Blog

Posts Tagged healthcare innovation

HIMSS WA Innovation Summit

I had the opportunity to attend the Washington HIMSS Innovation Summit, where leaders from Virginia Mason, Providence, Overlake, Seattle Children’s, UW Medicine, Vera Whole Health and Confluence spoke about innovation in their organizations. A lot of great themes and takeaways. These are the ones that stood out most to me.

Technology Adoption

Several panelists mentioned they have problems with their health systems adopting new technologies. Executives tend to bring in new technologies, get pilots kicked off, but struggle in the system-wide adoption. A lot of times new technologies are implemented and expected to work immediately. The reality is that no matter what Health Systems are implementing, they need to invest resources. Physicians and end users need to be engaged early on to really take ownership of the new technology. A well-defined change management process is also key to ensuring a successful adoption. Lastly, even though organizations are piloting the new technology, call it Phase 1 vs Pilot. Pilots imply a short-term project with and end date. Phase 1 makes the technology more real and gets people thinking about what Phase 2 and 3 look like.

Return on Investment

One of the panelists challenged any technology vendor to show him a technology that has ROI. He said his organization does over $200M in uncompensated care per year so he must evaluate new technologies against cost of patient care, which is a valid point. This brought up an interesting discussion about what health systems consider to be a ROI. Not all technologies will give Health Systems dollar-for-dollar return. Some technologies will. ROI can be a blend of hard and soft cost, so it’s important to spend time thoroughly defining a business case and make sure that success metrics align with the overall mission of the Health System.

Patients

I was surprised at how much of the discussion was focused around clinician-facing vs patient-facing technologies. I agree better tools and algorithms for clinicians will directly influence the quality of care that patients receive. Virginia Mason panelists did a great job bringing everything back to the patients. Patients should be the center and they should have access to all their data, regardless of where it comes from, in one place. They should have one seamless app and experience for all their healthcare needs. We at Wellpepper could not agree more!

Key Takeaways

When evaluating and implementing new technologies:

  • Define a realistic business case and what financial and non-financial ROI looks like
  • Ensure alignment to Health System’s mission and goals
  • Don’t assume that new technologies can just be plugged in and solve all problems
  • Allocate resources and engage providers and end users from the beginning
  • Treat it as a multi-year, phased journey; call it Phase 1 instead of a Pilot
  • Have a solid change management process
  • Keep patients’ experience and needs at the top of mind

Posted in: Adherence, Behavior Change, Healthcare costs, Healthcare Disruption, Healthcare Technology, Healthcare transformation, HIMSS, patient engagement, Patient Satisfaction, patient-generated data, Return on Investment, Uncategorized, Using Wellpepper

Leave a Comment (0) →

Wellpepper Deployment Options

Health Systems have 3 ways to deploy Interactive Treatment Plans at their organization:

  1. Using Wellpepper templates
  2. Leveraging the best practices from Mayo Clinic
  3. Custom Care Plan based on own best practices

Wellpepper Templates

We have a partnership with University of Georgia Medical School, that allows residents to join us on rotation for a month. Through this partnership, and with our excellent research partners, we’ve been able to build care plan templates based on best practice templates for over 30 chronic and acute conditions.

Health Systems may choose to implement these Wellpepper Templates, with minimal effort, which makes this deployment option the quickest.

Mayo Clinic Best Practices

At HIMSS 2018, we announced a partnership with Mayo Clinic to make their best practices available on the Wellpepper platform (here). This allows for health systems to leverage interactive care plans developed with Mayo Clinic content. This is also a very fast deployment and only requires a few configuration decisions from the health system.

Custom Care Plans

The third and most commonly selected option, especially for comprehensive care plans, is to develop an interactive treatment plan based on the Health System’s own best practices. These implementations typically take a bit more time to deploy. One of our tenants is if we can’t do better than paper, then we shouldn’t be doing it. Because of this, we’ll spend additional time going through the existing care plan documentation/discharge instructions and provide guidance and recommendations for how to deliver content digitally in context of where the patients are in their care.

EMR Integration

For initial deployments, we’ll typically see Health Systems choose to start without EMR integration. This is due to competing priorities with IT and allows the Health System to get up and running more quickly.

