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.
Saliva May Help Diagnose PTSD in Veterans
As a bioinformatician and young veteran, Guy Shapira welcomed the opportunity to help with conducting a study to determine if saliva can reveal if war veterans have post-traumatic stress disorder, or PTSD.
The research team, which drew mostly from Tel Aviv University’s Sackler Faculty of Medicine and Sagol School of Neuroscience, collected saliva samples from approximately 200 veterans who suffered psychological trauma stemming from the years they spent fighting in the First Lebanon War in 1982. The researchers also characterized the participants’ psychological, social and medical conditions, including a detailed analysis of their microbiomes.
They found that the former soldiers with PTSD have a certain set of bacteria in their saliva, a distinct microbiotic signature that is believed to be the first biological marker for PTSD. The finding suggests that, in the future, saliva tests could be used to help identify this disorder. As of now, PTSD is often challenging to diagnose.
Shapira, a Ph.D. student at Tel Aviv University, was responsible for examining genetic and health-related data of the veterans who participated – information that had been compiled steadily over four decades. The veterans provided this data voluntarily, Shapira says, at least partly because the study carries important implications for their own psychological health.
The research was led by Illana Gozes, professor emerita of clinical biochemistry. “We looked at the bacteria in their blood and their saliva,” Gozes explains. To discover the microbial signatures, they analyzed the biometric data for each soldier individually and as a group. Comparing the results of the participants’ microbial distribution to the results of their psychological examinations and their responses to personal welfare questionnaires, the researchers learned that veterans with PTSD – and, more generally, those with significant mental health issues – have the same bacterial content in their saliva.
“Having empirical metrics to assess whether or not someone has PTSD can help veterans who make their case to the Army to get reparations,” Shapira says.
More research is required to support this finding, published in July in Nature’s prestigious Molecular Psychiatry, but it could have important implications for identifying people with PTSD. Currently, it can be diagnosed only through psychological and behavioral symptoms such as flashbacks, nightmares, sleep disorders, increased irritability and physical aggressiveness. Veterans sometimes don’t report these symptoms to health providers or realize they’re related to the trauma they experienced during combat.
The researchers also identified a correlation that indicates people with a higher level of education show a lower occurrence of the microbiotic signature linked to PTSD, while people who experienced greater exposure to air pollution show a higher occurrence of this signature. That confirms their finding that the veterans’ health is dependent on their individual biology combined with the conditions of their environment.
“Thanks to this study, it may be possible in the future to use objective molecular and biological characteristics to distinguish PTSD sufferers, taking into account environmental influences,” Gozes said in an article in Israel21c. “We hope that this new discovery and the microbial signatures described in this study might promote easier diagnosis of post-traumatic stress in soldiers so they can receive appropriate treatment.”
Gozes added that roughly a third of the subjects in their study hadn’t been diagnosed with PTSD previously. That meant they had never received any support from Israel’s Ministry of Defense or other officials for treatment and reparations, the payments to compensate for injuries sustained during war.
Shapira’s motivation to participate in this study is personal as well as professional: in addition to being veteran himself, his father served in the First Lebanon War. “Fortunately, he did not develop any PTSD, despite being shot in the foot...some of his friends died, so it wasn’t easy on him,” says Shapira.
“Having empirical metrics to assess whether or not someone has PTSD can help veterans who make their case to the Army to get reparations,” Shapira says. “It is a very difficult and demanding process, so the more empirical metrics we have to assess PTSD, the less people will have to suffer in these committees and unending examinations that are mostly pitched against the veterans because the state is trying to avoid spending too much money.”
The Friday Five Weekly Roundup in Health Research
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:
- The right facial expression for your mental health
- Can virtual reality reduce pain?
- Lab made blood vessels
- Gene editing muscles to lower blood sugar
- A magic ingredient coming from exhaust vents