patient-generated data

Archive for patient-generated data

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) →

What Motivates You, May Not Motivate Me

At Wellpepper our goal is to empower people to be able to follow their care plans and possibly change their behavior, so we think a lot about how to motivate people. Early on when working with Terry Ellis, Director of the Boston University Center for Neurorehabilitation, wanted to make sure that our messages to patients that may struggle with adherence were positive. She works with people who have Parkinson’s disease, and stressed that while they may improve symptoms they would not “get better.”

Last week I had a similar conversation with an endocrinologist about diabetes care plans. People with chronic diseases are often overwhelmed and may take a defeatist attitude to their health. Feedback and tools need to be non-judgmental and encouraging. Ideas like “compliance” and “adherence” may not be the way to look at it. Sometimes the approach should be “something is better than nothing.” And humans, not just algorithms need to decide what “good” is.

Am I good or great?

Here’s an example, non-healthcare related of algorithmic evaluation gone wrong. Rather than applauding me for being in the top tier of energy efficient homes, the City of Seattle, says I’m merely “good.” There’s no context on my “excellent” neighbors, for example are they in a newly built home compared to my 112 year old one, and no suggestions on what I might want to do to become “excellent. (Is it the 30-year old fridge?) I’m left with a feeling of hopelessness, rather than a resolve to try to get rid of that extra 2KW. Also, what does that even mean? Is 2KW a big deal?

Now imagine you’re struggling with a chronic disease. You’ve done your best, but a poorly tuned algorithm says you’re merely good, not excellent. Well, maybe what you’ve done is your excellent. This is why we enable people to set their own goals and track progress against them, and why care plans need to be personalized for each patient. It’s also why we don’t publish stats on overall adherence. Adherence for me might be 3 out of 5 days. For someone else it might be 7 days a week. It might depend on the care plan or the person.

As part of every care plan in Wellpepper, patients can set their own goals. Sometimes clinicians worry about the patient’s ability to do this. These are not functional goals, they represent what’s important to patients, like family time or events, enjoying life, and so on. We did an analysis of thousands of these patient-entered goals, and determined that it’s possible to track progress against these goals, so we rolled out a new feature that enables patients to do this.

Patient progress against patient-defined goal

Success should be defined by the patient, and outcome goals by clinicians. Motivation and measures need to be appropriate to what the patient is being treated for and their abilities. Personalization, customization, and a patient-centered approach can achieve this. To learn more, get in touch.

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

Leave a Comment (0) →

Alexa Voice Challenge for Type 2 Diabetes: Evolving An Idea

For the past couple of months some of our Wellpepper team, with some additional help from a couple of post-docs from University of Washington, have been working hard on a novel integrated device, mobile, and voice care plan to help people newly diagnosed with type 2 diabetes as part of our entry in the Alexa Diabetes Challenge.

Team Sugarpod

This challenge offered a great opportunity to evolve our thinking in the power of integrating experiences directly into a person’s day using the right technology for the setting. It also provided the opportunity to go from idea to prototype in a rapid timeframe.

Our solution featured an integrated mobile and voice care plan, and a unique device: a voice powered scale that scans for diabetic foot ulcers, a leading cause of amputation, hospitalization, and increased mortality, and is estimated to cost the health system up to $9B per year.

During the challenge, we had access to amazing resources, including a 2-day bootcamp held at Amazon headquarters during which we heard from experts in voice, behavior change, caring for people with type 2 diabetes, and a focus group with people who have type 2 diabetes. We also had 1:1 sessions with various experts who had seen our entry and helped us think through the challenges of developing it. After the bootcamp, we were assigned a mentor, an experienced pharmacist and diabetes educator, who was available for any questions. Experts from the bootcamp also held office hours where we explored topics like

Early Prototype Voice Powered Scale & Scanner

how to help coach people in what they can do with an Alexa skill, and how to build trust with a device that takes pictures in your bathroom.

