Clever Firm Predicts Patients Most at Risk, Then Tries to Intervene Before They Get Sicker
Health firm Populytics tracks and analyzes patient data, and makes care suggestions based on that data.
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."
A historical perspective offers insights about how far we have come since the 1918 Spanish flu, and how far we have yet to go.
With a deadly pandemic sweeping the planet, many are questioning the comfort and security we have taken for granted in the modern world.
A century ago, when an influenza pandemic struck, we barely knew what viruses were.
More than a century after the germ theory, we are still at the mercy of a microbe we can neither treat, nor control, nor immunize against. Even more discouraging is that technology has in some ways exacerbated the problem: cars and air travel allow a new disease to quickly encompass the globe.
Some say we have grown complacent, that we falsely assume the triumphs of the past ensure a happy and prosperous future, that we are oblivious to the possibility of unpredictable "black swan" events that could cause our destruction. Some have begun to lose confidence in progress itself, and despair of the future.
But the new coronavirus should not defeat our spirit—if anything, it should spur us to redouble our efforts, both in the science and technology of medicine, and more broadly in the advance of industry. Because the best way to protect ourselves against future disasters is more progress, faster.
Science and technology have overall made us much better able to deal with disease. In the developed world, we have already tamed most categories of infectious disease. Most bacterial infections, such as tuberculosis or bacterial pneumonia, are cured with antibiotics. Waterborne diseases such as cholera are eliminated through sanitation; insect-borne ones such as malaria through pest control. Those that are not contagious until symptoms appear, such as SARS, can be handled through case isolation and contact tracing. For the rest, such as smallpox, polio, and measles, we develop vaccines, given enough time. COVID-19 could start a pandemic only because it fits a narrow category: a new, viral disease that is highly contagious via pre-symptomatic droplet/aerosol transmission, and that has a high mortality rate compared to seasonal influenza.
A century ago, when an influenza pandemic struck, we barely knew what viruses were; no one had ever seen one. Today we know what COVID-19 is down to its exact genome; in fact, we have sequenced thousands of COVID-19 genomes, and can track its history and its spread through their mutations. We can create vaccines faster today, too: where we once developed them in live animals, we now use cell cultures; where we once had to weaken or inactivate the virus itself, we can now produce vaccines based on the virus's proteins. And even though we don't yet have a treatment, the last century-plus of pharmaceutical research has given us a vast catalog of candidate drugs, already proven safe. Even now, over 50 candidate vaccines and almost 100 candidate treatments are in the research pipeline.
It's not just our knowledge that has advanced, but our methods. When smallpox raged in the 1700s, even the idea of calculating a case-fatality rate was an innovation. When the polio vaccine was trialled in the 1950s, the use of placebo-controlled trials was still controversial. The crucial measure of contagiousness, "R0", was not developed in epidemiology until the 1980s. And today, all of these methods are made orders of magnitude faster and more powerful by statistical and data visualization software.
If you're seeking to avoid COVID-19, the hand sanitizer gel you carry in a pocket or purse did not exist until the 1960s. If you start to show symptoms, the pulse oximeter that tests your blood oxygenation was not developed until the 1970s. If your case worsens, the mechanical ventilator that keeps you alive was invented in the 1950s—in fact, no form of artificial respiration was widely available until the "iron lung" used to treat polio patients in the 1930s. Even the modern emergency medical system did not exist until recently: if during the 1918 flu pandemic you became seriously ill, there was no 911 hotline to call, and any ambulance that showed up would likely have been a modified van or hearse, with no equipment or trained staff.
As many of us "shelter in place", we are far more able to communicate and collaborate, to maintain some semblance of normal life, than we ever would have been. To compare again to 1918: long-distance telephone service barely existed at that time, and only about a third of homes in the US even had electricity; now we can videoconference over Zoom and Skype. And the enormous selection and availability provided by online retail and food delivery have kept us stocked and fed, even when we don't want to venture out to the store.
Let the virus push us to redouble our efforts to make scientific, technological, and industrial progress on all fronts.
"Black swan" calamities can strike without warning at any time. Indeed, humanity has always been subject to them—drought and frost, fire and flood, war and plague. But we are better equipped now to deal with them than ever before. And the more progress we make, the better prepared we'll be for the next one. The accumulation of knowledge, technology, industrial infrastructure, and surplus wealth is the best buffer against any shock—whether a viral pandemic, a nuclear war, or an asteroid impact. In fact, the more worried we are about future crises, the more energetically we should accelerate science, technology and industry.
