Guest Article: Top 10 tips for successfully using speech recognition in EHRs and healthcare apps

August 28, 2010

Moving away from paper is an automation journey that is both challenging as well as rewarding and choosing the right data entry technology is certainly one of the biggest challenges. Choose the right data entry mechanism and your journey is smooth; choose unwisely, and you’re in for a great deal of pain. There is no right mechanism for everyone so you’ll need to go through the various options with great care. One of my favorite data entry techniques is speech recognition (something I use for dictating blogs and writing articles) so I invited Nick van Terheyden, MD, Chief Medical Information Officer (Clinical Language Understanding) from Nuance Healthcare to offer tips and tricks that can help simplify and ease the move towards electronic records using speech recognition. In addition to spending several years as a medical practitioner, Dr. van Terheyden was also behind the development of an electronic health record in the early 1990’s and later became a business leader in one of the first speech recognition Internet companies so he knows his stuff. He’s a very interesting physician and you can follow him on Twitter @drnic1 and on his blog, Voice of the Doctor. Here’s what Dr. van Terheyden had to say about how to maximize speech recognition in EHRs as well as some pitfalls to avoid:

  1. Have the right hardware installed – while technology has improved and Moore’s law remains in effect doubling the number transistors (and hence power) of the chip. But doubling the power in the laboratory and store doesn’t translate into doubling of power of the desktops in a clinical setting that may have been installed several years ago and are now underpowered for current applications. In fact for many the hardware is woefully inadequate and nothing will kill the value proposition than the dreaded hourglass cursor or worse repetitive delays and even crashes. Speech technology requires processing power and memory – make them available. Buying the low cost home computer from CostCo or Best Buy that features an older processor such as the older Intel Celeron. This is especially true for the Netbooks that just don’t have enough processing power or memory to meet the need. Much better to buy a higher end business machine with an Intel Pentium4 or AMD Athlon 64 chip with at least 1 Gb of RAM and preferable more.
  2. Intelligent application Coexistence – putting a speech recognition application on the same desktop as any graphic intensive application that creates 3-D models out of 2-D input (such as Vital Images Vitrea, Tera-Recon Aquarius or Barco’s Voxar 3D) is asking for trouble. Both these application need powerful processors and lots of memory. If both are installed they’ll be competing and likely neither will work well and frustrate users. Same applies to other processor and memory intensive applications such as video editing and processing applications or heavy data query/reporting tools.
  3. Use good quality microphones and sound recording equipment. Buying the cheapest microphone and expecting to get good results from speech recognition is similar to using the cheapest quality meats and food ingredients and expecting a 5 star dish worthy of placement in an Iron chef competition. If you want good results you need good quality audio. Most vendors have a recommended list of recording devices – find a range of choices and offer them to your users. Most of the modern Plantronic headsets are firm favorites with Speech recognition users including myself. The DSP 300 offers wireless connection, and the Audio 310 offers a flexible wired connection with straight audio jacks and a handy USB adaptor for computers that have no audio jacks built in. But for those looking for low profile connections the RevoLabs RF:xTag offers a device that clips on to your lapel for almost invisible recording capability. Bonus Tip: Assemble the full collection of styles and types of devices and keep them on hand available for users to view and test to determine personal suitability. One colleague has a suitcase filled with the various types of devices that is he takes to show colleagues the choices and help them settle on the most appropriate choice for them in their clinical setting
  4. Environmental Considerations. Think about the clinical environment – a busy and noisy setting may need a different approach for capturing audio. But there are basic actions – a radio playing loudly in the background is unlikely to help a speech recognition solution return accurate results. While the staff may want to have the radio playing this may not be the best choice if it interferes with the effectiveness of the technology. Bonus Tip: There has been some work that suggests that better than a quiet environment is an environment populated with White Noise – in troublesome areas introducing some white noise generators (assuming hey are acceptable to patients and staff) may help improve accuracy and the overall acceptance and usefulness of a speech solution.
  5. Create a Standard and Replicate. Once you have found the ideal configuration(s) using both technical specifications, local circumstances and requirements and some inevitable trial and error get several users to try the configuration to make sure this meets the broadest range of needs. Then rinse, lather and repeat. Take this configuration and replicate it faithfully throughout the facility, clinic or enterprise. So if you have found that Computer A, with a specific motherboard, memory size and type, hard drive, graphics and audio add options buy the identical set up and replicate the exact configuration down to the operating system version, software and even patches. This might sound daunting but this is exactly what corporate and enterprise IT system support centers do. They create one standard and then create an exact image of the drive and copy this to all the other machines (purchasing the necessary licenses for the number of installations created). This can be done with tools designed for this purpose for large numbers of machines or simply by following an identical setup procedure for each new machine. Once you have a working environment don’t be in a rush to update software components with the latest versions or patches before you test to make sure updates don’t break your working configuration.
  6. Anticipate Resistance. Expect resistance – resistance is part of life and best faced directly with a clear understanding of the reasons. Some of this arises from the prejudice based on historical bad experiences with technology that was implemented either before it was ready or without the right environment and support. Set up opportunities for everyone to see the technology in use and try it for themselves. Clinicians successfully using the solution in use in a there own clinical setting is most helpful in overcoming the resistance
  7. Quick Portable Guides. Develop a Short Guide/Cheat Sheet of Commands and tools and Techniques – taking a leaf out of the Apple playbook and simplify the experience. Overwhelming already frazzled clinicians with hours of training is unlikely to lead to success. Identify the key pain points of clinical documentation that can be helped using speech recognition and dictation, accepting that for some clinicians using speech may not be suitable for them at this time or in their particular circumstance and focus on delivering success here. This may not include all the features and short cuts available when using a speech recognition solution but early success is more important than using every element available in a solution.
  8. Preparation. Prepare, prepare and prepare some more – Once you have identified good targets offer a simple path to adoption that does not entail long user training sessions. Capitalize on the built in tools available in speech recognition products that jump-start the building of a customized profile. Pre load with previous reports for that user, carry out minimal audio enrollment and test the profile for effectiveness. At the elbow training is most helpful here to get a critical mass of users up to speed and using the solution effectively. Once you have the critical mass or early adopter super-users this group will help the late adopters when they elect to transition to using he technology (and this move will be driven in large part when they see their colleagues being successful using the technology)
  9. Horses for Courses. Some users will use the most basic features for simple typing replacement. Dictating into a box and seeing the results appear and being able to complete a document immediately may be enough. Mixed with some use of the keyboard and other documentation tools may be enough to keep some clinicians happy. Others may make use of templates, an the ability to customize standard content for different patient interactions. And there will be some who make extensive use of the features including all of the above as well as command and control to navigate applications, sign documents, display results and automate complex tasks. Accept the variation and be prepared to support all levels of usage –success is measured by each doctor not by a standard set by a group or department. If a doctor feels successful then he is
  10. Identify champion(s). More often than not facilities are full of existing users who have speech recognition in use in a range of circumstances. These individuals are often well connected to the industry and other power users through online forums and conferences. Identify them early and make them a apart of the process and implementation baring in mind that if you are asking them to give up clinical time they need to offset this lost income in some way – many contribute excess hours and time to projects to of goodwill and passion but finding ways to compensate them is likely to create a stronger more long lasting supporter

