Cancer research is moving faster than ever—but too many patients never feel the impact of that progress. Artificial Intelligence (AI) is emerging as one tool that could help change that. In the Season 6 finale of Science Will Win, Dr. Raven Baxter follows the human journey behind AI in oncology—from the moment of diagnosis to the real‑world barriers that determine access to care.
Cancer research is moving faster than ever—but too many patients never feel the impact of that progress. Artificial Intelligence (AI) is emerging as one tool that could help change that.
In the Season 6 finale of Science Will Win, Dr. Raven Baxter follows the human journey behind AI in oncology—from the moment of diagnosis to the real‑world barriers that determine access to care.
Along the way, we explore how thoughtfully designed artificial intelligence is reshaping trial design, enrollment, eligibility, and access—helping patients regain agency and bridging the gap between scientific breakthroughs and real‑world cancer care.
As the season concludes, one thing is clear: progress matters most when it reaches the people who need it.
Featured guests:
– Dr. Lionel Kankeu Fonkoua, Medical Oncologist and Translational Researcher, Mayo Clinic
– Jeff Legos, Chief Oncology Officer, Pfizer
– Dr. Ravi Parikh, Medical Oncologist; Director, Human‑Algorithm Collaboration Lab
– Maya R. Said, Founder and CEO, Outcomes4Me
Dive into the episode here:
00:00 – Past episodes introduce us to an emerging tech advancement
04:16 – What is a clinical trial?
07:35 – AI accelerating the pace of oncology
12:42 – Clinical trials and AI: How can it help?
16:17 – A gap between innovation and patient access
19:16 – Maya's story
23:47 – Clinical trials for AI tools
27:54 – Conclusion: building pathways alongside scientific innovation
Check out our YouTube channel (@Pfizer) to watch full interviews between Raven & some of the patients featured.
Season 6 of Science Will Win is created by Pfizer and hosted by Dr. Raven Baxter. It’s produced by Acast Creative Studios. Hosts in this podcast series were compensated for their time.
*The content in this episode is for informational purposes only and does not provide medical advice. Pfizer does not endorse or sponsor third‑party tools referenced. Patients should not use the tools described as a replacement for discussions with a healthcare provider. Patients should consult their healthcare provider regarding medical decisions.
Science Will Win Season 6
Episode 5: The Pace of Science: AI in Cancer Care
Final Transcript
RAVEN BAXTER
Cancer is overwhelming. It’s complex, uncertain, and deeply personal – for people with cancer, their families, clinicians, and researchers alike.
But, woven across every story this season was one theme that inspired hope: cancer moves fast, but science is moving fast, too.
We wanted to explore what cancer is, who it affects, how it’s changing, and how modern medicine and technology are working to meet that complexity head‑on. But most importantly, we wanted you to hear from the people living it.
Dr. Ross Camidge:
And I instantly pulled it up on my computer, and I went, oh my goodness, I have lung cancer.
Marshall Anthony:
I didn't think that cancer would ever play a factor in my life…personally.
Katrina Johnson:
I was just like, I guess most 28-year-olds living my best life, and I found a lump on my left breast.
Bob Riter:
My initial reaction was simply being stunned.
Kelly Huffman:
Scared. I think that was probably the word that came to mind. I was terrified.
RAVEN BAXTER
We talked about early detection, biomarker testing, precision medicine – targeted therapies that didn’t exist a decade ago – and what living longer with cancer means for patients and the healthcare system. And yet, there's one innovation that’s helping shape all of it. Not just changing what’s possible in oncology…but how quickly it becomes possible–that’s artificial intelligence, or AI.
[Music Out]
Jeff Legos:
I think the potential and possibilities from AI are limitless, and I think we're really just starting to scratch the surface.
RAVEN BAXTER:
That's Pfizer’s Chief Oncology Officer Jeff Legos. He’s helping drive the integration of AI and digital technologies across his organization, from how cancers are detected, to how treatments are designed. And even how clinical trials are built.
Jeff Legos:
If people can be diagnosed much earlier, if they could be treated faster, if they could be treated better with more precise therapies that are truly tailored for them as individuals…this can result in dramatic changes of how they are treated and the outcomes they may have.
[Fade in Theme]
RAVEN BAXTER:
Everywhere you look, people are talking about AI and new technology. But for a long time, healthcare has lagged behind that innovation curve. And in cancer care, that gap matters. Because progress isn’t just about discovery. It's about how quickly that discovery reaches patients.