In this sense, we have grown complacent. We take the modern world for granted, so much so that some question whether further progress is even still needed. The new virus proves how much we do need it, and how far we still have to go. Imagine how different things would be if we had broad-spectrum antiviral drugs, or a way to enhance the immune system to react faster to infection, or a way to detect infection even before symptoms appear. These technologies may seem to belong to a Star Trek future—but so, at one time, did cell phones.
The virus reminds us that nature is indifferent to us, leaving us to fend entirely for ourselves. As we go to war against it, let us not take the need for such a war as reason for despair. Instead, let it push us to redouble our efforts to make scientific, technological, and industrial progress on all fronts. No matter the odds, applied intelligence is our best weapon against disaster.
A participatory research project has evolved in the world's most powerful networked supercomputer to identify drug targets for COVID-19.
With millions of people left feeling helpless as COVID-19 sweeps across the U.S. and the rest of the planet, there is one way in which absolutely anyone can help fight the pandemic -- all you need is a computer and an Internet connection.
"The more donors that participate, the more science we're able to do."
The Folding@home project allows members of the public to contribute a portion of their computing power to a gigantic virtual network which has mushroomed over the past month to become the most powerful supercomputer on the planet.
As of April 6, more than one million people across the globe have donated some of their home computing resources to the project. Combined, this gives Folding@home processing powers that dwarf even NASA and IBM's most powerful devices. To join, all you have to do is go to this website and click 'Download Now' to load the Folding@home software on your computer. This runs in the background, and only adds your unused computing power to the project, so it will not drain resources from tasks you're trying to do.
"It's totally crazy," said Vincent Voelz, associate professor of chemistry at Temple University, Philadelphia, and one of the scientists leading the project. "A month ago, we had around 30,000 to 40,000 participants. And then last week, it rose up 400,000 and now we've hit a million. But the more donors that participate, the more science we're able to do."
Voelz and the other scientists behind Folding@home are using these vast resources to model the ever-changing shapes of the coronavirus's proteins, in the hopes of identifying vulnerabilities or 'pockets' in its structure that can be targeted with new drugs.
One of the reasons it's difficult to find treatments for viruses like COVID-19 and Ebola is because the proteins, the innate building blocks of the viral structure, have notoriously smooth surfaces, making it hard for drugs to bind to them.
But viral proteins don't stay still. They are constantly evolving and changing shape as the atoms within push and pull against each other. Having a supercomputer enables scientists to simulate all these different shapes, revealing potential weaknesses which were not immediately visible. And the more powerful the supercomputer, the faster these simulations can happen.
"Simulating these protein motions also enables us to answer basic questions such as what makes this new coronavirus strain different from previous strains," said Voelz. "Is there something about the dynamics of these proteins that makes it more virulent?"
Finding a genuinely novel drug for COVID-19 is particularly critical.
Once they have identified suitable pockets within the proteins of COVID-19, the Folding@home scientists can then take the many compounds being identified by chemists around the world as potential drugs, and try to predict which ones will stand the best chance of binding to those pockets and inhibiting the virus's ability to invade and take over human cells.
"We have so much bandwidth now with Folding@home that we really think we can make a dent with screening these, and prioritizing which compounds are then going to get experimentally tested," said Voeltz.
The team are particularly hopeful they can succeed, having already used the supercomputer to identify a new vulnerability in the Ebola virus, which could go on to yield a new treatment for the disease.
Finding a genuinely novel drug for COVID-19 is particularly critical. While researchers are also looking at repurposing existing medications, like the antimalarials Hydroxychloroquine and Chloroquine (which have just been approved by the FDA for emergency use in coronavirus patients), concerns remain about the safety of these treatments. Researchers at the Mayo Clinic recently warned that the use of these drugs could have the side effect of inducing heart problems and run the risk of sudden cardiac arrest.
But with the death toll increasing by the day, speed is of the essence. Voelz explains that the scientific community has been left playing catch-up, because a drug was never actually developed for the original SARS outbreak in the early 2000s. The enormous computational power of the Folding@home project has the potential to allow scientists to quickly answer some of the key questions needed to get a new treatment into the pipeline.
"We don't have a SARS drug for whatever reason," said Voelz. "So the missing ingredient really, is the basic science to reveal possible drug targets and then the pharma can take that information and do the engineering work and optimizing and clinically testing drugs. But we now have a lot of basic science going on in response to this pandemic."