What’s the new way to ask big questions in science?

Parkinson’s Voice Initiative founder and TEDMED 2013 speaker Max Little is an applied mathematician whose goal is to “see connections between subjects, not boundaries…to see how things are related, not how they are different” – which gives him an unusual perspective on how big data could change medicine. We  interviewed him via e-mail to find out more.

You’ve been working to discover the practical value of abstract patterns in various fields, with surprising results in areas as varied as diagnosing Parkinson’s disease over the phone to predicting the weather. Can you explain your approach?

Max Little

Max Little

As an applied mathematician, my training shows me patterns everywhere. Electricity flows like water in pipes, and flocks of birds behave like turbulent fluids. In my projects, I collate mathematical models from across disciplines, ignoring the assumptions of that discipline to a large extent, I put in overly simple models. I use artificial intelligence to throw out inaccurate models. And this approach of exploiting abstract patterns has been surprisingly successful.

For example, during my PhD I stumbled across the rather niche discipline of biomedical voice analysis, originating in 1940′s clinical work. With some new mathematical methods, and combining these with recent mathematics in artificial intelligence, I was able to make accurate medical predictions about voice problems. The clinician’s methods were not accurate. This sparked off research in detecting Parkinson’s disease from voice recordings – the basis of the Parkinson’s Voice Initiative.

But, success like this raises suspicions. So, with collaborators, I tried to make this approach fail. We assembled 30,000 data sets across a wide range of disciplines: exploration geophysics, finance, seismology, hydrology, astrophysics, space science, acoustics, biomedicine, molecular biology, meteorology and others. We wrote software for 9,000 mathematical models from a deep dive into the literature. We exhaustively applied each model to each data set.

When finished, a very revealing, big picture emerged. We found that many problems across the sciences could be accurately solved in this way. In many cases, the best models were not the ones that would be suggested by prevailing, disciplinary wisdom.

Are you doing other research that might have implications for clinical diagnosis?

Here is another example: There is a decades-old problem in biomedical engineering: automatically identifying epileptic seizures from EEG recordings. But, we found over 150 models, some exceedingly simple, each of which, alone, could detect seizures with high accuracy.

Empirical

This challenges quite a few assumptions – but it is not as if we are the first to find this. It happens often when new approaches to address old problems are attempted: for example, in obesity, a new, simple mathematical model revealed some surprising relationships about weight and diet.

You’ve also used fairly simple algorithms to successfully predict weather.

After my PhD, I teamed up with a hydrologist and an economist. We wanted to try weather forecasting using some fairly simple mathematics applied to rainfall data. Now, weather forecasting throws $10m-supercomputers and ranks of atmospheric scientists together, and they crunch the equations of the atmosphere to make predictions. So, competing against this Goliath with only historical data and a laptop would seem foolhardy.

But after two years of hard work, I came up with mathematics that, when fed with rainfall data, could make predictions often as accurate as weather supercomputers. We even discovered that models as simple as calculating the historical average rainfall, and using this as a forecast, were sometimes more accurate than supercomputers. We were all surprised. but this finding seems to line up with results that others have found in climate science: it is actually possible to make forecasts of future global temperatures using simple statistical models that are as accurate as far more complex, general circulation models relied upon by the Intergovernmental Panel on Climate Change.

Is this a new way of doing science?

If we divide science into three branches: experiment, theory and computer simulation, then what I am describing here doesn’t quite fit. These are not just simulations: the results are entirely reproducible with just the data and the mathematics. This approach mixes and matches models and data across disciplines, using recent advances in artificial intelligence.

The three branches of science. What happens when we add computational algorithms to the mix?

The three branches of science. What happens when we add computational algorithms to the mix?

I don’t know what to call this approach, but I’m not the only one doing it. The most enthusiastic proponents are computer scientists, who do something like this regularly in mass-scale video analysis competitions or one-off prizes financed by big pharma for molecular drug discovery as do statisticians working in forecasting.

In your TEDMED talk, you expressed concern that advances in science have stagnated. Can you explain?

Like many scientists, I’m concerned that science is becoming too fragmented. So many scientific papers are published each year that it is impossible to keep track of most new findings. Since most articles are never read, much new research has never been independently tested.

And, unfortunately, scientists are encouraged to ‘hyper-specialize’, working only in their narrow disciplines. It is alien to we applied mathematicians that a scientist who studies animal behavior might never read a scientific paper on fluid mechanics!  In isolation from each other, could they just be duplicating each other’s mistakes?

Max Little at TEDMED 2013

What can we do to create a more unified approach?

First of all, open up the data. There is far too much politics, bureaucracy and lack of vision in sharing data among researchers and the public. Sharing data is the key to eliminating the lack of reproducibility that is becoming a serious issue. Second, don’t pre-judge. We need to have a renewed commitment to radical impartiality. Too often, favoured theories, models, or data persist (sometimes for decades), putting whole disciplines at risk of missing the forest for the trees.

More collaboration would also greatly speed advances. Is first-to-publish attribution of scientific findings really that productive? I think of science as a collaborative journey of discovery, not a competition sport of lone geniuses and their teams.

Scientific theories that can withstand this “challenge” from other disciplines will have passed a very rigorous test. Not only will they be good explanatory theories, they will have practical, predictive power. And this is important because without this mixing of disciplinary knowledge, we will never know if science is really making progress, or merely rediscovering the same findings, time and again.

Follow Max Little @MaxALittle.

 

 

Can we paint a personal health picture from our daily digital traces?