AI has the potential to help close that gap–moving breakthroughs from the lab to the exam room faster. And that speed matters… because time is life.
Jeff Legos:
Just seeing over the past few years, how much AI and digital tools can improve, right? And how much they are already improving – gives me incredible hope for what this could mean for patients.
INTRO
RAVEN BAXTER
What’s up listeners? I’m Dr. Raven Baxter, aka Raven the Science Maven—I’m a molecular biologist and science educator. And this is season six of Science Will Win.
In this episode, we’re exploring the growing role that artificial intelligence, or AI, is playing across oncology.
[Fade out theme]
In the lab, AI is already transforming early discovery, helping scientists identify new drug targets and design therapies faster than ever before. But before any of those breakthroughs can reach patients, they all must pass through one of the most essential–and complex–processes in medicine: clinical trials.
So today, we’re looking at how AI is beginning to reshape that process—from how new therapies are discovered, to how clinical trials are designed, to how patients are matched with the studies that could change their care.
Along the way, we’ll explore how these tools could help close the long-standing gaps in equity, trust, and access.
Maya R Said:
For somebody that just got diagnosed, I don't know what's a clinical trial, I don't know that this is important to me…
RAVEN BAXTER
That’s Maya R Said, and she's a founder and CEO of a health technology company we’ll come back to later in the episode.
And she recognizes an important disconnect: most patients don't understand what a clinical trial is – let alone why it might matter to them at one of the most critical moments of their lives.
So, just as a quick refresher: clinical trials are how new treatments are tested to make sure they’re safe, effective, and ready for patients, before they get approved by health authorities1.
In fact, every cancer treatment available today, from chemotherapy to immunotherapy, was thoroughly tested in multiple clinical trials.
Clinical development typically unfolds in three main phases when patients are involved:
Phase 1: includes a small group of patients to determine: is the treatment safe, and what is the best dose for future trials?
Phase 2: includes a larger group of patients and asks: does the treatment work?
Phase 3: includes an even larger group of patients and asks: how well does it work and how safe is it compared to the current standard of care?
In oncology, this process is particularly complex as these phases can sometimes overlap or evolve as researchers learn more.
After the clinical trials are complete, regulators, like the FDA–that's the Food and Drug Administration in the United States– review all the data thoroughly before deciding whether a treatment can be approved.
This process alone can take 6 to 7 years2. And from initial drug discovery to approval, you’re looking at about 12-15 years3.
It is…at best, complicated, time consuming, and expensive.
Lionel Fonkoua:
If you're designing clinical trials, I think any clinical trialist will tell you it's, it's not easy. It's labor intensive. It's, it's, uh, resource intensive. Financially, it takes a lot.
RAVEN BAXTER
That’s Dr. Lionel Kankeu Fonkoua, a medical oncologist and translational researcher at the Mayo Clinic4. He discovers potential new treatments in his lab, runs clinical trials, and then sits face to face with patients, testing those very therapies. He calls himself a “bench to bedside” oncologist. And he’s not kidding about the price of drug development and innovation.
Getting a single drug from discovery through clinical trials to approval can cost an average of 1 to 2 billion dollars5. But if you’re talking about an oncology trial? You could be looking at more6. And even after all that time, money, and research…most drugs never make it to patients. In fact, in oncology, nearly 90% of drugs entering clinical testing ultimately fail.
Lionel Fonkoua:
That's part of the reason you need pharma and industry to partner because academic institutions cannot do it by themselves.
RAVEN BAXTER
Developing a new cancer treatment is expensive, often taking more than a decade and billions of dollars to move forward. And most of that cost begins long before a clinical trial ever starts.
It begins in the lab: during early discovery when scientists are searching for the right target, the right molecule, the right idea that might one day become a treatment.
But, more recently, academic institutions and industry partners have another collaborator to help with making the process more effective and efficient: AI.
[Music up]
Now, despite how new it feels, artificial intelligence isn’t new to medicine. Researchers had explored it for decades, but it lacked digital infrastructure to make it practical. Data was trapped in paper files, film scans, and siloed systems7.
That changed in the early 2000s when electronic health records transformed medicine into searchable data. Meaning it turned into something scientists – and AI – could actually analyze8.
When patient data becomes more searchable, patterns emerge– and those patterns help scientists understand which treatments work for which patients. Contributing to the rising use of precision medicine11.