As we evolved our solution, we were fortunate to have support from Dr Wellesley Chapman, medical director of Kaiser Permanente Washington’s Innovation Group. We were able to install the device in a Diabetes and Wound Clinic. We used this to train our image classifier to look for foot ulcers, and compare results to human detection, and also to test the voice service. We used an anonymous voice service as Alexa and the Lex services are not currently HIPAA-eligible.

We gathered feedback from diabetes educators, clinicians at KP Washington, and across the country, and from people with Type 2 diabetes. While not everyone wanted to use all aspects of the solution, they all felt that the various components: voice, mobile, and device offered a lot of support and value. As well, we determined that there is an opportunity for a voice-powered scale and scanner in the clinic which could aid in early detection and streamline productivity. Voice interactions in the clinic are a natural fit.

Judges and Competitors: Alexa Diabetes Challenge

The great thing about a challenge is the constraints provided to do something really great in a short period of time. We’re so proud of the Sugarpod team, and also incredibly impressed with the other entries in this competition ranging from a focus on supporting the mental health challenges faced by people newly diagnosed with Type 2 diabetes to a specific protocol for diet and nutrition, to solutions that helped manage all aspects of care. We enjoyed meeting our fellow competitors at the bootcamp and the final, and wish we had met in a situation where we could collaborate with them. We also appreciated the thoughtful feedback and questions from the judges, and would definitely have a lot to gain from deeper discussions with them on the topic.

Stay tuned for more on our learnings through this challenge and our experiences with voice.

Posted in: Healthcare Disruption, Healthcare Technology, Healthcare transformation, M-health, Managing Chronic Disease, Outcomes, patient engagement, patient-generated data

Leave a Comment (0) →

Introducing Sugarpod by Wellpepper, a comprehensive diabetes care plan

We’re both honored and excited to be one of five finalists in the Alexa Diabetes Challenge. We’re honored to be in such great company, and excited about the novel device our team is building. You may wonder how a team of software folks ends up with an entry with a hardware component. We did too, until we thought more about the convergence happening in technology.

We were early fans of the power of voice, and we previewed a prototype of Alexa integration with Wellpepper digital treatment plans for total joint replacement at HIMSS in February 2017. Voice is a great interface for people who are mobility or vision challenged, and the design of Amazon Echo makes it an unobtrusive home device. While a mobile treatment plan is always with you, the Amazon Echo is central in the home. At one point, we thought television would be the next logical screen to support patients with their home treatment plans, but it seems like the Echo Show is going to be more powerful and still quite accessible to a large number of people.

Since our platform supports all types of patient interventions, including diabetes, this challenge was a natural fit for our team, which is made up of Wellpepper staff and Dr Soma Mandal, who joined us this spring for a rotation from the University of Georgia. However, when we brainstormed 20 possible ideas for the challenge (admittedly over beer at Fremont Brewing), the two that rose to the top involved hardware solutions in addition to voice interactions with a treatment plan. And that’s how we found ourselves with Sugarpod by Wellpepper which includes a comprehensive diabetes care plan for someone newly diagnosed, and a novel Alexa-enabled device to check for foot problems, a common complication of diabetes mellitus.

Currently in healthcare, there are some big efforts to connect device data to the EMR. While we think device data is extremely interesting, connecting it directly to the EMR is missing a key component: what’s actually happening with the patient. Having real-time device data without real-time patient experience as well, is only solving one piece of the puzzle. Patients don’t think about the devices to manage their health – whether glucometer, blood pressure monitor, or foot scanner – separately from their entire care plan. In fact, looking at both together, and understanding the interplay between their actions, and the readings from these devices, is key for patient self-management.

And that’s how we found ourselves, a mostly SaaS company, entering a challenge with a device. It’s not the first time we’ve thought about how to better integrate devices with our care plans, but is the first time we’ve gone as far as prototyping one ourselves, which got us wondering which way the market will go. It doesn’t make sense for every device to have their own corresponding app. That app is not integrated with the physician’s instructions or the rest of the patient’s care plan. It may not be feasible for every interactive treatment plan to integrate with every device, so are vertically integrated solutions the future? If you look at the bets that Google and Apple are making in this space, you might say yes. It will be fascinating to see where this Alexa challenge takes Amazon, and us too.

