The Patient Equation: The Precision Medicine Revolution in the Age of COVID-19 and Beyond

Introduction

About a decade ago, I met Jack Whelan. An investment researcher working in the world of finance, Jack power-walked from the train to his office every day for years…until he noticed that walk getting more and more difficult, along with occasional nosebleeds that prompted him to see his doctor. He was diagnosed with a rare blood cancer—Waldenstrom macroglobulinemia (WM)—and his world changed completely. WM was (and is) incurable, with no FDA-approved treatments and an expected survival of just five to seven years. Wanting to extend his life, Jack sought out clinical trial after clinical trial. The first three trials failed, and then his fourth finally got him on a drug that stopped the cancer's progression for years.

Throughout his experience, Jack became an expert—and, more important for our story here, a tracker. Jack demanded weekly blood tests and charted a range of biomarkers—hematocrit, immunoglobulin, and others—hoping to find answers in the numbers, to be able to know if he was responding to treatment even before the doctors did. From physician to physician, from trial to trial, he brought these numbers with him in Excel spreadsheets. He hoped this growing collection of data about his body would uncover new and valuable information that could keep him alive.

Jack's diligence and initiative is rare, but he's not alone. Ray Finucane, a 75-year-old mechanical engineer with Parkinson's disease, built an app to track his symptoms and to try to optimize the dosing of his levodopa medication.¹ Dr. David Fajgenbaum used his own blood samples and software to find a new plausible biological explanation for Castleman disease that led him to try a drug never before applied to the condition—which has led him into remission for the past six years. Millions of people around the world—sick or not—wear fitness trackers or carry smartphones that are able to track massive amounts of data at a far more granular level than we could have ever conceived of just a few years ago.

Imagine a world where this data was harvested, analyzed, and combined with all of the medical records that are collected over the course of our lives and assembled into something useful, something to extend longevity, enhance the quality of life, and even help alter the arc of a pandemic.

Imagine if a patient like Jack didn't need to track his own body in an Excel spreadsheet because there were systems and devices that were doing it for him. What if he could do this while harnessing the collective wisdom of all of the research and real-world experience of the scientists, physicians, and patients who came before him to produce recommendations for the most effective treatments, the most critical behaviors, and the most valuable things he needed to know to beat his cancer and optimize his health?

Imagine a world where as soon as something useful could be detected, be it a data point we can track with conventional medical measurements or a misbehaving molecule or behavioral pattern that we may not even fully appreciate today (something about our sleep, our cognition, what we eat or drink, or an aspect of our environment, as just a few examples), we would be prompted to take action, use a medical device or drug, or change some aspect of how we live.

Instead of being limited to waiting for a scan to show an increased tumor volume or a blood value concentration rising to a level detectable by a relatively crude chemical medical test, imagine real-time, population-tested, scientifically-valid, difference-making, actionable recommendations—whether you're fighting cancer or just trying to maintain a healthy, high-quality life.

This is the future, and the analysis behind the scenes that will produce—and is already producing—these types of information are the patient equations that inspired the title of this book. Jack was ahead of his time because he knew that the numbers and his careful tracking of them mattered. His engineering intuition told him that within those numbers were the mathematical keys to unlocking extended life, and making sure he got the right treatments at the right time.

The world may not have been quite ready to put those numbers to use, but Jack was truly a trailblazer in realizing that many factors were relevant to his diagnosis and treatment, from his behavioral patterns (such as how tired he was when power-walking) to otherwise insignificant medical events (like a nosebleed). He understood that tracking his biology more proactively and frequently than would be done in standard-of-care medicine could make a difference, and that his own patient equation encompassed far more variables and inputs than many of us would suspect.

Jack passed away in late 2017, almost 10 years after his initial diagnosis, and spent the last years of his life as a speaker, a research advocate, and a fighter pushing for greater patient involvement in clinical trials and greater collaboration between the life sciences industry, the doctors on the front lines of treatment, and the patients ultimately receiving care. He knew that collaboration would be critical for achieving the future state of patient care that I'm describing, and for uncovering the business models that would make it all possible.