Digitizing medical records is not so much a destination but a journey and one that we must all take. There are challenges and achieving success is not entirely dependent on speech recognition technology but where it does make sense getting the best from the technology will go a long way to easing the strain everyone feels with change. The benefits are clear the question you must ask yourself as a physician is can you afford not to go digital and more importantly can your patients.

Also, if you’re looking for EHRs and other software don’t forget that you can get free medical software advice on HITSphere.com.

{ 0 comments }

Meeting practical business and security challenges of healthcare apps in the cloud

August 22, 2010

There has been, understandably, a great deal of interest for moving all kinds of applications “into the cloud” (like software as a service or SaaS) because it can ease deployment and reduce costs. However, due to the nature of the healthcare data, security is a special concern. If you’re interested in moving to the cloud, check out an article I wrote last week for IBM entitled “Cloud computing by government agencies“; while it’s focused on public sector, it’s just as applicable to healthcare sector because the problems are identical.

Here’s what I covered in the article:

{ 1 comment }

McKinsey estimates that MU incentives may pay for less than 20% of hospital EHR roll out costs

August 18, 2010

One of my favorite publications, McKinsey Quarterly, published an article this month entitled “Reforming hospitals with IT investment” which speaks in plain business language about the costs and benefits of hospitals rolling out EHRs. The article requires registration but is otherwise free and is worth reading. Here are some of the highlights for a 200 bed hospital:

  • They estimate the costs of EHRs to be around $80,000 to $100,000 per hospital bed
  • They estimate the government incentives will bring in about $17,500 per hospital bed
  • They say that if you use the high-end scenario of $100k per bed, the government incentives will amount to less than 20% of the cost
  • They note that these costs do not scale linearly for larger hospitals.

