“small data, N=me, Digital Traces”
Deborah Estrin, presented at TEDMED 2013 - more info and video
“We will be hearing a lot about how Big Data, Genomics, and smart devices are going to transform medicine -- and they will -- but there is another force that's going to change the way in which we think about and practice health, and that's small data.
My story is about small data derived from our individual digital traces; it's about the picture of your own health over time generated by a new kind of app running in the cloud that could continuously and privately analyze the digital traces you leave behind as you work, shop, sleep, eat, exercise, and communicate. While there are personal devices specifically designed for self-tracking (Fitbits and such), what I want to focus on is a much broader set of data that we generate every day, implicitly.
We generate these data because most of us mediate or at least accompany our lives with mobile technologies. As a result, we all leave a “trail of breadcrumbs” behind us with our digital service providers, which together create our digital traces. You all are generating such traces now, as you did this morning when you woke up at your hotel and perhaps read email before you even got out of bed, or when you decided to walk to the meeting instead of jumping in a taxi.
The social networks, search engines, mobile operators, online games, and e-commerce sites that we access every day use these digital traces that we leave behind extensively; they aggregate and analyze our digital traces to target marketing and tailor service offerings and advertisements and to improve system performance.
But none of these services currently think about the value of providing these personal traces back to the person who generated them And consequently, they do not yet have a readymade vehicle to repackage their data about me in a useful format for me and provide it to me!
This broader but highly personalized, data set can be analyzed to draw powerful inferences about my health from my “digital behavior.”
Let me be clear, I am not talking about apps doing detailed medical diagnosis, and I am not talking about replacing the insight and role of doctors or loved ones or the importance of our own self-awareness. It's about greatly enhancing all of those with personalized data-driven insights, insights such as early warning signs of a problem, or indicators of gradual improvement. Ginger.io refers to this as a check engine light; I like to think of it as a personalized “social pulse”. A pulse that can indicate subtle but significant changes in a person's wellbeing; and social because you share it with a select set of friends or family.
Once I, as a patient and consumer, can access the data that service providers have about me, I can then use these data to fuel apps that I subscribe to.
Imagine an app that helps my doctor figure out whether the new medication dosage I have been taking for the last two weeks is better for me than the previous dosage. The app could create a comparative picture of my daily function this month relative to last month, by automatically analyzing motion, location, and vocabulary data plucked from my digital traces.
Or, I could see, from an app running over my mobility traces that I get back from AT&T or Verizon, if the supplement I am taking for my early stage arthritis is actually reducing morning stiffness and helping me get out and about more quickly most days; and if overall I am less sedentary than I was previously.
From chronic pain to depression to memory enhancement and Crohn's Disease -- many chronic conditions have a lot of variability day to day, with many confounding factors, and both good and bad changes are gradual. Consequently, it's hard for me as an individual to reliably and precisely track the effect of a new treatment based only on my subjective and selective memory. But these same health conditions have symptoms and side effects that show in our functional, everyday, behaviors -- and for the first time really, our everyday behaviors are becoming data. While that might be disconcerting, it is the case, and what I am arguing for is that we as individuals should be able to mine our own traces for our own purposes. And we can do this for the young and old alike, because while we don't usually think of elders as digital natives, they do increasingly carry cell phones, if only feature phones, and they increasingly use the Internet (if only via their TV) and both feature phones and cable TV boxes are potential sources of digital traces! And, of course, as we become the elders of tomorrow we will carry with us our existing digital practices and addictions into our senior years.
When I think back to my own father's last few months of a life just over a year ago, I can identify signals that indicated that something was wrong, signals that could have shown up in his digital social pulse He suddenly stopped sending email (and this was a man who had been using Email on the Arpanet since the mid 1970s), and his daily patterns gradually changed so that he no longer shopped at the supermarket to prepare food at home, and took shorter and shorter neighborhood walks. His declining condition was not detectable on his regular visits to his cardiologist since it didn't show up in his EKGs, or traditional exchanges about how he felt, and he like others “pulled it together” for his favorite doctor. On an Emergency Room visit one day, the attending doctor observed nothing atypical of a 90 year old man; nothing in his vitals or his Electronic Health Record communicated to that ER doc that this 90 year old man was behaving entirely differently than he was just a few weeks earlier...a social pulse graph, derived from his digital traces, could have. Having access to my father's ‘digital social pulse’, would not have changed the outcome...it was his time...but it would have given us the tools to track these changes and communicate them objectively to members of his medical team.
Fortunately, I have a “real” doctor in the family, my eldest sister Margo, and her insight and vigilance effectively created a social pulse for my father, but most families don't have a ‘Margo’. So, what I am suggesting is that we begin to leverage our small data to bring more vigilance and insight to everyday care. We can think of this as new kind of medical evidence, evidence where n=me, because it complements traditional big-N population studies with data that are just about me (or you) over time. And what is so compelling about this approach, is that these data already exist. It does not require deployment of any new hardware, so we can start leveraging our small, n=me, data now. So, if the raw data are there, what is left to do to make small data and n=ME become the standard of care? First and foremost, I don't in any way want to trivialize the work that will be needed to convert these noisy sources of data into actual insight -- that is where we will see much of the iterative innovation in the coming years. But it won't happen until we can start tapping into our own data.
So our first step has to be what Todd Park refers to as data liberation: we need to liberate our data from mobile and Internet services, to you and me. We need a common (open) architecture so that a rich market of apps and services can grow around our n=me data in the same way that the HTTP standard created the World Wide Web with all its myriad of apps and services.
Admittedly, some service providers are apprehensive about whether customers will be put off once they see how telling their digital traces are, whether it will create a PR nightmare; but the data are already being captured for the most part, and I believe that in the long run consumers will know what is going on anyway; and transparency will lead to a more robust and sustainable basis for privacy.
Assuming we overcome such disincentives, where are the positive incentives for commercial service providers to cooperate and make digital traces available to the individual? I think the economics of the market are on our side. If standard interfaces to personal digital traces spark a cottage industry of app makers who process my small data and put it to work for me, then implicitly they will increase the value of my engagement with those digital services in the same way that mobiles apps greatly increased the value to consumers of smart phones.
Again, it's never as simple as just getting the data. We face technical and design challenges in making sense of that data for the users, and we have regulatory challenges in navigating through FDA, HIPAA and Privacy. But I don't think any of these are non-starters; I think that if we start the flow of n=me data, we can make the right things happen, and in the right way.
So, with my colleagues at Open mHealth and Cornell, we are building prototypes to demonstrate the power of small n=me data, and we are putting together a standard format that service providers, app creators, and science researchers can use to build the applications that will process, fuse, and filter your small data for you.
We’ve put up a website to let all of you tell service providers that we want our digital traces formatted and made available to us -- http://smalldata.tech.cornell.edu You will be the customer for the data about you; I’ll be the customer for the data about me.
Lets get our search engines, social networks and mobile carriers, to start packaging our small data, for us.”go back to the top