We are in a race to the holy grail of precision medicine—bringing the right treatments to the right patients at the right time. Progress is being made on so many fronts—life sciences companies are developing cell therapies in cancer, artificial pancreas device systems in diabetes, apps that help battle neurodegenerative diseases and optimize nutrition, and wearables that can track everything from heart disease to fertility. Technology companies are creating algorithms to select cancer treatments. Hospital systems are implementing decision support systems to help physicians and patients evaluate options for therapy. But it's a disjointed landscape, and so much of what we're aiming for is still in a black box.

We know intuitively—like Jack—that the answers are there, and, more and more, we are amassing the data and developing the analyses to fill in the gaps of our knowledge and make that black box transparent. It's in many different places (from the phones in our pockets to the medical records at hospitals and the clinical trial data used to approve drugs and devices by the FDA). It's not always well-organized, standardized, or easy to work with. But it exists. And for the first time in history, we're organizing it, making it accessible, learning how to analyze it, and creating new benefits from it every day.

The magic is in the algorithms behind the scenes, and how they translate all of those inputs and all of that data into actionable information. These are the equations that will impact us all, mapping every condition that affects or could affect our lives (and every therapy that exists along with those yet to be invented), with unprecedented accuracy.

When the smartest and most well-informed patients get sick, they look for experts—doctors who have seen their condition before, and who have vast stores of wisdom and experience to apply. They put together care teams, hoping that someone's intuition will combine with the particulars of their disease, an understanding of the treatments out there, and, perhaps, a bit of luck, to lead them to the best path forward. Patient equations are going to turn that intuition into mathematically-reliable insights—and bring those insights from the halls of major medical centers and top life sciences companies to patients of all demographics around the world.

We are at the intersection of biological and technological revolution, at a point where the digitization of health and medicine is becoming a reality. The next breakthrough cure—or treatment that turns a fatal condition into a chronic disease—will come from computers and algorithms working in concert with patients, physicians, and scientists. And the COVID-19 pandemic will catalyze this change at an even faster rate.

Very soon, if you're a life sciences executive, you won't just be launching your clinical trials to develop your next drug or device, but you'll be tapping into a set of data never before available to help you ensure that what you're developing is best equipped to help patients and improve your bottom line. If you're a health care provider, you'll be relying on more than just broadly applied standards of care to find the best treatments for individual patients. And if you're a patient yourself, you'll have so much more insight into your health, now and into the future, than ever before.

In the chapters that follow, I'll dive into the world of precision medicine, driven by data and analytics, from an individual patient level all the way to our global population:

In Section 1 (From Hippocrates to Epocrates), I'll set the stage and explain the landscape of precision medicine and data analysis, looking at how we got to where we are today. I'll also set a baseline for what everyone needs to understand about medical data and the fundamentals of patient equations, looking at the kinds of data streams that exist, which of them seem to offer the most promise, and the surprising connections between variables that research is starting to uncover. I'll also look at some of the devices, wearables, apps, and approaches making headlines today with a critical eye, to start to understand how to separate the glitz from the truly meaningful developments that will make it possible to impact patients and consumers at a whole new level.

In Section 2 (Applying Data to Disease), I'll introduce you to some of the individuals and companies already making headway in applying data and analytics to help solve a range of conditions, from acute (bacterial infection and sepsis) to chronic (asthma and diabetes), and from relatively simple, closed-loop individual issues (like infertility) to more complex conditions (like cancer and rare diseases), and then to population-level concerns (like predicting the flu). These case studies will highlight the range of opportunities out there, and how patient equations can make an impact on so many different levels.

