How One Woman’s Breast Cancer Experience May Revolutionize Cancer Care

breast cancer, health and wellness, Medicine, scientific discoveries 4 Minutes
Unknown-23
mammograms for early detection

I love to write about good news. I especially enjoy elaborating on advances in the world of science during these times when science is too often attacked. This story shares some qualities with my recent post about the extraordinary Nobel Prize Winners in Physiology or Medicine. 

Like the Nobel discovery, this one seems destined to save lives and dramatically reduce suffering. It’s the result of one brilliant woman’s using her own status as a breast cancer survivor to create potentially dramatic changes in the detection and treatment of the disease.

My new hero is Regina Barzilay, PhD. She isn’t a physician, yet she seems to be upending medical practice for the better through the use of artificial intelligence (AI).

Barzilay is a professor of computer science at the Massachusetts Institute of Technology (MIT) and a certified genius: in 2017, she was the recipient of a MacArthur Fellowship “genius grant.” 

She and her team, which now includes experts from both MIT and Massachusetts General Hospital (MGH), have created computer algorithms that predict the likelihood of a patient’s developing breast cancer in the next five years. 

The model they designed began with a database containing pathology reports of more than 100,000 women treated at MGH over 30 years. Barzilay and her team then “taught” the computers to provide specific information from mammograms of more than 60,000 patients. 

According to an article in MIT News, 

“Trained on mammograms and known outcomes from over 60,000 MGH patients, the model learned the subtle patterns in breast tissue that are precursors to malignant tumors.”

Barzilay told Susan Gubar, who wrote about this remarkable work in Science Times, the special Tuesday section of The New York Times, that

“machines work more effectively than human eyes. They can register subtle changes in tissue—influenced by genetics, hormones, lactation, weight changes—that we cannot see.” 

Barzilay showed Gubar the results of her own mammograms from 2012, 2013, and 2014. The cancer that was diagnosed in 2014 was, in fact, evident in the two previous views.

I found myself deeply touched by that information, imagining what it must have been like for her to learn her cancer could have been caught and treated two years earlier, and seeing how heroically she turned her personal knowledge into this bold campaign to prevent other women from experiencing similar anguish—or worse.

Gubar reports that

“The enthusiasm Dr. Barzilay brings to this undertaking is fueled by her dismay at current approaches to cancer care. While being treated at MGH, she was struck by the high degree of uncertainty surrounding treatment of her disease.

“Why did her questions go unanswered about how other patients at the same hospital with similar tumors fared with this or that drug or with this or that surgery? Why was there so little information?”

The apparent explanation was that oncologists rely on the results of clinical trials in determining treatment regimens. That’s not surprising; they seek evidence-based medicine.

The problem Barzilay saw was that the trials enrolled just about 3 percent of eligible women, meaning 97 percent weren’t part of the picture. 

Barzilay termed this approach a “primitive practice” that was a “travesty,” Gubar reports, “especially because large volumes of information about patients accumulate in every hospital.” (Emphasis mine)

But a stumbling block to the work she proposed was that the data are written in “free-text” English, rather than in a form a computer could process. That’s when she and her colleagues began building the databases.

In one study, the Barzilay team’s model identified 31 percent of patients as high risk for future breast cancer, in contrast with the existing clinical standard, which identified 18 percent. That difference encompasses a great many women.

Once this work is more fully implemented, the result, Gubar writes, will be that

“New patients will be empowered by learning how tumors with particular characteristics responded to specific treatments. Machines accessing subsets of the population will also make it faster and cheaper for clinicians to identify patients with particular disease characteristics and to enroll them in clinical trials.”

One particularly valuable aspect is that the cancers are detected regardless of the patient’s race—an important consideration in view of the much higher breast cancer mortality rate among African-American women.

According to Gubar, similar efforts are occurring at Google, where AI specialists are examining scans for lung cancer. It seems reasonable to me, as a nonscientist, that this approach is potentially replicable with all sorts of cancers. (I’d welcome hearing from anyone with expertise in AI, cancer, or the intersection of the two fields.)

Barzilay knows buy-in from oncologists is critical to this effort. She sought to learn whether oncologists were reaching out to AI researchers; when she found that they weren’t, she also made one of her aims to enlighten them about these new possibilities.