We leave a long trail of digital breadcrumbs every day as we go about even the most mundane tasks: Answering e-mail; making phone calls; using GPS to find a post office; shopping for dinner; tracking our sleep and steps with a Fitbit.

Data collected from search engines, social networks, and mobile carriers, combined with smart apps, can turn these tracks into a continuous, real-time picture of our personal health, said Deborah Estrin, co-founder of the non-profit open software builder Open mHealth and a professor of Computer Science at Cornell Tech, speaking at TEDMED 2013 in April.

“I’m not taking about doing detailed medical diagnosis…replacing the communication  between you and your doctor and with your loved ones or even your own self-awareness. I’m talking about enhancing each of these with personalized, data-driven insights…such as early warning signs of a problem or gradual improvement in response to a treatment,” she said.

She continued, “I like to think of it as a digital social pulse, because it’s a single measure that I can look at over time that represents my well being, and social because it’s something I can selectively share with a small number of friends and family. Once we as patients can get access to our small traces — our small data — we’ll be able to fuel a new market of apps and services,” she said.

Though our daily behaviors are already monitored and analyzed extensively, the results are unavailable to users and there’s no vehicle to make them accessible, Estrin said in an interview today.

“There’s nothing lost by letting an individual have their data back, and having them do things that are useful with it,” she said. “It simply plays into having people manage their lives and their health and welfare. Imagine the utility that I will get out of an app that helps me figure out whether I’m taking supplements in an effective dose or not, or helps me monitor a my kid whose going away to college who has a complicated health issue.”

Though Estrin co-founded Open mHealth in 2011, the group is already working on a number of initiatives, including a web app called ClinVis that trends subjective units of depression (SUD) scores. Estrin is already building a coalition of service providers and app developers for this venture. She’ll meet with a few major phone and network service providers in a few weeks to start a smaller-level “virtual testbed” in New York City. Wikilife, a collaborative that seeks to anonymously collect and share health data to measure the health impact of lifestyle choices and nutritional habits, among other measures, is also considering implementing Open mHealth’s API, she said.

Some carriers are apprehensive about appearing to violate privacy regulations, Estrin acknowledges, but adds, “There is a lot of interest in making sure this is done securely, and receptiveness to the notion of personal data vaults within the cloud. I think that the minute we can prototype an initial viable product and a couple of feeds and let people come together and run some apps, we’ll see a lot of uptake,” she says.

The apps will be built on an open-source development platform, which dovetails with the project’s goal of shared knowledge.

“Part of the story of small data is having it happen in an open architecture content because you can then build upon each other’s skills. You’re not counting on any one vendor to build the system, and you get a very exciting Internet economy,” Estrin says.

Watch her talk at TEDMED 2013, and click here if you’re interested in a compilation of your own small data.

Deborah Estrin at TEDMED 2013

How did the world’s most quantified man diagnose his own illness?

We’re drowning in health information on all fronts with very little guidance on how to make sense of it. How can we go about finding clarity and seeing sensible patterns in a morass of data?

Larry Smarr, perhaps the world’s most-quantified man, chronicled his bodily input and output in minute detail for months. He used the resulting mountains of microbiotic data — and a supercomputer — to self-diagnose a gastrointestinal illness, much to the discomfort of his doctor, who told him, “that’s science, not medicine.”  Still, Smarr may well be the patient of the future. Watch him tell his tale at TEDMED 2013.

Larry Smarr at TEDMED 2013

David Agus: Why we don’t “get” cancer

With the recent news about Angelina Jolie’s double mastectomy due to a faulty gene, cancer prevention — and the lengths to which it should go — became an even hotter topic in healthcare, grabbing at least 15 minutes of frenzied public attention about genetic testing and breast cancer.

Jay Walker, left, with David Agus at TEDMED 2013. Photo: Jerod Harris/TEDMED

Jay Walker, left, with David Agus at TEDMED 2013. Photo: Jerod Harris/TEDMED

Cancer took center stage at TEDMED 2013, too, as physician and author David Agus joined TEDMED curator Jay Walker to explain, as Agus told us today, why “cancer is not something the body gets, it’s something the body does.”  In other words, most of us are living with cancerous cells at any given time; it’s our body’s environment that decides whether they will multiply and flourish into disease.

“Anglelina Jolie doesn’t have cancer, and the BRCA1 mutation doesn’t cause cancer. It makes your cells more susceptible to getting these mutations that cause cancer,” he said. “What this is telling us is that her body has a systems issue.”

Agus is in favor of widespread genetic testing, particularly in cases of a family history, but in context.

“We’re in favor of getting all the information we can to help make decisions. Not that everyone should go out and have preventive mastectomies; BRCA1 mutations only cause 5 to 10 percent of all breast cancers. This is a small piece of the puzzle of information, but it’s an important piece,” he says.

What testing can do for us, he says, is help influence daily behavior.

“We’re not good at thinking about tomorrow, we’re only good about thinking about today. So if knowing your information changes how you live your life — whether you’re sedentary, whether you smoke or not, what you eat, how much you sleep – it’s still a major win.”

Agus talked more about the issue on CBS Today and yesterday published an op-ed in the New York Times about the cost of a gene test. He spoke at TEDMED 2011 about redefining cancer.

Video: Rafael Yuste climbs the Everest of science

A complete map of our brain activity is the “Everest of science,” says Rafael Yuste, who helped conceive of Obama’s Brain Research Through Advancing Innovative Neurotechnologies (BRAIN) Initiative as a first attempt at scaling it. (Click here for details of President Obama’s announcement.)

At TEDMED 2013, Yuste discussed why the initiative is critical to advancing neural knowledge.

Rafael Yuste at TEDMED 2013