Watch: Soft CGM Beta, Week 3

At Daibetter, formerly Tempo Health, LLC, we’re in the third week of our beta test, where 11 users are regularly using the Soft CGM diabetes management app. We’ve looked at some of the results from user data in the previous weeks, and our accuracy levels show great promise. We’re making great progress towards a non-invasive continuous glucose monitor powered solely by the Internet of Things and user inputs.

When it comes to predicting blood glucose levels without invasive sensors, no model is perfect. But with Soft CGM, each model is personalized. In this week’s Inside Aspire, we explore Soft CGM’s innovative approach to blood sugar predictions. Using multiple adaptive algorithms to provide personalized models according to each user, Soft CGM scores algorithms based on accuracy for each user and then selects the top performer each day for optimized, personal results.

News from the CEO: AI’s Big Leap Forward is Personalization

Here at Aspire we’re always talking about the immense impact artificial intelligence will have on nearly every industry, especially healthcare. We also talk a lot about our AI technology, A2I—our propriety system that makes AI more adaptable and more personalized.

When it comes to finding revolutionary uses for AI technology, we think A2I will be a game changer. That’s why many of our ventures are using A2I to enhance their products with personalization that’s on a whole other level.

But what is A2I and how does it work? Well, our CEO Essam Abadir lays out the answer along with some potential applications in a new blog post that you can read here.

Physical Therapists, We Need Your Feedback!

Physical therapists in the Lancaster area, here’s your chance to see the future of physical therapy technology!

If you’re available tomorrow – Friday, May 27th – between 9:30AM-2:00PM, Aspire Ventures will be demonstrating a concept product, featuring gamified physical therapy delivered via mobile devices.

This potential product integrates several of the coolest technologies within the Aspire universe, and we’d love to get your feedback!

If you’re a PT and you’re available tomorrow, please drop an email to Marcus Grimm, CMO, at

Demo and interviews will take place at our downtown Lancaster office: 100 N. Queen St., Suite 300, Lancaster, PA.

For Daibetter, formerly Tempo Health, LLC, it’s About More than Just the Data

We talk about data a lot at Aspire. And why not? It’s the fuel that A2I uses to produce better results for all of our ventures. Without data, we’ve got nothing.

But it’s really important to realize that the data represents something much bigger. In the case of Daibetter*, it represents the lives of the people with diabetes. Being one of those people myself, it’s a little easier for me to see this. But even so, like everyone, I think of diabetes in the context of what it means to me, and everyone is different.

I was reminded of this when I had the opportunity to speak at Centerville Elementary School as part of a fundraising effort for JDRF. I was joined by Luke and Sabrina, two former students at the school, as well as Lee Hawley, former pro soccer player and current teacher in the school district. All of us have T1d, but for each of us, the disease and its impacts on us are different.

Diabetes truly is as unique as the people afflicted by it, and that’s why I’m encouraged by the Daibetter* approach. We have some more work to do to realize our vision of personalized blood glucose management, but when you’re surrounded by such a diverse group of people – all with T1d – it’s hard to conclude that anything but a personal approach is what will work in the long run.

*Daibetter, formerly Tempo Health, LLC

Healthcare is Ready for Tech Disruption

Technology has transformed nearly every industry—from retail, to transportation, to telecommunication—causing paradigm shifts that give consumers more power, more convenience, and lower costs. Yet the one industry that’s most central to our well-being remains stubbornly unchanged by technological progress. Healthcare, at it’s core, isn’t keeping up with innovation. Even though new technologies are appearing all of the time, none of them are working together to make a real difference in the care continuum. 

Industry experts, investors, and technologists (including leadership here at Aspire) have been calling for a technological revolution in healthcare—one that fully integrates new technologies in a holistic way to improve outcomes and prevent disease; one that fundamentally changes the patient experience with mobile and IoT; and one that uses big data and AI to streamline operations and lower cost. 

Now, doctors are also joining the chorus in the call for change.

In an excellent article in Tech Crunch, precision-medicine physician Florence Comite calls for a “Silicon Valley-style overhaul” of healthcare, and she explores the myriad reasons why we haven’t done so yet.

