Clever Firm Predicts Patients Most at Risk, Then Tries to Intervene Before They Get Sicker
The diabetic patient hit the danger zone.
Ideally, blood sugar, measured by an A1C test, rests at 5.9 or less. A 7 is elevated, according to the Diabetes Council. Over 10, and you're into the extreme danger zone, at risk of every diabetic crisis from kidney failure to blindness.
In three months of working with a case manager, Jen's blood sugar had dropped to 7.2, a much safer range.
This patient's A1C was 10. Let's call her Jen for the sake of this story. (Although the facts of her case are real, the patient's actual name wasn't released due to privacy laws.).
Jen happens to live in Pennsylvania's Lehigh Valley, home of the nonprofit Lehigh Valley Health Network, which has eight hospital campuses and various clinics and other services. This network has invested more than $1 billion in IT infrastructure and founded Populytics, a spin-off firm that tracks and analyzes patient data, and makes care suggestions based on that data.
When Jen left the doctor's office, the Populytics data machine started churning, analyzing her data compared to a wealth of information about future likely hospital visits if she did not comply with recommendations, as well as the potential positive impacts of outreach and early intervention.
About a month after Jen received the dangerous blood test results, a community outreach specialist with psychological training called her. She was on a list generated by Populytics of follow-up patients to contact.
"It's a very gentle conversation," says Cathryn Kelly, who manages a care coordination team at Populytics. "The case manager provides them understanding and support and coaching." The goal, in this case, was small behavioral changes that would actually stick, like dietary ones.
In three months of working with a case manager, Jen's blood sugar had dropped to 7.2, a much safer range. The odds of her cycling back to the hospital ER or veering into kidney failure, or worse, had dropped significantly.
While the health network is extremely localized to one area of one state, using data to inform precise medical decision-making appears to be the wave of the future, says Ann Mongovern, the associate director of Health Care Ethics at the Markkula Center for Applied Ethics at Santa Clara University in California.
"Many hospitals and hospital systems don't yet try to do this at all, which is striking given where we're at in terms of our general technical ability in this society," Mongovern says.
How It Happened
While many hospitals make money by filling beds, the Lehigh Valley Health Network, as a nonprofit, accepts many patients on Medicaid and other government insurances that don't cover some of the costs of a hospitalization. The area's population is both poorer and older than national averages, according to the U.S. Census data, meaning more people with higher medical needs that may not have the support to care for themselves. They end up in the ER, or worse, again and again.
In the early 2000s, LVHN CEO Dr. Brian Nester started wondering if his health network could develop a way to predict who is most likely to land themselves a pricey ICU stay -- and offer support before those people end up needing serious care.
Embracing data use in such specific ways also brings up issues of data security and patient safety.
"There was an early understanding, even if you go back to the (federal) balanced budget act of 1997, that we were just kicking the can down the road to having a functional financial model to deliver healthcare to everyone with a reasonable price," Nester says. "We've got a lot of people living longer without more of an investment in the healthcare trust."
Popultyics, founded in 2013, was the result of years of planning and agonizing over those population numbers and cost concerns.
"We looked at our own health plan," Nester says. Out of all the employees and dependants on the LVHN's own insurance network, "roughly 1.5 percent of our 25,000 people — under 400 people — drove $30 million of our $130 million on insurance costs -- about 25 percent."
"You don't have to boil the ocean to take cost out of the system," he says. "You just have to focus on that 1.5%."
Take Jen, the diabetic patient. High blood sugar can lead to kidney failure, which can mean weekly expensive dialysis for 20 years. Investing in the data and staff to reach patients, he says, is "pennies compared to $100 bills."
For most doctors, "there's no awareness for providers to know who they should be seeing vs. who they are seeing. There's no incentive, because the incentive is to see as many patients as you can," he says.
To change that, first the LVHN invested in the popular medical management system, Epic. Then, they negotiated with the top 18 insurance companies that cover patients in the region to allow access to their patient care data, which means they have reams of patient history to feed the analytics machine in order to make predictions about outcomes. Nester admits not every hospital could do that -- with 52 percent of the market share, LVHN had a very strong negotiating position.
Third party services take that data and churn out analytics that feeds models and care management plans. All identifying information is stripped from the data.
"We can do predictive modeling in patients," says Populytics President and CEO Gregory Kile. "We can identify care gaps. Those care gaps are noted as alerts when the patient presents at the office."
Kile uses himself as a hypothetical patient.
"I pull up Gregory Kile, and boom, I see a flag or an alert. I see he hasn't been in for his last blood test. There is a care gap there we need to complete."
"There's just so much more you can do with that information," he says, envisioning a future where follow-up for, say, knee replacement surgery and outcomes could be tracked, and either validated or changed.
