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.
The Friday Five covers five stories in research that you may have missed this week. There are plenty of controversies and troubling ethical issues in science – and we get into many of them in our online magazine – but this news roundup focuses on scientific creativity and progress to give you a therapeutic dose of inspiration headed into the weekend.
Listen on Apple | Listen on Spotify | Listen on Stitcher | Listen on Amazon | Listen on Google
Here are the promising studies covered in this week's Friday Five:
- Research on a "smart" bandage for wounds
- A breakthrough in fighting inflammation
- The pros and cons of a new drug for Alzheimer's
- Benefits of the Mediterranean diet - with a twist
- How to recycle a plastic that was un-recyclable
Sexually Transmitted Infections are on the rise. This drug could stop them.
Sexually transmitted infections (STIs) are surging across the U.S. to 2.5 million cases in 2021 according to preliminary data from the CDC. A new prevention and treatment strategy now in clinical trials may provide a way to get a handle on them.
It's easy to overlook the soaring rates of gonorrhea, chlamydia, and syphilis because most of those infections have few or no symptoms and can be identified only through testing. But left untreated, they can lead to serious damage to nerves and tissue, resulting in infertility, blindness, and dementia. Infants developing in utero are particularly vulnerable.
Covid-19 played havoc with regular medical treatment and preventive care for many health problems, including STIs. After formal lockdowns ended, many people gradually became more socially engaged, with increases in sexual activity, and may have prioritized these activities over getting back in touch with their doctors.
A second blow to controlling STIs is that family planning clinics are closing left and right because of the Dobbs decision and legislation in many states that curtailed access to an abortion. Discussion has focused on abortion, but those same clinics also play a vital role in the diagnosis and treatment of STIs.
Routine public health is the neglected stepchild of medicine. It is called upon in times of crisis but as that crisis resolves, funding dries up. Labs have atrophied and personnel have been redirected to Covid, “so access to routine screening for STIs has been decimated,” says Jennifer Mahn, director of sexual and clinical health with the National Coalition of STD Directors.
A preview of what we likely are facing comes from Iowa. In 2017, the state legislature restricted funding to family health clinics in four counties, which closed their doors. A year later the statewide rate of gonorrhea skyrocketed from 83 to 153.7 cases per 100,000 people. “Iowa counties with clinic closures had a significantly larger increase,” according to a study published in JAMA. That scenario likely is playing out in countless other regions where access to sexual health care is shrinking; it will be many months before we have the data to know for sure.
A decades-old antibiotic finds a new purpose
Using drugs to protect against HIV, either as post exposure prophylaxis (PEP) or pre-exposure prophylaxis (PrEP), has proven to be quite successful. Researchers wondered if the same approach might be applied to other STIs. They focused on doxycycline, or doxy for short. One of the most commonly prescribed antibiotics in the U.S., it’s a member of the tetracycline family that has been on the market since 1967. It is so safe that it’s used to treat acne.
Two small studies using doxy suggested that it could work to prevent STIs. A handful of clinical trials by different researchers and funding sources set out to generate the additional evidence needed to prove their hypothesis and change the standard of care.
Senior researcher Victor Omollo, with the Kenya Medical Research Institute, noted, “These are prevention interventions that women can control on their own without having to seek or get consent from another person,” as is the case with condom use.
The first with results is the DoxyPEP study, conducted at two sexual health clinics in San Francisco and Seattle. It drew from a mix of transgender women and men who have sex with men, who had at least one diagnosed STI over the last year. The researchers divided the participants into two groups: one with people who were already HIV-positive and engaged in care, while the other group consisted of people who were on PrEP to prevent infection with HIV. For the active part of the study, a subset of the participants received doxy, and the rest of the participants did not.
The researchers intentionally chose to do the study in a population at the highest risk of having STIs, who were very health oriented, and “who were getting screened every three months or so as part of their PrEP program or their HIV care program,” says Connie Celum, a senior researcher at the University of Washington on the study.