In Section 3 (Building Your Own Patient Equations), I'll talk about collecting good data, and putting that data into action. From inputs—ensuring that we start with high-quality, analyzable, and interoperable data that avoid the garbage-in/garbage-out problem that can plague so many systems—to outputs—useful, actionable insights presented in forms that patients can actually benefit from—I'll explain the ways the life sciences industry is changing, and how medicine needs to change to fully leverage these emerging ideas. I'll talk about the changing world of clinical trials—instrumenting patients and creating smarter research programs that constantly adapt and evolve to produce the maximum amount of evidence from every piece of data collected…which in turn yield more bang for the buck for the companies and governments who invest in them, and more quickly bring new treatments to patients who are waiting for them. I'll also discuss disease management platforms that will put information into the hands of the people—the patients and caregivers—who need it, and at the same time create virtuous cycles where as we prevent and treat various diseases, new data and insights will continuously be generated.

In Section 4 (Scaling Progress to the World), I'll look at how all of this can work together to effect real global change, and how COVID-19 has brought many of these issues to the forefront and increased the urgency with which we all need to act. Beyond the practice of medicine and the health of a single patient, evolving reimbursement models, better-aligned incentives, and genuine collaboration have to emerge to create huge worldwide impact. The biggest improvements to health around the world will come from these combined efforts, the evolution of health care's business models, and attention paid to the needs of every participant across the care continuum: patients, physicians, payers, researchers, and regulators.

Finally, I'll conclude with real hope about the limitless, data-driven future ahead of us, and how a bright future for health care businesses and greater good for patients are convergent outcomes that are both within our reach. At the intersection of biological and technological revolutions there is an incredible opportunity for creating patient value—healthier, happier lives—at the same time as realizing huge economic value across the industry as patient equations continue to transform the way treatments are developed, delivered, and applied.

This book comes from over two decades of real-world experience and leadership in the life sciences industry, as well as a personal passion for data and data-driven medicine. I'm the co-founder and co-CEO of Medidata, a company I helped start in 1999 and the world's leader in providing technology and analytics to power clinical research, drug development, and medical device companies across the globe. Until our $5.8 billion purchase by French industrial design software manufacturer Dassault Systèmes SE in 2019, we were New York City's largest publicly traded technology company, and we continue to work with over 1,500 pharmaceutical manufacturers and life sciences companies across the globe as they develop and launch their drugs and devices.

This book is built on the conversations I have day after day with executives about how we can use the latest devices to take their clinical trials to the next level, how we can navigate the complexity of ever-changing guidance and regulations from the FDA, how we can arm doctors with the tools that can transform how effectively they can treat their patients, how we can discover, test, and market new breakthrough drugs more quickly and at lower cost, and how we can thrive in a world changed by pandemic threat.

It wasn't long ago that I opened many of the talks I give around the world with a bit of a trick. I would ask how many people in the audience were walking around with a medically-relevant device on them, some piece of telemetry that was helping them or their doctors manage a condition or disease. People would think insulin pump or heart monitor, and not too many hands would go up. And then I'd ask how many people had a smartphone in their pocket. Because, of course, that was the reveal, at least until my audiences started to get savvier about our future. We're all walking around instrumented with hugely powerful machines that can improve our medical futures, and these machines and the data they produce are upending health care.

Understanding patient equations is so very critical for everyone across the industry spectrum—from life sciences executives and researchers who need to understand how to create, test, deploy, and market digital therapies, and how technology can help them iterate and deliver new treatments faster and more efficiently; to doctors and other health care providers hoping to understand how a new set of tools is on the horizon that can help them provide improved care to their patients; to hospital executives and others based at institutions looking for new approaches that can help them achieve greater impact with lower cost and bring breakthrough advances to their teams; to biotech entrepreneurs and tech pioneers looking to create the next generation of drugs and devices, and who need to understand how data and the algorithms working in the background are helping us understand disease at a level never before possible; to insurers looking to understand how data may be able to power new payment and reimbursement models, as well as provide opportunities to find new, cost-effective ways to improve the health of their policyholders and their own bottom line; to regulators and policymakers needing to understand this space and the implications that private-sector development may have on public health, including opportunities to make health care expenditures in a far smarter and more productive way than currently; to patient advocates, nonprofit groups in the health care space, and academic thinkers and researchers looking at new developments in disease management and how data is affecting cures and treatments coming soon to patients across a huge range of conditions; to informed readers interested in the biotech space, particularly as the biggest tech players—Apple, Google, Amazon—take steps into the health care market and attempt to disrupt the industry from all sides; and, finally, to patients who want to understand how technology can give them more control over their care and allow them to partner with their doctors and utilize the breakthroughs coming from pharma and biotech to improve their health and longevity.

