Is Your EMR/EHR Smart?

I’m reposting a comment I made on @techguy‘s excellent blog EMR & EHR. He tweeted:

I wrote my comment and tweeted:

And here’s my comment:

I wrote a blog post about this question several years ago, from which I’ll adapt this comment.

  • Question: Do We Need Smarter Users or Smarter User Interfaces?
  • Answer: Smarter User Interfaces.

Consider the distinction between intuitable EMRs (EMRs that are “figure-outable” by their users) versus intuitive EMRs (EMRs that figure out their users and do something useful with that insight). Intuitable usability corresponds to what I call shallow usability. It’s the “surface” or skin of an EMR.

In contrast, intuitive usability (used “correctly”) corresponds to what I call deep usability. It is about how all the components and processes deep down behind the user interface actively work together, to perceive user context and intentions, reason and problem solve, and then proactively anticipate user needs and wants. Deep usability is like having the hyper-competent operating room nurse handing you the right data review or order entry screen, with the right data and options, at the right moment in your workflow.


To perceive, reason, and act (let alone learn) EMRs need at least a rudimentary “brain.” When many folks think of medical artificial intelligence, they think of medical expert systems or natural language processing systems (rule-based, connectionist, or statistical). However, the most practical candidate “brain” today, with which to improve usability by improving workflow, is the modern process-aware (and context-aware) business process management (BPM) engine (AKA workflow or process engine).

Intuitive EMRs need to represent user goals and tasks and execute a loop of event perception, reasoning, and helpful action. BPM process definitions represent goals and tasks. During definition execution, goal and task states are tracked (available to start, started, completed, postponed, cancelled, referred, executed, etc) and used to coordinate system-to-system, user-to-system, system-to-user, and user-to-user activity.

BPM engines “perceive” by reacting to not just user-initiated events, but potentially other environmental events as well, an example of complex event processing. For example, a patient entering or leaving a patient class or category, going on or off a clinical protocol or regime, moving into or out of compliance, measuring or needing to measure a clinical value, or a clinical value becoming controlled or not controlled, are all complex events that can and often should trigger automated workflow.

Smart EHRs are adaptive, responsive, proactive, and capable of autonomous action.

  • Adaptive systems: these learn their user’s preferences and adjust accordingly….
  • Responsive systems: these anticipate the user’s needs in a changing environment.
  • Proactive systems: these are goal-oriented, capable of taking the initiative, rather than just reacting to the environment.
  • Autonomous systems: these can act independently, without human intervention.”


Learn, anticipate, goal-oriented, initiative, independent…none of these describe the behavior of today’s typical EMR towards its users. As a consequence physicians must compensate with a torrent of clicks (so-called “clickorrhea”) to push and pull these EMRs through what should be simple patient encounters.

What “drives” this smart behavior? An executable process model. In older terminology, a workflow, or process, engine, executes a collection of workflow, or process, definitions, relying on user input and context (the who, what, why, when, where, and how) to select and control definition execution. If the engine encounters inputs for which there is no model, then fall back on general purpose adaptive case management techniques for tracking goals and tasks, making them visible and actionable by physician users. Traditional BPM technology automates the predictably routine. More recent adaptive case management supports dealing with unpredictable exceptions—the high value-added knowledge work that diagnoses and treats the complicated cases.

Usability can’t be “added” to EMR. It has to inform and influence the very first design decisions. And there are no more fundamental early design decisions than what paradigm to adopt and platform to use.

No matter how “intuitable,” EMRs without executable process models (necessary to perceive, reason, and act, and later systematically improve), cannot become fully active and helpful members of the patient care team. Wrong paradigm. Wrong platform.

A truly smart EHR, on the other hand, has a brain, variously called a BPM, workflow, or process engine. This is the necessary platform for delivering context-aware intelligent user interfaces and user experience to the point of care. Right paradigm. Right platform.

In the spirit of advice from my Speech teacher about effectively and efficiently beating dead horses (”Tell them what you’re going to tell them. Tell them. Tell them what you told them.”) …

  • Question: Do We Need Smarter Users or Smarter User Interfaces?
  • Answer: Smarter User Interfaces.

#HIMSS13 Social Media Through the Roof: PS I Was Number One On Twitter!

[Since I wrote this post, I changed my Twitter handle to @wareFLO.]

The increase from #HIMSS12 to #HIMSS13 Twitter statistics is impressive. If they didn’t go through the roof, they at least went through the ceiling.


Especially impressive is the almost doubling of number of actual tweeters using the #HIMSS13 hashtag, since conference attendance dipped from around 37,000 to 35,000. I think this qualifies for “going through the roof” proportionally. Then there is this interesting visual, in which I overlay tweet volume from 8AM on Monday to 2PM on Thursday.


I think the folks on social media and the folks not on social media experience different conferences. I know that as my involvement with Twitter at HIMSS has increased (now pretty much all in!), my experience has changed dramatically. It’s easy to explain to others on Twitter. All you have to say is “You know what I mean,” much harder to otherwise explain.

For me, the major change between pre-Twitter and post-Twitter HIMSS conferences is that post-Twitter HIMSS seems smaller, much more intimate and personal, like HIMSS conferences used to be. Perhaps this is because the 3,000 odd tweeters operate as a conference with a conference. The massive receptions and exhibit hall can seem so large, with familiar faces so sparse, that they can be intimidating and exhausting. In contrast, Twitter plays matchmaker (delighted to meet you, how did I miss you, follow, follow, follow…), sidewalk entertainer (I wish I has smarts/wits/speed to have tweeted that!), and real-time location system (where are you, where are the presentations, where are the products and service you’re interested in?).

By the way, from opening #HIMSS13 bell Monday at 8AM New Orleans time to closing bell Thursday at 2PM, I was the top #HIMSS13 tweeter, if you don’t count @HIMSS13 which simply retweeted tweets containing the #HIMSS13 hashtag. I barked with the big dawgs! (Tweeted with the big birds!)

I’m @EHRworkflow in the following tweets.

Qualitatively, what I wrote in #HIMSS10 Best Ever: Due in Large Part to Social Media also applies to #HIMSS13. Except for the red rose in my lapel, now I wear a camera on my head. Quantitatively? Multiple by ten! (Hmm. I wonder if that is literally true, tweet-wise.)