Here’s a graphic they have in their article that summarizes it well (click to see larger version):

{ 3 comments }

Guest Article: What the low-tech checklist can teach techies about medical business processes and proper system design

August 12, 2010

I’ve often said that if you can’t repeat something, you can’t automate it — meaning trying to jump into creating software or systems before you have identified and fixed your human processes is always prone to failure. One of the best ways to understand if your process is repeatable is to create checklists and see if people follow them. I recently ran across Jacob Ukelson, Chief Technology Officer of ActionBase, who is somewhat of an expert on human process management and action tracking solutions that enable organizations to manage business-critical processes. I invited Jacob to tell us how low-tech checklists can be useful in healthcare organizations and how as technicians we can use that knowledge in helping design systems. I’ve often wondered — if our users can’t follow simple checklists, can they really use complex systems? You can use Jacob’s advice in requirements gathering, process comprehension, usability analysis, and many other areas that have more to do with software success than the code we write. Here’s what Jacob had to say:

In his 2007 New Yorker article, “The Checklist,” writer Atul Gawande explores the work of a doctor at Johns Hopkins Hospital who wanted to bring a process model to the highly individualized, specialized work of physicians in intensive care units.  Medical personnel perform an average 178 tasks per day on the typical ICU patient, notes Gawande, raising the question of how to avoid errors in processes with so many steps.

The answer, according to a Johns Hopkins Hospital doctor at the center of the article, is checklists.  Using simple, low-tech, step-by-step guides for specific procedures, doctors in one sample study avoided an estimated eight deaths, 43 infections and $2 million in costs.

Even with their years of study, internship, residency and intense specialization, physicians experience risk in the area of human-driven, ad-hoc processes.  A management tool – in this case, checklists – enabled them to significantly lower that risk.  There is a lesson there for businesses – not just for doctors, but for the healthcare industry in general.

Management tools for knowledge work and knowledge worker productivity is a hot topic in the process management community.  The market is coming to the realization that knowledge work makes up a large and growing  part of today’s modern economies; and  studies show that while cost of goods sold (COGS) has gone down 2.7 percent over the last decade, sales, general and administrative (SG&A) costs haven’t budged (see “Five ways CFOs can make cost cuts stick”). Knowledge work isn’t the only component in SG&A costs – but it is the biggest and one that has traditionally thwarted attempts at management and control.

Topics like social business process management, adaptive case management and unstructured process management are different terms currently being used in the business process community for approaches to solving the problem of knowledge work productivity. The adaptive case management approach is particularly relevant in the healthcare industry, since case management is a recognized, well-established discipline in the field. Adaptive case management is an expansion of traditional case management technology and approaches.  It’s an attempt to look at knowledge work as a case process – not the kind of structured task that business process management tools address, but rather the barely repeatable, emergent processes done through meetings, conversations, e-mail and documents. There is no predefined rigorous model — the cornerstone of structured process management — so a different approach is needed. The goal of adaptive case management is to provide enough structure to knowledge work to make it manageable, but not so much as to strangle it.

So what’s unique about these types of processes? Well, first and foremost the focus is on the process instance, not a rigorous model of the process in general. The characteristics of these types of processes are:

  1. They consist mainly of interactions between human participants.
    1. Collaboration and negotiation are important components of the process.
    2. Documents are an integral part of the process. Documents are both consumed and produced as part of the process.
    3. Participants control the process and change it on a case-by-case basis.
      1. Participants are in charge of the flow, participant list and activities.
      2. Every process instance has an owner.
      3. Every process instance has a goal, deadline and a defined work product  (and often an associated guideline or best practice).

When analyzing unstructured knowledge processes, many times I have seen best practices and guidelines presented as checklists or a series of checklists (usually as Microsoft Word documents, or Microsoft Excel spreadsheets). Of course, checklists are a far cry from full-fledged process models.  They don’t go into enormous detail, they don’t prescribe how things should be done and they generally focus on a small part of a larger process.  However, checklists ensure that knowledge workers adhere to best practices, and they are much more fitting for human-centric processes than the models derived for more rote, automated tasks, such as business process management products.

Gawande explains in his article that the lowly checklist is quite effective as an aid for memory recall, particularly for those jobs associated with mundane matters that might be easily overlooked.  He also notes the value of explicitly stating the minimum, expected steps in any given process.

