Mayo Clinic Care Plans to be available on the Wellpepper patient engagement platform

PR Newswire release

Las Vegas, Nevada, March 5, 2018 – Mayo Clinic Global Business Solutions and Wellpepper, Inc. announced today that Mayo Clinic will be providing best practices for interactive care plans on the Wellpepper platform. Wellpepper is a clinically-validated patient engagement platform used by major health systems to improve outcomes and lower costs of care.

Wellpepper customers who use any electronic health record will be able to use Mayo Clinic care plan protocols to help patients follow their physicians’ instructions outside the clinic to self-manage and improve their outcomes.

Mayo Clinic Care Plans will be available through Wellpepper Marketplace, which launches later in the second quarter of 2018. Mayo Clinic Care Plans initially will be available to cardiac rehabilitation, headache and sports medicine patients. The care plans eventually will encompass hundreds of patient interventions showcasing the breadth of Mayo Clinic expertise.

“Wellpepper and Mayo Clinic share a continuous commitment to providing care that ultimately benefits patients,” says Steve Ommen, M.D., interim medical director of  Mayo Clinic Global Business Solutions. “We look forward to the opportunity to share our best practices with other health systems through the Wellpepper platform.”

Wellpepper’s interactive care plans are based on a framework of building blocks that support creating any type of patient instructions. Wellpepper patients are more than 70 percent engaged in their care plans, and control trials conducted by researchers at Boston University and Harvard University show clinically meaningful patient outcomes for patients using the Wellpepper platform.

“We are thrilled to launch the Wellpepper Marketplace starting with one of the leading academic medical centers in the world,” said Wellpepper CEO Anne Weiler. “Our customers and their patients will benefit immensely from access to Mayo Clinic best practices. Analysis of patient experience and outcomes from these care plans will enable continual improvement and new insights to deliver better care.”

The Wellpepper Marketplace will offer health systems the choice of best practice care plan templates from leading health systems and Wellpepper’s out-of-the-box care plan templates. These turnkey solutions will enable quick deployment of evidence-based and clinically-validated care plans to improve patient outcomes.

About Wellpepper 
Wellpepper is a health care technology company with an award-winning and clinically-validated patient engagement platform used by major health systems to improve outcomes and lower costs of care. Wellpepper treatment plans can be customized for each health system’s own protocols and best practices, and personalized for each patient. Wellpepper’s patented adaptive notification system helps drive over 70 percent patient engagement with treatment plans. Wellpepper was founded in 2012 to help healthcare organizations lower costs, improve outcomes and improve patient satisfaction. The company is headquartered in Seattle, Washington.

Media contacts:

Jennifer Allen Newton, Wellpepper, (503)-805-7540,

Rhoda Madson, Mayo Clinic Public Affairs, 507-284-5005,

Posted in: Press Release

Leave a Comment (0) →

HIMSS 2018…See you there!

HIMSS17 in Orlando was a great conference for Wellpepper. We’re looking forward to HIMSS18 in Las Vegas even more!

We have a long list of sessions to attend and booths to visit, but below are some places you’re guaranteed to find us:

Monday, March 5th

  • Hear from Tami Deangelis on how our research partners at Boston University engaged patients outside the clinic and improved outcomes using Wellpepper care plans. She is speaking at the “Remote Patient Messaging for Adherence and Engagement” session from 4:05pm-4:25pm at the Patient Engagement & Experience Summit

Tuesday, March 6th

  • Hall G, Innovation Zone: Booth 9900-78 from 9am-6pm
  • CTO, Mike Van Snellenberg will be demonstrating our voice-powered scale and foot scanner, and integrated diabetes care plan at the Industry Showcase at BHI & BSN 2018

Wednesday, March 7th

  • Hall G, Innovation Zone: Booth 9900-78 from 9am-6pm
  • CEO, Anne Weiler, will be sharing the Wellpepper Vision and Mission at HIMSS VentureConnect
  • CEO, Anne Weiler, will be joining other industry leaders to continue the conversation with CMS toward inclusion of patient engagement and outcomes tracking in the MIPS Improvement Activity for provider reimbursement

Thursday, March 8th

  • Hall G, Innovation Zone: Booth 9900-78 from 9am-4:30pm

We can’t wait to connect with friends, partners, colleagues and industry leaders to continue the journey towards an amazing patient experience. Hope to see you there!

Posted in: Healthcare Disruption, Healthcare Technology, M-health, Outcomes, patient engagement, Uncategorized

Leave a Comment (0) →

Supporting Patient Motivation

What motivates people to improve their health and stay on the right track over time?

This question is on the mind of every practitioner, whether it’s a physician sending someone home with a wound care plan, a nutritionist giving dietary advice to help manage diabetes or a physical therapist providing exercises to get a frozen shoulder moving again. They’re thinking: “Will the patient do it?” To a great extent, the answer to this question determines how successful their treatment plans will be.

Some of this blog’s most popular posts have explored the issue of motivation because it is a major underpinning of patient engagement technology – will the patient use, and stick with, the technology that in turn helps them adhere to their care plans?

The subject of motivation usually starts with a discussion about goal-setting. This process, at least in the medical context, typically begins when the practitioner sets goals for the patient and provides a care plan that tells the patient what they need to do in order to get there. Some practitioners feel this should be motivation enough for a patient. In reality, they know it’s not.

So what is motivation? A great deal of research has gone into the subject, particularly with regard to behavior change. It is most often described as being either extrinsic (outside the individual) or intrinsic (inside the individual). With extrinsic motivation, we engage in a behavior or activity either to gain some sort of external reward or avoid a negative consequence. With intrinsic motivation, we engage in something because we find it personally fun or rewarding.

While these are the two areas most often discussed, there are other, deeper dimensions to motivation, including fear-based and development-based motivators – and these can be either extrinsic or intrinsic. Understanding the interplay among these different forms of motivation is an important element in successful health coaching and in the creation of successful, supportive technologies that assist people in reaching their health goals.

Fear-based motivation comes in two basic flavors: deficiency-based and threat-based. Deficiency-based motivations come from the sense you are lacking in some way. These can have an external, socio-cultural source (just watch any personal care product advertisement: you smell bad, your hair is the wrong color and your teeth aren’t nearly white enough) or an intrinsic source (e.g. internal pressure “shoulds,” self-imposed discipline or overcoming the deficiency of lost health). Threat-based motivations tap into fear at a deeper level. In the world of medicine, this might be a medical incident that serves as a wake-up call, and the threat of disability or death propels a person to make serious lifestyle changes.

Development-based motivation tends to come from the desire for personal growth or self-actualization. It can also be externally sourced (e.g. from positive peer health norms or positive environmental conditions like smoke-free public spaces) or intrinsic – from the satisfaction, pleasure or joy we derive from doing something.

Research has shown that while fear can be a great motivator for getting people started on something, the positive, development-based motivators tend to be more powerful in keeping people engaged and active in behavior change over the longer term.

I believe one of the reasons the Wellpepper patient engagement platform is so successful at driving patient engagement with care plans (70% engagement compared to an average of 20% engagement with portals) is because the Wellpepper team understands this complex motivation dynamic very well and they have incorporated some of the most successful elements from it into their platform. They call it the “3rd approach” and here’s why I think it works.