Ethical Issues at the Forefront
Of course, embracing data use in such specific ways also brings up issues of security and patient safety. For example, says medical ethicist Mongovern, there are many touchpoints where breaches could occur. The public has a growing awareness of how data used to personalize their experiences, such as social media analytics, can also be monetized and sold in ways that benefit a company, but not the user. That's not to say data supporting medical decisions is a bad thing, she says, just one with potential for public distrust if not handled thoughtfully.
"You're going to need to do this to stay competitive," she says. "But there's obviously big challenges, not the least of which is patient trust."
So far, a majority of the patients targeted – 62 percent -- appear to embrace the effort.
Among the ways the LVHN uses the data is monthly reports they call registries, which include patients who have just come in contact with the health network, either through the hospital or a doctor that works with them. The community outreach team members at Populytics take the names from the list, pull their records, and start calling. So far, a majority of the patients targeted – 62 percent -- appear to embrace the effort.
Says Nester: "Most of these are vulnerable people who are thrilled to have someone care about them. So they engage, and when a person engages in their care, they take their insulin shots. It's not rocket science. The rocket science is in identifying who the people are — the delivery of care is easy."
Coronavirus Risk Calculators: What You Need to Know
People in my family seem to develop every ailment in the world, including feline distemper and Dutch elm disease, so I naturally put fingers to keyboard when I discovered that COVID-19 risk calculators now exist.
"It's best to look at your risk band. This will give you a more useful insight into your personal risk."
But the results – based on my answers to questions -- are bewildering.
A British risk calculator developed by the Nexoid software company declared I have a 5 percent, or 1 in 20, chance of developing COVID-19 and less than 1 percent risk of dying if I get it. Um, great, I think? Meanwhile, 19 and Me, a risk calculator created by data scientists, says my risk of infection is 0.01 percent per week, or 1 in 10,000, and it gave me a risk score of 44 out of 100.
Confused? Join the club. But it's actually possible to interpret numbers like these and put them to use. Here are five tips about using coronavirus risk calculators:
1. Make Sure the Calculator Is Designed For You
Not every COVID-19 risk calculator is designed to be used by the general public. Cleveland Clinic's risk calculator, for example, is only a tool for medical professionals, not sick people or the "worried well," said Dr. Lara Jehi, Cleveland Clinic's chief research information officer.
Unfortunately, the risk calculator's web page fails to explicitly identify its target audience. But there are hints that it's not for lay people such as its references to "platelets" and "chlorides."
The 19 and Me or the Nexoid risk calculators, in contrast, are both designed for use by everyone, as is a risk calculator developed by Emory University.
2. Take a Look at the Calculator's Privacy Policy
COVID-19 risk calculators ask for a lot of personal information. The Nexoid calculator, for example, wanted to know my age, weight, drug and alcohol history, pre-existing conditions, blood type and more. It even asked me about the prescription drugs I take.
It's wise to check the privacy policy and be cautious about providing an email address or other personal information. Nexoid's policy says it provides the information it gathers to researchers but it doesn't release IP addresses, which can reveal your location in certain circumstances.
John-Arne Skolbekken, a professor and risk specialist at Norwegian University of Science and Technology, entered his own data in the Nexoid calculator after being contacted by LeapsMag for comment. He noted that the calculator, among other things, asks for information about use of recreational drugs that could be illegal in some places. "I have given away some of my personal data to a company that I can hope will not misuse them," he said. "Let's hope they are trustworthy."
The 19 and Me calculator, by contrast, doesn't gather any data from users, said Cindy Hu, data scientist at Mathematica, which created it. "As soon as the window is closed, that data is gone and not captured."
The Emory University risk calculator, meanwhile, has a long privacy policy that states "the information we collect during your assessment will not be correlated with contact information if you provide it." However, it says personal information can be shared with third parties.
3. Keep an Eye on Time Horizons
Let's say a risk calculator says you have a 1 percent risk of infection. That's fairly low if we're talking about this year as a whole, but it's quite worrisome if the risk percentage refers to today and jumps by 1 percent each day going forward. That's why it's helpful to know exactly what the numbers mean in terms of time.
Unfortunately, this information isn't always readily available. You may have to dig around for it or contact a risk calculator's developers for more information. The 19 and Me calculator's risk percentages refer to this current week based on your behavior this week, Hu said. The Nexoid calculator, by contrast, has an "infinite timeline" that assumes no vaccine is developed, said Jonathon Grantham, the company's managing director. But your results will vary over time since the calculator's developers adjust it to reflect new data.
When you use a risk calculator, focus on this question: "How does your risk compare to the risk of an 'average' person?"
