My Patient, an Asian Male Like Me, Wanted to Know Cancer Outcomes for Patients Like Him. Ten Years Later, Are We There Yet?

Improving outcomes for cancer patients starts with answering a simple question: Do our data and tools reflect the people we treat? Nearly a decade ago, I worked with a patient, a 50-year-old Asian male, who was diagnosed with stage III colon cancer during his first screening colonoscopy. He had just undergone surgery, and, as his medical oncologist, I recommended chemotherapy – the standard of care. He was adamantly opposed, prioritizing his active lifestyle and busy work and travel schedules. To make a final decision about his treatment, he asked two questions: Had I treated patients like him – healthy, middle-aged, Asian males with identical cancer diagnoses who did not receive chemotherapy – and did the clinical trial I based my recommendation on include patients like him? 

I knew answering the first question would be difficult. I was sure I had treated patients like him, but it would have been nearly impossible back then, or even now, to back up my response with data. I was, however, surprised to learn that the clinical trial’s publication disclosed nothing about the racial or ethnic makeup of its participants. This absence of critical information left the patient questioning whether the trial’s findings applied to him specifically. For me, the lack of data was a wake up call. How can clinicians deliver precise care when our trials and datasets aren’t representative of all patients, or at least transparent about who they represent? 

Too often, the available clinical data tells incomplete stories of how cancer and its treatments affect specific patient groups in the real world. Clinical trial populations are less diverse and healthier than those we see in practice, leaving us unaware of the gaps we must address to improve outcomes in underrepresented populations. Black women and Alaska Native individuals, for instance, both groups who are poorly represented in research, experience significantly worse cancer outcomes than better-represented groups. 

In addition, many datasets inaccurately or inconsistently capture race and ethnicity data using unhelpful, historically flawed census categories. For example, “Asian” is used to represent people from India to Korea to the Pacific Islands – groups with vastly different health histories and lifestyles. Oversimplifying these identities in research can mask inequities among subpopulations. 

Unfortunately for oncologists and our patients, it’s nearly impossible to answer questions about the potential impact of cancer and treatments on individual patients’ lives without high-quality data – and the tools to query it. Ten years after that patient interaction, I’m still exploring how we could better harness today’s real-world data (RWD) and artificial intelligence (AI) to more reliably, quickly, and economically improve outcomes for all patients – not just those traditionally represented in research.   

Early examples of RWD and AI in clinical care have highlighted the potential to address gaps in representation, alongside the need for caution in their application. Bridging representation and equity gaps in cancer research will require a multifaceted approach, with these tools serving a broader effort to make clinical trials and research more inclusive and impactful. 

To start, datasets must resemble the real-world populations affected by a disease, accurately representing races, ethnicities, ages, genders, regions and treatment settings. RWD that reflects narrow populations – for example, only those with access to treatment at academic medical centers – will perpetuate non-generalizable findings. For instance, multiple myeloma (MM) is a blood cancer that disproportionately affects African Americans, so the datasets used to study it must include African American patients at a comparable proportion and geographic distribution to the real U.S. patient population. 

After decades of evolving guidelines and modest progress, it’s unlikely that we will solve representation gaps in the context of clinical trials alone. We can improve access to insights for scientists and clinical oncologists alike by taking advantage of new tools – such as those powered by AI – that make it easier for any user to query high-quality, representative datasets and answer patients’ questions with data-driven certainty in near-real time. Of course, these tools are just one piece of the puzzle. Systemic changes – prioritizing diversity in clinical trials and standardizing data collection, as a start – are critical to ensuring all patients benefit from research advancements.

As we continue to refine clinical oncologists’ analytic toolkits, solutions must be designed for the diverse range of people affected by cancer – who very reasonably expect treatment plans that take their lives into account. By prioritizing diversity in datasets and empowering clinicians with accessible AI, we can finally begin to deliver the promise of personalized medicine. At a time when innovations enable highly targeted cancer treatment, tools that account for how each patient’s unique and varied identities impact their cancer journey will bring similar precision to the point of care. This will be transformative for all patients.  

About C.K. Wang

C.K. Wang is the Chief Medical Officer at COTA Healthcare where he leads the medical team to meet the interest and demand for real-world data in cancer care. Previously, he served as the Manager and Oncology lead at IBM’s Watson Health where he supported their Global AI-driven, oncology efforts. He was also Medical Director at USMD Health System–a large cancer center in Dallas-Fort Worth. A medical oncologist by training, he started his career in oncology and was in practice as a physician at Dallas Oncology Consultants for around 12 years. He received his undergraduate training at Washington University in St. Louis and his M.D. from the University of Texas Health Science Center at San Antonio before completing his residency at University Hospitals in Cleveland, OH and his hematology/ oncology fellowship at the University of Texas Southwestern Medical Center.