Shortly after that initial deployment, or in parallel with, we will start to map out what EMR integration looks like, with the goal of streamlining the clinical experience. The graphic below shows several ways that we integrate with EMRs, with the first step frequently being single sign on for patients and clinicians, followed by an ADT feed to onboard patients.

For more information on how to get the most of your deployment, please email me at luke@wellpepper.com.

Posted in: Healthcare Technology, Interoperability, patient engagement, Using Wellpepper

Leave a Comment (0) →

See you at HIMSS19

HIMSS19 is a couple weeks away and we have a lot to be excited for!

Stop by and see us in the Personalized Health Experience, Booth 888-96. Alongside our great partners at Ensocare, we will be showcasing our latest product updates, discussing ROI for patient engagement platforms, promoting care plans based on Mayo Clinic best practices, and sharing our vision for the future of patient engagement.

We have a long list of booths to visit and sessions to attend. Below are some of the topics that we’re particularly interested in this year:

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

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 SemanticScholar.org 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) →

Patient engagement and design in the art of medicine

Patient engagement is controversial for many physicians because it interferes with the traditional values that arise from the several hundred-year old guild of medicine. Per the NEJM Catalyst Insights Council, patient engagement is characterized as patients interested in participating in choices about their health care, taking ownership of those choices, and having an active role in improving their outcomes. Given the current epidemiology of chronic diseases, it is not surprising that many patients have low levels of engagement as well as health literacy. As someone who is preoccupied with the diagnosis and treatment of diseases, it is difficult for me to view any problem solving from the patient’s lens; yet, I know through the literature and intuitively that how patients feel impacts their outcomes. The following are a few of the things I have learned and will work on as I improve my ability to deliver care:

  • Time = effectiveness Opinions of clinicians and leaders in patient care have determined that increased patient time with a health care team lends to increased engagement. A basic concept in human dynamics is that the mere exposure to someone over time is enough to start an unlikely relationship. Tack onto that high quality communication and understanding nuances of healthcare literacy, and you have a more engaged patient. In modern medicine, this would be accomplished through a multidisciplinary team effort. This task is challenging given the constraints of our current healthcare system. Could I increase time with patients through mobile technology? If there was an automated way for me or another care team provider to connect with patients via text or a quick phone call at specific intervals, I would be able to increase exposure and augment time.
  • Shared decision making is key Another finding of the NEJM Catalyst is that shared decision making is one of the most effective strategies in improving engagement. We learn about this academically through the interpretative model (as opposed to paternalistic, etc.) of provider-patient relations; but this is also just common sense. I like to think this gives patients a sense of control, a sense of choice in a matter, where frankly, a lot make be out of your control. We are also better able to accept the consequences of the decisions we make, rather than the ones that are placed upon us. One of the reasons that UNICEF has been effective in helping children around the world is from the core guiding principle that children inherently have rights. American political views are reflected in the current model of access, but I would like to practice medicine with the belief that patients have inherent rights. It is a slippery slope because patients’ actions can be counterproductive to their health – but my preference is still to protect patient autonomy.
  • Technology alone cannot solve the problem The concept of remote monitoring with wireless devices doesn’t appear to improve chronic disease management or outcomes. Technology alone cannot solve a dilemma in a people’s “business”. I would opt to use adaptive technologies that improve my relationship and sense of connectedness to the patient over technology that would offer mostly education or content to the patient. The idea of people taking ownership for a difficult problem is non-trivial. It requires motivation at a level that is primarily internal. How do you access that in people? In the self-help world, the most effective motivational coaches tend to elicit a hyper-emotional state in people along with placing a high premium on discipline. I think it’s logical to work on building a relationship, connecting, allowing a safe space for vulnerability, and witnessing the struggle to achieve begin from that foundation. While patient engagement is primarily a patient responsibility, I think providers have a responsibility to elicit patient activation as this directly affects outcomes.
  • Design-thinking can help When Indra Nooyi became the CEO of Pepsi, one of her top priorities was to explore her staff’s beliefs on the concept of design. She asked business executives to take photographs of anything that they believed constituted design. After such an abstract request, she noticed that not only did people not care to complete the assignment, that some had even hired professional photographers to complete the task. My interpretation of this story is that she believes that there is an artistic aspect in the most unsuspecting of transactions. According to IDEO, human-centered-design is about building a deep empathy with the people you are designing for. In the process of being inspired, ideating, and implementing, a design researcher explores the texture and what matters most to a person before execution of a solution. How is this any different from delivering empathetic, tailored care to a patient? What we do well in medicine, some of the time, is already done at a higher level of sophistication in the real world outside of our clinics and hospitals. While design-centric thinking may lead to innovations in healthcare, for the provider I think the greatest advantage is that you amplify the relationship you have with the patient and increase overall engagement.

