Saturday, March 15, 2014

Does Your Analytics Vendor Deliver Long-term Value?

Walking through the vendor area at HIMSS14, it was impossible to avoid being bombarded with analytics, analytics, analytics; everywhere you turned a vendor was advertising and pushing analytics. Unfortunately, most were overselling an underwhelming product. They look pretty, but they only scratched the surface of analytics and they will not be the partner that will carry your organization forward for the long run.

Before you pick an analytics partner and make a significant investment of time and money, you need determine if your vendor will be able to deliver long-term value. To do that, you need to understand the three phases of analytics and determine if your vendor will be able to support all three.

The first phase of analytics is descriptive analytics. Descriptive analytics use data visualization, statistics and mathematical models to show the current or historic state of an organization or population. The math may be fancy, but it only shows what has or is happening. This phase of analytics is best used for identifying patterns and correlations and is often used in management decision making. If your health system does not have transparency into its data, descriptive analytics can be a very powerful step forward. However, it is only phase one.

Predictive analytics is the second phase. We are all familiar with predictive analytics even if we don’t realize it. According to my phone, tomorrow is supposed to be sunny with a high of 70 degrees. Meteorologists have been using predictive analytics for decades, but it is relatively new technology to healthcare delivery. Predictive analytics are best used for relatively short term predictions of future state. In healthcare, that may mean predicting the number of nurses needed to staff a unit based on the number of expected admission and discharges, or risk stratification of an individual patient. I saw very few vendors that could clearly demonstrate meaningful predictive analytics.

The third phase is prescriptive analytics. Prescriptive analytics combines predictive analytics with pre-defined actions (or rules). The best known use of this type of analytics is automated trading on the stock market. The predictive algorithm predicts the price of the stock will rise if x or y occurs, so when x or y does happen the computer buys a predetermined amount of stock without human intervention.  Similar types of algorithms are used by Amazon to give you suggestions while you shop. No human is involved when they recommend you buy conditioner to go with your shampoo.

 There is extremely limited use of prescriptive analytics in healthcare, but its use will grow as we get better at population health.  At this time, the best use of prescriptive analytics is to identify a high risk population and then automate a low risk intervention. For example, if you were able to identify a group of patients at high risk for a heart attack you could then use an automated calling system to screen them for evidence of chest pain or shortness of breath. Those that screened positive could receive follow-up care and those that screened negative had a very low risk intervention.

As you consider an analytics vendor, look past the how pretty their graphs are and determine if they will be able to carry you through to prescriptive analytics. It will be hard to justify why,  after months of developing data models and making charts you need to do it again with a different vendor because your first one only did descriptive analytics.

Thursday, February 27, 2014

HIMSS14 Highlights (Vlog)

In addition to the incredibly powerful closing session by Erik Weihenmayer (@ErikWeihenmayer), Leigh Williams (@leightw) and I are bringing you our highlights from HIMSS14.

What were your highlights from HIMSS14? What would you like to see changed for HIMSS15?

Monday, November 26, 2012

Synergy in Health Care and Technology

noun, plural syn·er·gies.
the interaction of elements that when combined produce a total effect that is greater than the sum of the individual elements,contributions, etc.; synergism.
Physiology, Medicine/Medical the cooperative action of two or more muscles, nerves, or the like.
Biochemistry, Pharmacology the cooperative action of two or more stimuli or drugs.

Synergy is often listed as one of the most hated words in the corporate world. However, achieving synergy between clinicians and health care technology is a crucial element in achieving return on investment.

I have rarely been in discussions, meetings, or presentations where people are discussing how clinicians and technology are going to work together to produce the best outcomes. Most commonly, the discussion is centered on how we are going to tweak the technology to suit the clinicians... or motivate the clinicians to use the existing technology. Sometimes, the impact on the patient is part of the discussion, but rarely- if ever- is the benefit to the institution included. The content of these discussions are exactly why most institutions have not seen the return on investment that they expected from their health care technology.

Achieving synergy between clinicians and technology is absolutely necessary. Here's why. Clinicians are good at being clinicians: ambiguity and the unknown are acceptable and expected parts of their decision making. Computers, on the other hand, are good at being computers: they excel at making consistent and accurate decisions when provided with a full set of data. Most health care delivery involves decision making on both ends of this spectrum. When computers provide consistent and accurate information to clinicians  they are freed to make better decisions about the unknown. This facilitates optimal patient care, which of course benefits not only patients but creates value for institutions.

For anyone who has sat in a meeting like I described above, creating this needed synergy between clinicians technology may seem unlikely or even unattainable. The good news is that it is completely possible.

When I was involved in the project to decrease venous thromboembolism (VTE), it was clear to the team that interactions between clinicians and the EHR were synergistic. Recent research into the clinical decisions support tools we developed has actually quantified the effect of the synergy between providers and the EHR. While a computer-based algorithm could have been used to create reminders for clinicians about VTE prophylaxis, it would have only been 70% accurate in the population studied. However, without clinical decision support, providers were under-prophylaxing patients. By combining provider-based risk assessment with CDS to facilitate ordering prophylaxis, a greater than 50% reduction in nosocomial VTE was achieved. The synergy between clinicians and technology clearly improved care and outcomes for patients while also providing value to the institution by reducing never events.

Despite the sometimes negative connotations of the term "synergy," it needs to be on the agenda for any meeting discussing how clinicians and technology will work together to create the best outcomes.

