Precision Medicine concept
Is the value of "personalized medicine" over-promised? Why is the quality of health care declining for many people despite the pace of innovation? Do patients and doctors have conflicting priorities? What is the best path forward?
"How do we generate evidence for value, which is what everyone is asking for?"
Some of the country's leading medical experts recently debated these questions at the prestigious annual Personalized Medicine Conference, held at Harvard Medical School in Boston, and LeapsMag was there to bring you the inside scoop.
Personalized Medicine: Is It Living Up to the Hype?
The buzzworthy phrase "personalized medicine" has been touted for years as the way of the future—customizing care to patients based on their predicted responses to treatments given their individual genetic profiles or other analyses. Since the initial sequencing of the human genome around fifteen years ago, the field of genomics has exploded as the costs have dramatically come down – from $2.7 billion to $1000 or less today. Given cheap access to such crucial information, the medical field has been eager to embrace an ultramodern world in which preventing illnesses is status quo, and treatments can be tailored for maximum effectiveness. But whether that world has finally arrived remains debatable.
"I've been portrayed as an advocate for genomics, because I'm excited about it," said Robert C. Green, Director of the Genomes2People Research Program at Harvard Medical School, the Broad Institute, and Brigham and Women's Hospital. He qualified his advocacy by saying that he tries to remain 'equipoised' or balanced in his opinions about the future of personalized medicine, and expressed skepticism about some aspects of its rapid commercialization.
"I have strong feelings about some of the [precision medicine] products that are rushing out to market in both the physician-mediated space and the consumer space," Green said, and challenged the value and sustainability of these products, such as their clinical utility and ability to help produce favorable health outcomes. He asked what most patients and providers want to know, which is, "What are the medical, behavioral, and economic outcomes? How do we generate evidence for value, which is what everyone is asking for?" He later questioned whether the use of 'sexy' and expensive diagnostic technologies is necessarily better than doing things the old-fashioned way. For instance, it is much easier and cheaper to ask a patient directly about their family history of disease, instead of spending thousands of dollars to obtain the same information with pricey diagnostic tests.
"Our mantra is to try to do data-driven health...to catch disease when it occurs early."
Michael Snyder, Professor & Chair of the Department of Genetics and Director of the Center for Genomics and Personalized Medicine at Stanford University, called himself more of an 'enthusiast' about precision medicine products like wearable devices that can digitally track vital signs, including heart rate and blood oxygen levels. "I'm certainly not equipoised," he said, adding, "Our mantra is to try to do data-driven health. We are using this to try to understand health and catch disease when it occurs early."
Snyder then shared his personal account about how his own wearable device alerted him to seek treatment while he was traveling in Norway. "My blood oxygen was low and my heart rate was high, so that told me something was up," he shared. After seeing a doctor, he discovered he was suffering from Lyme disease. He then shared other similar success stories about some of the patients in his department. Using wearable health sensors, he said, could significantly reduce health care costs: "$245 billion is spent every year on diabetes, and if we reduce that by ten percent we just saved $24 billion."
From left, Robert Green, Michael Snyder, Sandro Galea, and Thomas Miller.
(Courtesy Rachele Hendricks-Sturrup)
A Core Reality: Unresolved Societal Issues
Sandro Galea, Dean and Professor at Boston University's School of Public Health, coined himself as a 'skeptic' but also an 'enormous fan' of new technologies. He said, "I want to make sure that you all [the audience] have the best possible treatment for me when I get sick," but added, "In our rush and enthusiasm to embrace personalized and precision medicine approaches, we have done that at the peril of forgetting a lot of core realities."
"There's no one to pay for health care but all of us."
Galea stressed the need to first address certain difficult societal issues because failing to do so will deter precision medicine cures in the future. "Unless we pay attention to domestic violence, housing, racism, poor access to care, and poverty… we are all going to lose," he said. Then he quoted recent statistics about the country's growing gap in both health and wealth, which could potentially erode patient and provider interest in personalized medicine.
Thomas Miller, the founder and partner of a venture capital firm dedicated to advancing precision medicine, agreed with Galea and said that "there's no one to pay for health care but all of us." He recalled witnessing 'abuse' of diagnostic technologies that he had previously invested in. "They were often used as mechanisms to provide unnecessary care rather than appropriate care," he said. "The trend over my 30-year professional career has been that of sensitivity over specificity."
In other words: doctors rely too heavily on diagnostic tools that are sensitive enough to detect signs of a disease, but not accurate enough to confirm the presence of a specific disease. "You will always find that you're sick from something," Miller said. He lamented the counter-productivity and waste brought on by such 'abuse' and added, "That's money that could be used to address some of the problems that you [Galea] just talked about."
Do Patients and Providers Have Conflicting Priorities?
Distrust in the modern health care system is not new in the United States. That fact that medical errors were the third leading cause of death in 2016 may have fueled this mistrust even more. And the level of mistrust appears correlated with race; a recent survey of 118 adults between 18 to 75 years old showed that black respondents were less likely to trust their doctors than the non-Hispanic white respondents. The black respondents were also more concerned about personal privacy and potentially harmful hospital experimentation.
"The vast majority of physicians in this country are incentivized to keep you sick."
As if this context weren't troubling enough, some of the panelists suggested that health care providers and patients have misaligned goals, which may be financially driven.
