Thursday, February 26, 2009

From Dictation to Direct Computer Input

I hosted a panel at the recent TEPR conference on "From Dictation to Direct Computer Input" that included presentations from Laura Bryan (MedEDocs Transcription) and Louis Cornacchia, MD, of (Doctations). I already posted my presentation on LinkedIn and in Google Docs but with the consent of my co-presenters I post the other presentations here

Laura Bryan, MedEDocs Transcription:
"Narrative Data in the EMR: Have Your Cake and Eat it Too"

Louis Cornacchia, MD, Doctations, Inc.

Documentation at the Point of Care

and for completeness
Nick van Terheyden, MD
Dictation to Clinical Data: Automating the Production of Structured and

Wednesday, February 25, 2009

Healthstory - Providing Data to Healthcare Business Analytics

A recent posting by Laura Madsen on the b-eye-network site titled "The Impact of the Obama Healthcare Agenda on Business Intelligence" reviews the stimulus package and its potential effect on Healthcare Business intelligence and Analytics. As she points out the package has said they intend to invest in
“invest in proven strategies to reduce preventable medical errors.” First and foremost is wider adoption of electronic medical records (EMR)
There is little doubt that EMR's can contribute to improving medical errors but as Laura rightly points out this impact is limited as
the disadvantage is that much of the data is textual and therefore more difficult to analyze
And promoting the advantages of the data base centric solution that demands specific answers and fills in fields does produce "quantifiable data for analysis" but is very limiting to the physician, but more importantly is turning our most highly paid. knowledgeable expert, the clinician into a data entry clerk - as I have said before and was quoted here you don't find the CEO of Merrill Lynch entering stock data....!

So how do we satisfy this need while not limiting clinicians to the small boxes and multiple choice hunt and peck nightmare yet still satisfy the need for structured data to provide some of the value for applying business analytics to this burgeoning pile of data.

The answer is already here with the Healthstory Project that provides the perfect container to capture and hold the full story of the clinicians patient interaction. Satisfying the needs of the clinicians to capture the fine detail of the interaction but also fulfilling the data requirements for EMR's and Business Analytic systems. Healthstory has already created and published four technical guidelines for the
  • Consultation Note
  • History and Physical
  • Operative Note
  • Diagnostic Imaging Reports
and unlocks the valuable data from narrative documents enrich the flow of data into the electronic health record and creating interoperable clinical document repositories. The coalition is growing and you should expect to see these specifications becoming part of any requirements for clinical systems and documentation providers to be able to comply and both receive and send Clinical Document Architecture for Common Document Types (CDA4CDT) documents. Time to get on board.

Tuesday, February 24, 2009

Patient Confidentiality and the Clinical Documentation

Breaches in patient data by the clinical documentation industry shine an uncomfortable light on the industry and when stories surface (Slip puts Patient data on the Internet) of lapses in security relating to a transcription company they should be a wake up call to all the participants in the production of clinical documentation (read medical transcription companies, transcription editors, technology and infrastructure providers etc).

In this instance the patient was seen by Northeast Orthopedics in NY and they outsource their transcription to MRecord based on Raleigh NC who offer both technology and outsourced transcription solutions. Northeast Orthopedics rightly posts a letter on their web site (Letter to our Patients Regarding Patient Confidentiality) getting front of the issue, notifying their patients of the possible breach, apologizing and providing contact information for anyone who has a concern. But surprisingly there is no statement on the web MRecord web site regarding the security breach and while I could find some legal notices they were all about the protection of their solution and usage and nothing regarding the security breach......I suspect no plan in place for dealing with such an issue and a lock down the hatches mentality that often permeates when such mistakes happen.

Like every advancement in the history of mankind it can have good and bad uses. The internet is no exception. I am sure most of us would find it hard to imagine our business and personal lives without the ready access to information. Those weighty tomes - Yellow Pages were relegated to the recycling bin in our house (after passing through a quick session on learning how to tear them in half) once we realized that searching the internet was faster and more relevant. But that same relevance and ease of searching provides instant access to everyone on for all sorts of information. In this instance it was a chance finding on the part of a relative searching for condolence messages for her deceased daughter.

So if your belief is that your security and confidentiality is fine in part because no one would be interested in the data your company deals with - think again. The internet is a great leveler - it only takes one person and that information can then be instantly available to everyone else on the internet. Google just makes that even easier with its constant searching and compiling of information on the internet.

In the medical documentation industry we are dealing with confidential data every day - imagine this was your data and treat it accordingly. Use this as a wake up call to review your security and data practices and take the time to prepare a PR Disaster plan with the expectation that you will never need it.

How is your security? Have you ever had a breach or seen a breach and if so what was your feeling about it?