“Why is the nation’s $3 trillion creaky, monstrous and convoluted healthcare sector seemingly impervious to technological change?” Comite asks.

Innovation silos, incomplete understanding of human biology, and a massive, complex system of providers, patients, payers, and vendors have thus far prevented healthcare from keeping up. Add that to strict regulation, low profit margins, and overworked physicians who are too busy taking care of people to rethink new ways to integrate technology, and we have a recipe for stagnation, Comite concludes.

But Comite finds reason for optimism. Investors, researchers, and physicians are all beginning to coalesce to find a solution. And with more and more great minds addressing the challenge, there are sure to be breakthroughs that will extend throughout our lifetime.

Already, we’re beginning to see where the puzzle pieces fit. As AI technology advances by leaps and bounds, doctors are realizing the immense role it could play in making sense of the ever growing sea of information.

In his blog The Medical Futurist, Dr. Bertalan Mesko lists the many ways AI could be applied to healthcare to make him a more effective doctor. Ultimately, Mesko writes, empathy and communication are the most important factors to delivering better care, but as the amount of medical information explodes, it’s becoming humanly impossible to keep up with data and also have sufficient time for each patient. Mesko writes that the assistance of AI would free him as a doctor to spend more time with his patients.

Mesko lays out how AI could be used to eradicate wait times, help doctors quickly find the information they need, handle administrative tasks, improve doctor/patient communication, and encourage more collaboration.

But before AI can be truly useful to doctors, it will need access to data. And currently, no one is sharing it.

At the Health Datapalooza in Washington DC last week, Vice President Joe Biden pleaded with researchers and healthcare professionals to break down silos and begin sharing data more openly to advance research. If technology platforms can’t talk to each other, or if researchers don’t share their data, making accurate assessments is difficult, no matter how powerful the intelligence—human, artificial, or otherwise.

As important technologies like AI, predictive analytics, cloud computing, IoT, and mobile reach maturity, the key players in the healthcare space are all beginning to recognize how those technologies could be applied to revolutionize healthcare. It’s just a matter of willpower, along with some creativity, to bring it all together within the healthcare continuum. As the writer William Gibson famously said, “The future is already here—it’s just not evenly distributed.”

Watch: How Accurate is Soft CGM?

Over at Daibetter, formerly Tempo Health, LLC, we’ve reached the mid-point of the Soft CGM beta. Eleven users in the US and Canada continue to use our app that we believe when complete will be a non-invasive continuous glucose monitor powered by the Internet of Things.

The easiest way to think about Soft CGM is that it’s really two products in one. There’s the “app experience,” which can be described simply as how easy and attractive the app is to use. But then there’s also the efficacy of the app – how well it actually works, and that’s what we’re going to talk about this week.

There are two ways we are monitoring the effectiveness of the app. The first is MARD, or how close the app’s prediction is to actual BG. The first CGMs approved by the FDA had MARDs around 80%. With Soft CGM, we’re seeing overall scores as high as 72% currently. This is similar to my own experience as an alpha user last month.

The second tool to measure accuracy is the Clarke Error Grid. Here’s a video describing what it is and how we’re looking at the results for Soft CGM. In the video, we show that overall results have us inside zones A and B 87% of the time. That said, this is an area that varies widely by user, with some beta users scoring into the mid-90s.

The results have been fascinating and our developers are already implementing changes to improve the performance of the app on the next beta, currently scheduled by June.

Aspire CEO Essam Abadir Weighs In

If you’ve been following our blog at Aspire Ventures, you know we’re doing a lot of great things with exceptional technologies to help change the world. Now we’re excited to announce the latest addition to our newsroom that will give even more insight to our readers. 

Aspire CEO Essam Abadir has been burning the midnight oil. In a new CEO blog, Essam will weigh in with the big picture at Aspire each week. His first post is an introduction to the Aspire mission, our methodology, and our technology. You can find the first post here, and stay tuned for more.