The #HIMSS13 Stock Report: Meaningful Use Down, Usability Sideways, SMACWL Up, Social Through Roof

Short Link:

This is not an objective account of last week’s #HIMSS13 conference in New Orleans It is quite, quite subjective. As long as you keep that in mind, I hope you find it interesting and useful.

So you can cut to whatever interests you most (and so you can tweet links to individual segments), here’s a table of contents with links to anchors.

Meaningful Use, #HIMSS13, and #EHRbacklash

First, the elephant. The phrases “Meaningful Use” and “Meaningful [X]” were everywhere. Before #HIMSS13 I searched the HIMSS conference website and counted over 40 presentations with the word “meaningful” someplace in their title or abstract. Over a hundred exhibitors self-selected the meaningful use category of product or service, second only to the HIE category.

Recently, in the non-health IT media and social media, Meaningful Use has been pilloried. See my blog posts:

In return, the pillorers have been pilloried by some in health IT media and social media.

Meaningful Use at #HIMSS13 was mostly about cheerful progress and a rosy future. But there was some defensiveness too.

That second part of the tweet, “until HIT…”, that’s me editorializing, not abstracting from the news article.

As noted, on the surface, (almost) all was cheerful and rosy. Under the surface: psychic turbulence. Private conversation with front-line physician users of EHRs and health IT technical professionals were full of concern, exasperation, mixed feelings and “We can’t go back to paper!” On the #HIMSS13 Twitter hashtag I saw declarations (for example, embedded below) about what Meaningful Use should be (or should have been from the beginning), such a Meaningful Interoperability or Meaningfully Present.

The media has been criticized for not being evidence-based in its assessment of HIT and EHR success or lack of success. But there was actual data at #HIMSS13 about declining user satisfaction with EHR usability since 2010. I tweeted the following summary slide from a survey of 4,279 physicians.

This survey received considerable play in health IT media and social media during and after #HIMSS13. Since this blog focuses on EHR and HIT workflow, I’ll quote that portion of a blog post about the survey.

“With Meaningful Use, users may have lost some of their workarounds or have new ones that they have to do, e.g. clinical visit summary that now takes 10 clicks; as a result, workflow may feel more cumbersome.”

Government and vendor reps point fingers at each other. Pundits blame, in no particular order, rapacious vendors, micro-managing bureaucrats, oblivious patients, and Luddite physicians.

That last one really rankles. It’s classic blaming the victim, in my view. And it displays remarkable misunderstanding of both Luddites and physicians. The Luddites disliked automated looms because they were *too* efficient. Automated looms increased efficiency, reduced the amount of work to be done and therefore the number of humans to be employed. In contrast, in many physicians’ view, many EHRs or *not* efficient enough. They create more work for already overworked physicians. Furthermore, the Luddites lashed out at automated looms due to their working conditions, not because of hate of technology. Ironic it is, that these automated looms, especially the famous Jacquard loom, were forerunners of modern digital computers, and therefor EHRs too!

There’s even a new hashtag, #EHRbacklash. (Click the link to search recent tweets for this hashtag.)

#EHRbacklash has been fascinating to watch since it appeared in early February. It’s worth reading The Hashtag Economy, particularly about hashtags as forms of self-expression, and reflecting on tweets search for #EHRbacklash dredges up.

Frankly, I don’t blame any of the usual culprits. And I don’t blame broken business or incentive models. I blame the technology (Fixing Our Healthcare Mess). The problem with most EHRs and much HIT, with or without meaningful use, is workflow. If this is the case, I ask, maybe EHRs need to be built on workflow management system foundations instead of document management system foundations, as most are?

Social, Mobile, Analytics, Cloud, Workflow, and Language at #HIMSS13

On to SMACWL! You may already be familiar with SMAC, for Social, Mobile, Analytics, and Cloud. Since I blog and tweet so much about Workflow and Language Technology, I’ve taken the liberty to extend SMAC to SMACWL (rhymes with “tackle”). The SLA (Six Letter Acronym) works rather nicely.


To me the single most encouraging development at this year’s HIMSS conference was an interesting reversal of fortune. In past years, educational presentations were more exciting than vendor exhibits. This year the exhibit floor was more exciting than the presentation podium. Many of these companies leverage various combinations of the SMACWL technologies. Relative to the Workflow and Language tack-ons, I walked the HIMSS13 exhibit floor with a “HatCam” clicked to a ball cap while talking to myself about workflow and language technology.

For higher resolution, but shorter videos, visit HatCam Tour 2013: I Walk The #HIMSS13 Exhibitor Hall Talking To Myself About Workflow.

Much is made of Social, Mobile, Analytics, and Cloud and their potential to disrupt and transform. It is their combination that makes them most potent. Think of the synergy between ubiquitous smartphone video cameras with ubiquitous online video services such as YouTube. Now think not just two, but four, technologies coming together in creative and seductive ways. Social, Mobile, Analytics, and Cloud aren’t just platforms, they are becoming “the” platform. This platform is giant ramjet gathering people and resources, searching for innovation, delivering it, and then releasing people and resources for more progress.

People become aware of new ideas, technologies, and initiatives through social media (forming/orientation). They sound out potential partners through debate and agreement (storming/conflict and norming/cohesion). They move from superficial activity streams (Twitter, LinkedIn, even FaceBook) to email, forums, and task/case management systems (groupware and case management). Finally, for the data and workflow that’s worth it, tasks are performed while maximizing heads-down productivity.

At each stage of the funnel, some return to earlier stages, either because they’ve achieved what they sought or because they determine achievement is not possible for a given level of personal commitment of time, money, and resources. Finally, when workflows and processes are worked out, debugged so to speak, they are institutionalized in software and hardware, becoming an invisible and taken-for-granted ambient context of support and enablement.

Unstructured data (word, tweets, sentences) and unstructured workflow (do what you want when you want) gradually compile down to more structured data (database entries and tagged textual data) and structured workflows (executed by process-aware information systems). The unstructured to structured data relies on natural language processing. The unstructured to structured workflow business process management, workflow engine, and case management systems.