This book was about to go to press just before COVID-19 became a reality. In the midst of the pandemic, I realized the ideas here not only still mattered, but they mattered even more. Patient equations can inform everything we do in life sciences—and we are going to have to rely on them more as we move toward the future state described in these pages. I've written a chapter at the end that talks directly about COVID-19, how all of these issues play out in the context of a pandemic, and what the world can, should, and will look moving forward—but the rest of this book is no less relevant than it was a year ago, and the pandemic mostly serves to point out how critical all of this thinking really is. We can dramatically improve the future by embracing the patient equation-powered world described in the pages that follow.

As we refine the mathematical models for a long list of diseases, it will truly be transformational. We'll be able to make better predictions about what will happen to patients, and engage in smarter interventions, create smarter drugs, and build smarter devices, the ultimate goal being not just that our customers live longer but that they live longer with a higher quality of life, avoiding as many bad health outcomes as they can, and making sure the right people get the right therapies faster and more cost-effectively.

There are huge business advantages to being ahead of the curve, to being faster and more accurate about iterating and delivering new treatments, and to being able to effectively apply technology while still upholding the principles of traditional therapeutic medicine. Finding and applying the next great digital technologies in health care is the biggest business challenge facing us all.

Right now, we're merely scratching the surface. No less an authority than the New England Journal of Medicine wrote recently that [t]here is little doubt that algorithms will transform the thinking underlying medicine and that [t]he integration of data science and medicine is not as far away as it may seem.² The article I'm quoting, titled Lost in Thought: The Limits of the Human Mind and the Future of Medicine, argues that the health care system is ill-prepared to meet the needs of the new technologies, and that medical education is absurdly outdated, doing little to train doctors in the data science, statistics, or behavioral science required to develop, evaluate, and apply algorithms in clinical practice. This book is an attempt to remedy these failings, bring everyone in the industry up to speed, and reveal the truly critical steps we must take to ensure the best possible future for all of us.

Notes

1.   Peter Andrey Smith, One Inventor's Race to Manage His Parkinson's Disease With an App, Medium (OneZero, May 22, 2019), https://onezero.medium.com/one-inventors-race-to-treat-parkinson-s-with-an-app-f2bf197ee70.

2.   Ziad Obermeyer and Thomas H. Lee, Lost in Thought—The Limits of the Human Mind and the Future of Medicine, New England Journal of Medicine 377, no. 13 (September 28, 2017): 1209–1211, https://doi.org/10.1056/nejmp1705348.

SECTION 1

From Hippocrates to Epocrates

1

Before We Cured Scurvy

What do we know about a person? If you asked Hippocrates, he might not have that much to say. Hot or cold. Big or small. Dead or alive. Ask a physician today, and the answer is much more complex. There are thousands of medical tests we can run on a person, inside and out. Blood chemistry, urinalysis, X-rays, Dopplers, and more. We can track these results over time, in various systems, or research information online, with powerful programs like Epocrates, a medical reference app, and others. We can sequence the genome. Or we can count how many steps someone takes in a day.

Categorizing all of these observations about a person is important as we think about them as inputs to patient equations. Whether ancient or modern, these observations come with different levels of reliability and resolution. For example, movement and mood have been observed by physicians for centuries, but we can now check them digitally, reliably, and automatically—without the biases or endurance limitations of a human observer. Hippocrates could certainly count steps—but nowhere near the way a fitness tracker can.