MedStatix Leading Conversation on Patient Satisfaction

MedStatix, an Aspire venture, was featured today on athenahealth’s blog, CloudView, with a great post from MedStatix CEO Kim Ireland about the importance of measuring patient satisfaction. Asking patients for feedback and measuring satisfaction is a great starting point for building patient engagement, improving health outcomes, and ensuring the financial health of a medical practice.

MedStatix recently partnered with athenahealth to offer a freemium version of their patient satisfaction platform to athenaOne members, a client base of more than 50,000 providers. The new partnership will greatly increase the reach of the MedStatix platform to providers nationwide. As patient engagement and patient feedback become ever more important in today’s healthcare industry, we’re proud that MedStatix is helping to lead the way. 

Watch: Soft CGM Beta Test Yields Promising New Data

Now that we’re well into the 2nd week of beta testing our Soft CGM application, we’re finally getting to see some new data from external users on the app’s performance; and for our developers and data scientists in the venture lab, it’s a little bit like Christmas morning. Following a month-long alpha test with internal users, 11 type 1 diabetes patients outside of Aspire have been using the diabetes management tool on their phones every day, inputting finger stick, carbohydrate, and insulin data to get blood glucose predictions. And for just one week of use, those predictions are looking pretty accurate.

Our Senior Software Engineer Jason Hertzog created a great data visualization tool that lets us compare each user’s Soft CGM blood glucose predictions with their actual blood glucose level, along with all of their finger stick, carbohydrate, and insulin data inputs throughout the day. In this video, a small sample of data shows just how accurately Soft CGM can predict glucose levels, even when we’re looking ahead four hours into the future. Without invasive sensors or expensive hardware, our adaptive algorithm can achieve predictions that are nearly as accurate as a traditional CGM. But there is still plenty of room for improvement, as a few predictions miss the mark. 

Overall, out of 468 predictions made for our beta users so far, 85 percent of the predictions fall within zones A and B of the Clarke Error Grid. That means that 85 percent of Soft CGM’s predictions would lead to appropriate treatment. We will be addressing areas of improvement over the coming weeks with new operational features and a new model to include in our adaptive algorithm, which should greatly improve our results in the future. 

Now that Soft CGM is finally in the hands of a few T1D’s, we’re getting extremely valuable data and feedback that will help us fine tune our models, improve accuracy, and enhance the personalized user experience. As data pours in over the next several weeks, we’re very excited to learn more ways we can refine this truly innovative approach to diabetes management. Stay tuned for more updates.

Medical Errors Third Leading Cause of Death in the U.S.

In the national debate over how to improve healthcare in the U.S., experts often focus on topics like the rising costs of care, baffling pricing structures, or long wait times. But according to

headlines last week,

the consequences of healthcare’s shortcomings are far more serious than a long wait at the doctor’s office. 

A recent report published in the British Medical Journal reaches the alarming conclusion that medical errors are the number 3 cause of death in the U.S., after heart disease and cancer. The report estimates that at least 250,000 people die a year from blunders in care at hospitals. The authors also guess that the number underestimates the actual toll because it doesn’t include deaths surgery centers, nursing homes, or other healthcare settings. 

Clearly, we have some room for improvement. Upgrading healthcare IT networks to standardize and centralize patient data without disrupting workflows; using machine learning and predictive analytics to make better use of that data; improving doctor/patient communication with mobile technology and the IoT; and delivering patient-centered care to keep patients actively involved in their healthcare are just a few ways that we can seriously reduce errors and improve outcomes.

Although some of those changes will require major cultural shifts, the right technologies can transform culture so rapidly that we hardly realize it’s happened until long after the fact. And while some think it’s a long road ahead to change healthcare, here at Aspire we believe the future is much closer than it appears.

Mark Zuckerberg Thinks We Might Be On To Something

Over at Forbes there’s nice coverage of Mark Zuckerberg’s recent speech hinting at the power of AI to transform healthcare. In addition, the article suggests that the market for AI powered solutions could reach $40 billion by 2020, and that this type of technology may power 50% of all apps.

The article references a powerful dermatology solutions called DermaCompare that we’ve had the pleasure to review at Aspire. Here’s a video giving you a peek under the hood of this technology that can spot dysplastic lesions before they become melanoma.