We’ve got a lot of work cut out for us before the final pitch on September 25th in New York. If you’re interested in our progress, subscribe to our Wellpepper newsletter, and we’ll have a few updates. If you’re interested in this overall hardware and software solution for Type 2 diabetes care, either for deploying in your organization or bringing a new device to market, please get in touch.

Read more about the process, the pitch, and how we developed the solution:

Ready When You Are: Voice Interfaces for Patient Engagement

Alexa Voice Challenge for Type 2 Diabetes: Evolving a Solution

 

Posted in: Behavior Change, chronic disease, Healthcare Disruption, Healthcare Technology, Healthcare transformation, M-health, Managing Chronic Disease, patient-generated data

Leave a Comment (1) →

In Defense of Patient-Generated Data

There’s a lot of activity going on with large technology companies and others trying to get access to EMR data to mine it for insights. They’re using machine learning and artificial intelligence to crawl notes and diagnosis to try to find patterns that may predict disease. At the same time, equal amounts of energy are being spent figuring out how to get data from the myriad of medical and consumer devices into the EMR, considered the system of record.

There are a few flaws in this plan:

  • A significant amount of data in the EMR is copied and pasted. While it may be true that physicians and especially specialists see the same problems repeatedly, it’s also true that lack of specificity and even mistakes are introduced by this practice.
  • As well, the same ICD-10 codes are reused. Doctors admit to reusing codes that they know will be reimbursed. While they are not mis-diagnosing patients, this is another area where there is a lack of specificity. Search for “frequently used ICD-10 codes”, you’ll find a myriad of cheat sheets listing the most common codes for primary care and specialties.
  • Historically clinical research, on which recommendations and standard ranges are created, has been lacking in ethnic and sometimes gender diversity, which means that a patient whose tests are within standard range may have a different experience because that patient is different than the archetype on which the standard is based.
  • Data without context is meaningless, which is physicians initially balked about having device data in the EMR. Understanding how much a healthy person is active is interesting but you don’t need FitBit data for that, there are other indicators like BMI and resting heart rate. Understanding how much someone recovering from knee surgery is interesting, but only if you understand other things about that person’s situation and care.

There’s a pretty simple and often overlooked solution to this problem: get data and information directly from the patient. This data, of a patient’s own experience, will often answer the questions of why a patient is or isn’t getting better. It’s one thing to look at data points and see whether a patient is in or out of accepted ranges. It’s another to consider how the patient feels and what he or she is doing that may improve or exacerbate a condition. In ignoring the patient experience, decisions are being made with only some of the data. In Kleiner-Perkin’s State of the Internet Report, Mary Meeker estimates that the EMR collects a mere 26 data points per year on each patient. That’s not enough to make decisions about a single patient, let alone expect that AI will auto-magically find insights.

We’ve seen the value of patient engagement in our own research and data collected, for example in identifying side effects that are predictors of post-surgical readmission. If you’re interested, in these insights, we publish them through our newsletter.  In interviewing patients and providers, we’ve heard so many examples where physicians were puzzled between the patient’s experience in-clinic or in-patient versus at home. One pulmonary specialist we met told us he had a COPD patient who was not responding to medication. The obvious solution was to change the medication. The not-so-obvious solution was to ask the patient to demonstrate how he was using his inhaler. He was spraying it in the air and walking through the mist, which was how a discharge nurse had shown him how to use the inhaler.

By providing patients with useable and personalized instructions and then tracking the patient experience in following instructions and managing their health, you can close the loop. Combining this information with device data and physician observations and diagnosis, will provide the insight that we can use to scale and personalize care.

Posted in: Adherence, big data, Clinical Research, Healthcare Disruption, Healthcare Research, Healthcare Technology, Healthcare transformation, Interoperability, M-health, patient engagement, patient-generated data

Leave a Comment (0) →
Google+