Jeff Legos:
The pace of science and innovation has just exploded. Cancer treatments in particular have really shifted from broad one size fits all treatment to much more specialized and personalized care. This could be through targeted therapies that are focusing on molecular and genetic alterations, or more recently, precise targeting mechanisms that leverage antibodies to deliver cancer therapies directly to the cancer cells themselves.
RAVEN BAXTER
That's Jeff from earlier. And what he’s describing is a fundamental shift: cancer care isn't just about where tumors start anymore–like the lung, breast, or colon. It's about addressing cancer at a molecular level.
But, once you start looking that closely: at genes, mutations, protein signals across thousands of patients–you’re dealing with a massive amount of data. Data that could take months, if not years, for people to analyze.
So, if precision medicine is the goal, the real question is: how do we get through all that data fast enough to turn discoveries into treatments for patients?
According to Jeff, it's AI.
Jeff Legos:
AI and digital technologies are particularly important and they're really helping to accelerate this shift from analyzing genomic data at a scale that was previously incomprehensible to helping predict patient responses and even designing molecules virtually.
RAVEN BAXTER
Essentially, AI can scan millions of genetic data points at scale. Instead of researchers manually reviewing datasets one at a time, algorithms can identify patterns across thousands–sometimes hundreds of thousands–of genetic sequences and patient records9.
That scale matters. Because tools like natural language processing can sift through scientific literature, clinical trial databases, and electronic health records–information that would otherwise take teams months to review10. And with that speed, researchers can begin to ask a more precise question: How can we design drugs that are more targeted from the start?
Jeff Legos:
This will really help free scientists from the administrative burden and allowing them to focus more time on discovery of the next generation of innovation, you know, by helping our researchers identify higher quality drug targets much faster and increasing the odds that a promising idea makes it to patients.
RAVEN BAXTER
And this shift isn’t just theoretical. Companies like Pfizer are already using AI tools to synthesize massive volumes of internal data, published research, and real-world evidence – surfacing insights that can help guide research decisions more quickly.
Jeff Legos:
We have a generative AI tool that could summarize high volumes and multiple types of data across the scientific literature, incorporating not only the external data, but also our internal data to help inform decision making. And it's helping us identify our high-quality drug targets and thereby further increasing the odds that a promising idea makes it into early clinical development.
RAVEN BAXTER
In other words, AI isn’t just reducing the administrative burden of research, it's increasing the likelihood of a potential treatment and making it into the hands of patients.
Jeff Legos:
Hopefully this will result in more than a doubling of our overall success rates, of not only getting these new molecules into the clinic, but also ultimately translating these molecules into new and practice changing medicines.
RAVEN BAXTER
And once a therapy enters a clinical trial, AI can help researchers understand - earlier and more precisely - how well it’s working.
Jeff Legos:
The company called Vysioneer is helping us leverage AI technology in oncology clinical trials with the goal of improving our overall response assessments and for more precise insights on how well a drug may be working or how well a drug may not be working.
RAVEN BAXTER
This technology analyzes medical scans over time, tracking how tumors change throughout treatment - rather than just comparing a scan at the beginning and end of a trial11. That means researchers can see sooner whether a drug is shrinking a tumor, whether the disease is adapting, or whether it’s progressing.
And when researchers can see that information in real time, they can adjust trials faster - and get effective treatments to patients sooner.
[Music In]
Recent data shows that AI’s assistance in research and clinical trial design has already accelerated trial timelines by 30-50% – and reducing costs by at least 40%12.
But even with faster discovery and smarter trial design, one challenge has persisted for decades. Clinical trials need patients.
Jeff Legos:
Only about two to 4% of all eligible cancer patients actually participate in clinical trials.
RAVEN BAXTER
That means the overwhelming majority of eligible patients never enroll. And when enrollment slows, innovation slows with it. In fact, an estimated 20 to 40% of cancer trials are terminated early because they can’t recruit enough patients13. Here’s Lionel:
Lionel Fonkoua:
So, there's one thing to design a drug, but you have to make sure that once you prove that something works, it actually reaches real patients in real communities.
RAVEN BAXTER
One way AI is beginning to help this challenge is through trial matching – using patient records to identify which studies may be a fit, quickly and accurately. AI tools that utilize Large Language Models or LLMs, make this possible14.
Lionel Fonkoua:
Identifying which patients are the best match for which clinical trial in a very easy, seamless, fast way. Because when someone shows up in my clinic and has cancer, you wanna know right away what are the options for this trial? And I think with AI, artificial intelligence, now we have the potential to really design trial matching systems that are integrated into the electronic records.