Whether it’s the creation of something that didn’t exist before or making decisions that are influenced by intuition, everyone is at one level involved in artwork. Improving patient engagement particularly with design-centric thinking would bring more value and meaning to the art of medicine, a skill I look forward to building throughout my career.

Posted in: Behavior Change, Healthcare transformation, patient engagement

Leave a Comment (0) →

HIMSS17 Sessions of Interest

We are thrilled to attend a number of sessions at HIMSS17 with topics pertaining to Wellpepper’s Vision and Goals!

Patient Engagement

Sessions that impact our ability to deliver an engaging patient experience that helps people manage their care to improve outcomes and lower cost:

Insight from Data

Sessions that impact our ability to derive insight from data to improve outcomes and lower cost:

Clinical Experience

Sessions that impact our ability to deliver more efficient experience for existing workflows and are non-disruptive for new workflows:

 

Posted in: big data, Healthcare Technology, Interoperability, M-health, patient engagement

Leave a Comment (0) →

Cross-Fit for Healthcare: An HX360 Workshop

At the recent HIMSS 2016 conference in Las Vegas, Robin Schroeder-Janonis, Wellpepper’s VP of Business Development,  and I were up early for cross-fit. Not the total body workout you may expect, but a workout nonetheless in the session “Innovation Cross-Fit” facilitated by Leslie Wainwright, Molly Coye, Gregory Makoul, and John Kutz. The cross-fit in this session referred to cross-organizational teams, the type required to implement innovation in healthcare and the workout took the form of a workshop where participants determined how big of a lift it would be to implement a new innovation.

Each table was comprised of a cross-section of senior healthcare leaders including CIOs, CEOs, business development, innovation leaders, IT, and marketing/communications. As a warm up, we were asked to evaluate the effort to implement a new innovation from a number of axes including user experience, implementation, stakeholders, path to scale, and opportunity. Our table was asked to evaluate the Proteus Discover Platform, a new category of ingestible medicine. We were given a high-level brief of Proteus and set loose.

In evaluating the “lift” for Proteus our group took into consideration a number of factors. First, while the population that would receive the ingestible medication would be relatively small, the legal and privacy impacts could be huge. As a result, we ranked higher complexity on user training and stakeholders, particularly with respect to medical users who would need to explain how the medication worked. Implementation costs were low as there was no IT involvement and no new hires, and only some new hardware required.

Here’s an example of the scorecard from our table:

Cross-Fit For Innovation

The next step was to map the implementation journey by adding steps in the process and stakeholders involved at each step. Our group started with the process steps and added stakeholders after the initial process was mapped out. Others fully explored each step before moving on to the next in the process. We found that there were a few stakeholders missing from the provided stack, for example although this was a medication we didn’t have a sticker for pharmacists, and that we had stakeholders participating in multiple process steps: patients and end users for example were seen at multiple stages.

In this stage the interdisciplinary teams brought their own experiences and filters to the table, which resulting in a more inclusionary process. For example, marketing representatives suggested that although the board of directors was not required to approve the implementation because the budget was so low, that they should be on an FYI list before any press releases related to using the new technologies. Operations people pointed out that procurement was left out of the process initially, and yet they’d have to sign the contracts and issue the POs.

Here’s what the process looked like from my group:

Innovation Journey Map

Finally, groups presented to each other, and this is where things got really interesting, as you can see the approach differed significantly across groups. Our group heavilty weighted the beginning of the process while another used iteration to get the same effect. Another group’s results showed that organization was the driving principle.

