Scientists Are Building an “AccuWeather” for Germs to Predict Your Risk of Getting the Flu
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.
Even before the pandemic created a need for more telehealth options, depression was a hot area of research for app developers. Given the high prevalence of depression and its connection to suicidality — especially among today’s teenagers and young adults who grew up with mobile devices, use them often, and experience these conditions with alarming frequency — apps for depression could be not only useful but lifesaving.
“For people who are not depressed, but have been depressed in the past, the apps can be helpful for maintaining positive thinking and behaviors,” said Andrea K. Wittenborn, PhD, director of the Couple and Family Therapy Doctoral Program and a professor in human development and family studies at Michigan State University. “For people who are mildly to severely depressed, apps can be a useful complement to working with a mental health professional.”
Health and fitness apps, in general, number in the hundreds of thousands. These are driving a market expected to reach $102.45 billion by next year. The mobile mental health app market is a small part of this but still sizable at $500 million, with revenues generated through user health insurance, employers, and direct payments from individuals.
Apps can provide data that health professionals cannot gather on their own. People’s constant interaction with smartphones and wearable devices yields data on many health conditions for millions of patients in their natural environments and while they go about their usual activities. Compared with the in-office measurements of weight and blood pressure and the brevity of doctor-patient interactions, the thousands of data points gathered unobtrusively over an extended time period provide a far better and more detailed picture of the person and their health.
At their most advanced level, apps for mental health, including depression, passively gather data on how the user touches and interacts with the mobile device through changes in digital biomarkers that relate to depressive symptoms and other conditions.
Building on three decades of research since early “apps” were used for delivering treatment manuals to health professionals, today’s more than 20,000 mental health apps have a wide range of functionalities and business models. Many of these apps can be useful for depression.
Some apps primarily provide a virtual connection to a group of mental health professionals employed or contracted by the app. Others have options for meditation, sleeping or, in the case of industry leaders Calm and Headspace, overall well-being. On the cutting edge are apps that detect changes in a person’s use of mobile devices and their interactions with them.
Apps such as AbleTo, Happify Health, and Woebot Health focus on cognitive behavioral therapy, a type of counseling with proven potential to change a person’s behaviors and feelings. “CBT has been demonstrated in innumerable studies over the last several decades to be effective in the treatment of behavioral health conditions such as depression and anxiety disorders,” said Dr. Reena Pande, chief medical officer at AbleTo. “CBT is intended to be delivered as a structured intervention incorporating key elements, including behavioral activation and adaptive thinking strategies.”
These CBT skills help break the negative self-talk (rumination) common in patients with depression. They are taught and reinforced by some self-guided apps, using either artificial intelligence or programmed interactions with users. Apps can address loneliness and isolation through connections with others, even when a symptomatic person doesn’t feel like leaving the house.
At their most advanced level, apps for mental health, including depression, passively gather data on how the user touches and interacts with the mobile device through changes in “digital biomarkers” that can be associated with onset or worsening of depressive symptoms and other cognitive conditions. In one study, Mindstrong Health gathered a year’s worth of data on how people use their smartphones, such as scrolling through articles, typing and clicking. Mindstrong, whose founders include former leaders of the National Institutes of Health, modeled the timing and order of these actions to make assessments that correlated closely with gold-standard tests of cognitive function.
National organizations of mental health professionals have been following the expanding number of available apps over the years with keen interest. App Advisor is an initiative of the American Psychiatric Association that helps psychiatrists and other mental health professionals navigate the issues raised by mobile health technology. App Advisor does not rate or recommend particular apps but rather provides guidance about why apps should be assessed and how health professionals can do this.
A website that does review mental health apps is One Mind Psyber Guide, an independent nonprofit that partners with several national organizations. One Mind users can select among numerous search terms for the condition and therapeutic approach of interest. Apps are rated on a five-point scale, with reviews written by professionals in the field.
Do mental health apps related to depression have the kind of safety and effectiveness data required for medications and other medical interventions? Not always — and not often. Yet the overall results have shown early promise, Wittenborn noted.
“Studies that have attempted to detect depression from smartphone and wearable sensors [during a single session] have ranged in accuracy from about 86 to 89 percent,” Wittenborn said. “Studies that tried to predict changes in depression over time have been less accurate, with accuracy ranging from 59 to 85 percent.”