RAVEN BAXTER
This technology could play a huge role in connecting patients to a higher number of clinical trials…but what if you know about the trial…but you can’t get to the trial. That’s the next hurdle.
Lionel Fonkoua:
If you look at clinical trials today, the majority of them are conducted at academic medical centers, right? But the majority, 80% of the patients actually are not at those academic towers. They are in the communities, and a lot of 'em don't want to leave their communities.
RAVEN BAXTER
One study showed that when asked, most people were more than willing to participate in a trial relevant to their specific diagnosis. But around 70% of potential participants live more than two hours away from a study site15. That distance can mean time off work, long drives, caregivers rearranging schedules–or opting out altogether.
But this is another place where technology may be able to help.
Here’s Jeff:
Jeff Legos:
Some of the opportunities that I, in particular, see for AI is to help really maximize the efficiencies of our clinical trials, in particular by streamlining the overall clinical development processes, improving our protocol and study designs, helping to optimize site selection.
RAVEN BAXTER
And, AI could even help decentralize clinical trials by meeting patients where they are16.
Instead of requiring every visit at a research center, some aspects of a trial can now happen remotely. Wearable devices can track health data in real time: things like heart rate, activity levels, and other vital signs - while patients go about their daily lives.
AI systems can then analyze that information and flag changes for clinicians as they happen. With fewer trips to the hospital and more flexibility built into participation, patients are more likely to stay enrolled – and more likely to complete the study
So, that’s trial design and participation – all areas where AI is beginning to help improve how studies are built and who can access them.
But even when trials are better designed, more inclusive, and closer to patients, there’s still a critical hurdle. Turning possibility into participation.
Because knowing a trial exists isn’t the same as being able to navigate it - especially in the middle of a cancer diagnosis.
Lionel Fonkoua:
I'm at an academic center, so I know what trials are here, but patients, providers in the community may not have that.
RAVEN BAXTER
Clinicians like Lionel actively encourage their trial participation, but many patients don’t fully understand how trials work– let alone whether one exists for their specific diagnosis. And that gap isn’t just on the patient side.
Many community physicians don’t work at institutions running trials. They may not have real-time access to what studies are open, who qualifies, or how to initiate a referral. And all of this happens within short appointments, heavy workloads, and a disease where time matters.
So, when awareness is limited, and the clock is ticking…clinical trials may never enter the conversation.
That disconnect is something Maya Said understands deeply.
Maya R Said :
I discovered the gap both professionally and personally. So, on the professional side, you know, I'm a scientist by background spent the good part of my career in pharma global R&D and then got into market access and oncology.
RAVEN BAXTER
In 2017, Maya was serving as the Global Head of Oncology Policy and Market Access at a large pharmaceutical company17. And If anyone knew the system, it was her.
But when she experienced a health scare, knowing the system and navigating it turned out to be two very different things.
Maya R Said:
Despite the fact that I'm a scientist, despite the fact that also both my parents are medical doctors. I googled those words because some of those words, even despite being a scientist, I didn't know what they meant. And that emotional state, where you're actually kind of, you know, not sure which one it is, and you can't even ask the questions, and you don't even know which questions to ask.
RAVEN BAXTER
What Maya describes is something we heard again and again this season—the moment when hearing the word “cancer” slows everything down. Even for someone fluent in science, clarity doesn’t arrive all at once.
After months of uncertainty and undergoing surgery, Maya fortunately learned that she didn’t have cancer. But the experience stayed with her.
Maya R Said:
In healthcare industry, everybody's patient focused. But this experience made me realize that actually, I have no clue. I've never been through cancer, so I cannot know what that looks like. And for me, that moment was me knowing everything I had at that moment professionally. And everything I came to learn over the years and the tools I could have, and recognizing that I had this amazing opportunity to take this and try to make a difference.
RAVEN BAXTER
Maya left her role in pharma to focus on a different part of the cancer journey.
What stood out most wasn’t the science—it was the experience of trying to make decisions while emotionally overwhelmed, under time pressure, and without a clear path forward.
So she started asking the question: what do patients actually need to navigate a diagnosis and the choices that follow?
For Maya, it came down to four things:
Maya R Said:
Understanding, you know, what are the choices that I have to make that are gonna impact my life? Number two is emotional, Like, just me being at the doctor and the doctor telling me everything I need to do during that half hour I'm with the doctor, doesn't mean that at that point in time, I'm emotionally ready to listen to it.
