Blog

Archive for May, 2019

Transforming Health at Montana HIMSS Annual Spring Conference

Possibly the most interesting thing in healthcare technology is the breadth of scope that health tech needs to cover, and the talks at the HIMSS Montana annual spring conference represented that with talks about security, how to find money for projects, consumer engagement, and how to create a state-wide initiative for healthcare IT. Just like the state of Montana, talks covered a lot of territory.

 

 

 

Here’s a small review of what attendees experienced:

Voice Technology

I had the honor of kicking off the HIMSS Montana Chapter “Transforming Healthcare” conference with an introduction to how voice technologies show promise in patient care. There’s still a lot of concern in the industry about what these voice assistants are tracking, and the speaker immediately after me talked about a surgeon using Alexa to play music in the operating room (a non-compliant use as Alexa might be ‘listening’ to the conversation). However, today’s news that Comcast is also getting into the voice healthcare game shows that there is real promise and high stakes. If you’re interested in this topic you might want to check out our white paper on considerations for designing voice interfaces for patient care, or join me at Voice Summit in Newark this fall for a workshop.

Security

Not surprisingly security remains a hot topic in healthcare, probably because of the surface area of devices and IOT devices. While bad actors and hackers remain a constant threat, people and process are as important, and speakers stressed that often breaches are not malicious but when people don’t follow proper process like the backup company driver who left a van full of backup tapes in his driveway overnight where it was broken into.

Interestingly according to Fred Langston, CISSP, CCSK Executive VP of Professional Services CI Security, imaging systems account for almost 50% of security alerts, possibly because the systems involve both hardware and software, and have often been installed for years. EMRs are seen as relatively safe, and other risks come from devices, attached to the hospital network, where manufacturers have stopped upgrading or patching devices, or simply stopped support for them. The reason is that any sort of software or firmware upgrade requires new FDA certification, which may be cost prohibitive on a discontinued product. There are startups trying to solve this problem, however the FDA may also want to reconsider the unintended consequences of their certification program.

Generally, it takes 205 days within a hospital system until a compromised asset is detected. Decreasing this time and the time from the realization of the compromise and fix (known as dwell time), should be the goal of all IT departments. Hiring a security consultant organization may be the best bet for the broad scope of monitoring that needs to happen.

Finding Money for Innovation

Dianna Linder, MPA, FACHE Director of Grants and Program Development, Billings Clinic is a grant-writer who has been successful at finding funding sources for innovative projects. Much like targeting sales, donor targeting involves figuring out the value proposition you can offer to a particular donor. The Billings Clinic has a shark-tank day where everyone comes with their projects to request funding. Projects are stack-ranked and budget is applied. For those that don’t get budget, Linder looks for other sources like grants. She warns that grants are best used for projects that are new experiments and where the headcount is not part of the spend since they cannot ensure someone of a job when the grant money runs out. A great example of a use of grant money was for building an intake facility for mental health, so that people did not languish in the ED. This program used staff that were already at the system and proved successful enough that it became operationalized the following year.

At Wellpepper, we’ve seen a few projects start with grants, like the one that the Schultz Foundation provided to EvergreenHealth to kick off a patient engagement project that has since been operationalized. Grants for research projects like the one with Harvard are also interesting.

Consumer Experience

Ben WanamakerHead, Consumer Technology & Services from Aetna made us promise not to blog or tweet about his session where he shared some results from Aetna’s partnership with Apple’s smart watch. So, go see for yourself how the application uses behavioral economics and design principles to reward people for healthy behavior.

Building a State-Wide Healthcare IT Strategy

Did you know that 10 states have a state-wide healthcare IT strategy? No? Neither did I. These strategies, when aligned with Medicare and Medicaid initiatives can help drive adoption and support for healthcare technology, innovation, and modernization initiatives. The benefits of the roadmaps are to focus on healthier residents, and freeing information. Another important benefit is funding that is matched by the federal government. While this type of program may be out of reach for the average healthcare technology enthusiast, knowing that they exist can offer opportunities to align with larger initiatives.

Posted in: Adherence, Behavior Change, Health Regulations, Healthcare costs, Healthcare Disruption, Healthcare Policy, Healthcare Research, Healthcare Technology, Healthcare transformation, HIMSS, M-health, patient engagement

Leave a Comment (0) →

Way Way Beyond HCAHPs: Cleveland Clinic’s Patient Experience Summit

It was the 10th year for the Cleveland Clinic’s innovation & empathy conference, a journey at Cleveland Clinic which started from a question from an MBA student to then CEO Toby Cosgrove asking if the Clinic’s physicians learned empathy.

