Download Research Tools
Millions of people worldwide live with type 1 diabetes, a potentially devastating disease with no known cure. People who have type 1 diabetes do not produce insulin in their pancreas, so they must constantly monitor their blood sugar levels while balancing food intake against insulin intake. It’s a mentally taxing, painful process that must be repeated throughout the day.
A collaboration between Associate Professor Babak Parviz at the University of Washington (UW) and Microsoft Senior Researcher Desney Tan is focused on developing a non-invasive, technological solution that promises to improve both the health and overall quality of life for people with diabetes: a contact lens that monitors blood glucose levels. The functional lens technology is representative of a trend in technology known as Natural User Interface (NUI).
NUI technology has the potential to provide user benefits without being obvious to others or intrusive to the user. We believe it has tremendous potential in the healthcare industry, where technology is a necessary, but not always pleasant, part of a patient’s diagnosis or care. The functional contact lens is an excellent example of how NUI can change patient monitoring from “snapshots” of information to continuous health monitoring that could potentially improve the wearer’s overall health—especially for those with a chronic disease, such as diabetes.
Today, people with type 1 diabetes use needles to draw blood from their fingers multiple times throughout the day—every day, including meal times—to check their blood glucose levels. By monitoring their glucose levels, they can more easily ensure that they maintain an acceptable glucose level, which is critical to optimal health and longevity for diabetes patients.
The Daily Impact of Diabetes
Daily, repeated blood draws are a painful necessity for people with diabetes. This process has limitations because the monitoring is only periodic. Diabetics may experience glucose fluctuations that require correction—for example, by increasing insulin intake or eating a piece of candy to raise their blood sugar level—anytime of the day. Regular glucose monitoring, in addition to sensible dietary choices, are part of daily life for Kevin McFeely, who was diagnosed with type 1 diabetes 30 years ago, and his two young children, who also have diabetes.
“If I don’t check my blood sugar, or my children don’t check their blood sugar daily, there are some different things that could potentially happen,” he explained. “If my blood sugar gets too high, I have noticed that my vision begins to blur, I begin feeling nauseous, very, very tired, and just almost physically sick. And potentially, if I let that go, I could pass out from having high blood glucose.”
Low blood sugar also presents a danger to people with diabetes. If glucose falls too low, a diabetic may begin to sweat, suffer an elevated heart rate, and potentially lose consciousness. So it is critical that diabetics monitor their blood glucose on a regular basis throughout the day. McFeely’s children, who are ages seven and ten, are responsible for managing their disease and monitoring themselves at school throughout the day.
“I’m used to testing myself six to eight times per day. I’ve been doing it for 30 years,” McFeely says. “But boy, when I think about my children… I mean, you have a spring-loaded needle that’s coming into your finger, and it hurts them. I can see their faces [when they test], and I can see them cringe.”
A New Approach to Monitoring Health
As envisioned, the lens would be worn daily, just like regular contact lenses. But instead of, or in addition to, correcting vision, the lens would monitor the wearer’s glucose level through their tears. Much of the information that can be obtained through blood testing is also accessible on the surface of the eye. The functional lens is being designed to sample eye fluid, analyze it, and transmit the information to a reporting machine. A tiny radio transmitter embedded in the lens will handle the information transfer.
Parviz’s team at UW has built a variety of contact lenses with small radios and antennas built in, enabling them to draw power as well as send and receive information through radio frequencies. Also, the UW team has been able to place a glucose sensor on the contact lens and demonstrate that it can detect glucose at levels that are found in the tear film. The goal is to unite these elements to develop a contact lens that constantly monitors the blood glucose level and records information that can be accessed later by the patient’s doctor.
McFeely is hopeful that technology, like the functional contact lens, can improve the monitoring and care options available to his children. “Thinking about the functional contact lens for my children who are both type 1 diabetic—I think that would be incredible,” he said. “Given that my children are diagnosed at such a young age, it does have the potential to help them live a longer, healthier life.”
Visualizing Future Applications
Ideally, the lens will do more than just record information. The UW team envisions a way to automatically display important information—including abnormal glucose or insulin alerts—in the lens wearer’s view. It could alert the wearer when they should stop eating due to glucose levels, or remind them when it’s time to get a snack. This real-time feedback would empower the user to react quickly, avoiding health-threatening or uncomfortable episodes. The visual information would be dormant the rest of the time, adhering to the NUI idea of being unobtrusive until needed.