The SMACWL funnel is the big-picture platform condensing out of our social, technological, and economic ether. It’s bit further along in other industries, but healthcare is not immune from its operation. I saw lots of HIMSS13 exhibit vendors who combined two, three, four, or more of these six digital enabling technologies.

From my workflow- and language-centric point of view, SMAC is much like an epidemiological “vector”, bringing language-tech (particularly the machine learning aspects of natural language processing) and workflow technology (of special interest to me) into healthcare.

#HIMSS13 Social Media Through the Roof

#HIMSS12 to #HIMSS13 Twitter statistics are impressive. If they didn’t go through the roof, they at least went through the ceiling.


Especially impressive is the almost doubling of number of actual tweeters using the #HIMSS13 hashtag, since conference attendance dipped from around 37,000 to 35,000. I think this qualifies for “going through the roof” proportionally. Then there is this interesting visual, in which I overlay tweet volume from 8AM on Monday to 2PM on Thursday.


I think the folks on social media and the folks not on social media experience different conferences. I know that as my involvement with Twitter at HIMSS has increased (now pretty much all in!), my experience has changed dramatically. It’s easy to explain to others on Twitter. All you have to say is “You know what I mean,” much harder to otherwise explain.

For me, the major change between pre-Twitter and post-Twitter HIMSS conferences is that post-Twitter HIMSS seems smaller, much more intimate and personal, like HIMSS conferences used to be. Perhaps this is because the 3,000 odd tweeters operate as a conference with a conference. The massive receptions and exhibit hall can seem so large, with familiar faces so sparse, that they can be intimidating and exhausting. In contrast, Twitter plays matchmaker (delighted to meet you, how did I miss you, follow, follow, follow…), sidewalk entertainer (I wish I has smarts/wits/speed to have tweeted that!), and real-time location system (where are you, where are the presentations, where are the products and service you’re interested in?).

By the way, from opening #HIMSS13 bell Monday at 8AM New Orleans time to closing bell Thursday at 2PM, I was the top #HIMSS13 tweeter, if you don’t count @HIMSS13 which simply retweeted tweets containing the #HIMSS13 hashtag. I barked with the big dawgs! (Tweeted with the big birds!)

I’m @EHRworkflow in the following tweets.

Qualitatively, what I wrote in #HIMSS10 Best Ever: Due in Large Part to Social Media also applies to #HIMSS13. Except for the red rose in my lapel, now I wear a camera on my head. Quantitatively? Multiple by ten! (Hmm. I wonder if that is literally true, tweet-wise.)

EHR and HIT Workflow and Usability at #HIMSS13

At every HIMSS conference I focus on workflow and usability. This year I looked at every vendors website (1200+!) and searched for and read about workflow and usability. Sometimes I found interesting material among technical documentation, such as how to edit a process definition. Sometimes it was the marketing message fascinating (“Your Workflow, Only Better!”). Then I created an entire new website to highlight and showcase the #HIMSS13 vendors who, in my view, are going in the right workflow and usability directions.

Less than ten percent of the #HIMSS13 exhibitors qualified for a POW!HIT! Profile. POW!HIT! stands for People and Organizations improving Workflow with Health Information Technology. (Yes, it intentionally evokes the POW! and HIT! during the campy Batman TV series fight scenes.) Walking the exhibit hall I stumbled across a half-a-dozen more I need to add.

I managed to attend several #HIMSS13 presentations that impressed me.

Let’s review some tweeted slides from the Care Process Management presentation first.

Take a look at the title of this blog: EHR Workflow Management Systems. Now take a look at the following slide:

The slide came from a talk about Care Process Management, which is basically a rebranding of Business Process Management in respect for clinical sensibilities.

The following is a complicated slide that you won’t be able to make out unless you click the following link to see the originally uploaded photo. I also follow with an outline based on the slide.

Above is a business slide and the pink background of the Care Process Management Layer (AKA Business Process Management Layer) doesn’t help. The originally uploaded photo is clearer. Clearer yet is the following outline of layers:

Enterprise Process Architecture and Key Components

  • Users
    • Nurse
    • Physician
    • Health Professional
  • Web/Mobile User Interfaces
    • PC
    • iPhone
    • iPad
    • Portal
    • RFID
    • Whiteboard
  • Care Process Management Capabilities
    • Business Process Management Suite (BPMS)
    • Rules/Event Engine
    • Business Intelligence (BI) Tools
    • Collaboration Messaging
    • Notifications
  • Enterprise Service Bus/Integration Engine
    • HL7 Messaging
    • Database Management
    • Entitlement
    • Real-Time Location System (RTLS)
  • Application Layer
    • Patient Registration
    • Scheduling
    • Operating Room (OR) Management
    • Electronic Medical Record (EMR)
    • Communications

Note the prominent and important presence of a Business Process Management Suite in one of the middle layers of the architectures. Also notice that a process engine (slide below) is different from an interface engine (slide above). Though they increasingly share some functionality. I talk about this during my 25 minute HatCam walk of the exhibit floor.

It was a great presentation. I encourage you to watch it online on the HIMSS website.

On to usability!

I’ve been somewhat disappointed and frustrated many discussions and debates about EHR usability. (My two masters degrees, in Industrial Engineering and Intelligent Systems, included healthcare workflow, aviation human factors, cognitive science and artificial intelligence.) This presentation about usability myths was a pleasant surprise.

The following slide, about disillusionment and frustration among users is consistent with the previously tweeted slide about user satisfaction and EHR usability ratings dropping across specialties and vendors.

The number one usability myth is that clinicians aren’t uncomfortable with technology. If you’ll excuse me, that is a complete load of tripe. Physicians aren’t Luddites. As noted earlier, Luddites disliked looms because they were so efficient. Physicians who criticize EHRs usually do so because EHRs aren’t efficient enough.

No, current HIT technology doesn’t fit the way health providers think and work. I have written extensively about this (pick a post, almost any post, on this blog). A good place to start is a blog post about my five workflow usability principles: naturalness, consistency, relevancy, supportiveness, and flexibility.