Number three is logistical navigation, right? If I have a job, if I have children, if I need to care for my care partner, how do I logistically organize my life around going also to treatments?
And number four is also cost. how do we deal with that? So put all those, and any person who has to deal with any of this, it’s really crazy, right?
RAVEN BAXTER
Maya already had the building blocks to act on that insight. She understood the pharmaceutical system. She had lived through how disorienting a health scare could be. And at the same time, the technology landscape in oncology was beginning to change.
[Music Up]
Algorithms were assisting radiologists. Robotics were advancing in operating rooms. And digital tools were emerging that could organize complex medical information- not just for researchers, but in ways patients could understand. In other words, the infrastructure was there.
Maya R Said:
So, we wanted something that was tech forward. We wanted something that was evidence-based. So again, it's all about science.
If I'm gonna help you take action, it's not about me telling you what you need to know in cancer care or breast cancer care, or metastatic breast cancer care. It's about me telling you specifically, given your clinical history, given your personal preferences, given your logistical needs, what's at your disposal? And how can I help you take action?
RAVEN BAXTER
For Maya, AI became a way to make sense of complexity—to help translate a diagnosis into information that felt timely, relevant, and actionable.
That idea eventually took shape as Outcomes4Me—an AI‑supported tool grounded in clinical evidence, designed around how patients actually experience a diagnosis.
Maya R Said:
Patients are in control. Meaning they get to decide how much they want to share or not about their diagnosis, and they can decide to do it immediately or at any point in time.
RAVEN BAXTER
What mattered most wasn’t the technology itself—but what it made possible: agency.
Unlike general information tools, Maya wanted something that could keep pace with a patient’s specific situation—and with how quickly cancer science changes.
[Music Out]
Her tool works by integrating evidence‑based clinical guidelines, and covers nearly all cancer types.
Maya R Said:
What that means is essentially we're able to tell you specifically all the treatment options as per the latest of science. And this is based on the amount of information we have from you.
RAVEN BAXTER
Cancer research and drug development are always evolving. Clinical guidelines change, trials open and close, and eligibility criteria shift over time–meaning a patient who wasn’t eligible six months ago may qualify today.
And that’s the part patients–and sometimes doctors–can’t immediately see. But when patients are alerted in real time, they can bring that information into the exam room.
Maya told me about one patient who used the tool to do just that:
Maya R Said:
She brought the trial to her treating physician. We showed the trial and the inclusion exclusion criteria because we give that information. And that's when the physician said, “Oh, I didn't know that the inclusion exclusion criteria expanded.” he immediately called the nurse. he referred her to the trial, she got on the trial.
RAVEN BAXTER
That moment captures what happens when information moves faster - and gets to patients directly. AI isn’t replacing doctors. It’s helping patients and providers work together with shared knowledge.
[Music Up]
Not all AI tools in oncology are designed for patients. Many–like the surgical robot we mentioned earlier–are built for health care providers.
They help doctors assess risk, predict outcomes, and guide decision making. And if those tools are going to shape care, they need to be evaluated just as rigorously as any new drug.
Through clinical trials.
That's where Dr. Ravi Parikh comes in. He’s a medical oncologist and the director of the Human-Algorithm Collaboration Lab.
Ravi Parikh:
I think we had recognized early on that the fundamental design of an AI based trial just ought to be differently considered. We ought to have a different playbook for an AI-based study compared to a traditional drug or device-based paradigm.
RAVEN BAXTER
Ravi’s lab runs clinical trials not on drugs–but on algorithms18. They test whether AI systems are working, up to date, and more importantly whether healthcare providers can use them in a real-world setting.
Ravi Parikh:
I think the one that oftentimes gets ignored when it comes to tools that are used in the medical setting is explainability.
RAVEN BAXTER
By “explainability,” he means this: it isn’t enough for an algorithm to just produce a strong prediction. Some AI tools are being created by data scientists and engineers outside of hospitals and health centers19. And while they may perform well statistically, medicine isn't practiced in isolation–it needs to work in daily life
Ravi Parikh:
We sort of assume that tools that give a better predictive performance, statistical performance, or even have some sort of level of patient impact are gonna be automatically trusted by doctors when, in reality, doctors are really only gonna trust what they can explain to a patient. And whether it sort of correlates with some sort of underlying knowledge.