On his “Strategies for Internet Citizens” blog, Jon Udell notes that while the simplicity of the checklist might initially offend highly skilled workers, it is a valuable tool for any field, including IT and business.

Certainly, the complex, changeable processes that comprise 60 to 80 percent of the work performed in any business need a safety net for the risks inherent in human-centric activities.    Checklists are a start, and adaptive case management solutions are their extension.  By building in prompts for required process steps and establishing a means to audit business-critical, ad hoc tasks, adaptive case management provides organizations with the medicine they need to perform comprehensive action tracking and avoid the business equivalent of the ICU.

So which processes are candidates for adaptive case management?  They include:

  • Strategic and tactical management and decision-making
  • Processes that cross organizational boundaries
  • Processes requiring negotiations and commitments
  • Processes that change their structure and participants as work progresses
  • Processes that require an audit trail of commitments and actions to demonstrate compliance
  • Process that have deep implications and require investigation, such as suspected fraud or new business risk

Adaptive case management provides a process-oriented IT framework for managing these types of processes – or as Scott Francis puts it in his blog, “optimizing the outcome of an individual run of a process by providing better information and tools to the case worker:”

  • Ensuring every process instance has an owner
  • Ensuring every process instance has a goal, deadline and a defined work product
    • A goal defines what must get done, not how the process is done
    • May also provide an associated guideline or best practice (usually in the form of a checklist) that gives a generic outline of the process
    • Providing visibility within the context of the execution of a process instance or after it is complete
      • Details on both the emerging flow of the process (the hand-offs between participants) and the work done by each participant (either in summary or detail form)
      • Minimizes failed handoffs which are the most likely cause of process failure
      • Providing management and control through tracking, deadlines and goals
        • Process participants decide how to best achieve their goals,
        • Process owner can track the current process state and progress
        • “Hawthorne effect” can change participant behavior

The doctors Gawande mentions in his article balked at the checklists; they were unfamiliar tools in the realm of their workplace.  This is not so for adaptive case management solutions, which can be integrated into familiar Microsoft Office applications, enabling workers to easily adopt them as a natural extension of traditional methods for monitoring and tracking tasks.

{ 7 comments }

NIST says Meaningful Use Test Procedures have been approved by ONC

NIST updated Meaningful Use Test Approved Test Procedures page today:
The Approved (Pending) Test Procedures were formally approved on August 2, 2010 for the Office of the National Coordinator for Health Information Technology (ONC) Temporary Certification Program. Notice of the approval appears in the August 9, 2010 Federal Register. The set [...]

View Comments Read the full article →

Guest Article: Lessons from the trenches – transitioning to EMR without risking data loss

The government’s promise of billions in EHR incentives has you interested in what you might be able to get so many of you are looking for advice and lessons learned from practices who have taken the leap to EMRs. I invited James Andrassy, M.Ed, PA-C, who has worked as a healthcare provider for the [...]

View Comments Read the full article →

An overview of NHIN, NHIN CONNECT, and NHIN Direct

IBM developerWorks invited me to write an article that provides a technical overview of the National Health Information Network (NHIN) along with its related sub projects called NHIN CONNECT and NHIN Direct. The article was published today and covers how you can use CONNECT right now to create your own health information exchange (HIE) or [...]

View Comments Read the full article →

My view on HIT (or other technical) certifications

On July 14th I conducted a seminar on How Meaningful Use Impacts Healthcare Data Management and IT Professionals. It was pretty popular and I got lots of questions at the event and many afterwards as well. One of the questions that kept coming up over and over again was about how to enter the healthcare [...]

View Comments Read the full article →

NIST releases revised draft test procedures to adjust to the final Meaningful Use rules

As promised, NIST has released its revised draft test procedures to adjust to the final Meaningful Use rules that were unveiled last week. Here’s how they describe the latest updates:
Approved (Pending) Test Procedures
A Final Rule on an initial set of standards, implementation specifications, and certification criteria for adoption by the HHS Secretary was [...]

View Comments Read the full article →

NIST planning to update draft test procedures tied to final MU rules on July 22

NIST just posted the following on their Health IT Testing and Standards draft test plans page:
July 19, 2010 Note: A Final Rule on an initial set of standards, implementation specifications, and certification criteria for adoption by the HHS Secretary was issued on July 13, 2010. NIST is currently updating the Test Procedures [...]

View Comments Read the full article →

← Previous Entries