I’ve also written about the second myth, that clinicians want everything on one screen. As I discuss in The Cognitive Psychology of EHR/EMR Usability and Workflow, Fitts’ Law (larger targets are more easily, quickly, and accurately hit) and Hick’s Law (the fewer the alternatives to the correct choice, the better) dictate just a few large targets across more than one screen. Smartphones are a good example of this. They chain two or three screens in workflows that do what the user needs to do.

The presentation emphasized, on more than one slide with respect to more than on usability myth, the importance of getting workflow right. Now, I would take this observation one step further. If the problem with EHRs and HIT is workflow, why not use workflow technology? If your interest is piqued, check out Contextual Usability, My Apple iPad, and Process-Aware Clinical Groupware.

Related to the problem with trying to put too much data and order entry options on one screen, is trying to stuff an EHR with too many features and functions. These bells and whistles get in the way of ease-of-use. This is the biggest detrimental consequence of Meaningful Use on EHR design. There is nothing necessarily unnatural about a physician or other clinical staff using using an EHR. However, if there is too much data, too many order entry options on too many screens, EHR use becomes very unnatural indeed. Meaningful Use has crammed to many features and functions into EHRs too quickly for designers to figure out how to make them usable and users to train to use them. I write about this in Fixing Our Health IT Mess.

This is a very good point. Since mobile devices have smaller screens, the need to be very selective about what goes on each screen is even more important. Interestingly, the success of smartphones and tablets are influencing both website and desktop application design. I actually looked at every website of every vendor exhibiting at HIMSS, as part of creating my POW!HIT! directory (People and Organizations improving Workflow with Health Information Technology, housed at Many #HIMSS13 exhibitors has websites that looked like they fit nicely on smartphones and tablets.

It’s true that allowing clinicians to customize screens usually won’t make them happy. What they really want to customize is workflow, or at least screen flow. And you can’t do this unless you’ve got a workflow engine executing process definitions, spanning data and order entry screens, editable by a human clinician who doesn’t have to be a programmer. Check out Can Healthcare Really Have Both Consistent and Flexible Information Systems?.

I absolutely agree with this slide, except I’d replace the words “information architecture for user workflow” with “workflow management system executing process definitions based on user workflow.”

Again, I agree with the following slide. Usability is more than a subjective experience. It reflects, at the very least, the fit between EHR workflow and user workflow. And, again, if the problem is workflow, then maybe we should use workflow technology to build EHRs?

One more usability myth: Usability Stifles Innovation. I agree this is a myth. But the cause and effect is reversed. Innovation drives and creates usability, not the other way around. I write about this in Efficient and Moral Market-driven EMR and EHR Usability Innovation.

There’s a another couple usability myths, but I am running out of steam! These were a great couple of presentations. One was about workflow technology and the other was about usability and workflow. They were fascinating to attend, one right after another!

This year’s HIMSS13 conference confirms trends I’ve writing about, and tweeting about, for years, the need for, and actual diffusion of, true workflow technology into healthcare. Workflow tech professionals call this business process management, which, apparently, needs to be rebranded because “business” not a welcome word in some clinical venues. Perhaps healthcare will be more comfortable calling these case management systems, since that overlaps with BPM and even derives is name from early clinical and social case management terminology. BPM researchers call these systems “process-aware” as in process-aware information systems (PAISs). If you are interested in learning more, I’ve got a couple of excellent interviews with world experts on workflow, BPM, and process-aware tech and its relevance to healthcare. If you got this far, you might as well read them!

Hajo Reijers, Head of BPM Research at Perceptive SW, on Healthcare Business Process Management

Short Link:

Last week, during #HIMSS13, I tweeted out individual questions and answers from the following interview with Prof. Hajo Reijers, runner up for “BPM Personality of the Year” in the Netherlands. Here is the combined interview. I’ve included the original tweets so you can retweet answers to individual questions….

From Prof Hajo Reijers’ personal home page:

“I am a full professor in the AIS group of the Department of Mathematics and Computer Science of Eindhoven University of Technology (TU/e) as well as head of Business Process Management (BPM) Research at Perceptive Software…. My research and teaching focus on process-aware information systems, business process improvement, and process modeling. I am closely cooperating with companies from the services and healthcare domains”

If you read this blog, EHR Workflow Management Systems, or follow me on Twitter at @EHRworkflow, you know how delighted I feel to engage Professor Reijers (Hajo!) in this interview. The good professor is also on Twitter…


Prof. Reijers,

1. Splitting your time between academia (TU/e) and industry (Perceptive Software) do you ever feel pulled in multiple directions? How are you integrating and synthesizing across roles and subjects? Unexpected advantages?

Yes, the difference of pace in these domains is what it makes it a bit
challenging sometimes. Industrial issues need to be solved yesterday,
but an academic puzzle may easily span months. What I try to do is to
find a balance between working on what is urgent and what is
important. For example, we are looking into a new style of process
modeling and need to know how usable it is. So, I am having a
lightweight workshop next week with a handful of professional modelers
within Perceptive Software, which gives me some tentative insights.
Concurrently, I am setting up a much more rigorous experimental
comparison that involves a hundred modelers, but will run in a couple
of months .

Unexpected advantages? Well, I found out that in industry people seem
to take you more seriously when you have an academic affiliation. But
that advantage is almost completely negated by those academics who
take me less seriously because I do practical stuff!

2. You’ve authored, or co-authored, over 150 papers, reports, chapters, etc., plus two books. Roughly speaking, how many are directly about healthcare? How would you characterize the current state of the art, regarding relevance of process-aware, BPM-style technology to healthcare and its information management problems?

I would say that 10% of my work is related to healthcare and that this
ratio is increasing. The healthcare domain is probably the most
underdeveloped area with respect to the use of process-aware
technologies. I simply cannot think of a domain that is more
functionally oriented, which is an enormous obstacle for the uptake of
BPM. I am mildly positive that this situation will improve, though.
You can see the influence and positive experiences with clinical
pathways, which bring a process focus to the work floor. For example,
in China each hospital is required by law to implement IT systems that
support healthcare professionals in adhering to clinical pathways.
Also, given the enormous pressure on healthcare institutes to reduce
costs, handle more patients, and improve safety, I think it is
inevitable that process-aware technologies will become widely adopted.
It’s a pity that it takes so much time and that the current focus is
purely on records.