You can hear him tell the story himself, and it’s personal for him.

And, if you haven’t seen Cleveland Clinic’s quintessential video on empathy, be sure to check it out.

Dr Toby Cosgrove at Cleveland Clinic

This year, Dr Cosgrove was back to talk about what Google could learn from healthcare and visa versa, as he is a newly appointed advisor to Google Health. As a surprise, he was interviewed by the same student who asked the question so many years ago. Not surprisingly, Dr. Cosgrove believes that healthcare needs to embrace big data, and care outside the clinic. He didn’t have much to offer about what Google could learn, but we’d say protecting personal data would be the biggest thing.

Possibly because he’s no longer running a physician organization and yet he is a physician himself, Dr Cosgrove was pretty blunt about the biggest barrier to transform an organization to deliver empathetic care: the doctors themselves.

Dr Victor Montori at Cleveland ClinicAnother notable keynote came from Mayo Clinic’s Dr. Victor Montori, an endocrinologist, and author of Why We Revolt: A Patient Revolution for Kind and Careful Care. Dr Montori asks us to question our biases, assumptions, and language. He decries “industrial healthcare” where we “provide care.” Care is already a verb. He advocates a person-centered approach where the goals and needs of the individual, not billing or the organization are center. Dr. Montori talked about the phenomenon of doctors doing volunteer travel vacations in other countries because it gets them back to why they became physicians: to care for people.

 

The example of a woman struggling to understand her medication, and make good food choices while being aware of her culture reminded me of visiting my mom when she was in a rehabilitation hospital. When we started bringing homecooked meals and even restaurant takeout, she ate. Physicians couldn’t understand her weight loss and hair loss, blaming it on medication. The problem was the terrible nutritional value and taste of the food.

Patient Stories

Patient stories were a key feature in the conference, while backing research up with data is important, it’s the stories that people remember.

How Walmart Started a Movement of Engagement

The power of human stories was prevalent in the presentation from Walmart’s David Hoke, who has created a movement of better health activities within the Walmart employee base, a challenging job when some stores have 100 per cent employee turnover. To create a movement that inserted a healthy virus into stores, David turned to military strategy:

  • Compelling reason to join
  • Place to join
  • Have to have something to do
  • Have something to share with people they love
  • People follow people

Instead of going directly to digital health, the program was designed to be analog to have the broadest reach, and to overcome people’s fears of being tracked. The program featured story booklets in breakrooms that highlighted other employees journey’s to health. Participants described thinking “well if that person can do it, so can I” after reading the stories, and seeing videos of successful program participants.  By the way, if you’re a Walmart customer, you can also join the program, which is now available digitally as well as analog.

Nebraska Medicine’s Situational Interviewing

Observational patient interviewingIn order to find the patient stories, you have to ask the right questions, and HCHAPs isn’t doing that. We see this all the time at Wellpepper: You need to talk to patients to get the story behind the data points. In this example, a patient had rated Nebraska Medicine highly for caring about her. Rather than just accepting this as praise, researchers dug deeper and asked how the patient perceived this, and the patient’s example was of a nurse who noticed she had dry skin and applied lotion. Another patient rated the facility high on cleanliness because he saw a physician pick up some garbage in the patient’s room. The key takeaway from this session was that patients infer intent.

Geisinger Longitudinal Patient JourneyGeisinger’s Longitudinal Patient Record

Chanin Wendling from Geisinger talked about their implementation of a CRM to be able to track a longitudinal patient experience. Knowing when and where patients are interacted with by the health system will go a long way towards understanding their overall experience.

Wellpepper Digital Intervention for Seniors

Dr. Jonathan Bean from Harvard, talked about why interventions for seniors are so important, and how design impacts whether someone is considered “able” by sharing an example of a cross walk timer being decreased so that slower people could no longer get across the street. Dr. Bean the Director of the New England GREC at the VA, professor at Harvard, and our research partner at Wellpepper, and we were extremely proud when he presented results of the REACH digital intervention using Wellpepper that reduced ED visits in seniors by 73%. We’ll share more when the study outcomes are published in the journal of PM&R.