The Food and Drug Administration encourages the development of apps and has approved a few of them—mostly ones used by health professionals—but it is generally “hands off,” according to the American Psychiatric Association. The FDA has published a list of examples of software (including programming of apps) that it does not plan to regulate because they pose low risk to the public. First on the list is software that helps patients with diagnosed psychiatric conditions, including depression, maintain their behavioral coping skills by providing a “Skill of the Day” technique or message.
On its App Advisor site, the American Psychiatric Association says mental health apps can be dangerous or cause harm in multiple ways, such as by providing false information, overstating the app’s therapeutic value, selling personal data without clearly notifying users, and collecting data that isn’t relevant to mental health.
Although there is currently reason for caution, patients may eventually come to expect mental health professionals to recommend apps, especially as their rating systems, features and capabilities expand. Through such apps, patients might experience more and higher quality interactions with their mental health professionals. “Apps will continue to be refined and become more effective through future research,” said Wittenborn. “They will become more integrated into practice over time.”
Podcast: Has the First 150-Year-Old Already Been Born
Steven Austad is a pioneer in the field of aging, with over 200 scientific papers and book chapters on pretty much every aspect of biological aging that you could think of. He’s also a strong believer in the potential for anti-aging therapies, and he puts his money where his mouth is. In 2001, he bet a billion dollars that the first person to reach 150-years-old had already been born. I had a chance to talk with Steven for today’s podcast and asked if he still thinks the bet was a good idea, since the oldest person so far (that we know of), Jeanne Calment, died back in 1997. A few days after our conversation, the oldest person in the world, Kane Tanaka, died at 119.
Steven is the Protective Life Endowed Chair in Health Aging Research, a Distinguished Professor and Chair of the Department of Biology at the University of Alabama Birmingham. He's also Senior Scientific Director of the American Federation for Aging Research, which is managing a groundbreaking longevity research trial that started this year. Steven is also a great science communicator with five books, including one that comes out later this year, Methuselah’s Zoo, and he publishes prolifically in national media outlets.
See the rest of his bio linked below in the show notes.
Listen to the Episode
Listen on Apple | Listen on Spotify | Listen on Stitcher | Listen on Amazon | Listen on Google
Steven Austad is featured in the latest episode of Making Sense of Science. He's a distinguished professor of biology at the University of Alabama Birmingham and has a new book due to be published in August, Methuselah's Zoo.
Photo by Steve Wood
Show notes:
2:36 - Steven explains why a particular opossum convinced him to dedicate his career to studying longevity.
6:48 - Steven's billion dollar bet that someone alive today will make it to 150-years-old.
9:15 - The most likely people to make it to 150 (Hint: not men).
10:38 - I ask Steven about Elon Musk’s comments this month that if people lived a really long time, “we’d be stuck with old ideas and society wouldn’t advance.” Steve isn’t so fond of that take.
13:34 - Why women are winning maybe the most important battle of sexes: staying alive. This is an area that Steven has led research on (see show notes).
18:20 - Why women, on average, actually have more morbidities earlier than men, even though they live longer.
23:10 - How the pandemic could affect sex differences in longevity.
24:55 - How often should people work out and get other physical activity to maximize longevity and health span?
29:09 - Steven gave me the latest update on the TAME trial on metformin, and how he and others longevity experts designed this groundbreaking research on longevity not in their offices, not on a zoom call, but in a castle in the Spanish countryside.
32:10 - Which anti-aging therapies are the most promising at this point for future research.
39:32 - The drug cocktail approach to address multiple hallmarks of aging.
41:00 - How to read health news like a scientist.
45:38 - Should we try a Manhattan project for aging?
48:47 - Can Jeff Bezos and Larry Ellison help us live to 150?
Show links:
Steven Austad's bio
Pre-order Steven's new book, Methuselah's Zoo - https://www.amazon.com/dp/B09M2QGRJR/ref=dp-kindle-redirect?_encoding=UTF8&btkr=1
Steven's journal article on Sex Differences in Lifespan - https://pubmed.ncbi.nlm.nih.gov/27304504/
Elon Musk's comments on super longevity "asphyxiating" society - https://www.cnbc.com/2022/04/11/elon-musk-on-avoid...
Steven's article on how to read news articles about health like a pro - https://www.nextavenue.org/how-to-read-health-news...
AFAR's research on Targeting Aging with Metformin (TAME) - https://www.afar.org/tame-trial