3. When and how did you come to become Perceptive Software’s Head of BPM Research? From your unique perspective, one foot in research and one in industry, what are you most excited about in Perceptive Software’s product pipeline?

I started in this new role in September 2012. Perceptive Software
offers a wide suite of products, which include tools to search through
large amounts of data, tools to turn unstructured information into a
manageable form, a wide set of process management tools, and content
management tools (for which it is best known for). What thrills me are
the opportunities that there are in combining the data that is
collected and managed by what were once separate tools. Process
management, for example, will become more effective through deeply
understanding the data context of the activities that are being
managed. Also, access to historic and contextual data will help to
better predict the nature of new cases and how they can be managed

4. In an earlier role, I had the opportunity to work with process mining technology that is now part of Perceptive Software. I’ve blogged processing mining of healthcare event data. What is the key to productizing this amazing, and potentially very useful, technology in the healthcare space?

There are some things that have to be in place, of course. The
technology must be powerful and accurate; it must also be easy to use
and configurable by its target users. Once you have that, what is
needed most are success stories. And I think they are coming in fast. One of
the postdocs in our group, Ronny Mans, is carrying out a lot of these
projects. We have recently used process mining to investigate dental
implantology and are turning to eye surgery now. It’s amazing what we
find out and I think that these insights are hard to get by in any
other way.

5. Going beyond process mining how about todays modern business process management suite. I’ve written about why BPM has been slow to defuse into healthcare. What is it going to take, to get the workflow out of hardcoded Java and C# code and into formats more easily created, understood, edited, and improved?

Well, perhaps a certain generation of healthcare professionals needs
to die out first. My experience is that many of the younger doctors
are more open-minded to the use of technology and are really
interested in holistic approaches to improve the quality of care,
including BPM. I have seen this during my long-lasting cooperation
with a group of Dutch dermatologists, who are willing to try out any
good idea. Come to think of it: They are all women as well, by the
way–not sure whether this plays a role. And we need people like you,
Chuck, who spread the word 24/7. Keep it up.

6. Europe has been, and is, ahead of the US in exploiting workflow management systems and business process management suites. Netherlands appears, to this observer on US side of the pond, to be the largest and most influential center of process-aware thinking and technology in Europe. What are the historical roots of how this came to be?

Here is my ten cents. In many European countries, there is a tradition
of purely documenting how work is being done. Perhaps this is still a
relic of all these bureaucratic empires we had here. I am not saying
that mere adiministration is always that useful but capturing existing
operations is at least the basis for thinking about processes and
re-thinking them. In the US, there is much more emphasis on direct
results. And I admit that it is hard to answer the question of what
the ROI is of modeling a process or how it will contribute to
quarterly results. Europeans seem more receptive to the idea that you
may need to invest in something that pays off in the long run. At the
same time, I am still flummoxed about a highly efficient people as the
Americans not being interested more in BPM.

7. I understand that you recently came in second place in a contest to chose the “BPM Personality of the Year” in the Netherlands. You mention this during the open session of the recent BPM Round Table in Eindhoven, Netherlands. Have you gotten over this loss?

Ouch, thanks for reminding me. No, I will not get over that.

I grabbed the following shot of a slide shown during your introduction.


That’s an interesting list of topics:

  • Healthcare
  • Process Improvement
  • Data and Process
  • Visual Analytics
  • Harmonization
  • Public Sector
  • Process Architecture
  • Process Modeling
  • Process Mining
  • Model Management

I arranged them in order from familiar to unfamiliar to a health IT professional. Even “Harmonization” should resonate, since there’s been efforts to harmonize among different healthcare data standards. But one gets toward the bottom of the list it’s less familiar. Those last four terms, process architecture, modeling, mining and management. What are they and why should they interest a health IT professional?

Process architecture is about how processes relate to each other and
becomes increasingly important once you start working in a process
oriented manner. After all, processes interact in different ways, most
notably because people may work in different processes. This topic is
about how to capture and manage the relations between processes.

Modeling is mostly about graphical ways to describe processes.
Pictures are really liked by people and simplify communication between
them about processes. I think it’s the most widely researched topic by
BPM academics, too.

Process mining deals with techniques to infer from historic records
how operational processes actually work. A guy you previously
interviewed, Wil van der Aalst, is the godfather of this area.

Finally, model management is about how to deal with large collections
of process models. In Europe and Australia, we see that large
companies now have repositories of thousands of process models. These
are real treasure toves for these companies. Just think how you can
use such a collection to identify redundant work and find
opportunities to standardize work.

8. What question do you wish that I’d asked? How would you have answered?

That’s easy: “The next time you are in Washington DC, Hajo, will you
come with me and visit the Smithsonian together? I will give you a
personal tour.” I would have said: “Gladly.”

9. I believe we connected through Twitter. Did I find and follow you first? You’re lots of fun to follow, by the way. Links you share are interesting. And you are very interactive, retweeting and replying and so forth. I’m sure you’d agree that Twitter is fun. But is it useful?

I recall that I found you. You were Tweeting long before I started.
Yes, it’s highly useful, I would say. First, I thought that Twitter is
mainly used by people who wanted to share things like: “Just taken a
shower” , “Off to work”, and “Busy with stuff”. I found out that when
you follow the right people that this is an efficient way of becoming
aware of great content. In other words, I most value the filtering
function Twitter provide me with.

10. This is a request, not a question. Perceptive Software will have a booth at the Health Information Management Systems Society Conference in New Orleans, March 3-7. They were a very active tweeter at last year’s conference in Las Vegas. I hope you’ll monitor the #HIMSS13 hashtag and retweet, reply, etc. Could you tweet an introduction to yourself so I can embed the tweet here, as well as retweet it during the conference?

Thank you Hajo. That was fun!

My pleasure, thanks for having me!

Best Chuck

I Interview New M*Modal Website(!) on Future of Language and Workflow in Healthcare

Short (well, memorable!) Link:

Last week, during #HIMSS13, I tweeted out individual questions and answers from the following interview with [wait for it!] the new M*Modal website at Here is the combined interview. I’ve included the original tweets so you can retweet answers to individual questions….

I’m going to try something a little different this week. I’ll talk to a website! I usually submit geeky questions about workflow or language technology to an industry expert, then top it off with a One-Minute Interview (on YouTube) embedded in the resulting blog post.