4. Focus on the Big Picture
The Nexoid calculator gave me numbers of 5 percent (getting COVID-19) and 99.309 percent (surviving it). It even provided betting odds for gambling types: The odds are in favor of me not getting infected (19-to-1) and not dying if I get infected (144-to-1).
However, Grantham told me that these numbers "are not the whole story." Instead, he said, "it's best to look at your risk band. This will give you a more useful insight into your personal risk." Risk bands refer to a segmentation of people into five categories, from lowest to highest risk, according to how a person's result sits relative to the whole dataset.
The Nexoid calculator says I'm in the "lowest risk band" for getting COVID-19, and a "high risk band" for dying of it if I get it. That suggests I'd better stay in the lowest-risk category because my pre-existing risk factors could spell trouble for my survival if I get infected.
Michael J. Pencina, a professor and biostatistician at Duke University School of Medicine, agreed that focusing on your general risk level is better than focusing on numbers. When you use a risk calculator, he said, focus on this question: "How does your risk compare to the risk of an 'average' person?"
The 19 and Me calculator, meanwhile, put my risk at 44 out of 100. Hu said that a score of 50 represents the typical person's risk of developing serious consequences from another disease – the flu.
5. Remember to Take Action
Hu, who helped develop the 19 and Me risk calculator, said it's best to use it to "understand the relative impact of different behaviors." As she noted, the calculator is designed to allow users to plug in different answers about their behavior and immediately see how their risk levels change.
This information can help us figure out if we should change the way we approach the world by, say, washing our hands more or avoiding more personal encounters.
"Estimation of risk is only one part of prevention," Pencina said. "The other is risk factors and our ability to reduce them." In other words, odds, percentages and risk bands can be revealing, but it's what we do to change them that matters.
Pseudoscience Is Rampant: How Not to Fall for It
Whom to believe?
The relentless and often unpredictable coronavirus (SARS-CoV-2) has, among its many quirky terrors, dredged up once again the issue that will not die: science versus pseudoscience.
How does one learn to spot the con without getting a Ph.D. and spending years in a laboratory?
The scientists, experts who would be the first to admit they are not infallible, are now in danger of being drowned out by the growing chorus of pseudoscientists, conspiracy theorists, and just plain troublemakers that seem to be as symptomatic of the virus as fever and weakness.
How is the average citizen to filter this cacophony of information and misinformation posing as science alongside real science? While all that noise makes it difficult to separate the real stuff from the fakes, there is at least one positive aspect to it all.
A famous aphorism by one Charles Caleb Colton, a popular 19th-century English cleric and writer, says that "imitation is the sincerest form of flattery."
The frauds and the paranoid conspiracy mongers who would perpetrate false science on a susceptible public are at least recognizing the value of science—they imitate it. They imitate the ways in which science works and make claims as if they were scientists, because even they recognize the power of a scientific approach. They are inadvertently showing us how much we value science. Unfortunately they are just shabby counterfeits.
Separating real science from pseudoscience is not a new problem. Philosophers, politicians, scientists, and others have been worrying about this perhaps since science as we know it, a science based entirely on experiment and not opinion, arrived in the 1600s. The original charter of the British Royal Society, the first organized scientific society, stated that at their formal meetings there would be no discussion of politics, religion, or perpetual motion machines.
The first two of those for the obvious purpose of keeping the peace. But the third is interesting because at that time perpetual motion machines were one of the main offerings of the imitators, the bogus scientists who were sure that you could find ways around the universal laws of energy and make a buck on it. The motto adopted by the society was, and remains, Nullius in verba, Latin for "take nobody's word for it." Kind of an early version of Missouri's venerable state motto: "Show me."
You might think that telling phony science from the real thing wouldn't be so difficult, but events, historical and current, tell a very different story—often with tragic outcomes. Just one terrible example is the estimated 350,000 additional HIV deaths in South Africa directly caused by the now-infamous conspiracy theories of their own elected President no less (sound familiar?). It's surprisingly easy to dress up phony science as the real thing by simply adopting, or appearing to adopt, the trappings of science.
Thus, the anti-vaccine movement claims to be based on suspicion of authority, beginning with medical authority in this case, stemming from the fraudulent data published by the now-disgraced Andrew Wakefield, an English gastroenterologist. And it's true that much of science is based on suspicion of authority. Science got its start when the likes of Galileo and Copernicus claimed that the Church, the State, even Aristotle, could no longer be trusted as authoritative sources of knowledge.
But Galileo and those who followed him produced alternative explanations, and those alternatives were based on data that arose independently from many sources and generated a great deal of debate and, most importantly, could be tested by experiments that could prove them wrong. The anti-vaccine movement imitates science, still citing the discredited Wakefield report, but really offers nothing but suspicion—and that is paranoia, not science.