Wellpepper takes a very obvious extrinsic motivator – the practitioner’s care plan – and turns it into an application that incorporates both intrinsic and extrinsic development-based motivators that keep people engaged over time. There are many layers we could explore here, but we’ll start with a few of the big ones.

Setting aspirational goals: In addition to the functional goals set by the practitioner, Wellpepper provides the ability for patients to set their own personally meaningful, aspirational goals that can support and reinforce their motivation to heal. For example, someone recovering from a total joint replacement operation might set a future vision of wanting to hike to their favorite fishing spot with a grandchild. They can use Wellpepper to set interim goals that lead them toward that vision and can rate their own progress on a Likert scale.

Research in positive psychology has shown that this kind of personal vision and goal setting is highly successful at sustaining motivation over time. In this case the patient is more likely to complete their prescribed exercises because it leads them toward goals that are personally meaningful about their own healing and about doing something special with someone they love.

Personalized experience: Wellpepper also provides a personalized experience for the patient. Using the same joint replacement example, instead of getting a piece of paper with a series of exercise diagrams or a generic video, the practitioner can record the patient doing their own exercises. Seeing yourself, and hearing the personal comments of the physician or physical therapist as you do it, is not only easier to follow, it feels personal. And, as you begin to improve, when you watch yourself then and now, seeing your own progress can be very satisfying (a powerful development-based motivator).

Adaptive notification: Wellpepper’s patented adaptive notification system means the patient doesn’t get the same generic reminder every day – it changes the notification based on the patient’s progress and level of engagement, keeping the extrinsic motivator relevant, fresh and focused on personal development.

Tracking progress: By enabling people to track progress on their goals and sharing that information with their practitioners, patients tap into positive, extrinsic motivation. Also tracking progress on personal, aspirational goals helps people feel a greater sense of accomplishment and direction over their own developmental outcomes.

While motivation for any one individual can be elusive, the way Wellpepper weaves together the positive extrinsic and intrinsic development-based motivators may be the key to its success in helping patients stay motivated and helping practitioners answer the age-old question: “Will the patient do it?”

If they’re using Wellpepper, chances are, they will.

Jennifer Allen Newton is Wellpepper’s PR lead, and also a Functional Medicine Certified Health Coach. 

Posted in: Adherence, Healthcare motivation, Healthcare Technology, Healthcare transformation, patient engagement, Physical Therapy

Leave a Comment (0) →

Alexa, Get Well Soon

The unofficial winner of the Super Bowl ad race this year was “Alexa Loses Her Voice”, an ad that shows celebrities subbing for Alexa when she (anthropomorphic being that she is, comes down with a cold). Both USA Today and YouTube are calling it the most watched ad.

Alexa, who won USA TODAY’s 30th Ad Meter?

“Well, um – me.”

Jeff Bezos looks skeptical that his team can replace Alexa as he should be, since their solution of Gordon Ramsay, CardiB, Rebel Wilson, and Anthony Hopkins is both extremely expensive, (Wellppper CTO Mike Van Snellenberg did the math), and breaks the key trust relationship that people have with Alexa.

Voice is a natural interface, and empathy can be quickly established by the types of utterances and engagement. By default, Alexa apologizes when she doesn’t understand something and it feels genuine. Compare that to Gordon Ramsay insulting his poor hapless user—all the guy wants is a bit of help making some comfort food. What he gets is abuse.

Or, the woman who wants Alexa’s help while she’s in her boudoir presumably getting ready for a date with her love. Instead, Anthony Hopkins insinuates that something horrific has happened to her beau possibly involving a pet peacock.

Cardi B insults a young man’s interest in Mars. Let’s hope she has not squashed his spirit of discovery and his desire to ask questions.

Since this is an all-ages blog, we won’t even mention the response Rebel Wilson gives from her bubble bath to the poor gentleman who asked Alexa to set the mood for a party. He and everyone at his party were fully traumatized.

We get it, Alexa is just better at delivering what people are asking for than real people. Especially real people with attitude like these celebrities.

As we found in our research with people with type 2 diabetes, Alexa has a natural ability that these celebrity Alexa impersonators do not. You can see it in this feedback we received from real people trying to manage Type 2 diabetes.

  • “Voice gives the feeling someone cares. Nudges you in the right direction”
  • “Instructions and voice were very calm, and clear, and easy to understand”

Voice is a natural fit to deliver empathy and care. However, since each one of these people is expecting Alexa, and has no visual indicator that anything has changed, the negative experiences will reflect on Alexa and she’ll have to win back their trust.

While the implied message of the ad spot is that Alexa does a better job of delivering on your needs than any of these celebrity experts we’re still feeling a bit traumatized by the abuse they hurled. For the sequel to this commercial, we’d expect to see Jeff firing the team that replaced Alexa with celebrities, and Alexa as a therapist working through the trust issues that her replacements created. She can do it. We believe in her.

Posted in: Behavior Change, Healthcare Disruption, Healthcare Technology, Voice

Leave a Comment (0) →

The Secrets of Strong CIO and CMIO Relationships

What’s the secret of a strong CIO and CMIO relationship? Many things including the ability to be adaptable, understand organizational priorities, and deadlines, but most importantly to align on shared goals and purpose.

These were some of the takeaways from the insights shared by CIOs and CMIOs of Confluence Health, and EvergreenHealth at the annual Washington State HIMSS Executive dinner. While the conversation was split between how to foster innovation, and how to manage the demands of an EMR rollout (including the resulting backlog of other IT requests), where the relationship really shone was in the implementation of tools for a shared purpose, in this case tracking and control of opioids to help curb the epidemic we’re seeing in this country.

In particular a project at EvergreenHealth to implement e-prescribing of controlled substances, showed the need for strong CMIO and CIO collaboration. The program is designed to decrease fraud and misuse of controlled substances, but it can also improve patient care. Since it involves both technology implementation and clinical guidelines it’s a perfect example of medical and technology collaboration. In Washington State, where we’re based, the Bree Collaborative also has recommended guidelines for prescribing opioids, that while optional are widely adopted across the state.

We’ve written about this problem before in pain management for total joint replacement. Sadly, an unintended consequence of the pain management question on the HCAHPS survey, is sometimes an overprescribing of prescription pain medication. According to one speaker at the event, 30mg of oxycontin over 7 days is enough to trigger an addiction, and yet often post-surgery up to 30 days of pills are prescribed. We talked to one patient (not a Wellpepper user) who reported taking all of her prescribed pain medication, not because she needed it but because it was prescribed. The first step to solving this problem is with the prescription, and EvergreenHealth’s e-prescription program, combined with locked cabinets in the operating room (the idea is that if you don’t need it immediately, you don’t actually need it), alerts on over prescribing, and programs to substitute suboxone, coupled with behavior health management can all help. As well behavior change happens with the physicians, and a powerful image was the story of a pharmacist who put a bag of unused opioid prescriptions on the table to show that even if they didn’t think so, some physicians may have been over-prescribing.

However there are ways to take it a step further: tracking what the patient actually took outside the clinic, which is why we include a pain medication usage task in many care plans. This activity asks patients some simple questions about their over-the-counter and prescribed pain medication usage, and alerts if the numbers or the length of time is over certain thresholds. It’s in use in care plans that include general pain management, surgical, and neurology (headache management), and provides a view into usage, and the opportunity to reach out and help patients outside the clinic before usage becomes a problem.