I recently interviewed M*Modal’s Chief Scientist Juergen Fritsch, Ph.D. Like any good interview, it left me wanting more. As smart as Juergen is, using a whole-is-greater-than-the-parts logic, M*Modal must be even smarter than he is. But I can’t interview 12,000 people. So I decided to have a conversation with, M*Modal’s new website.

Live Thumbnail

By the way, I’m aware and concerned about walking the fine line between education and marketing (and have written about it). I am not endorsing any M*Modal product or service. However, I’ve written hundreds of thousands of words (and 15,000 tweets!) about workflow tech in healthcare. I look for confirmation wherever I can find it. 🙂 I certainly endorse combination of workflow technology and language technology to help make EHRs and health IT systems more usable and useful. M*Modal is a leader in this area and I appreciate their cooperation to increase public understanding of both workflow tech and language tech opportunities.

My interviews? They’re more like conversations in which I talk almost as much the person (or, in this case, website) I’m talking to. I’ll mention earlier blog posts, quote from Wikipedia, even textbooks.  I eventually do get to the point. I don’t think my interviewees mind. I’m not like Larry King, who reputedly never read the books before he interviewed their authors (“So, what’s your book about?”) I’m more like Charlie Lamb on CSPAN (“On page 582 you write, [Charlie reads a couple paragraphs]. What did you mean by that?”)

So,, thank you for agreeing to this interview. Silence. Hmm.

I searched for “workflow”. I got 165 hits. I looked at each instance and context. Using the most interesting material I created 10 “answers.” Then I wrote the questions.

Let’s try again…

1., in a nutshell, in words people who aren’t rocket scientists or computational linguists can understand, what problem are you trying to solve?

“Physicians are natural storytellers. They prefer to document the complete patient story by simply speaking and naturally capturing the full narrative. With Electronic Health Records (EHR) it’s not that simple. Clinicians have to change their behavior and use point-and-click into various templates that just can’t tell the whole story. Using EHRs, collaboration remains difficult, prone to errors and incomplete. Speech-based narrative documentation is workflow-friendly and permits the whole story to be told, and easily and more completely passed along, creating a much more collaborative sharing of intelligence from doctor to doctor.”

Nicely put! EHR usability is a big issue these days. “Clickorrhea” does seem part of the problem. Got it.

2. From your unique perspective, what is the connection between language tech and workflow tech?

“This is an absolute dead-on question, I’m so happy you asked it. The important connection is if we would just do speech-to-text transcription we wouldn’t affect anything. We’d just be creating a piece of text, without being able to drive actions. Ultimately we want to drive that action in the workflow – for example, have a physician create that order for a new medication. We want to make sure follow up happens and facilitate the workflow that enables that process from beginning to end. Also, healthcare is all about collaboration among providers. There is a lot of patient handoff and effective coordination of care doesn’t happen nearly as much as it should, and it only happens if proper workflow processes are in place. If we’re not trying to get involved in that process and drive more effective workflow processes, we’re not being successful in affecting change.”

(You’re right, doesn’t have “This is an absolute dead-on question, I’m so happy you asked it.” on it anywhere. That would be a remarkable feat of dynamic natural language generation and extrasensory perception now, wouldn’t it! It’s Juergen’s answer to question 8 in that recent interview. However, the interview is noted on M*, with a link to the full interview on my blog.)

3. I’m especially interested in how workflow technology, combined with language technology, can improve efficiency and user experience. Could you expand a bit on those themes?

(“Certainly” I faintly hear.)

“By extracting, aggregating, analyzing and presenting clinical information based on business intelligence, M*Modal imaging solutions make sure that the right information is available at the right time for game-changing workflow management. Based on semantic understanding, M*Modal technology dynamically reacts to what is said and what is known from priors to automatically initiate a unique, information-driven, situationally-appropriate workflow. This content-based, real-time, corrective and pre-emptive physician feedback and decision support not only enhance efficiency and user experience, but also support downstream processes like compliance, coding and quality reporting.”

Wow! Now this is a lot more technical! However, I wrote a paper a couple years about about using event processing and workflow engines to improve “EHR Productivity.” Let me go back and reread that…. OK…. yes, I do think we are speaking of similar ideas. I wrote about use of structured EHR data to trigger EHR workflows, not unstructured free text, but similar idea. Let me tease this apart.

  • Speech recognition turns sounds into free text.
  • Natural language processing turns free text into structured data.
  • Semantic understanding figures out what is means and which workflows to trigger.
  • So, based on what the physician says, within moments after it’s said, asking for clarification if necessary, tasks are automatically queued, executed, tracked, etc.

Am I right?

And then the strangest thing happened. The webpage refreshed and the following text appeared:

“In principle you’re right, except that this is not a sequential process where one technology works on the output of the previous one. Instead, we have tightly integrated speech recognition, natural language processing and semantic understanding in a way that they complement each other. For example, speech recognition accuracy is improved by leveraging some of the semantic understanding that would indicate that a physician is talking about patient problems, rather than patient medications. When you adequately combine all the technologies mentioned above, you get more out of it than just the sum of their individual capabilities.” has some seriously wicked tech to pull that off! Both natural language processing *and* natural language understanding, not to mention remote extrasensory perception!

4. I’m a visual kinda guy, at a high level, what does your language and workflow platform look like?


Thanks. Let’s unwind the workflow from the moment a physician says something to the moment it helps someone.

  • Real-Time Speech Recognition
  • Cloud
  • Automated transcription
  • Human post-editing?
  • Cloud
  • Natural language processing
  • Cloud
  • (Then, in parallel, no particular order)
    • Insert data into EHR
    • Submit codes to billing
    • Distribute management reports
    • Analyze data to improve effectiveness and efficiency

Speech Understanding, the small cloud on the upper right, is sort of a label for the entire cloud, including speech recognition, natural language understanding, and workflow orchestration, right?

How did I do?

“Very well!! And as I said in my previous comment, Speech Understanding represents a tight integration of various technologies, using them in a non-linear way.” is even diplomatic! That requires remarkable discourse processing technology.

