A future app may help you avoid getting the flu by informing you of your local risk on a given day.
Applied mathematician Sara del Valle works at the U.S.'s foremost nuclear weapons lab: Los Alamos. Once colloquially called Atomic City, it's a hidden place 45 minutes into the mountains northwest of Santa Fe. Here, engineers developed the first atomic bomb.
Like AccuWeather, an app for disease prediction could help people alter their behavior to live better lives.
Today, Los Alamos still a small science town, though no longer a secret, nor in the business of building new bombs. Instead, it's tasked with, among other things, keeping the stockpile of nuclear weapons safe and stable: not exploding when they're not supposed to (yes, please) and exploding if someone presses that red button (please, no).
Del Valle, though, doesn't work on any of that. Los Alamos is also interested in other kinds of booms—like the explosion of a contagious disease that could take down a city. Predicting (and, ideally, preventing) such epidemics is del Valle's passion. She hopes to develop an app that's like AccuWeather for germs: It would tell you your chance of getting the flu, or dengue or Zika, in your city on a given day. And like AccuWeather, it could help people alter their behavior to live better lives, whether that means staying home on a snowy morning or washing their hands on a sickness-heavy commute.
Sara del Valle of Los Alamos is working to predict and prevent epidemics using data and machine learning.
Since the beginning of del Valle's career, she's been driven by one thing: using data and predictions to help people behave practically around pathogens. As a kid, she'd always been good at math, but when she found out she could use it to capture the tentacular spread of disease, and not just manipulate abstractions, she was hooked.
When she made her way to Los Alamos, she started looking at what people were doing during outbreaks. Using social media like Twitter, Google search data, and Wikipedia, the team started to sift for trends. Were people talking about hygiene, like hand-washing? Or about being sick? Were they Googling information about mosquitoes? Searching Wikipedia for symptoms? And how did those things correlate with the spread of disease?
It was a new, faster way to think about how pathogens propagate in the real world. Usually, there's a 10- to 14-day lag in the U.S. between when doctors tap numbers into spreadsheets and when that information becomes public. By then, the world has moved on, and so has the disease—to other villages, other victims.
"We found there was a correlation between actual flu incidents in a community and the number of searches online and the number of tweets online," says del Valle. That was when she first let herself dream about a real-time forecast, not a 10-days-later backcast. Del Valle's group—computer scientists, mathematicians, statisticians, economists, public health professionals, epidemiologists, satellite analysis experts—has continued to work on the problem ever since their first Twitter parsing, in 2011.
They've had their share of outbreaks to track. Looking back at the 2009 swine flu pandemic, they saw people buying face masks and paying attention to the cleanliness of their hands. "People were talking about whether or not they needed to cancel their vacation," she says, and also whether pork products—which have nothing to do with swine flu—were safe to buy.
At the latest meeting with all the prediction groups, del Valle's flu models took first and second place.
They watched internet conversations during the measles outbreak in California. "There's a lot of online discussion about anti-vax sentiment, and people trying to convince people to vaccinate children and vice versa," she says.
Today, they work on predicting the spread of Zika, Chikungunya, and dengue fever, as well as the plain old flu. And according to the CDC, that latter effort is going well.
Since 2015, the CDC has run the Epidemic Prediction Initiative, a competition in which teams like de Valle's submit weekly predictions of how raging the flu will be in particular locations, along with other ailments occasionally. Michael Johannson is co-founder and leader of the program, which began with the Dengue Forecasting Project. Its goal, he says, was to predict when dengue cases would blow up, when previously an area just had a low-level baseline of sick people. "You'll get this massive epidemic where all of a sudden, instead of 3,000 to 4,000 cases, you have 20,000 cases," he says. "They kind of come out of nowhere."
But the "kind of" is key: The outbreaks surely come out of somewhere and, if scientists applied research and data the right way, they could forecast the upswing and perhaps dodge a bomb before it hit big-time. Questions about how big, when, and where are also key to the flu.
A big part of these projects is the CDC giving the right researchers access to the right information, and the structure to both forecast useful public-health outcomes and to compare how well the models are doing. The extra information has been great for the Los Alamos effort. "We don't have to call departments and beg for data," says del Valle.
When data isn't available, "proxies"—things like symptom searches, tweets about empty offices, satellite images showing a green, wet, mosquito-friendly landscape—are helpful: You don't have to rely on anyone's health department.
At the latest meeting with all the prediction groups, del Valle's flu models took first and second place. But del Valle wants more than weekly numbers on a government website; she wants that weather-app-inspired fortune-teller, incorporating the many diseases you could get today, standing right where you are. "That's our dream," she says.
This plot shows the the correlations between the online data stream, from Wikipedia, and various infectious diseases in different countries. The results of del Valle's predictive models are shown in brown, while the actual number of cases or illness rates are shown in blue.