We’re strong believers in the ability for patients to record their own outcomes and experiences, and the value of combining this with prescribing and clinical data to close the loop on delivering better care. If you’re interested in learning more, get in touch.

Posted in: Adherence, Behavior Change, Healthcare Legislation, HIPAA, Opioids, Outcomes, patient engagement

Leave a Comment (0) →

CES 2018 Review: More Consumer Healthcare Disruption Please

CES 2018 Review: More Consumer Healthcare Disruption Please

We went to CES 2018 to understand more about how the consumer technology space was poised to disrupt healthcare. As a digital healthcare company, we sit in many conversations with established healthcare organizations. We know that they are concerned about the consumerization of healthcare and how this could disrupt the very core of their business. Fears about the big-5 technology companies moving into healthcare are themes in many an executive healthcare planning retreat.

So, what did this bold, disruptive vision of consumer-driven, technology-driven healthcare look like? Hundreds of companies selling rip-off activity tracking watches, and connected blood pressure cuffs and scales. The big booths felt depressingly resigned to a future where consumers would somehow want to buy big clunky medical monitoring devices-rebranded-as-consumer-devices, and then maybe sign into a dusty old web portal to view the data. “Requires Internet Explorer 5 or higher” warned one brochure – a browser that was literally released in the 90s. A disruptive consumer story this was not. Nothing to worry about here, big healthcare.

There was some innovation to be seen, of course, including some truly interesting devices in the small 10×10 booths. Products like TytoCare’s tricorder for at-home vitals capture, and healthcare-relevant wearables like those from Sensoria. Also the number of do-it-at-home biological tests like Ellume’s at-home flu and strep tests and food allergen detectors like Nima are of particular interest to my household and our matrix of peanut, tree-nut, gluten, strawberry and peach allergies.

What’s missing is someone to pull these innovative ideas and devices together and offer a comprehensive vision for what consumer-driven healthcare could look like in a way that consumers would actually want to spend money on. Where’s the LG-OLED-tunnel of consumer health? Even if they didn’t have anything yet – at least sell the vision the way all those car vendors are selling the vision of self-driving cars.

We suspect that, as with self-driving cars (Tesla, Google) and smart phones (Apple), the companies with most complete vision in healthcare maybe just aren’t telling this story at CES. Google, Apple, Amazon, Microsoft, Facebook: can’t wait to see your consumer healthcare booth when it’s ready, either at CES or some other show.

Posted in: Healthcare Disruption

Leave a Comment (0) →

Your Cupcakes Are Not My Goals

This year Google Maps tried out a short-lived motivational technique of showing how many cupcakes you would burn off or ostensibly could eat if you chose to walk to your destination. Not surprisingly this backfired, and they quickly retracted the feature. The reasons ranged from users expressing feelings of shame for not walking, to those with eating disorders saying it would encourage more obsessive behavior. Beyond that, many questioned how Google was even calculating both caloric expenditure and the actual calories in the cupcakes.

Regardless of the myriad of criticisms the experiment illustrated a key point: motivation and goal setting is best left to the individual, and understanding someone’s personal context is extremely important if you want to help them set goals.

One of our most read blog posts of 2017 was a 2015 post on whether setting SMART or MEANINGFUL goals was most effective for patients. I’m not sure why this bubbled to the top this year but the post provides an overview of two thoughtful frameworks for helping patients set goals.

At Wellpepper, we’d like to propose a third methodology: let people figure out what’s important to them. This year we expanded a capability we’ve had since V.1 that enables patients to set their own goals. This is a free-form, 140 character text box where patients write about what’s important to them. Over the years, we’ve had some clinicians express concern about whether patients could set their own goals. Functional goals are best left to the experts, but these are life goals, things that are important to people and why they are even bothering to use this app which helps them through healthcare activities to manage chronic diseases or recover from acute events.

Since we already knew that setting patient-generated goals is motivating, we also got to wondering whether you could track progress in a generic way based on patient-generated goals. After analyzing thousands of patient-generated goals, we figured out that asking a question about the patient’s perception progress on a Likert scale would work, and so this year we expanded the patient goal task type to include tracking.

It looks like this.

In case you’re skeptical that this works, here are a few examples of patient-generated goals.

Spend more time with family.

Get outside more frequently.

Walk more.

Be ready for vacation.

Now ask the question. See, it’s entirely possible for patients to set their own goals, unaided, and track progress against those goals. We’re pretty excited about the possibilities of this for improving motivation, and also for further analysis of patient adherence and outcomes. If you’d like to know more, or see a demo, we’d love to hear from you.

Posted in: Behavior Change, Healthcare motivation, Healthcare Technology, Healthcare transformation, patient engagement, patient-generated data

Leave a Comment (0) →

May You Live In Interesting Times: Wellpepper’s Most Interesting Blog Posts of 2017

Who would have predicted 2017? As soon as the election results were in, we knew there would be trouble for the Affordable Care Act no one could have predicted the path through repeal with no replacement to claw backs in a tax bill that no one has read. It’s been a crazy ride in healthcare and otherwise. As we look ahead to 2018, we’ve found that a good place to start is by looking back at what was popular in 2017.

Looking back over the past year’s top blog posts, we also believe trends that started in 2017, but will even stronger in 2018. These four themes bubbled up to the top in our most-read blog posts of 2017:

Shift to the cloud

We’ve noticed a much wider spread acceptance of cloud technologies in healthcare, and the big cloud platform vendors have definitely taken an interest in the space. Wellpepper CTO Mike Van Snellenberg’s comprehensive primer on using AWS with HIPAA protected data was one of our most read posts. Since he wrote it, even more AWS services have become HIPAA-eligible.

Using AWS with HIPAA-Protected Data – A Practical Primer

Consumerization of healthcare

Consumer expectations for efficient online interactions have been driven by high-deductible plans and an expectation from consumer technology and industries like retail and banking that customer service should be personalized, interactive, and real-time. These two posts about the consumerization of healthcare were among the most popular.

The Disneyfication or Consumerization of Healthcare

Consumerization Is Not A Bad Word

Value of patient-generated data

In 2017 we saw a real acceptance of patient-generated data. Our customers started asking about putting certain data in the EMR, and our analysis of the data we collect showed interesting trends in patient adherence and predictors of readmission. This was reflected in the large readership of these two blog posts focused on the clinical and business value of collecting and analyzing patient-generated data.

In Defense of Patient-Generated Data

Realizing Value In Patient Engagement

Power of voice technology

Voice technology definitely had a moment this year. Okay Google, and Alexa were asked to play music, turn on lights, and more importantly questions about healthcare. As winners of the Alexa Diabetes Challenge, we saw the power of voice firsthand when testing voice with people newly diagnosed with Type 2 diabetes. The emotional connection to voice is stronger than mobile, and it’s such a natural interaction in people-powered healthcare. Our blog posts on the Alexa Diabetes Challenge, and developing a voice solution were definitely in the top 10 most read.