5. It would be great it we could actually track a hypothetical phrase, from beginning to end, what NLP engineers call a “linguistic pipeline.”

“While we could provide an example of that, it would look fairly generic and like any other NLP pipeline you may have seen before. The core differentiator of M*Modal’s speech understanding technology is that we don’t run a sequential pipeline, but that we have feedback loops and non-linear interactions between the individual stages of speech recognition, NLP, etc.”

“[F]eedback loops and non-linear interactions”, yes I’ve read about this. Speech and language understanding is a complex mixture of data-driven, bottom-up processing and context-driven, top-down processing. (Just think if how many times you don’t actually “hear” what’s said, but know it nonetheless purely from context.)

6. About that sub-cloud labeled “Workflow Orchestration”… Are we talking “workflow orchestration” in the same sense it is used in the workflow automation and business process management community?

From Wikipedia:

Workflow engines may also be referred to as a Workflow Orchestration Engines.

“The workflow engines mainly have three functions:

    • Verification of the current status: Check whether the command is valid in executing a task.
    • Determine the authority of users: Check if the current user is permitted to execute the task.
    • Executing condition script: After passing the previous two steps, workflow engine begins to evaluate condition script in which two processes are carried out, if the condition is true, workflow engine execute the task, and if execution successfully complete, it returns the success, if not, it reports the error to trigger and roll back the change.

Workflow engine is the core technique for task allocation software application, such as BPM in which workflow engine allocates task to different executors with communicating data among participants. A workflow engine can execute any arbitrary sequence of steps. For example, a workflow engine can be used to execute a sequence of steps which compose a healthcare data analysis.”

Do you use a workflow engine? Could you describe what we discussed earlier in terms of this engine?

“We do use a workflow engine in various of our solutions. In the case of clinical documentation services, it is used to orchestrate the processing, proofreading and distribution of millions of clinical documents per year, involving tens of thousands of users. In the case of coding and clinical documentation improvement workflows, it is used to orchestrate intricate workflows involving a combination of technology and humans, with lots of different users with different roles.”

That’s fantastic! I think healthcare needs more true workflow technology, such as what you describe. I increasingly frequently prepend “Workflow engine sighting” to links I tweet from @EHRworkflow.

7. But I’d like to shift gears now, over to the computational linguistics and natural language processing side. Computational linguistics, the science behind the NLP engineering, includes conversation (discourse) and achieving goals (pragmatics), not just sounds, syntax, and semantics. Where do you see medical language technology going in this regard?

“Again, you hit it dead-on – in the past, people have ignored the pragmatics aspect. At M*Modal we have been focused on pragmatics since the very beginning. Where it’s all going is being able to understand the content of speech, using semantics and syntax to understand what people are really talking about. You are absolutely right that without pragmatics we’d never be able to accomplish what we’re trying to with NLP technology.”

8. I picked up a copy of Introduction to Pragmatics. It was a great review, since the last graduate course in pragmatics that I took was so ago. And I read it! (I’m planning a blog post about importance of pragmatics to EHR and HIT interoperability and usability.)

At the end of the book, in the summary, was this:

“Who could doubt that the world of artificial intelligence will soon bring us electronic devices with which we can hold a colloquial natural-language conversation? The problem, of course, is pragmatics. Not to slight the difficulties involved in teaching a computer to use syntax, morphology, phonology, and semantics sufficiently well to maintain a natural-sounding conversation, because these difficulties are indeed immense; but they may well be dwarfed by the difficulties inherent in teaching a computer to make inferences about the discourse model and intentions of a human interlocutor. For one thing, the computer not only needs to have a vast amount of information about the external world available (interpreting I’m cold to mean “close the window” requires knowing that air can be cold, that air comes in through open windows, that cold air can cause people to feel cold, etc.), but also must have a way of inferring how much of that knowledge is shared with its interlocutor.”


“Thus, the computer needs, on the one hand, an encyclopedic amount of world knowledge, and on the other hand, some way of calculating which portions of that knowledge are likely to be shared and which cannot be assumed to be shared – as well as an assumption (which speakers take for granted) that I will similarly have some knowledge that it doesn’t. Beyond all this, it needs rules of inference that will allow it to take what has occurred in the discourse thus far, a certain amount of world knowledge, and its beliefs about how much of that world knowledge we share, and calculate the most likely interpretation for what I have uttered, as well as to construct its own utterances with some reasonable assumptions about how my own inferencing processes are likely to operate and what I will most likely have understood it to have intended. These processes are the subject of pragmatics research.”

In his recent interview, Juergen said “At M*Modal we have been focused on pragmatics since the very beginning”. Could you expand on his comments?

You would be justified to suspect that the answer to this question is not to be found on However, Wikipedia says “Pragmatics is a subfield of linguistics which studies the ways in which context contributes to meaning.”

“Context” occurs 48 times on For example:

  • “Healthcare Challenges and Context-Enabled Speech
  • “the real context and meaning behind a physician’s observations”
  • Context-specific patient information — from prior reports, EHRs, RIS, PACS, lab values, pathology reports, etc”
  • “providing real understanding of context and meaning in the narrative – not simply term matching or tagging”
  • “combine […workflow management…] with Natural Language Understanding to bring context to text
  • “Enabling physicians to populate the EHRs with color, context and reasoning without changing their established workflow
  • context-aware content that is codified to standardized medical lexicons, such as. SNOMED®-CT, ICD, RadLex®, LOINC, and others”

I love the connection between context and workflow. I’ve written about that too. But my point here is: if pragmatics is about context and M*Modal is about context then M*Modal is about pragmatics too. I won’t go any further into the subject of the importance of pragmatics to healthcare workflow. I’m planning a future blog post about import of discourse, reference, speech acts, implicature, intent, inference, relevance, etc. to EHR interoperability and usability.

In our interview, when Juergen said “You are absolutely right that without pragmatics we’d never be able to accomplish what we’re trying to with NLP technology,” what did he mean?

“The context of any natural language statement is extremely important for the correct semantic understanding. It is not sufficient to identify a key clinical concept like ‘pneumonia’ in a statement like ‘Two months ago, the patient was diagnosed with pneumonia, which turned out to be a mis-diagnosis.” Pragmatics (context, really) informs us that the statement is about the patient, that it is about something that occurred 2 months ago, and that it was a false diagnosis. Without a level of pragmatics, we would completely misinterpret that statement.”