Writes Gubar:

“Dr. Barzilay and her collaborators want to usher in the day when no woman is surprised by a late-stage diagnosis and when all breast cancers are curable.

“They also hope to solve the problems of over- and under-testing. Instead of a one-size-fits-all practice, the frequency of screenings and biopsies could be customized with sufficient data.”

That could be a huge benefit to patients. For example, at present, the MIT article notes, there is a discrepancy in screening guidelines, with the American Cancer Society recommending yearly screening beginning at age 45, while the U.S. Preventative Task Force says screening should be every two years, beginning at age 50.

And for implications for individual patients, Gubar points to the young women she knows who are aware that they have an inherited BRCA genetic mutation, which can substantially increase their risk for breast cancer (as well as for ovarian cancer).

With great anxiety, they are contemplating prophylactic double mastectomies—although there’s no assurance that such drastic surgery is necessary for them. The numbers of such women are increasing now that genetic testing is so readily available. 

Barzilay’s work can help women better face this difficult decision. In responding to Gubar’s query about such affected women, she stressed:

 “With a CD of their scan, we would be able to tell them their personal risk.”

I wish Dr. Regina Barzilay a long and productive life as she continually refines and expands her invaluable work.

Annie

Published by annieasksyou

I've been a nonfiction writer for many years, exploring diverse topics that pique my curiosity, as noted in my first blog posting (Greetings!). I'm seeking dialogue with others committed to joining me in this exploration, sharing my conviction that different views can be exchanged in a respectful, civil discourse where we can learn from one another and be agreeable, even when we disagree. These postings depend for their enrichment on your participation: your ideas, insights, knowledge, opinions, and personal stories.

Published

36 thoughts on “How One Woman’s Breast Cancer Experience May Revolutionize Cancer Care”

  3. This sounds like excellent news! There is much that is wrong with our current medical system, but much that is right with it as well, as this work shows. I hope this kind of diagnostics is as promising as it appears.

    Liked by 2 people

    Reply

  4. Interesting and important development in the world of breast cancer. It raises similar issues I think to oncotyping which is a process of using genetic info evaluate treatment options post breast cancer surgery. One is insuring the process is available to everyone no matter where they receive care and that the testing is covered by insurance v be it private, Medicaid, Medicare et al. In addition, tolerance for risk or odds by a patient is important. For example people can handle a low percentage of risk of developing breast cancer better than others. This is alluded to in your post with reference to prophylactic mastectomies. All this of course must be discussed with one’s oncologist.

    Liked by 2 people

    Reply

    1. You’ve introduced some valuable points. There are also the broad societal issues surrounding patient privacy protection. Re: your reference to oncologists, I was extremely impressed by Dr. Barzilay’s reaching out to them in order to ensure that they are on board with these efforts. Without such clinical participation, this work can’t possibly succeed as intended.

      Liked by 1 person

      Reply

  7. This is so encouraging!
    How fortunate it is that Barzilay is so brilliant in artificial intelligence and was motivated by her own breast cancer to use her knowledge to enable early intervention for others.
    The result will undoubtedly save many lives.

    Apropos to this…not that long ago I read an article about the utilization of AI to improve the care of MS patients in the UK. I just found the article online. Here is a link if you care to read it: https://www.ft.com/content/2ade7112-8927-11e9-a028-86cea8523dc2. No doubt AI will be mainstream for early detection and cures for many disorders in the not too distant future.

    Liked by 2 people

    Reply

    1. Thanks so much, Fran. Unfortunately, the link requires a subscription. If you have the time to summarize or cut and paste what you think is most important, that would be great. If not, it’s good to know that other disease states in addition to cancer are reaping the benefits of AI. I am extremely appreciative when you add materials that advance the discussion.

      Liked by 1 person

      Reply

    1. That is strange; I tried it on both computer and phone. Anyway, the second link worked, and it’s fascinating to see the similarities between this work and the breast cancer efforts. Thanks again. This is great!

      Liked by 2 people

      Reply

  9. Thank you for this refreshing news. The mountains of collected data, the nitty-gritty of human beings’ experiences, has to point to positive futures for many others. How absolutely wonderful!!

    Liked by 2 people

    Reply

  10. “No woman surprised by a late-stage diagnosis” . . . words to live by! Thank you for this encouraging news and I, too, salute her and wish her a long and productive life!