A useful first step in our categorization comes from what most people learned in high school biology: the difference between genotype and phenotype. Before Gregor Mendel's experiments with the physical attributes of peas in the 1800s, we had little knowledge about inheritance from a medical perspective. And until James Watson and Francis Crick's famous work with DNA less than a hundred years ago, we had no notion of the mechanisms by which our genetic makeup was stored and transmitted to subsequent generations. Our genome is incredibly important in determining our health—but it is merely a starting point.

Phenotype, on the other hand, includes every observable aspect of ourselves that is not encoded in our DNA. Everything about us and how we exist in the world is phenotype: our hair color, eye color, height, weight, and so much more. The observation of phenotypes begins well before the days of Hippocrates. Imagine an ancient doctor simply using a hand to determine if a person had a fever. Or, not even a doctor—we should instead use the term healer in that example, since people were likely checking for fevers long before any notion of the structured discipline of medicine.

Of course, this technique continues today. Imagine a parent touching a child to check for the same. These kinds of observations certainly go under the heading of phenotype. But even what goes on in our heads—our cognition—and how those thoughts manifest in what we do every day—our behavior: it's all phenotype.

Over time, the precision with which phenotypes can be measured has continued to evolve. The hand, to start, was replaced by a thermometer to check for a fever. A modern mercury or alcohol-based thermometer can be read to a tenth of a degree of precision. 37.0° Celsius is the widely accepted average normal value of a healthy person's temperature. On a modern analog thermometer, that is distinguishable from 37.1° or 36.9°. A digital thermometer might be even more precise, perhaps to the level of hundredths or even thousandths of a degree.

These digital readings show a greater resolution—which is another useful dimension that we can use to categorize phenotypes. An inexperienced hand might be able to distinguish between two states: fever and no fever. For those familiar with the language of computers, we can represent this in binary as a zero or a one. Perhaps a more experienced nurse, physician, or mom can distinguish between a low fever and a high fever. Add hypothermia (the body becoming too cold for normal functioning) and we've got four possible outcomes of the measurement. The computer-literate will realize that this is now not one binary bit, but two digits, each a zero or one. If we want to know if a patient is recovering from a fever (or hypothermia), we probably need to grab that liquid thermometer and measure the temperature more precisely, so that we can see the value change over time.

As we look at more complex problems in disease diagnosis, or, for instance, predicting fertility, we may indeed need the digital version. As we take these more-and-more-precise measurements (and need more and more computer bits to store them), you can start to see how the convergence of biology and digital technologies is inextricably linked to the resolution at which we measure phenotype.

Nanometers to Megameters

Beyond resolution or precision, we can think of the available knowledge about a person in terms of scale. Starting small: individual atoms combine to form molecules that define the tiniest end of our scale, at least when it comes to our current knowledge about how to observe our state of health. (A keen futurist—or a particle physicist—might predict that future editions of this book will reflect not-yet-uncovered findings about subatomic interactions being relevant to predicting or managing our health. But, for now, the atom is as small as it gets.)

Let's begin with our DNA, at a couple of nanometers in size, as the starting point. When our genes are turned on—activated as a first step in a cascade of observable phenotypes—they are transcribed to RNA. We're still talking nanometers. Ultimately, those genes produce proteins, protein complexes, organelles (just as our body has organs, so do the cells that make it up), and we reach the next milestone of scale: a cell, at tens of micrometers in size. Figure 1.1 illustrates this continuing progression of phenotypic scale.

Figure 1.1 A multiscale view of health

Our organs, in centimeters, are next. And if we look at the ways phenotype has been measured over time, the organs were the smallest level at which we could observe for many, many generations. The Greek anatomist Herophilus, around the year 300 BC, is said to be the first to systematically dissect and start to understand the human body.¹ He described the cardiovascular system, the digestive system, the reproductive system, and more.

Perhaps embarrassingly,