9. By the way, while the web page didn’t come up in response to my “workflow” query, I stumbled across an M*Modal developer certification program. Which leads me to my final question. All of this workflow technology and language technology for improving efficiency and user experience? How do I, as a developer (and I are one), harness what you have created?

HCIT vendors can take advantage of M*Modal’s free Partner Certification
Program. M*Modal Fluency Direct speech-enables electronic health records (EHR) and other clinical documentation systems by verbally driving actions normally associated with point-and-click, templated environments.

    • No cost to certify or for yearly recertification
    • Access to product development engineers
    • Access to product development documentation
    • Onsite engineering-focused, peer-to-peer training session
    • Featured on program website
    • Allowed to use a specialized certified logo
    • Co-marketing and marketing opportunities
    • Signage for tradeshows
    • Product labels and specialized documentation

How to Get Started

M*Modal has made certification as simple and smooth as possible. The certification process consists of an onsite Speech Enablement Workshop at no cost to the vendor. To get started, vendors simply visit and register or email us at We will follow up with you and provide additional information that will prepare you for the certification workshop.

Well now! I have to admit you nailed that last question. You even used bullet points. I’ve never, ever, had an interviewee who (er, which, that, you tell me, you’ve got all the grammar rules!), who did that before.

I appreciate all the time you’ve spent with me. I hope I didn’t put too much of a strain on the web server. If anyone has any follow up questions, are you on Twitter?

Cool! I already follow you.

Well, that was my interview, about the future of language and workflow, with the website. I’m sure you’ll agree that it’s remarkable.

HatCam One-Minute Interview Videos at #HIMSS13: Passion!

This post is a place to park some of the best HatCam One-Minute Interview videos tweeted on the #HIMSS13 hashtag during the HIMSS13 conference. I’ll precede each OMI with a screenshot of their Twitter profile, linked to their actual Twitter profiles so you follow them.

The following are links to anchors immediately preceding each Twitter profile and HatCam One-Minute Interview, just in case you’d like to tweet links to individual interviews with the context of this blog post.





What do all these One-Minute Interview Twitterians have in common?


HatCam Tour 2013: I Walk The #HIMSS13 Exhibitor Hall Talking To Myself About Workflow

Neither snow nor rain nor heat nor flaky wireless stays the HatCam from the swift eventual completion of its appointed rounds. (after Herodotus)

I usually write a blog post after the HIMSS conference (I will still, several even). But I need a place to park some YouTube videos during festivities. I’ll also tweet them separately during the daily deluge of tweets.

If you’ve never been to HIMSS, or are not here this year and miss the buzz, I affixed my HatCam to my Fighting Illini ball cap, and walked the exhibit floor. Here’s the HatCam…

…and here is 25 minutes of me talking to myself while shuffling down the mile-and-a-half (I think, certainly seemed so) “Mandatory Wide Aisle.”

You can also watch higher definition segments of running 5-7 minutes apiece. You’ll need to go to YouTube Settings (gear icon in lower right) and select 720p. At this rez you can more readily make out booth signage and expressions of people’s faces 🙂

In case you’d like to tweet links to individual clips, but still with in the context of this blog post, I’ve added the following anchors:

HatCam Tour: Perceptive SW to IBM

HatCam Tour: Philips to Epic

HatCam Tour: Nuance to FormFast and KLAS

HatCam Tour: M*Modal and Chipsoft to end of tour.

I hope you enjoyed our tour of the #HIMSS13 Mandatory Wide Aisle, from a point of view about two inches above my right ear!

#POWHIT at #HIMSS13: People & Organizations improving Workflow w/Health Information Technology

Short Link:

I searched for “workflow” on every website of every #HIMSS13 exhibitor (1200+!). I also searched for an active Twitter account. Some were surprisingly hard to find! I created two Twitter lists (they have a 500 member maximum).

Here are the 846 active #HIMSS13 exhibitor Twitter accounts I could find.

Feel free to subscribe. Let me know of more accounts to add!

For the 100 or so exhibitors whose products and marketing “resonate” with the 200+ posts on this blog and 16,000+ tweets from @EHRworkflow, I created a POW! HIT! Profile on my new website at


In each profile I briefly describe the vendor, include a Live Thumbnail of their website (cool tech, but may not work on some smartphones), and explain why I think they should be recognized. I also embed a tweet mentioning their Twitter account, so you can easily find and follow. And then I present them with the POW! HIT! banner.







If you’re on the list below, congratulations, have a POW! HIT! Profile banner. Display it proudly! (Let me know if you need a custom size.) Please link back to your POW! HIT! Profile on If you’re not on this list, but you are reading this blog post after #HIMSS13, check out the to-be-kept-up-to-date POW! HIT! Profile index on

Resemblance of the POW! HIT! logo to the 1960 Batman TV show fight graphics is entirely intentional.

March 4-7 I’ll be tweeting about these vendors, as well as #HIMSS13 presentations of relevance to healthcare workflow, on the #POWHIT hashtag. If I mention you, I hope you’ll retweet, reply, etc. The better healthcare and health IT understand workflow, the better educated and prepared they will be to understand your value.

Depending on when you read this…

  • Have a great #HIMSS13.
  • Hope you’re having a great #HIMSS13.
  • Hope you had a great #HIMSS13.

Again, congratulations and keep up the good work!

ACF Technologies
AirStrip Technologies
Applied Pathways
Artificial Medical Intelligence
Axis Technologies
Bellevue College
Compressus MEDxConnect
DB Technology
Genensys SimplfyEMR-EHR
GSI Health
Harris Healthcare
Health Language Inc.
Innovative Workflow Technologies
Liberty Solutions
Northrop Grumman
Nuance Healthcare
Peer Consulting
Perceptive Software
Perforce Software
Philips Healthcare
Practice Insight
Praxis EMR
Quest Diagnostics
Sandlot Solutions
Shareable Ink
Siemens Health IT
Society for Health Systems
T-System, Inc.
Tableau Software
The Advisory Board
VitalHealth Software
Workflow EHR
Yseop (“Easy-op”)