For instance, Galea stated that health care is currently 'curative' even though that money is better spent on prevention versus cures. "The vast majority of physicians in this country are incentivized to keep you sick," he declared. "They are paid by sick patient visits. Hospital CEOs are paid by the number of sick people they have in their beds." He highlighted this issue as a national priority and mentioned some case studies showing that the behaviors of hospital CEOs quickly change when payment is based on the number of patients in beds versus the number of patients being kept out of the beds. Green lauded Galea's comment as "good sense."
Green also cautioned the audience about potential financial conflicts of interest held by proponents of precision medicine technologies. "Many of the people who are promoting genomics and personalized medicine are people who have financial interests in that arena," he warned. He emphasized that those who are perhaps curbing the over-enthusiasm do not have financial interests at stake.
What is the Best Path Forward for Personalized Medicine?
As useful as personalized medicine may be for selecting the best course of treatment, there is also the flip side: It can allow doctors to predict who will not respond well—and this painful reality must be acknowledged.
Miller argued, "We have a duty to call out therapies that won't work, that will not heal, that need to be avoided, and that will ultimately lead to you saying to a patient, 'There is nothing for you that will work.'"
Although that may sound harsh, it captures the essence of this emerging paradigm, which is to maximize health by using tailored methods that are based on comparative effectiveness, evidence of outcomes, and patient preferences. After all, as Miller pointed out, it wouldn't do much good to prescribe someone a regimen with little reason to think it might help.
For the hype around personalized medicine to be fully realized, Green concluded, "We have to prove to people that [the value of it] is true."
AI was integral to creating Moderna's mRNA vaccine against COVID.
But the truth is that before ChatGPT nabbed the public’s attention, AI was already here, and it was doing more important things than writing essays for lazy college students. Case in point: It was key to saving the lives of tens of millions of people.
AI-designed mRNA vaccines
As Dave Johnson, chief data and AI officer at Moderna, told MIT Technology Review‘s In Machines We Trust podcast in 2022, AI was integral to creating the company’s highly effective mRNA vaccine against COVID. Moderna and Pfizer/BioNTech’s mRNA vaccines collectively saved between 15 and 20 million lives, according to one estimate from 2022.
Johnson described how AI was hard at work at Moderna, well before COVID arose to infect billions. The pharmaceutical company focuses on finding mRNA therapies to fight off infectious disease, treat cancer, or thwart genetic illness, among other medical applications. Messenger RNA molecules are essentially molecular instructions for cells that tell them how to create specific proteins, which do everything from fighting infection, to catalyzing reactions, to relaying cellular messages.
Johnson and his team put AI and automated robots to work making lots of different mRNAs for scientists to experiment with. Moderna quickly went from making about 30 per month to more than one thousand. They then created AI algorithms to optimize mRNA to maximize protein production in the body — more bang for the biological buck.
For Johnson and his team’s next trick, they used AI to automate science, itself. Once Moderna’s scientists have an mRNA to experiment with, they do pre-clinical tests in the lab. They then pore over reams of data to see which mRNAs could progress to the next stage: animal trials. This process is long, repetitive, and soul-sucking — ill-suited to a creative scientist but great for a mindless AI algorithm. With scientists’ input, models were made to automate this tedious process.
“We don’t think about AI in the context of replacing humans,” says Dave Johnson, chief data and AI officer at Moderna. “We always think about it in terms of this human-machine collaboration, because they’re good at different things. Humans are really good at creativity and flexibility and insight, whereas machines are really good at precision and giving the exact same result every single time and doing it at scale and speed.”
All these AI systems were in put in place over the past decade. Then COVID showed up. So when the genome sequence of the coronavirus was made public in January 2020, Moderna was off to the races pumping out and testing mRNAs that would tell cells how to manufacture the coronavirus’s spike protein so that the body’s immune system would recognize and destroy it. Within 42 days, the company had an mRNA vaccine ready to be tested in humans. It eventually went into hundreds of millions of arms.
Biotech harnesses the power of AI
Moderna is now turning its attention to other ailments that could be solved with mRNA, and the company is continuing to lean on AI. Scientists are still coming to Johnson with automation requests, which he happily obliges.
“We don’t think about AI in the context of replacing humans,” he told the Me, Myself, and AI podcast. “We always think about it in terms of this human-machine collaboration, because they’re good at different things. Humans are really good at creativity and flexibility and insight, whereas machines are really good at precision and giving the exact same result every single time and doing it at scale and speed.”
Moderna, which was founded as a “digital biotech,” is undoubtedly the poster child of AI use in mRNA vaccines. Moderna recently signed a deal with IBM to use the company’s quantum computers as well as its proprietary generative AI, MoLFormer.
Moderna’s success is encouraging other companies to follow its example. In January, BioNTech, which partnered with Pfizer to make the other highly effective mRNA vaccine against COVID, acquired the company InstaDeep for $440 million to implement its machine learning AI across its mRNA medicine platform. And in May, Chinese technology giant Baidu announced an AI tool that designs super-optimized mRNA sequences in minutes. A nearly countless number of mRNA molecules can code for the same protein, but some are more stable and result in the production of more proteins. Baidu’s AI, called “LinearDesign,” finds these mRNAs. The company licensed the tool to French pharmaceutical company Sanofi.
Writing in the journal Accounts of Chemical Research in late 2021, Sebastian M. Castillo-Hair and Georg Seelig, computer engineers who focus on synthetic biology at the University of Washington, forecast that AI machine learning models will further accelerate the biotechnology research process, putting mRNA medicine into overdrive to the benefit of all.
This article originally appeared on Big Think, home of the brightest minds and biggest ideas of all time.
