By GEORGE BEAUREGARD
How AI Could Have Personalized My Cancer Journey in 2005
I don’t think I’m in the minority of baby boomer doctors when it comes to my curiosity and ambivalence about the progressive application of AI in medicine. But that curiosity is not only prospective, but also retrospective. In 2005, I became an outlier who perhaps needed more than the standard of care for an illness.
During the fall of 2005, I first saw a single drop of blood fall into the toilet water while urinating in the bathroom. After hitting the water, the pink bead slowly sank, twisting and contorting, dissipating like a cloud of smoke. The evidence was fleeting: it disappeared in seconds. If I were a viewer instead of the source, I might have admired his visual artistry. There was no associated pain.
A single thought crossed my mind: Did I just pee blood? I thought maybe I had imagined it.
He was 49 years old and had no what were considered risk factors for kidney or bladder cancer: smoking, obesity, advanced age, high blood pressure or exposure to cadmium, trichlorethylene or herbicides. But I was adopted and lacked any knowledge of my family history. Did he have a bleak genealogy? However, what was perhaps significant was that both of my adoptive parents had developed different types of urogenital cancer. That led me to speculate that environmental factors related to the materials of our house and/or the land it sat on or around it may have played a role.
I tried to dismiss any worries, but the saying “Painless hematuria is cancer until proven otherwise” It crossed my mind Chiron-style.
The episodes continued and worsened, so an ultrasound was performed, the report of which said: “…A soft tissue density is seen at the base of the bladder to the right. While this could represent a thrombus, I cannot rule out a primary mucosal injury. The lesion measures approximately 4 X 5 cm in diameter.”
I consulted a urologist colleague, who performed a cystoscopy. His comment on what he saw: “As you know, you have a mass in your bladder. I got a good look at it. It looks pretty angry, so I suspect it’s not benign. I tried to remove as much as I could. It would have been quite risky to scrape deeper and risk perforating the bladder. I know I didn’t get it all out.” A TURBT soon followed. Pathology showed a high-grade urothelial carcinoma that extensively invaded the lamina propria and muscularis propria. There was multifocal lymphovascular invasion, so I probably had a more advanced subgroup than the localized SEER stage.
At that time, the five-year relative survival rate for stage II muscle-invasive bladder cancer was about 45 percent.
Overwhelmingly, bladder cancer is an age-related malignancy. So, there I was, 49 years old, with a cancer whose average age of incidence (septuagenarians) was much older than mine. A WTF moment.
One that made me think about how much time I had left.
I had cancer, but in some ways I was cautiously optimistic. I had access to Boston-based academic centers and specialist colleagues who were willing to see me quickly and with good insurance.
But receiving the diagnosis was just the beginning. I visited three expert urologists, each of whom recommended radical cystectomy, small bowel resection, and construction of an orthotopic ileal neobladder. Convergence. Certainty for me.
By the mid-2000s, approximately five hundred thousand new research publications were indexed in PubMed. Back then, oncologists typically began their investigation into a complex case with the NCCN/ASCO Guidelines (synthesized evidence), checked supporting RCTs (gold standard), meta-analyses, and possibly consulted ClinicalTrials.gov for new or ongoing studies before making a treatment recommendation.
I also saw three expert medical oncologists from different renowned academic medical centers. A memorable comment from one of them was, “The wolf is out of the cage,” meaning that the likelihood of extensive microscopic disease beyond the bladder was high.
Each of them recommended what was known and available at the time: a different, “one size fits all, seventy-year-old” chemotherapy regimen, in terms of the types and numbers of agents used (doublet, triplet, quartet) and the timing of their administration in relation to surgery (neoadjuvant, adjuvant, or half and half). Contradictory opinions. Divergence. Uncertainty for me.
The lack of firm evidence about which regimen conferred a longer survival benefit left me with the equivalent of what felt like a bull’s-eye shot. I wondered if my choice would leave me underwater but I would eventually be able to surface, rather than drown. My decision-making process ended up being driven primarily by intuition. I told myself: make the decision and don’t look back.
In 2005, the benefit of adding trastuzamab (Herceptin) in the treatment of HER-2 positive breast cancer had already been established. The oncologist I chose had a conversation with a colleague at the University of Michigan, a researcher focused on HER2 and bladder cancer. FISH data of my cancer cells demonstrated a subclone of HER2-amplified cells; the percentage was uncertain, but low. After some discussion about the harm-benefit ratio of adding Herceptin to my regimen, I agreed. For me, that decision was not to satisfy an academic curiosity, but rather a survival advantage.
So, here I am and, for the most part, a grateful (and I think lucky) survivor of 20 years.
But how things have changed in oncology since then, as cancer care is progressively shifting from the old generic nuclear bomb approach to a stealth bomber one.
In the black bag of today’s oncologists, they have new and improved tools at their disposal. Improvements in NGS, ctDNA and cfDNA assays, CAR-T cell therapy, qPCR and RT-PCR, spatial transcriptomics, epigenetic profiling technologies, mass spectrometry-based proteomics, epigenetic profiling technologies and more. The advancing frontier of medicine.
While it’s nice to have many more sophisticated tools, if the diagnostician or fixer doesn’t know exactly which one will work best for a single person’s unique combination of cancer characteristics, he or she will have to go back to rummaging through the medical literature, remembering what worked (or more or less worked) in other “similar” patients, pattern recognition, patterns, and intuition.
In the pursuit of precision medicine, a powerful ally, AI, is accelerating from the sidecar to the main engine, powered by large language models that can collect, absorb and collate heretofore unimaginable quantities of disparate and clinically meaningful data points, and synthesize them, predict and divert treatment options away from dead ends and invisible and unforeseen future rabbit holes, and tailor treatment recommendations for an individual patient. And make any necessary course corrections along the way. Interpretation of the keys to medicine. At high speed.
Fine scalpels, not blunt instruments, guided by iterative learning and adaptation.
While I’m grateful to still be here, I’ve wondered what a data-driven personalization platform would have recommended for my anomalous N-of-1 situation back then.
I will never know, but my optimism and hope for further advances in the future effectiveness of cancer care personalized for each individual is growing. While it will never be perfect, it will likely mean better outcomes for patients.
One important thing remains: moving towards early detection of significant cancers at lower stages. Hope lives there too.
George Beauregard, DO is an internal medicine physician and author of Reservations for nine: a doctor’s family faces cancer. This came from his Substack