Financial Impact of Care

Another theme that bubbled up in so many sessions at the conference is the financial impact of care, and the intertwined aspects of financial and physical health. A few key points:

  • Walmart has introduced a banking/payday loan application for employees so that they don’t have to pay the exorbitant rates of quick loan companies.
  • People cut back in other areas of their lives to pay for healthcare
  • 95% of patients want to talk to their provider about healthcare costs but providers aren’t equipped to do so. They don’t want to talk to the health plan or billing/collections department.

This was my first time at the summit, but it won’t be the last, especially as it evolves to encompass more aspects of patient experience outside the clinic, and through non-traditional methods like chatbots, virtual assistants, and virtual reality.

It’s hard to encapsulate all the learning at the conference, and no one person can attend all the sessions, but MobiHealth News has a great recap of the keynotes and individual sessions as well.

https://www.mobihealthnews.com/content/patients-more-vulnerable-other-consumers-technology-must-keep-human-empathy-center

https://www.mobihealthnews.com/content/north-america/without-co-design-technologys-healthcare-potential-wasted

https://www.mobihealthnews.com/content/north-america/providence-st-joseph-patient-engagement-begins-call-center

https://www.mobihealthnews.com/content/patient-stories-inspire-new-digital-tools-singapore-health-systems-sutter-health

Posted in: Adherence, Healthcare costs, Healthcare Disruption, Healthcare Research, Healthcare Technology, Healthcare transformation, HIMSS, M-health, Outcomes, patient engagement, Patient Satisfaction, patient-generated data, physician burnout

Leave a Comment (0) →

Self-Driving Healthcare

It’s 2019 and your car can drive itself most of the way to your doctor’s office, but once there, you will be handed a clipboard with a paper form asking you for your name, date of birth, and insurance information. Then you will wait to be seen by a doctor, who will spend your visit facing a screen transcribing your spoken complaint into the EMR, and then ask you where you’d like your lab results faxed.

How can it be that technology is making such huge strides in some areas of our lives, while others are seemingly stuck in the last century? When will healthcare have its self-driving moment?

The Promise of Self-Driving Cars

Self-driving cars are a great example of how computer science has been applied to solve difficult real-world problems. It was less than 15 years ago that the computer science community celebrated the first autonomous vehicles successfully completing a 130 mi course in under 10 hours as part of the DARPA grand challenge. Most of the heavily-funded university research teams that entered used traditional programming techniques. The winner of this competition, Stanford University, was characterized by its use of machine learning to train a vehicle by example, rather than writing the if-then-else code by hand.

Since this time, machine learning generally, and deep neural networks in particular, have proven to be unreasonably effective in solving problems with huge and highly complex inputs like image recognition, sensor integration and traffic prediction, among others. Companies like Waymo, Volvo, Uber, and Tesla have been pouring money into the autonomous vehicle space and making rapid progress. Many cars sold today come with some level of assisted driving like lane holding and collision prevention, and Tesla vehicles even come with a “Full Self Driving” option.

Machine Learning in Healthcare

So, what about healthcare? People’s health is a highly complex function of genetics, medicine, diet, exercise, and a number of other lifestyle factors. In the same way you make thousands of little steering corrections to stay in a lane, you make thousands of choices each day that impact your susceptibility to disease, quality of life, and longevity to name a few. Can the same toolset that can help cars drive themselves help us build good predictive models for health and healthcare?

There have certainly been efforts. Including some high profile failures. One big limitation is the data. On the one hand, healthcare is awash in data. Some claim it won’t even fit in the cloud (spoiler: it will). Much of the data in healthcare today is locked up in EMR systems. Once you’ve liberated it from the EMR, the next problem is that it’s not a great input for machine learning algorithms. A recent study in JAMA focused on applications of ML in healthcare found that EMR data had big data quality issues, and that models learned on one EMR’s dataset were not transferrable to another EMR’s dataset, severely limiting the portability of models. Imagine trying to build a self-driving car with partial and incompatible maps from each city and you’ll start to understand the problem with using EMR data to train ML models.

All The Wrong Data

But more important than this: even if the EMR data was clean and consistent, a big piece of the puzzle is missing: the data about the person when they’re not in the doctor’s office. We know that a person’s health is influenced largely by their lifestyle, diet, and genetics. But we largely don’t have good datasets for this yet.