(Courtesy del Valle)
The goal isn't to turn you into a germophobic agoraphobe. It's to make you more aware when you do go out. "If you know it's going to rain today, you're more likely to bring an umbrella," del Valle says. "When you go on vacation, you always look at the weather and make sure you bring the appropriate clothing. If you do the same thing for diseases, you think, 'There's Zika spreading in Sao Paulo, so maybe I should bring even more mosquito repellent and bring more long sleeves and pants.'"
They're not there yet (don't hold your breath, but do stop touching your mouth). She estimates it's at least a decade away, but advances in machine learning could accelerate that hypothetical timeline. "We're doing baby steps," says del Valle, starting with the flu in the U.S., dengue in Brazil, and other efforts in Colombia, Ecuador, and Canada. "Going from there to forecasting all diseases around the globe is a long way," she says.
But even AccuWeather started small: One man began predicting weather for a utility company, then helping ski resorts optimize their snowmaking. His influence snowballed, and now private forecasting apps, including AccuWeather's, populate phones across the planet. The company's progression hasn't been without controversy—privacy incursions, inaccuracy of long-term forecasts, fights with the government—but it has continued, for better and for worse.
Disease apps, perhaps spun out of a small, unlikely team at a nuclear-weapons lab, could grow and breed in a similar way. And both the controversies and public-health benefits that may someday spin out of them lie in the future, impossible to predict with certainty.
The Brown family at the Grand Tetons (2019). Clockwise from left, Christine, Kevin, Keagan, Connor, and Kellen.
But Christine Brown knew none of this when the hospital called saying that standard newborn screening of her son Connor had come back positive for PKU. It was urgent that they visit a special metabolic clinic the next day, which was about a three-hour drive away.
“I was told not to go on the Internet,” Christine recalls, “So when somebody tells you not to go on the Internet, what do you do? Even back in 2005, right.” What she saw were the worst examples of retardation, which was a common outcome from PKU before newborn screening became routine. “We were just in complete shell shock, our whole world just kind of shattered and went into a tail spin.”
“I remember feeding him the night before our clinic visit and almost feeling like I was feeding him poison because I knew that breast milk must have protein in it,” she says.
“Some of my first memories are of asking, ‘Mommy, can I eat this? There were yes foods and no foods.'"
Over the next few days the dedicated staff of the metabolic clinic at the Waisman Center at the University of Wisconsin Madison began to walk she and husband Kevin back from that nightmare. They learned that a simple blood test to screen newborns had been developed in the early 1960s to detect PKU and that the condition could be managed with stringent food restrictions and vigilant monitoring of Phe levels.
Everything in Your Mouth Counts
PKU can be successfully managed with a severely restricted diet. That simple statement is factually true, but practically impossible to follow, as it requires slashing protein consumption by about 90 percent. To compensate for the missing protein, several times a day PKU patients take a medical formula – commonly referred to simply as formula – containing forms of proteins that are digestible to their bodies. Several manufacturers now add vitamins and minerals and offer a variety of formats and tastes to make it more consumer friendly, but that wasn't always the case.
“When I was a kid, it tasted horrible, was the consistency of house paint. I didn't think about it, I just drank it. I didn't like it but you get used to it after a while,” recalls Jeff Wolf, the twang of Appalachia still strong in his voice. Now age 50, he grew up in Ashland, Kentucky and was part of the first wave of persons with PKU who were identified at birth as newborn screening was rolled out across the US. He says the options of taste and consistency have improved tremendously over the years.
Some people with PKU are restricted to as little as 8 grams of protein a day from food. That's a handful of almonds or a single hard-boiled egg; a skimpy 4-ounce hamburger and slice of cheese adds up to half of their weekly protein ration. Anything above that daily allowance is more than the body can handle and toxic levels of Phe begin to accumulate in the brain.
“Some of my first memories are of asking, ‘Mommy, can I eat this? There were yes foods and no foods,’” recalls Les Clark. He has never eaten a hamburger, steak, or ribs, practically a sacrilege for someone raised in Stanton, a small town in northeastern Nebraska, a state where the number of cattle and hogs are several-fold those of people.
His grandmother learned how to make low protein bread, but it looked and tasted different. His mom struggled making birthday cakes. “I learned some bad words at a very young age” as mom struggled applying icing that would pull the cake apart or a slice would collapse into a heap of crumbs, Les recalls.
Les Clark with a birthday cake.
Courtesy Clark
Controlling the diet “is not so bad when you are a baby” because that's all you know, says Jerry Vockley, Director of the Center for Rare Disease Therapy at Children's Hospital of Pittsburgh. “But after a while, as you get older and you start tasting other things and you say, Well, gee, this stuff tastes way better than what you're giving me. What's the deal? It becomes harder to maintain the diet.”