RAVEN BAXTER
Doctors need to be able to verify the information and understand where that information is coming from, especially if it’s shaping treatment pathways. AI doesn’t need to prove that it's efficient, but it does need to show its work.
And that’s why Ravi argues that AI needs its own clinical trial playbook.
Ravi Parikh:
Intentionally building AI or explainable frameworks built on sort of principles of clinician and doctor knowledge, I think is gonna be really important down the line, even if it means that our accuracy isn't continually getting higher.
RAVEN BAXTER
In other words, progress isn’t just about speed. It’s about trust. And that’s where oversight comes in.
[Music Out]
Today, AI alone can’t solve disparities in cancer care or close every gap in clinical trials. It doesn’t automatically eliminate bias; it reflects the data it’s built on. But with thoughtful human oversight, it can surface where bias exists. It can highlight what’s missing and reveal patterns that might otherwise go unseen.
That’s why institutions aren’t just adopting AI - they’re building guardrails around it. Just last year, the Joint Commission and Coalition for Health AI released guidance for how health systems should evaluate, monitor, and govern AI tools20.
As those frameworks take shape, the focus can return to what this technology was meant to do: expand access, accelerate research, and improve patient care.
And that’s where Jeff sees the possibilities.
Jeff Legos:
I think in part what we will see over time is sort of these incremental changes in ways of working, the ways we are not just thinking about researching new molecules, but ultimately translating those molecules into clinical practice… you know, will result in a series of changes that over time you will see exponential improvements in innovation as a whole. And even if we can achieve that, enabled by AI, that is a quantum leap forward and something that every patient, family, and caregiver not only needs, but it's what they deserve.
RAVEN BAXTER
We shouldn’t treat AI in healthcare as a magic wand, nor fear it as a looming threat. We should evaluate it the same way we evaluate any new technology or clinical intervention–rigorously, continuously, and transparently.
It’s about redefining how health care providers spend their time and how patients access and take control of their care. And if algorithms can handle trial design, routine analysis, and pattern recognition… that may leave more room for what matters most.
More options, more inclusion, more time for the conversations that shape care.
And that balance between innovation and clinical wisdom…may be where the future of cancer care truly lives.
[Music up]
This season started with me and my friend Marshall in a hospital room. A moment where everything blurred. I heard cancer and I froze right along with him. I watched in real time fear turn into action: the disbelief, the hesitation, the grief…and then his decision to advocate for his life. And all throughout the season we heard other patients doing the same.
Kelly Huffman:
So ultimately, I decided to call an old friend who was a pulmonologist.
Katrina Johnson:
I pushed for that next step, And I think that takes a lot of courage to do.
Dr. Ross Camidge:
I said, by the way, I'm a thoracic oncologist. Can I have a chest x-ray please?
BOB RITER:
I remember 30 years ago during breast cancer, some of the information I found was in the form of paper. I mean, articles literally ripped out of magazines and put into a file. But today you can just go online and find so much information
RAVEN BAXTER
Science can move at lightning speed, but if the pathways to care are paved in confusion–or out of reach entirely…patients are left behind. Breakthroughs in labs are only one part of the story–we also must build pathways patients can actually step onto.
Because “patient-focused” doesn’t mean much if the burden is still on the patient to fight for information, time, and options. So, if there are tools being put in place to lift the burden, whether it is AI, community forums, or access to a trusted, informed physician…what matters is that they create clarity, agency, and time. Because in cancer care, time is LIFE.
Marshall Anthony:
But if you are feeling symptoms now, go get the screening now. Be an advocate. And if your primary care is refusing, get you another primary care that will, like, you have to be an advocate for your own life. So get the support and get the help that you need and deserve.
RAVEN BAXTER
This marks the final episode of Season Six of Science Will Win. Thank you all for taking this journey with us: through science, personal stories, and the evolving future of cancer care. It’s looking bright, ya’ll!
Science Will Win is created by Pfizer and hosted by me, Dr. Raven Baxter. It’s produced by Acast Creative Studios.
Please take a minute to rate, review and follow Science Will Win wherever you get your podcasts. It helps new listeners to find the show.
Special thanks to all our guests and the Pfizer oncology team.
Thank you for listening! We’ll see you next season.
*The content in this episode is for informational purposes only and does not provide medical advice. Pfizer does not endorse or sponsor third‑party tools referenced. Patients should not use the tools described as a replacement for discussions with a healthcare provider. Patients should consult their healthcare provider regarding medical decisions.