You can’t build a self-driving car no matter how much many fluid level measurements and shop records you have: “I don’t know why that one crashed, its oil was changed just 4 weeks ago. And with a fresh air filter too!”  You also can’t build meaningful healthcare ML models with today’s EMR-bound datasets. Sure, there will be some progress in constrained problems like billing optimization, workflow, and diagnostics (particularly around imaging), but big “change the world” progress will fundamentally require a better dataset.

There are efforts to begin collecting parts of this dataset, with projects like Verily’s Project Baseline, and the recently-failed Arivale. Baseline, and others like it will take years or decades to come to fruition as they track how decisions made today impact a person many years down the line.

On a more modest scale, at Wellpepper we believe that driving high-quality and patient-centered interactions outside the clinic is a major key to unlocking improved health outcomes. This required us to start by building a communication channel between patients and their care providers to help patients follow their care plans. Using Wellpepper, providers can assign care plans, and patients can follow along at home and keep track of health measures, track symptoms, and send messages. Collecting this data in a structured way opens the door to understanding and improving these interactions over time.

For example, using regression analysis we were able to determine certain patterns in post-surgical side-effects that indicate a 3x risk of readmissions. And more recently we trained a machine learned classifier for unstructured patient messages that can help urgent messages get triaged faster. And this is just scratching the surface. Since this kind of patient-centric data from outside the clinic is new, we expect that there is a large greenfield of discovery as we collect more data in more patient care scenarios.

Better patient-centric data combined with state of the art machine learning algorithms hold huge promise in healthcare. But we need to invest in collecting the right patient-centric datasets, rather than relying on the data that happens to be lying around in the EMR.

 

Posted in: Healthcare Disruption, Healthcare Technology, Healthcare transformation, machine learning, patient-generated data

Leave a Comment (0) →

Reading for Healthcare Disrupters: In Shock, by Rana Awdish, MD

May 13-15, I’m heading to the Patient Experience Conference at Cleveland Clinic where Dr. Jonathan Bean, our research partner from Harvard Medical School will be presenting the results of a study using Wellpepper to deliver an interactive care plan for people between 65 and 85 who are at risk of adverse events. We’re excited about the positive clinical outcomes he saw, but more importantly, about the ability for technology to deliver empathy in patient care.

in shock book coverThe ultimate in empathy is to “walk a mile in someone’s shoes.” While this is often not physically possible, if you can emotionally understand someone else’s view this is the beginning of empathy. Research shows that reading fiction increases empathy, but I can imagine that non-fiction like Dr Rana Awdish’s compelling and gripping “In Shock” would do the same. Dr Awdish chronicles her near-death experience and subsequent recovery at the hospital where she practices. By becoming a patient with the mind of a doctor, she is able to deeply experience and understand both sides of a situation: the doctor who sees a case, and the patient who is so much more than a collection of symptoms. As a patient she experiences incorrect diagnoses, not being believed or listened to, arrogance, and condescension. As a physician, she struggles with her training to not get involved emotionally involved with patients and to shrug off traumatic events with her newfound understanding that experiencing pain is the only way to really empathize and connect with each other, and the only thing that will enable physicians to truly deliver care.

The book can be read as case study of experiences from both sides of the equation as Dr. Awdish struggles to make sense of her experiences, and learn how well-meaning instructions can result in the wrong outcome. For example, Dr Awdish reflects on her medical school and residency training and how it was designed to search for diagnosis not for meaning.

“We weren’t trained to listen. We were trained to ask questions that steered people to a destination”

When she’s taken to emergency and immediately steered to OB despite her protestations that the problem is not the pregnancy it’s something else, she directly experiences the impact of this training.

When Awdish is admitted to the hospital for bed rest during later pregnancy, her room becomes a defacto support group for medical professionals who need somewhere to properly process and sometimes grieve patient outcomes. This community defies their training which was to shrug off the emotions, and it’s during this period that Awdish comes to her hypothesis that switching communication may have the most powerful impact of all.

“This way of questioning, this recommendation built on empathy and a patient-centered narrative has the potential to heal everyone involved.”

Awdish is full of hope that the medical community can change. She’s a frequent lecturer and has won awards for building empathy and communication programs. The book also includes a study guide, and is being included in medical school curriculum.

You can hear Dr Awdish read from her book in this clip, or follow her on twitter @RanaAwdish

If you’re looking for more great reads check out these recommendations from our blog. Or, if podcasts are more your style, we’ve got those too.

Posted in: Behavior Change, Healthcare Disruption, Healthcare Research, physician burnout, Uncategorized

Leave a Comment (0) →
Google+