Each member of the active group was given a supply of doxy and asked to take two pills within 72 hours of having sex where a condom was not used. The study was supposed to run for two years but, in May, it stopped halfway through, when a safety monitoring board looked at the data and recommended that it would be unethical to continue depriving the control group of the drug’s benefits.
Celum presented these preliminary results from the DoxyPEP study in July at the International AIDS Conference in Montreal. “We saw about a 56 percent reduction in gonorrhea, about 80 percent reduction in chlamydia and syphilis, so very significant reductions, and this is on a per quarter basis,” she told a later webinar.
In Kenya, another study is following a group of cisgender women who are taking the same two-pill regimen to prevent HIV, and the data from this research should become available in 2023. Senior researcher Victor Omollo, with the Kenya Medical Research Institute, noted that “these are prevention interventions that women can control on their own without having to seek or get consent from another person,” as is the case with condom use, another effective prevention tool.
Antibiotic resistance
Antibiotic resistance is a potentially big concern. About 25 percent of gonorrhea strains circulating in the U.S. are resistant to the tetracycline class of drugs, including doxy; rates are higher elsewhere. But resistance often is a matter of degree and can be overcome with a larger or longer dose of the drug, or perhaps with a switch to another drug or a two-drug combination.
Research has shown that an established bacterial infection is more difficult to treat because it is part of a biofilm, which can leave only a small portion or perhaps none of the cell surface exposed to a drug. But a new infection, even one where the bacteria is resistant to a drug, might still be vulnerable to that drug if it's used before the bacterial biofilm can be established. Preliminary data suggests that may be the case with doxyPEP and drug resistant gonorrhea; some but not all new drug resistant infections might be thwarted if they’re treated early enough.
“There are some tradeoffs” to these interventions, Celum says, and people may disagree on the cost of increased resistance balanced against the benefits of treating the STIs and reducing their spread within the community.
Resistance does not seem to be an issue yet for chlamydia and syphilis even though doxy has been a recommended treatment for decades, but a remaining question is whether broader use of doxy will directly worsen antibiotic resistance in gonorrhea, or promote it in other STIs. And how will it affect the gut microbiome?
In addition, Celum notes that we need to understand whether doxy will generate mutations in other bacteria that might contribute to drug resistance for gonorrhea, chlamydia or syphilis. The studies underway aim to provide data to answer these questions.
“There are some tradeoffs” to these interventions, Celum says, and people may disagree on the cost of increased resistance balanced against the benefits of treating the STIs and reducing their spread within the community. That might affect doctors' willingness to prescribe the drug.
Turning research into action
The CDC makes policy recommendations for prevention services such as taking doxy, requiring some and leaving others optional. Celum says the CDC will be reviewing information from her trial at a meeting in December, but probably will wait until that study is published before making recommendations, likely in 2023. The San Francisco Department of Public Health issued its own guidance on October 20th and anecdotally, some doctors around the country are beginning to issue prescriptions for doxy to select patients.
About half of new STIs occur in young people ages 15 to 24, a group that is least likely to regularly see a doctor. And sexual health remains a great taboo for many people who don't want such information on their health record for prying parents, employers or neighbors to find out.
“People will go out of their way and travel extensive distances just to avoid that,” says Mahn, the National Coalition director. “People identify locations where they feel safe, where they feel welcome, where they don't feel judged,” Mahn explains, such as community and family planning clinics. They understand those issues and have fees that vary depending on a person’s ability to pay.
Given that these clinics already are understaffed and underfunded, they will be hard pressed to expand services covering the labor intensive testing and monitoring of a doxyPEP regimen. Sexual health clinics don't even have a separate line item in the federal budget for health. That is something the National Association of STI Directors is pushing for in D.C.
DoxyPEP isn't a panacea, and it isn't for everyone. “We really want to try to reach that population who is most likely going to have an STI in the next year,” says Celum, “Because that's where you are going to have the biggest impact.”