Introducing Sugarpod by Wellpepper, a comprehensive diabetes care plan

Building a Voice Experience for People with Type 2 Diabetes

Ready When You Are: Voice Interfaces for Patient Engagement

Since these themes are still evolving we think 2018 will present a shift from investigation to action, from consideration to deployment and possibly insights. Machine-learning and AI will probably remain high in the hype cycle, and certainly the trends of horizontal and vertical healthcare mergers will continue. We also expect a big move from one of the large technology companies who have all been increasing their focus in healthcare, which in turn will accelerate the shift to a consumer-focus in healthcare.

There’s a saying “may you live in interesting times.” We expect 2018 to be at least as interesting as 2017. Onwards!

Note: There was one additional post that hit the most popular list. Interestingly, it was a post from 2014 on whether SMART or MEANINGFUL goals are better for patients. We’re not sure why it resurfaced, but based on analysis we’ve done of patient-directed goals, we think there’s a third approach.

Posted in: Behavior Change, Healthcare Disruption, Healthcare motivation, Healthcare Research, Healthcare Technology, Healthcare transformation, HIPAA, patient engagement, patient-generated data, Voice

Leave a Comment (0) →

HealthLoop, Wellpepper, and Livongo Collaborate to Advance Digital Health

Three companies engaged with CMS toward inclusion of patient engagement and outcomes tracking in the MIPS Improvement Activity for provider reimbursement.

MOUNTAIN VIEW, CA, UNITED STATES, December 13, 2017 / — Approved digital health tools will soon be eligible for Medicare reimbursement. Beginning in 2018, physicians and other healthcare providers participating in the Merit Based Incentive Program (MIPS) track of the Medicare Access and CHIP Reauthorization Act (MACRA), can qualify for reimbursement for using clinically endorsed digital health tools to remotely guide and monitor patients outside of the clinical encounter. The new Improvement Activity recognizes the important value that digital patient engagement tools play in driving healthcare quality and lowering costs.

The new CMS MIPS Improvement Activity, entitled “Engage Patients and Families to Guide Improvement in the System of Care,” enables healthcare providers to be reimbursed for the remote monitoring, review, and interpretation of patient generated health data (PGHD) gathered through clinically endorsed mobile patient engagement applications. This provides an incentive for physicians to use digital health tools to track patient progress and improve the quality of ongoing care outside of the hospital or clinical setting while empowering patients to take more active roles in managing their own health.

Three digital health companies, HealthLoopWellpepper, and Livongo – leaders in this fast-growing market – collaborated in working with CMS to raise awareness of how PGHD and digital patient engagement tools can play critical roles in improving the quality of care and outcomes for patients. Top executives from the three companies also participated in the CMS PGHD Round Table in Washington, D.C. on December 6 to further the importance and understanding of the value of PGHD in patient care.

HealthLoop, Wellpepper, and Livongo can improve the level of personalized care for patients by providing ongoing guidance and assessments outside the physician-patient encounter. Physicians and care teams can use these tools to provide and adjust care plans, assist with ongoing disease management, and support return-to-work and patient quality of life improvement. Data collected from these digital health platforms can be used to track patient outcomes in support of continuous improvement initiatives and for participation in alternative payment models.

“Patient generated health data is a valuable tool in patient care,” said Anne Weiler, co-founder and CEO of Wellpepper, a clinically-validated platform for patient engagement that provides personalized, digital patient treatment plans delivered via mobile devices, SMS, email, Web and interactive voice interfaces. “We’re pleased that CMS has recognized this, and is enabling the collection and analysis to be used in demonstrating quality patient care.”

While many consumer digital devices like smart watches and activity trackers are in use by patients, the new MIPS Improvement Activity requires that physicians and other providers use clinically endorsed patient engagement and outcomes tracking tools that provide an active feedback loop – meaning they provide timely (real or near-real time) PGHD to the care team or generate timely automated feedback to the patient, such as automated patient-facing instructions based on care plan adherence or glucometer readings. These patient engagement tools may inform the patient and the clinical team of important parameters regarding a patient’s status, adherence to care plans, comprehension and indicators of clinical concern.

“This new rule is an important step forward for physicians and patients using digital engagement tools,” said Dr. Ben Rosner, CMIO of HealthLoop, a software solution that enables care teams to engage all patients before and after clinical encounters through automated daily check-ins. “For clinicians already using a patient engagement platform, these efforts will help satisfy the Improvement Activities category and earn 10 Advancing Care Information bonus points. Eligible clinicians must simply attest to completing the activity for at least 90 days to meet 2018 reporting requirements. Financial incentives aside, engaging with patients is the right thing to do. Practices using automated patient engagement solutions see reduced readmission and complication rates, lower call center volume, better online ratings for physicians, and, most important, happier, healthier patients.”

“It’s not enough to want providers to expand care beyond the four walls of the office, it’s about empowering consumers and updating all parts of the system,” said Michael Sturmer, Livongo Senior Vice President of Health Services. “The new CMS MIPS Improvement Activity further connects digital health with providers and care practices and is a significant advancement in making digital health part of the fabric of the health care experience. It is better for patients and providers, and that’s better for all of us.”

Posted in: Press Release

Leave a Comment (0) →

4 Reasons Why the Future of Health IT is Serverless (AWS re:Invent 2017 wrap-up)

The big theme at AWS re:Invent 2017 was serverless computing. Whether deploying microservices in containers using ECS, Kubernetes, or Fargate, or building systems using Lambda that connect to serverless relational databases like Serverless Aurora or DynamoDB, Amazon is rapidly moving to remove “undifferentiated heavy lifting” common to building and deploying software applications.

Healthcare has historically been slow to move to the cloud. Some of this stemmed from spotty HIPAA eligibility, and from a desire of health systems not to be the first to break new ground. Today, however, many of the barriers have been cleared away: serverless technologies like Lambda and ECS are already on Amazon’s HIPAA-eligible services list with many more likely to come in the future.

There are many benefits to serverless architectures, including faster time to market, lower operating costs, and lower complexity. Here are 4 compelling reasons why serverless systems are uniquely positioned to thrive in healthcare:

Improved Security

The HIPAA security rule contains a number of requirements for server security. You’d be hard pressed to find a list of security recommendations that doesn’t start with patching your servers. Indeed, over the last year unpatched servers have led to several major security incidents and breaches. There are many (poor) reasons why people don’t patch. Failure to patch machines promptly is a significant risk vector.

With serverless systems, this risk vector goes away.

In actuality, the risk is not entirely removed; instead you’re selling it to Amazon. Underneath serverless technologies, there are still servers running operating systems. However, the bet that you’re making is that Amazon has this down to a science across their millions of servers in a way that other IT departments can’t match.


Governance and Compliance

HIPAA mandates a set of administrative controls that govern things like access control and auditability. This is another area that is already baked deeply into serverless architectures.

AWS contains a strong policy-driven identity and access framework in AWS IAM. This is a core component of serverless architectures to control access at every step in the architecture. Applying the ‘least privilege’ principle with IAM roles naturally limits the “blast radius” if a service does become compromised. And because policies are all held in one place, it’s easier to see and control which accounts have access to what.

Auditability and robust logging go hand-in-hand, and if serverless architectures do anything, they generate a ton of log data. Each service, from AWS Gateway routing request to VPC delivering network traffic, to Lambda services handling requests, to S3 getting and setting bulk data is heavily logged, with most logs aggregating into either S3 or CloudWatch Logs. Several of the re:Invent sessions this year explored novel ways to report on this data using tools like ElasticSearch (note: the AWS-managed ElasticSearch Service is not yet on the HIPAA eligible list), and even automatically detect anomalous usage patterns using Kinesis Analytics.