IMG_2559 IMG_2558

 

For me, the top takeaways from the session were:

  • Don’t be surprised how quickly a group of individuals with completely different backgrounds and experiences can coalesce to get a job done.
  • Innovation takes a cross-disciplinary team.
  • Making sure the right stakeholders are involved at each step is important, and consider that stakeholders aren’t necessarily decision makers, but they can also be people who need to be informed about the project.
  • The more time you spend in the first part of the process the easier the actual implementation
  • Conferences need more interactive sessions like this but it would also be an easy activity for a team within a health system

Posted in: Healthcare Disruption, Healthcare transformation, Lean Healthcare

Leave a Comment (0) →

Something old, something new, something borrowed, something blue

As someone, (most likely French philosopher Blaise Pascal ) once said, “I would have written a shorter letter but I didn’t have time.” Stanford Professor Dr. Arnold Milstean started his talk for the Health Innovator’s Collaborative on “Providing Better Care With Less.” with a variation of this, saying that if he knew his topic better he would only have 4 slides instead of the 8. Those 8 slides represented so much practical data-driven advice and highly quotable and provocative statements like

“1/3 of healthcare spending could be cut without affecting anything except the quality of life of the providers.”

that it’s hard to imagine how rapid fire the content would have been with only 4 slides. Mistean took us along a path to define goals in healthcare transformation and then apply some simple formulas to affecting that change.

To determine some generally agreed upon principles for healthcare improvement, Milstean and team reviewed policy, research reports, and employer and payer surveys. The team found that getting to a 1% annual increase in quality, with a 30% reduction in costs, and a 2.5 percentage point long term increase in spend (less than GDP) would suit most policy recommendations and were therefore to be considered reasonable goals. To bring about this level of change, Milstean recommended implementing an “Old, New, Borrowed, Blue” strategy, which has nothing to do with marriage: it’s just a catchy and easy way to categorize some common sense thinking.

Old: Take a methodical review of existing evidence. As anyone who’s spent much time in healthcare research will tell you, there are a wealth of studies and best practices out there. Given that it takes 17 years to get from research to clinical practice, rather than starting a new study, reviewing what’s been done and implementing best practices is a better way to go.

New: Use technology to automate assessment, help with decision support, and improve workflow. Being at Stanford and working on multi-disciplinary teams lead Milstean to believe that the area healthcare could benefit most from “new” is in healthcare IT. In other industries the move to electronic records produced 2-6 percentage points in productivity improvement after 10 years. Healthcare, with only recent moves to electronic medical records, is just at the beginning of this and hasn’t seen the rewards yet. As well they have just scratched the surface of the digital opportunities.

Finding Outlier Physicians

Finding Outlier Physicians

Borrowed: Look at examples from other countries best practices and figure out how to implement locally. Milstean gave the example of a city in Finland where the time from stroke identification to tPA injection at an ER was 17 minutes. With each minute of time after the onset of stroke representing the death of 1.9 million braincells, emulating the Finnish model can have real impact on quality of patient life and long-term costs. (The average “door to needle” time in the US today is 60-75 minutes.)

Blue: Focus on human-centered design. Too much of healthcare is not working at the most basic human level, which as it turns out is the place where better and cheaper care resides. Here, Mistean showed a chart of “outliers” physicians who delivered a high-level of care at lower costs than their peers. It turns out what these physicians did differently was at the human level. They truly cared for their patients and looked at the whole patient, not the disease or not the specific incident. These primary care physicians acted as quarterbacks when their patients were managing complex issues with specialists. They cared, caught issues, and also motivated patients to participate in their own care.

The Impact of Blood Sugar on Parole Hearings

The Impact of Blood Sugar on Parole Hearings

While the formula is simple, it takes a lot of effort to change the system. Some are organization issues like the number of people involved in making any decision. One hospital, trying to implement a new program, took 3 months to get to the kick-off meeting due to the number of people involved in scheduling. The other issue is the human factor in creating repeatable systems. Here, Milstean used an example from the legal world, where judges were less likely to grant early release when their blood sugar was low. Comparing this to medicine, is remembering that everyone thinks that they are delivering high-quality care, but you often need data to convince them otherwise, and that you need to repeat, repeat, repeat to get to a precision that can cancel out the human factor. As a result, Milstean believes that computer science and behavioral science are two keys to making the big changes we need to improve quality and lower costs in healthcare.

 

 

Posted in: Health Regulations, Healthcare Disruption, Healthcare Policy, Healthcare Technology, Healthcare transformation, M-health

Leave a Comment (0) →
Google+