    Liked by 2 people

    Reply

  12. My mother developed breast cancer at the age of 45. When the tumour was detected, she was already in 3rd stage, which subsequently caused metastatic tumours. I have often wondered how different our lives would have been if the tumour had been detected a bit early.All the pressure and pain our family went through these years, all the time and effort which is spend on her palliative care, the distressing reality that she won’t have much time, would all be gone like a woosh.
    A decade ago, when she was first diagnosed, awareness about breast cancer was negligible here in India and the treatment options were also less. India doesn’t have mandatory health care insurance like in many developed countries and the treatment costs took quite a toll. Even today, drugs used in cancer care are quite expensive and the rich goes abroad for best treatment. The sad reality is that in developing countries like India, the poor are not in a position to avail the latest technologies and diagnosis methods in health care because they are simply not affordable. And the poor constitutes more than 80 percent of the country. So until and unless these technologies are made available to anyone and everyone regardless of their financial status, it won’t make much progress, at least in developing nations!

    Liked by 3 people

    Reply

    1. So sorry to hear about your mother’s premature death. There are actually shameful health disparities based on income in the US too— and drug companies reaping profits far beyond their development costs.

      I wish there were worldwide collaborative efforts to share these life-saving technologies so that neither economics nor geographical locale were hindrances to care.

      Liked by 3 people

      Reply

  14. That was interesting too Annie. I suspect once they get applying AI algorithms to the field of radiology that there will be less need for radiologists as the programmed machines have been shown to be as or often more accurate than the human eye. I no longer know any radiologists to ask if they are excited about this new wave of diagnosing.

    Liked by 2 people

    Reply

    1. My niece and nephew are both radiologists. They have lots of questions about how this will all play out—and not just from their personal roles. The scenario you describe is a long way off. But it does sound promising.

      Liked by 2 people

      Reply

      1. I’ve only read bits and pieces about the application of AI to certain areas of medicine, including pharmacy. Would I tell a young person to go into pharmacy – no – other than needing a few drug information and hospital specialists the act of dispensing and checking of drug interactions/allergies is being done by robotics in big hospitals and computer databases. One could argue that the pharmacist or radiologist will be the overseer of these AI programs but certainly there will be a need for fewer of them, as the AI programs will do it will more accuracy and more speed. Just my thoughts, as they say a third of current jobs will be made obsolete by AI in the future, but maybe I am being pessimistic. Radiology is one area that is so important for diagnosing but so fraught with the potential for error if something is missed, so it would be a good place to start.

        Liked by 2 people

      3. PS. I remember when you used to have to read an EKG – now it tells you what your arrhythmia is right away. Same with the Holter heart monitor I wore last week for 48hrs – the tape is read by a machine and then checked by a technician and doctor so the technician explained to me.

        Liked by 2 people

  15. Thank you for this news (from the next town over from where I live). I like the idea of the vast amounts of data from real patients’ lives becoming a resource for future patients to make better choices. I also like all of the comments that followed your post — about how AI is making more and more jobs obsolete, for example. We only had one political candidate in our recent presidential primary race who was explicit about how significant this ongoing loss of jobs is going to be in future months/years. While reading your blog post I also found myself thinking about the dogs who have been trained to sniff human beings for early detection of cancer… a very different response to early diagnosis (and much more pet-able than a computer database…)

    Liked by 1 person

    Reply

    1. Thank you, Will. I find it gratifying when people go back to my earlier posts and appreciate the findings. This struck me as a particularly relevant and hopeful story.

      Concerning the Covid-sniffing dogs, I read a new story about them only weeks ago, so they are definitely not a passing “thing.”

      I’m so happy that you’ve rejoined the blogosphere. I hope your other projects are progressing well.

      Like

      Reply

  16. Have you read or listened on audiobook (recommended) Gubars Memoirs of a Debulked Woman? Excellently written and with her brand of humor it’s well worthwhile listening to her read it in her voice, it’s one if my go to books.

    Like

    Reply

Leave a Reply

Fill in your details below or click an icon to log in:

Gravatar
WordPress.com Logo

You are commenting using your WordPress.com account. ( Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. ( Log Out /  Change )

Cancel

Connecting to %s