Finally, AWS Artifact organizes all of the compliance documentation for Amazon’s part of the shared-responsibility model, including things like your AWS Business Associate Addendum (BAA), and access to SOC2 audits.

All of this stuff is just baked in, and there’s hardly any work needed to make use of it.


Availability and Scalability

While the security and encryption parts of HIPAA get most of the attention, it also contains provisions for ensuring availability, business continuity, and emergency mode operations.

Capacity and availability is something that used to be hard to plan in the days of individual server instances. A well-designed serverless architecture, by contrast, encourages robust-by-design implementations that can scale based on actual usage. Deploying across multiple data centers (AZs) is the default. Deploying across multiple regions is easy. This once again removes a common source of error and failure and gives solution builders tools to build “internet scale” systems that deliver three, four, or more 9’s of availability.

And in the unlikely event that there is an outage, backup and restore is also easy. Relational (Aurora) databases automatically perform backups, and backup/restore support for the DynamoDB document database was announced at re:Invent.


Increased Interoperability

Healthcare data has often been locked into data silos inside EMRs and other proprietary systems-of-record. Additionally, the quantity of data has meant that health systems need to undertake massive data consolidation and data warehousing projects to begin to recognize the value stored in this data.

At the same time, in recent years, there has been an explosion in patient-generated data. Vast quantities of activity tracking data, medication adherence records, blood glucose measurements, and patient reported outcome data (to name a few examples) sits collected but underused and uncorrelated.

In modern serverless architectures, patient data from inside and outside the four walls of the clinic can be easily collected and stored in large-scale data lakes like S3 where it can be easily aggregated, cleaned, transformed, queried, and reported on. HIPAA regulations are easily fulfilled, with HIPAA-compliant encryption at no additional cost just a button-click away (or sometimes a few buttons if you want to manage your own encryption keys). Control over who can access and use this data are returned to governance groups and clinicians based on business requirements and policy rather than obscure formats, closed databases, and network firewalls.


Wrap Up

At Wellpepper, we help healthcare providers deploy interactive care plans to their patients, so we take our data security and compliance responsibilities seriously. We were an early adopter of the AWS cloud back when EC2 and S3 were the only services available under the HIPAA umbrella, but things have changed! Following AWS’ announcement earlier this year that Lambda is now HIPAA-elegible, we’ve been looking more seriously at serverless system design, and we like what we see.

This is the future that anyone building solutions in healthcare IT should be excited about.


Relevant Content from AWS re:Invent 2017

Adopting Microservices in Healthcare: Building a Compliant DevOps Pipeline on Amazon ECS

What’s new in AWS Serverless 

Simplifying Healthcare Data Management on AWS 

Building a Secure and Healthcare-Compliant Platform for Adopting a Cloud-First Strategy using AWS 

American Heart Association: Finding Cures to Heart Disease Through the Power of Technology 



Posted in: Adherence, Data Protection, Healthcare Technology, Interoperability

Leave a Comment (0) →

Pointing Fingers at Healthcare Problems

I’m only halfway through Elizabeth Rosenthal’s “An American Sickness: How Healthcare Became Big Business and How You Can Take It Back” which means that I haven’t gotten to the “what you can do about the problem” part. It’s a slow read, not because it’s not compelling but because it’s too compelling, and if like the current President, you were surprised at how complicated healthcare is, this book will do nothing to dissuade you. It’s really really complicated.

So far, I have two main takeaways from the book, that are easily illustrated through my recent experience of breaking and dislocating my finger: a simple, non-life-threatening problem, that unearthed a couple of key dysfunctions and unintended consequences.

My first takeaway is that everyone is complicit, and yet seem to manage to finger point at everyone else. Rosenthal spares no punches in unearthing decisions that are not made with the best interest in of the patient at heart. Providers, healthcare organizations, payers, pharma, and employers all are complicit in the mess that is our current healthcare system.

This past fall, I broke and dislocated my finger. It wasn’t a big deal, but because it happened on a Saturday night, my only option for care was at the ER. Last week I received a letter in the mail from my insurance company, that according to the envelope required my urgent reply. In the letter, the insurance company suggested that perhaps someone other than them may be on the hook for my ER bill. While I understand they wanted to make sure this wasn’t a worker’s compensation claim, the form was basically for me to tell them whose fault my injury was so that they could go after another insurance company to pay. This was a sports injury in a game of Ultimate Frisbee, a game so granola-like that there are no referees: players call fouls on themselves. . No one was at fault, and even if they were, I would never have considered suing. However, the form didn’t give me that option: only gave me the option of saying whether I had settled my claim. I created a new box that said “NA” and checked it.

When I received the letter, I couldn’t help but think back to Rosenthal’s book, and also consider the amount of effort and cost that was going into finding someone else to blame and pay. Just imagine what this effort and cost would have been if there were legal action….

The second takeaway is that the original intention of a decision always has much farther reaching implications than anyone who agreed on what seemed like a reasonable decision though. Again with the finger, I was asked a number of times if I wanted a prescription for OxyContin. I did not. As has been well publicized we have an opioid addiction problem in North America. While my finger hurt, aside from morphine during inpatient for an appendectomy, I hadn’t had opioids, and really didn’t think that it was necessary, which I explained to the physician. It wasn’t. Tylenol worked fine—however, it seemed that it was very important that I be the one to make this call, not the physician.

One of the unintended consequences of patient satisfaction scores may be the over prescription of pain medication, as many of the questions on the HCAHPS are about whether the patient’s pain was well managed. In Rosenthal’s book, I was also surprised to learn that a finger fracture where an opioid is prescribed has a different billing code than if it is not prescribed, and that with the fracture plus opioid billing code, hospitals get paid more. Now, if you are wondering how this may be the case, if you think about it, a fracture that requires an opioid must be more severe than one that doesn’t and therefore the billing code reflects the severity. This is exactly where the unintended consequences of billing codes can result in exactly the wrong behavior for patient care and safety.

It’s quite possible that the physicians on duty were not aware of either of these two drivers for prescribing, especially the billing code one. They may have just been told “this is our standard of care” and were following guidelines.

If a simple finger fracture and dislocation can shine a light on two key problems in our healthcare system, just imagine what else is out there. Actually, you don’t have to, just get a copy of Elizabeth’s book yourself, and let’s compare notes when I get to the part about what the fix is. It’s going to take all of us.

Posted in: Health Regulations, Healthcare costs, Healthcare Disruption, Healthcare Legislation, Healthcare Policy, Healthcare transformation, Opioids

Leave a Comment (0) →

Healthcare + A.I. Northwest

The Xconomy Healthcare + A.I. Northwest Conference at Cambia Grove featured speakers and panels discussing the opportunities and prospects for applying machine learning and artificial intelligence to find solutions for health care. The consensus was that we are no longer held back by a lack of technological understanding and ability. A.I. and M.L. models can be learned at a large scale by harnessing the power of the cloud and advances in data science. According to the panelists, today’s challenges to incorporating A.I. into healthcare include abundant, but inadequate data and resistance from health systems and providers.

