini kidneys enable scientists to better understand the progression of such disorders because they can be grown with a patient's specific genetic condition.
Mature stem cells can be extracted from a patient's blood sample and then reprogrammed to become like embryonic cells, able to turn into any type of cell in the body. It's akin to walking back the clock so that the cells regain unlimited potential for development. (The Japanese scientist who pioneered this technique was awarded the Nobel Prize in 2012.) These "induced pluripotent stem cells" can then be chemically coaxed to grow into mini kidneys that have the patient's genetic disorder.
"The (genetic) defects are quite clear in the organoids, and they can be monitored in the dish," Little says. To date, her research team has created organoids from 20 different stem cell lines.
Medication regimens can also be tested on the organoids, allowing specific tailoring for each patient. For now, such testing remains restricted to mice, but Little says it eventually will be done on human organoids so that the results can more accurately reflect how a given patient will respond to particular drugs.
Next Steps
Although these organoids cannot yet replace kidneys, Little says they may plug a huge gap in renal care by assisting in developing new treatments for chronic conditions. Currently, most patients with a serious kidney disorder see their options narrow to dialysis or organ transplantation. The former not only requires multiple sessions a week, but takes a huge toll on patient health.
Ten percent of older patients on dialysis die every year in the U.S. Aside from the physical trauma of organ transplantation, finding a suitable donor outside of a family member can be difficult.
"This is just another great example of the potential of pluripotent stem cells."
Meanwhile, the ongoing creation of organoids is supplying Little and her colleagues with enough information to create larger and more functional organs in the future. According to Little, researchers in the Netherlands, for example, have found that implanting organoids in mice leads to the creation of vascular growth, a potential pathway toward creating bigger and better kidneys.
And while Little acknowledges that creating a fully-formed custom organ is the ultimate goal, the mini organs are an important bridge step.
"This is just another great example of the potential of pluripotent stem cells, and I am just passionate to see it do some good."
Phil Gutis never had a stellar memory, but when he reached his early 50s, it became a problem he could no longer ignore. He had trouble calculating how much to tip after a meal, finding things he had just put on his desk, and understanding simple driving directions.
From 1998-2017, industry sources reported 146 failed attempts at developing Alzheimer's drugs.
So three years ago, at age 54, he answered an ad for a drug trial seeking people experiencing memory issues. He scored so low in the memory testing he was told something was wrong. M.R.I.s and PET scans confirmed that he had early-onset Alzheimer's disease.
Gutis, who is a former New York Times reporter and American Civil Liberties Union spokesman, felt fortunate to get into an advanced clinical trial of a new treatment for Alzheimer's disease. The drug, called aducanumab, had shown promising results in earlier studies.
Four years of data had found that the drug effectively reduced the burden of protein fragments called beta-amyloids, which destroy connections between nerve cells. Amyloid plaques are found in the brains of patients with Alzheimer's disease and are associated with impairments in thinking and memory.
Gutis eagerly participated in the clinical trial and received 35 monthly infusions. "For the first 20 infusions, I did not know whether I was receiving the drug or the placebo," he says. "During the last 15 months, I received aducanumab. But it really didn't matter if I was receiving the drug or the placebo because on March 21, the trial was stopped because [the drug company] Biogen found that the treatments were ineffective."
The news was devastating to the trial participants, but also to the Alzheimer's research community. Earlier this year, another pharmaceutical company, Roche, announced it was discontinuing two of its Alzheimer's clinical trials. From 1998-2017, industry sources reported 146 failed attempts at developing Alzheimer's drugs. There are five prescription drugs approved to treat its symptoms, but a cure remains elusive. The latest failures have left researchers scratching their heads about how to approach attacking the disease.
The failure of aducanumab was also another setback for the estimated 5.8 million people who have Alzheimer's in the United States. Of these, around 5.6 million are older than 65 and 200,000 suffer from the younger-onset form, including Gutis.
Gutis is understandably distraught about the cancellation of the trial. "I really had hopes it would work. So did all the patients."
While drug companies have failed so far, another group is stepping up to expedite the development of a cure: venture philanthropists.
For now, he is exercising every day to keep his blood flowing, which is supposed to delay the progression of the disease, and trying to eat a low-fat diet. "But I know that none of it will make a difference. Alzheimer's is a progressive disease. There are no treatments to delay it, let alone cure it."
But while drug companies have failed so far, another group is stepping up to expedite the development of a cure: venture philanthropists. These are successful titans of industry and dedicated foundations who are donating large sums of money to fill a much-needed void – funding research to look for new biomarkers.
Biomarkers are neurochemical indicators that can be used to detect the presence of a disease and objectively measure its progression. There are currently no validated biomarkers for Alzheimer's, but researchers are actively studying promising candidates. The hope is that they will find a reliable way to identify the disease even before the symptoms of mental decline show up, so that treatments can be directed at a very early stage.
Howard Fillit, Founding Executive Director and Chief Science Officer of the Alzheimer's Drug Discovery Foundation, says, "We need novel biomarkers to diagnose Alzheimer's disease and related dementias. But pharmaceutical companies don't put money into biomarkers research."
One of the venture philanthropists who has recently stepped up to the task is Bill Gates. In January 2018, he announced his father had Alzheimer's disease in an interview on the Today Show with Maria Shriver, whose father Sargent Shriver, died of Alzheimer's disease in 2011. Gates told Ms. Shriver that he had invested $100 million into Alzheimer's research, with $50 million of his donation going to Dementia Discovery Fund, which looks for new cures and treatments.
That August, Gates joined other investors in a new fund called Diagnostics Accelerator. The project aims to supports researchers looking to speed up new ideas for earlier and better diagnosis of the disease.
Gates and other donors committed more than $35 million to help launch it, and this April, Jeff and Mackenzie Bezos joined the coalition, bringing the current program funding to nearly $50 million.
"It makes sense that a challenge this significant would draw the attention of some of the world's leading thinkers."
None of these funders stand to make a profit on their donation, unlike traditional research investments by drug companies. The standard alternatives to such funding have upsides -- and downsides.
As Bill Gates wrote on his blog, "Investments from governments or charitable organizations are fantastic at generating new ideas and cutting-edge research -- but they're not always great at creating usable products, since no one stands to make a profit at the end of the day.
"Venture capital, on the other end of the spectrum, is more likely to develop a test that will reach patients, but its financial model favors projects that will earn big returns for investors. Venture philanthropy splits the difference. It incentivizes a bold, risk-taking approach to research with an end goal of a real product for real patients. If any of the projects backed by Diagnostics Accelerator succeed, our share of the financial windfall goes right back into the fund."
Gutis said he is thankful for any attention given to finding a cure for Alzheimer's.
"Most doctors and scientists will tell you that we're still in the dark ages when it comes to fully understanding how the brain works, let alone figuring out the cause or treatment for Alzheimer's.
"It makes sense that a challenge this significant would draw the attention of some of the world's leading thinkers. I only hope they can be more successful with their entrepreneurial approach to finding a cure than the drug companies have been with their more traditional paths."