Monday, August 20, 2012

Prioritizing End Users

Via tedytan on Flickr

Implementing an integrated electronic health record invariably results in competing priorities and competing end users. I've written before that I believe patients are the most important end user. However, that still leaves clinicians, technicians, support and ancillary staff- and the often-ignored institution- competing for high ranking in decision making and resource allocation.

In order to assist in decision making and set system-wide strategy, I utilize a three-tiered approach to ranking these needs. Growing up with a strong Star Trek influence, I've come to agree with the Vulcan notion that "the good of the many outweighs the good of the few."

With this belief in mind, patients, as a group, represent the top tier of importance. This means that with every decision that we make, we are asking "is this what is best for our patients?" If the answer is no, than another path must be chosen.

The second tier is the institution. The reasoning is two-fold.

Via puuikibeach on Flickr

First, the patients are best served through the success of high-quality institutions. The era of the individual physician providing comprehensive care is coming to a close in the US; it's simply too difficult for a single physician to organize and orchestrate the multiple facets of a patient's care. Although many are nostalgic for the days when a doctor made house calls with his stethoscope and bag, modern health care requires advanced diagnostics, multiple providers, nurse coordination, complex billing and an increasing technology.

Second, the institution exists as the governing body of the multiple individuals involved in delivering patient care. A successful institution will create an environment where conflicts are resolved and effective collaboration for the benefit of the patients is possible. The institution can arbitrate the wants and desires of individuals and groups of individuals to meet the ultimate goal of serving the patient.

Via janwillemsen on Flickr

The third tier are the individuals that are employed by or contracted by the institution. Many have tried to rank the importance of individuals and groups within this tier, suggesting that the desires of clinicians should receive greater weight in decision making than support and ancillary staff. However, in order to best meet the needs of the patients, the needs of these individuals must remain balanced. For instance, it does not serve the patient to purchase the fancy equipment requested by clinicians if it cannot be adequately disinfected by environmental services. Ultimately, the collective actions of every individual in the institution determine the quality of care that patients receive.

In order to realize the potential return on investment from integrated electronic health records, this tiered model must be embedded as a core value of healthcare institutions. By focusing efforts on benefiting patients, we will learn to use EHRs in ways that improve care and decrease cost, resulting in benefits for institutions and individuals.

Monday, May 14, 2012

For Immediate Release: #LiveTheGoLive via Live Tweeting

Chief Medical Information Officer Invites Public Inside Go-Live Experience Via Social Media

Dr. John Showalter, Chief Medical Information Officer at the University of Mississippi Medical Center is preparing to implement a fully integrated electronic health record on June 1, 2012. Thought to be the largest single-day go-live to date, 20+ applications will be implemented at 5 hospitals and 95 clinics throughout central Mississippi. As June 1 approaches, Showalter is sharing his experiences and insights on popular social media sites in an effort to demystify the “big bang go live.”

May 14, 2012

JACKSON, Miss. – John Showalter, MD will be live Tweeting his experiences as CMIO during the upcoming big bang go-live. On June 1, 2012, Showalter will lead the implementation of 24 applications at 5 hospitals and 95 clinics with over 6,500 users in the University of Mississippi Health System.

Showalter will be Tweeting from @JohnShowalterMD and using #LiveTheGoLive to convey the experience of the CMIO before, during, and after a go-live. He will also be fielding questions submitted via Twitter and engaging in discussions on Facebook at

‘While many healthcare leaders realize that a big bang go-live is technologically best for their institution, they remain apprehensive because of the operational challenges,’ Showalter said. ‘I am sure we will have our share of challenges, but I hope that by being open and honest about my experience, others will have less anxiety about large scale go-lives. Ultimately, it’s about doing what’s best for our patients and the community we serve.’

Showalter’s Twitter and Facebook communications will be separate from the official UMMC Twitter and Facebook updates.

Showalter has already begun Tweeting his take on the implementation process. He will continue to dialogue on both Twitter and Facebook leading up to and following go-live on June 1, 2012.

About John Showalter:
Showalter is a board certified Internal Medicine physician. He also holds a Master’s Degree in Information Systems and completed fellowship training in Medical Informatics. Showalter joined the University of Mississippi Medical Center last year to assist in leading the implementation of the electronic health record. He also practices Internal Medicine as a hospitalist.

John Showalter

Thursday, May 10, 2012

What is #GoLiveGetCKM?

Doctor, Patient, and EHR. Source

Going live with 20+ applications at 5 hospitals and 95 clinics is a big deal. But a fully integrated electronic health record isn’t the end game.

#GoLiveGetCKM is about keeping the patient in the forefront of our minds during the intensity and mayhem of a big-bang go-live.

#GoLiveGetCKM is what happens when we leverage our EHR in every way possible to benefit our patients through research, practice-based evidence, improved efficiency, improved quality and decreased cost.

#GoLiveGetCKM is not about getting the system working, it’s about working the system.

Follow me on Twitter and follow #GoLiveGetCKM to see where we are headed!

What is #LiveTheGoLive?

There are go-lives. There are big go-lives.  There are really big go-lives.

Big Bang Source

And then there are truly EPIC go-lives.

June 1, 2012 will be the dawn of an EPIC go-live at the University of Mississippi Medical Center. At 5am CST we are going live with 20+ applications in 5 hospitals and 95 clinics with over 6,500 end users. 

As the CMIO, I will be on the front-lines as we revolutionize health care in Central Mississippi. I will be live tweeting my experiences with this EPIC go-live. I am sure there will be challenges, but I’m also sure our team is poised for victory. Follow me on Twitter and follow #LiveTheGoLive to get the latest scoop!