Many researchers have found insufficient data to be an unexpected challenge. As keynote speaker Peter Lee of Microsoft Research pointed out, the more data we have, the better our machine learned models can be. He used an analogy to a speech identifier trained on multiple languages such that the model predicted English better after learning French to illustrate that improvements can be made with large sets of unstructured data. Unfortunately, because we are not capturing enough of the right kind of data for researchers, much patient data is getting lost in the “health data funnel” due to PHI and quality concerns. Lee called for more data sharing and data transparency at every level.

Physician researchers on multiple panels were concerned about a lack of suitable data. Soheil Meshinchi, a pediatric oncologist from Fred Hutchinson Cancer Research Center, is engaged in collecting data specific to children. He discussed his research on Acute Myeloid Leukemia on the panel titled, ‘Will A.I. Help Discover and Personalize the Next Breakthrough Therapy?’. While there is a large body of research on AML in adults, he has found that the disease behaves much differently at a genomic level in children. He also expressed distrust in some published research because studies are rarely reproduced and often a researcher who presents results contrary to existing research faces headwinds at journals who are reticent to publish “negative data”. His focus at this point is gathering as much data as he can.

Matthew Thompson, a physician researcher at the University of Washington School of Medicine, argued on the “Innovations for the Over-Worked Physician” panel that technology has made patient interaction demonstrably worse, but that these problems can and should be solved innovatively with artificial intelligence. His specific complaints include both inputting and extracting data from health system EHRs, as well as an overall glut of raw patient data, often generated by the patient himself, and far too much published research for clinicians to digest.

Both keynote speakers, Microsoft’s Lee and Oren Etzioni of the Allen Institute for Artificial Intelligence, referenced the large numbers of research papers published every year. According to Etzioni, the number of scientific papers published has doubled every nine years since World War II. Lee referenced a statistic that 4000 studies on precision cancer treatments are published each year. They are both relying on innovative machine reading techniques to analyze and categorize research papers to make them more available to physicians (and other scientists). Dr. Etzioni’s team has developed to combat the common challenges facing those who look for research papers. He aims to reduce the number of citations they must follow while also identifying the most relevant and up-to-date research available. One of the advantages of taking this approach to patient data

is that scientific texts have no PHI concerns. Lee’s team is marrying patient data and machine reading to match potential research subjects with appropriate NIH studies.

Dr. Thompson was concerned that too much data is presented to the medical staff and very few of the “predictive rules” used by ER personnel are both ‘accurate and safe’. When reviewing patient outcomes and observations to predict the severity of an infection, he found that patients or their caregivers would provide ample information, but often clinicians would disregard certain details as noise because they were atypical symptoms. The amount of data that providers have to observe for a patient is massive, but machine learned models may be utilized to distill that data into the most relevant and actionable signals.

Before data is gathered and interpreted, it must be collected. Like Dr. Thompson, Harjinder Sandhu of Saykara sees ponderous, physician-driven data entry via EHR as significant barrier to efficient data collection. Sandhu notes that healthcare is the only industry where the highest-paid teammember is performing this onerous task and his company is using artificial intelligence to ease that burden on the physician.

Once patient data has been aggregated and processed into models, the challenge is getting the information in front of providers. This requires buy-in from the health system, physician, and, occasionally, the patient and his caregivers. Mary Haggard of Providence Health and Services spoke on the “Tech Entrepreneurs Journey into Healthcare” panel and stated that the biggest problem for entrepreneurs is defining the correct problem to solve. During the “Investment Perspective” panel, Matt Holman of Echo Health Ventures recommended tech startups emphasize an understanding of the context of the problem within a health system.

One of the most important and difficult hurdles for health technology companies is working into clinical workflow. Mike McSherry from Xealth has found that physician champions who know how they want to use technology help with integrating into a health system or physicians group. Lynn McGrath of Eigen Healthcare believes physicians want their data to be defined, quick to assess, condensed, and actionable, while Shelly Fitz points out that providers are not used to all the data they are receiving and they don’t yet know how to use it all. These are all issues that can and will be solved as healthcare technology continues to become more intelligent.

As Wellpepper’s CTO, Mike Van Snellenberg pointed out, health systems and doctors are resistant to “shiny new things”, for good reason. When approaching a health system, in addition to engaging the administration, clinicians need to understand why the machine learned model is recommending a given course of treatment. After integration, patients will also want to understand why a given course of treatment is being recommended. Applying artificial intelligence solutions to medicine must take into account the human element, as well.

The exciting possibilities of artificial intelligence and machine learning are hindered more by human constraints in health systems and data collection than by available technology. “Patients are throwing off all kinds of data when they’re not in the clinic,” according to our CTO. Wellpepper’s tools for capturing patient-generated data provide a pathway for providers to access actionable analysis.

Posted in: Healthcare Disruption, Healthcare Technology, patient engagement

Leave a Comment (0) →

Are Women Better Surgeons? Patient-Generated Data Knows The Answer

As empowerers of patients and collectors of patient-generated data, we’re pretty bullish on the ability for this data to show insights. We fully admit to being biased, and view things through a lens of the patient experience and outcomes, which is why we had some ideas about a recent study that showed female surgeons had better outcomes than male surgeons.

The study, conducted on data from Ontario, Canada, was a retrospective population analysis of patients of male and female surgeons looking at rates of complications, readmissions, and death. The results of the study showed that patients of female surgeons had a small but statistically significant decrease in 30-day mortality and similar surgical outcomes.

Does this mean that women are technically better surgeons? Probably not. However, there is one sentence that stands out to a possible reason that patients of female surgeons had better outcomes.

A retrospective analysis showed no difference in outcomes by surgeon sex in patients who had emergency surgery, where patients do not usually choose their surgeon.

This would lead us to believe that there is something about the relationship between the patient and the provider that is resulting in better outcomes. We have seen this at Wellpepper, while we haven’t broken our aggregate data down by gender lines, we have seen that within the same clinic, intervention, and patient population, we see significant differences in patient engagement and outcomes between patients being seen by different providers.

Some healthcare professionals are better than others at motivating patients, and the relationship between provider and patient is key for adherence to care plans which improve outcomes. By tracking patient outcomes and adherence by provider, using patient-generated data, we are able to see insights that go beyond what a retroactive study from EMR data can show.

While our treatment plans, and continued analysis of patient outcomes against those treatment plans go much further than simply amplifying the patient-provider relationship, for example with adaptive reminders, manageable and actionable building blocks, and instant feedback, never underestimate the power of the human connection in healthcare.

Posted in: Adherence, Behavior Change, big data, Clinical Research, patient-generated data

Leave a Comment (0) →

Boston University Center for Neurorehabilitation: A Novel Mobile Intervention For People With Parkinson’s Disease

In 2013, when we were a brand new m-health company, we had the good fortune to meet Terry Ellis, PhD, Director of the Center for Neurorehabilitation at Boston University. Dr. Ellis was an early investigator in the value of digital interventions, and saw an opportunity to partner with Wellpepper so that her team could focus on the new care models, and Wellpepper could focus on the technology. The first building blocks in the Wellpepper platform aligned closely with outpatient rehabilitation, and Dr Ellis and team wanted to prove that people who had Parkinson disease could improve strength and mobility without costly in-person visits. At Wellpepper, we also had an interest in proving that mobile health can improve outcomes, and also that those 50 plus could use mobile technology.