First is the lure of forbidden foods as children venture into the community away from the watchful eyes of parents. The support system weakens further when they leave home for college or work. “Pizza was mighty tasty,” Wolf' says of his first slice.
Vockley estimates that about 90 percent of adults with PKU are off of treatment. Moving might mean finding a new metabolic clinic that treats PKU. A lapse in insurance coverage can be a factor. Finally there is plain fatigue from multiple daily dosing of barely tolerable formula, monitoring protein intake, and simply being different in terms of food restrictions. Most people want to fit in and not be defined by their medical condition.
Jeff Wolf was one of those who dropped out in his twenties and thirties. He stopped going to clinic, monitoring his Phe levels, and counting protein. But the earlier experience of living with PKU never completely left the back of his mind; he listened to his body whenever eating too much protein left him with the “fuzzy brain" of a protein hangover. About a decade ago he reconnected with a metabolic clinic, began taking formula and watching his protein intake. He still may go over his allotment for a single day but he tries to compensate on subsequent days so that his Phe levels come back into balance.
Jeff Wolf on a boat.
Courtesy Wolf
One of the trickiest parts of trying to manage phenylalanine intake is the artificial sweetener aspartame. The chemical is ubiquitous in diet and lite foods and drinks. Gum too, you don't even have to swallow to receive a toxic dose of Phe. Most PKUers say it is easier to simply avoid these products entirely rather than try to count their Phe content.
Treatments
Most rare diseases have no treatment. There are two drugs for PKU that provide some benefit to some portion of patients but those drugs often have their own burdens.
KUVAN® (sapropterin dihydrochloride) is a pill or powder that helps correct a protein folding error so that food proteins can be digested. It is approved for most types of PKU in adults and children one month and older, and often is used along with a protein-restricted diet.
“The problem is that it doesn't work for every [patient's genetic] mutation, and there are hundreds of mutations that have been identified with PKU. Two to three percent of patients will have a very dramatic response and if you're one of those small number of patients, it's great,” says Vockley. “If you have one of the other mutation, chances are pretty good you still are going to end up on a restricted diet.”
PALYNZIQ® (pegvaliase-pqpz) “has the potential to lower the Phe to normal levels, it's a real breakthrough in the field,” says Vockley. “But is a very hard drug to use. Most folks have to take either one or two 2ml injections a day of something that is basically a gel, and some individuals have to take three.”
Many PKUers have reactions at the site of the injection and some develop anaphylaxis, a severe potentially life-threatening allergic reaction that can happen within seconds and can occur at any time, even after long term use. Many patients using Palynziq carry an EpiPen, a self-injection devise containing a form of adrenaline that can reverse some of the symptoms of anaphylaxis.
Then there is the cost. With the Kuvan dosing for an adult, “you're talking between $100,000 and $200,000 a year. And Palynziq is three times that,” says Vockley. Insurance coverage through a private plan or a state program is essential. Some state programs provide generous coverage while others are skimpy. Most large insurance company plans cover the drugs, sometimes with significant copays, but companies that are self-insured are under no legal obligation to provide coverage.
Les Clark found that out the hard way when the company he worked for was sold. The new owner was self-insured and declined to continue covering his drugs. Almost immediately he was out of pocket an additional $1500 a month for formula, and that was with a substantial discount through the manufacturer's patient support program. He says, “If you don't have an insurance policy that will cover the formula, it's completely unaffordable.” He quickly began to look for a new job.
Hope
It's easy to see why PKUers are eager for advances that will make managing their condition more effect, easier, and perhaps more affordable. Synlogic's efforts have drawn their attention and raised hopes.
Just before Thanksgiving Jerry Vockley presented the latest data to a metabolism conference meeting in Australia. There were only 8 patients in this group of a phase 2 trial using the original version of the company's lead E. coli product, SYNB1618, but they were intensely studied. Each was given the probiotic and then a challenge meal. Vockley saw a 40% reduction in Phe absorption and later a 20% reduction in mean fasting Phe levels in the blood. The product was easy to use and tolerate.
The company also presented early results for SYNB1934, a follow on version that further genetically tweaked the E. coli to roughly double the capacity to chop up the target proteins. Synlogic is recruiting patients for studies to determine the best dosing, which they are planning for next year.
“It's an exciting approach,” says Lex Cowsert, Director of Research Development at the National PKU Alliance, a nonprofit that supports the patient, family, and research communities involved with PKU. “Every patient is different, every patient has a different tolerance for the type of therapy that they are willing to pursue,” and if it pans out, it will be a welcome addition, either alone or in combination with other approaches, to living with PKU.
Author's Note: Reporting this story was made possible by generous support from the National Press Foundation and the Fondation Ipsen. Thanks to the people who so generously shared their time and stories in speaking with me.