Once fully developed, the technology could be used to replace virtually any screening or diagnostics that currently depend upon blood draws. Additionally, the researchers who are involved in the project envision a future in which contact lenses deliver medicine directly into the bloodstream through the cornea.
—Kristin Tolle, Director, Natural User Interface, Microsoft Research Connections
In June 2011, Microsoft released Debugger Canvas on DevLabs, the result of a year-long collaboration between Microsoft Research, the Microsoft Visual Studio product team, and Brown University. Debugger Canvas transforms how software developers use and experience their programming environments.
In a traditional programming environment, a developer views code like most people view the web: by hopping from document to document, following link after link, with many documents opened in tabs across the top of the screen. Just like hyperactive web surfers, developers often get “lost in the tabs,” struggling to find (and re-find!) information that is relevant to their tasks. Debugger Canvas replaces these tabbed documents with a pan-and-zoom presentation of the specific source code that is relevant to the task. This keeps all of the necessary pieces together in one place, eliminating a lot of disorienting navigation steps.
Debugger Canvas is the result of a bit of serendipity. At last summer’s International Conference on Software Engineering, two separate teams—one from Microsoft Research and one from Brown University—each presented a paper about redesigning programming environments. The two teams quickly discovered each other, found many points of overlap between their designs, and decided to join forces and combine the best of both designs. With support from Microsoft Research Connections, we pulled together a team from Microsoft Research, Brown University, and the Visual Studio product team. The goal was to create a “power tool” (that is, an experimental extension) for Visual Studio that enables professional developers across the world to try out these new ideas. The result: Debugger Canvas.
The initial public reaction to Debugger Canvas has been overwhelmingly positive both on Twitter and in the comments area of blog posts that are discussing the tool. (One of my favorite tweets: “Thank you Debugger Canvas http://bit.ly/ls7zgn I found the error in secs after I installed you.”)
Up next: the collaborative team is currently adding enhancements based on user feedback, as well as scheduling interviews with active users to learn how they are using the tool. That feedback, plus other input and personal observations, will inform our next release of the tool.
—Arjmand Samuel, Research Program Manager, Microsoft Research Connections, and Rob Deline, Principal Researcher, Microsoft Research
Ever mistype your query in a search engine? Or just flat out misspell it? Of course you have—we all do, especially when our search involves “spelling demons” like minuscule, millennium, or embarrassment. Or personal names: believe it or not, there are more than 500 ways that Britney Spears has been misspelled on the web. Misspellings and typos make it difficult for search engines to give users the best results.
Better spelling algorithms can get users to the information they seek, without their having to carry around a dictionary or scroll through several pages of results. Quality spelling algorithms become even more relevant when the searcher is using a smartphone, as it is difficult to browse through page after page of results on those tinier screens.
With this in mind, Microsoft Research and Microsoft Bing launched the Speller Challenge, encouraging participants worldwide to compete in creating a spelling algorithm that generates the most plausible alternatives for web search queries. Participants were able to access real-world data at web scale by using the Microsoft Research Web N-gram Services. Moreover, participants were able to improve their algorithm and see how it compared to other spelling correction systems by using an evaluation service that we made available to them.
More than 300 participants registered for the Speller Challenge, representing every continent (well almost; no one actually registered from Antarctica) and including researchers from academia, research laboratories, and industry. Winners were automatically selected, based on how well their system performed with respect to figuring out the best spelling alternatives (for example, “Britney Spears” for “briteny spears”). On Tuesday, July 19, we hosted a workshop at Bing headquarters, where Harry Shum, corporate vice president of Bing, presented the winners their prizes. Congratulations to everyone who took part in the program:
Finally, here are a few remarks from first-place winner Gord Lueck:
“Microsoft has been a leader in offering visibility into search data for research purposes. Big data is the driver of many of the tools that make the Internet useful. Through Microsoft, some of that data is now available to the community at large to build up and design algorithms with. It’s this generosity and openness that has allowed many independent researchers, such as myself, to design a high quality software product that leverages these valuable data.
“A very good quality dataset for training was given to the researchers, providing a benchmark against which to compare their work in near real-time against other researchers in the same field. This quick feedback cycle undoubtedly helps to accelerate the pace of research beyond that which might have occurred in an environment where data and methods are hoarded and protected.”
Gord also noted that the competition focused on U.S. English spellings, pointing out that “it would have been nice to see some more variety in input languages and grammars.” Sounds like an idea for another contest!
—Evelyne Viegas, Director of Semantic Computing, Microsoft Research Connections