Persons with Parkinson Disease (PD) have been described as 29% less active than older adults without PD, and see a 12% decline in mobility for each year after their first diagnosis with the disease. In-person interventions with physical therapists can help, but in the usual care condition, a person has one in-person assessment at The Center for Neurorehabilitation, and may not be seen again for 6 months to a year, during which time there was a decline in mobility. Dr Ellis and team were looking for a way to prove out a novel intervention that could improve outcomes for these patients.

Patient Experience

This video does a great job of showing the patient experience, both with the clinician and while using the application at home.

User Journey from Wellpepper on Vimeo.


While Dr. Ellis and team are still analyzing additional data, and will be submitting to a peer-reviewed journal, and are exploring expanded studies on the topic, we can share some very promising results.

  • This study revealed that using mobile health technology to remotely monitor and adapt exercise programs between bouts of care in persons with Parkinson disease was feasible and acceptable.
  • On average, subjects engaged with the app every week for 85% (+/- 20%) of the weeks with an 87% satisfaction rating.
  • Significant improvements in physical activity, walking and balance measures were observed over 12 months.
  • People who showed lower exercise self-efficacy at the beginning of the study saw the greatest gains.


  • This technology used the Wellpepper platform, clinic application for iPad, and patient application for iOS. Requirements were for ease of use for both clinicans and patients. Features include the ability to record custom video of patients doing their exercises, for patients to record results, and for patients and providers to message securely with each other.
  • Fitbit was used for patients to track non-exercise activity, and this was the first integration of a consumer exercise tracker with the Wellpepper platform.
  • The entire Wellpepper platform is built on Amazon Web Services, in a HIPAA secure manner, which was a requirement for the study. No data was stored on mobile devices and all personal health information was encrypted in transit and at rest.
  • The Boston University team required a monthly data extract of all patient-generated data for their analysis purposes.
  • Post study, we were able to analyze anonymized patient-provider messages using a machine learned message classifier, and have presented this data at digital health conferences.

The positive preliminary results of this study, lead to a larger study with seniors at risk of falls, lead by principal investigator Jonathan Bean, MD from Harvard Medical School. Details of this intervention are available here. While Dr Bean is also in the process of submitting to a peer-reviewed journal, his assessment is that outcomes exceeded clinically significant measures.

We are looking forward to sharing more about the results of both of these studies when they are publicly available in peer-reviewed journals. If you are a researcher who would like to know more, contact us and we may be able to put you in touch with the study leads.

Posted in: Clinical Research, Exercise Physiology, Healthcare Technology, Healthcare transformation, M-health

Leave a Comment (0) →

Meet Wellpepper At Connected Health

We’re gearing up for a great week at Connected Health. See Wellpepper, and our Alexa Diabetes Challenge Grand Prize winning entry Sugarpod in Boston next week. Contact to schedule a demo, drop by Booth 84 in the Innovation Zone.


Wednesday October 25
Natural Language Pre-Conference, we’ll be talking about the Alexa Diabetes Challenge, Sugarpod, and voice

Thursday October 26

Voice Technologies In Healthcare Applications

  • Room: Harborview 2/3
  • Session Number:R0240D
  • 2:40 PM – 3:30 PM

U.S. Department of Health and Human Services Town Hall with Bruce Greenstein, Entrepreneur Panel and Q&A (Invite-only)

Friday October 27

The Power of Patient-Generated Data

Exhibition Showcase 11:00 AM – 11:10 AM



Posted in: patient engagement, Voice

Leave a Comment (0) →

Wellpepper Wins $125K Grand Prize in Alexa Diabetes Challenge

NEW YORK: Today, the Challenge judges awarded Wellpepper the $125,000 grand prize in the Alexa Diabetes Challenge. Wellpepper is the team behind Sugarpod, a concept for a multimodal diabetes care plan solution using voice interactions.

The multi-stage Challenge is sponsored by Merck & Co., Inc., Kenilworth, New Jersey, U.S.A., supported by Amazon Web Services (AWS), and powered by Luminary Labs. In April, the competition launched with an open call for concepts that demonstrate the future potential of voice technologies and supporting Amazon Web Services to improve the experience of those who have been newly diagnosed with type 2 diabetes.

“Technology advances are creating digital health opportunities to improve support for people managing life with a chronic disease,” said Tony Alvarez, president, Primary Care Business Line and Customer Strategy at Merck & Co., Inc. “One purpose of the Alexa Diabetes Challenge was to identify new ways to use the technology already present in a patient’s daily routine. The winner of the Challenge did just that.”

Sugarpod is a concept for an interactive diabetes care plan solution that provides tailored tasks based on patient preferences. It delivers patient experiences via SMS, email, web, and a native mobile application – and one day, through voice interfaces as well. Since much of diabetes management occurs in the home, the Wellpepper team recognized that integrating voice was the natural next step to make the platform more convenient where patients are using it most. During the Challenge, Wellpepper also prototyped an Alexa-enabled scale and foot scanner that alerts patients about potential foot problems, a common diabetes complication.

“Sugarpod helps newly diagnosed people with type 2 diabetes integrate new information and routines into the fabric of their daily lives to self-manage, connect to care, and avoid complications. The Challenge showed us the appeal of voice solutions for patients and clinical value of early detection with home-based solutions,” said Anne Weiler, co-founder and CEO of Wellpepper.

The Challenge received 96 submissions from a variety of innovators, including research institutions, software companies, startups, and healthcare providers. The panel of judges, independent from Merck, narrowed the field down to Wellpepper and four other finalists, who each received $25,000 and $10,000 in AWS promotional credits and advanced to the Virtual Accelerator. During this phase of the competition, the finalists received expert mentorship as they iterated their solutions in preparation for Demo Day. At Demo Day on September 25, 2017, the five finalists presented their solutions to the judges and a live audience of industry leaders at the AWS Pop-up Loft in New York to compete for the grand prize.

“The Alexa Diabetes Challenge has been a great experiment to re-think what a consumer, patient, and caregiver experience could be like and how voice can become a frictionless interface for these interactions. We can imagine a future where technological innovations, like those provided by Amazon and AWS, are supporting those who need them most,” said Oxana Pickeral, Global Segment Leader in Healthcare and Life Sciences at Amazon Web Services.

Learn more at and follow the Challenge at @ADchallenge.                                                                   


Contact: Emily Hallquist

(425) 785-4531 or

Posted in: Healthcare Technology, Healthcare transformation, patient engagement, Press Release

Leave a Comment (0) →

Building a Voice Experience for People with Type 2 Diabetes

Recently we were finalists in the Merck-sponsored Alexa Diabetes Challenge, where we built a voice-powered interactive care plan, complemented by a voice-enabled IOT scale and diabetic foot scanner. The scanner uses the existing routine of weighing-in to scan the person’s feet for foot ulcers, a serious but usually preventable complication of Diabetes.

We blogged about our experience testing the device in clinic here

We blogged about feedback from patients here

This was a fun and productive challenge for our team, so we wanted to share some of our lessons learned from implementing the voice interface. This may be of interest to developers working on similar problems.

Voice Experience Design

As a team, we sat down and brainstormed a long list of things we thought a person with diabetes might want to ask, whether they were interacting with the scale and scanner device, or a standalone Amazon Echo. We tried not to be constrained by things we knew our system could do. This was a long list that we then categorized into intents and prioritized.