Similarly, there are those who try to cloak their nefarious motives in the trappings of science by claiming that they are taking the scientific posture of doubt. Science after all depends on doubt—every scientist doubts every finding they make. Every scientist knows that they can't possibly foresee all possible instances or situations in which they could be proven wrong, no matter how strong their data. Einstein was doubted for two decades, and cosmologists are still searching for experimental proofs of relativity. Science indeed progresses by doubt. In science revision is a victory.
But the imitators merely use doubt to suggest that science is not dependable and should not be used for informing policy or altering our behavior. They claim to be taking the legitimate scientific stance of doubt. Of course, they don't doubt everything, only what is problematic for their individual enterprises. They don't doubt the value of blood pressure medicine to control their hypertension. But they should, because every medicine has side effects and we don't completely understand how blood pressure is regulated and whether there may not be still better ways of controlling it.
But we use the pills we have because the science is sound even when it is not completely settled. Ask a hypertensive oil executive who would like you to believe that climate science should be ignored because there are too many uncertainties in the data, if he is willing to forgo his blood pressure medicine—because it, too, has its share of uncertainties and unwanted side effects.
The apparent success of pseudoscience is not due to gullibility on the part of the public. The problem is that science is recognized as valuable and that the imitators are unfortunately good at what they do. They take a scientific pose to gain your confidence and then distort the facts to their own purposes. How does one learn to spot the con without getting a Ph.D. and spending years in a laboratory?
"If someone claims to have the ultimate answer or that they know something for certain, the only thing for sure is that they are trying to fool you."
What can be done to make the distinction clearer? Several solutions have been tried—and seem to have failed. Radio and television shows about the latest scientific breakthroughs are a noble attempt to give the public a taste of good science, but they do nothing to help you distinguish between them and the pseudoscience being purveyed on the neighboring channel and its "scientific investigations" of haunted houses.
Similarly, attempts to inculcate what are called "scientific habits of mind" are of little practical help. These habits of mind are not so easy to adopt. They invariably require some amount of statistics and probability and much of that is counterintuitive—one of the great values of science is to help us to counter our normal biases and expectations by showing that the actual measurements may not bear them out.
Additionally, there is math—no matter how much you try to hide it, much of the language of science is math (Galileo said that). And half the audience is gone with each equation (Stephen Hawking said that). It's hard to imagine a successful program of making a non-scientifically trained public interested in adopting the rigors of scientific habits of mind. Indeed, I suspect there are some people, artists for example, who would be rightfully suspicious of changing their thinking to being habitually scientific. Many scientists are frustrated by the public's inability to think like a scientist, but in fact it is neither easy nor always desirable to do so. And it is certainly not practical.
There is a more intuitive and simpler way to tell the difference between the real thing and the cheap knock-off. In fact, it is not so much intuitive as it is counterintuitive, so it takes a little bit of mental work. But the good thing is it works almost all the time by following a simple, if as I say, counterintuitive, rule.
True science, you see, is mostly concerned with the unknown and the uncertain. If someone claims to have the ultimate answer or that they know something for certain, the only thing for sure is that they are trying to fool you. Mystery and uncertainty may not strike you right off as desirable or strong traits, but that is precisely where one finds the creative solutions that science has historically arrived at. Yes, science accumulates factual knowledge, but it is at its best when it generates new and better questions. Uncertainty is not a place of worry, but of opportunity. Progress lives at the border of the unknown.
How much would it take to alter the public perception of science to appreciate unknowns and uncertainties along with facts and conclusions? Less than you might think. In fact, we make decisions based on uncertainty every day—what to wear in case of 60 percent chance of rain—so it should not be so difficult to extend that to science, in spite of what you were taught in school about all the hard facts in those giant textbooks.
You can believe science that says there is clear evidence that takes us this far… and then we have to speculate a bit and it could go one of two or three ways—or maybe even some way we don't see yet. But like your blood pressure medicine, the stuff we know is reliable even if incomplete. It will lower your blood pressure, no matter that better treatments with fewer side effects may await us in the future.
Unsettled science is not unsound science. The honesty and humility of someone who is willing to tell you that they don't have all the answers, but they do have some thoughtful questions to pursue, are easy to distinguish from the charlatans who have ready answers or claim that nothing should be done until we are an impossible 100-percent sure.
Imitation may be the sincerest form of flattery.
The problem, as we all know, is that flattery will get you nowhere.
[Editor's Note: This article was originally published on June 8th, 2020 as part of a standalone magazine called GOOD10: The Pandemic Issue. Produced as a partnership among LeapsMag, The Aspen Institute, and GOOD, the magazine is available for free online.]