  • ~60% of the utterances we knew we’d be able to handle well (“My blood sugar is 85.”, “Send a message to my care team”, “Is it ok to drink soda?”)
  • ~20% of the utterances we couldn’t handle fully, but could reasonably redirect (“How many calories are in 8oz of chicken and a half cup of rice?”)
  • ~20% of the utterances we didn’t think we’d be able to get to, but were interesting for our backlog (“I feel like smoking.”)

After some “wizard of oz” testing of our planned voice interactions, we decided that we needed to support both quick-hit interactions, where a user quickly records their blood sugar or weight for example, and guided interactions where we guide the patient through a few tasks on their care plan. The guided interactions were particularly important for our voice-powered scale and foot scanner so that we could harness an existing habit (weighing oneself) and capture additional information at the same time. This allows the interaction to fit seamlessly into someone’s day.


Challenge 1: We wanted to integrate the speech hardware into our scale / foot scanner device using the Alexa Voice Service, rather than using an off-the-shelf Echo device.

The Alexa Voice Service is a client SDK and a set of interface standards for how to build Echo-like capabilities into other hardware products. We decided early on to prototype our device around a Raspberry Pi 3 board to have sufficient processing power to:

  • Handle voice interactions (including wake-word detection)
  • Drive the sensors (camera array, thermal imaging, load sensors)
  • Run an image classifier on the device
  • Drive on-device illumination to assist the imaging devices
  • Securely perform network operations both for device control and for sending images to our cloud service

Raspberry Pi in Sugarpod

The device needed built-in illumination in order to capture usable photos of peoples feet to look for ulcers and abnormalities. Since the device needed built-in illumination to perform imaging, one of our team members came up with the idea of dual-purposing the LED lighting as a speech status indicator. In the same way that the Amazon Echo uses blinking cyan and blue to show status on the LED ring, our entire scale bed could do this.

As we started prototyping with basic audio microphones and speakers, we quickly discovered how important the audio-preprocessing system is in our application. In our testing there were many cases of poor transcriptions or unrecognizable utterances, especially when the user was standing any distance from the device. Our physical chassis designs put the microphone height around 2’ from the ground, which is far from the average user’s mouth, and also in real-world deployments would be in echo-filled bathrooms. Clearly, we needed to use a proper far-field mic array. We considered using a mic array dev kit, which we decided was too expensive and added too much complexity for the challenge. We also spent a couple hours investigating whether we could hack an Echo Dot to use it’s audio hardware.

Eventually we decided that it would make the most sense to stick with an off-the-shelf Echo for our prototype. Thus, in addition to being a foot scanner and connected scale, the device is also the world’s most elegant long-armed Echo Dot holder! It was easy to physically include the Echo Dot into our design. We figured out where the speaker was, and adjusted our 3D models to include sound holes. Since the mic array and cue lights are on top, we made sure that this part of the device remained exposed.

We will be revisiting the voice hardware design as we look at moving the prototype towards commercial viability.


Challenge 2: We wanted both quick-hit and guided interactions to use the same handlers for clean code organization but hit some speed bumps enabling intent-to-intent handoff

Our guided workflows are comprised of stacks and queues that hand off between various handlers in our skill, but we found this hard to do when we moved to Alexa Skill Builder. The Alexa Skill Builder (currently in beta) enables skill developers to customize the speech model for each intent and provide better support for common multi-turn interactions like filling slots and verifying intents. This was a big improvement, but also forced us rework some things.

For example, we wanted the same blood sugar handler to run whether you initiated a conversation with “Alexa, tell Sugarpod my blood sugar is 85”, or if the handler was invoked as part of a guided workflow where Alexa asks “You haven’t told me your blood sugar for today. Have you measured it recently?”

We tried a number of ways to have our guided workflow handlers switch intents, but this didn’t seem to be possible to do with the Alexa API. As a workaround we ended up allowing all of our handlers to run in the context of both the quick-hit entry point intent (like BloodSugarTaskIntent) as well as in guided workflows (like RunTasksIntent), and then expanded the guided workflow intent slots to include the union set of all slots needed for any handler that might run in that workflow.

Another challenge was that we wanted to use the standard AMAZON.YesIntent or AMAZON.NoIntent in our skill, however the Alexa Skill Builder does not allow this, presumably because it needs to reserve these intents for slot and intent confirmation. Our workaround for this was to use a fictitious slot (we called ours “ConfirmationSlot”) in basically all of our intents which could be “confirmed”, every time we wanted to ask for Yes/No values. We factored this into a helper library that is used throughout our skill codebase.

if (confirmationSlot.confirmSlotStatus === 'CONFIRMED') {
  confirmationSlot.confirmationStatus = "NONE";
  return true;
} else if (confirmationSlot.confirmSlotStatus === 'DENIED') {
  confirmationSlot.confirmationStatus = "NONE";
  return true;

Challenge 3: The Voice Kit speech recognizer did not always reliably recognize complicated and often-mispronounced pharmaceutical names

One of our intents allows the user to report medication usage, by saying something like “Alexa, tell Sugarpod I took my Metformin.” People are not always able to pronounce drug names clearly, so we wanted to allow for mispronunciation. For the Alexa Diabetes Challenge, we curated a list of the ~200 most common medications associated with diabetes and its frequent co-morbidities, including over-the-counter and prescription medication. These were bound to a custom slot type.

When we tested this, however, we found that Alexa’s speech recognizer sometimes struggled to identify medication from our list. This was especially true when the speaker mispronounced the name of the medication (understandable with an utterance like “Alexa, tell Sugarpod I took my Thiazolidinedion”). We observed this even with reasonably good pronunciation. We particularly liked “Mad foreman” as a transcription when one of us asked about “metformin.” Complex pronunciations are a well-known problem in medical and other specialized vocabularies, so this is a real-world problem that we wanted to invest some time in.

Ideally, we would have been able to take an empirical approach and collect a set of common pronunciations (and mispronunciations) of the medications and train a new model. It may additionally be interesting to use disfluencies such as hesitation and repetition in the recorded utterance as features in a model. However, this is not something that is currently possible using Alexa Skills Kit.

Our fallback was to use some basic algorithmic methods to try to find better matches. We had reasonable success with simple fuzzy matching schemes like Soundex and NYIIS, which gave us a good improvement over the raw Alexa ASR results. We also started to evaluate whether an edit-distance approach would work better (for example, comparing phonetic representations of the search term against the corpus of expected pharmaceutical names using a Levenshtein edit distance), but we eventually decided that a Fuzzy Soundex match was sufficient for the purposes of the challenge (Fuzzy Soundex: David Holmes & M. Catherine McCabe

Even though our current implementation provides good performance, this remains an area for further investigation, particularly as we continue to work on larger lists of pharmaceuticals associated with other disease or intervention types.



This challenge helped us stretch our thinking about the voice experience, and gave us the opportunity to solve some important problems along the way. The work we’ve done is beneficial not just for Diabetes care plans, but also for all of our other care plans too.

While the Alexa voice pipeline is not yet a HIPAA-eligible service, we’re looking forward to being able to use our voice experience with patients as soon as it is!

Posted in: Healthcare Technology, Voice

Leave a Comment (0) →
Page 1 of 15 12345...»