Thursday, February 19, 2009

Rating Doctors

The blogs and twitters are alive with commentary both good and bad on the concept of rating doctors. It all seemed to be triggered by a NY Times article: Restaurants Brings Its Touch to Medicine that discussed briefly the concept of developing a ratings system for doctors.
Now the editors are asking people covered by one of the country’s largest commercial insurers to post reviews of their doctors and rate them in categories like trust and communication. As in other Zagat guides, the responses are summarized and presented as scores that, in this case, are edited by the insurance company WellPoint. They can be viewed only by WellPoint customers. The reviews are being introduced online to millions of WellPoint’s Blue Cross plan members across the country.
Many folks jumped in - I tweeted the article and Paul Levy Blogged the conundrum which generated a veritable avalanche of comments including my own both positive and negative. e-Patient Dave (I still have not received an answer to where he keeps his time machine to cram 33 hours into a 24 hour day!) weighed in
I don't know how it'll all shake out. Being publicly judged by others is challenging at first; I've come to accept that some people are crazy and there's no accountin' for tastes, let alone the variability of provider or reviewer having a bad day.
and the justifiable concerns (this from Lachlan Forrow MD FACP)
...but if we develop systems that make it easy for any unhappy patient to post for the world her/his unhappiness and name my name, that would be a serious threat to my morale, and while it might not make me actively avoid patients I thought might express their unhappiness (though it might) it would almost certainly have reduced my energy for actively seeking out “difficult patients” because I found the challenges and occasional rewards had satisfactions that outweighed the frustrations.
But I think anonymous said it best for me:
Ratings are coming: On the web nobody needs your permission or approval to set up a ratings system. If it seems unbiased, fair and rates the things people care about it will get traction.
Do you want to help steer the bus or get run over by it?
I agree and here is what I said

  1. We have to start somewhere and adapt as we learn more about this concept
  2. It is currently being done anyway and with little consistency or transparency
  3. Like it or not much of the rating is about the overall experience, not so much the care or the doctor but the decor, cleanliness, friendliness & helpfulness of the staff, the quality of the food..... to quote a recent discussion with a specialist radiologists in cancer care "the value measurement has changed: it used to be measured based on whether you were carried out in a box or walked out, now we are so much better and more successful the measure of success is about everything else, food, decor, the linen"
  4. Having seen some of the shocking comparisons of success/failure rates in different hospitals for the same conditions even taking account of a different case mix I would definitely want some indicator on quality/comparison to help make my choice for obtaining what I believe to be the best care for myself and my family.
So lets get over it and get the ball rolling - the beauty of rating systems is that the community is self policing and correcting. Outlandish claims that are out of sync with the majority are quickly identified and squashed and attempts to manipulate the system are discovered and exposed quickly.

Tuesday, February 10, 2009

Why Speech Recognition is no Longer Sufficient

Speech recognition has been around for over 30 years and part of our consciousness since the mid 1960’s but it is only in the last 3-4 years that we have see the technology really start to deliver some value to the much beleaguered and over worked clinician. There are innumerable studies that demonstrate the savings linked to the efficiencies possible with faster report turnaround. Unfortunately producing more reports faster is not always the best answer and oftentimes this is simply making the patient information haystack larger. This tsunami of data is overwhelming even the best organized clinicians and many are struggling to keep up with this alongside the explosion of diagnostic and treatment choices. Keeping up with the medical knowledge is a full time job if anyone had the time – but they don’t.

Clinicians want to give great care - that's a universal maxim for the profession and anything that enables or facilitates this will be successful. But that's not what has been going on with speech recognition which has not only required a change in behavior to enunciate in special ways, dictate commands, speak slowly and add punctuation and in the ultimate punishment requiring the highly skilled and time pressured expert to review and correct poorly drafted content. The output is a blob of text that cannot be read or interpreted by the electronic medical record (EMR) since it is not machine readable.

Innovation in speech recognition was last made in 1993 when continuous speech recognition was rolled out. Since then the technology has stagnated and while allowing clinicians to type with their tongue has provided some efficiencies and improvements, speech recognition has failed to address the underlying challenges facing clinicians today. So now we have reached this point what’s next?

It is the capture of structured clinical data that can automatically feed the EMR that is the real goal. Achieving this requires an alternative approach to speech recognition, not just recognizing the words but actually understanding the meaning and context. Comprehending normal human speech is not a word recognition process but speech understanding process that takes as input not just the phonemes or parts of words but the complete context of a conversation including the intonation, the subject matter and relevant prior information which is all applied to the complete conversation. It is this process that enables humans to exhibit the “cocktail effect” which allows us to listen in to more than one conversation at a time even though we are not fully participating in either. The added knowledge allows for inferring of missed words and understanding the content allows us to complete the picture producing a fully understood interpretation of the speech. Speech understanding is the next frontier of innovation in clinical documentation.

This content can be stored as part of the full story - the Healthstory that contains the computer interpretable data AND the fine detail in the narrative that is the essence of clinical insight, judgment and essential to the transmission and flow of useful clinical information between all the team members delivering care in our multi disciplinary model.

Friday, February 6, 2009

Does the Information get Captured - Not even a Fraction of it

In an HIT moment with Andy Kapit, the CEO of Coderyte Mr HISTalk explores the trouble with coding. There are some good insights into the challenges facing the clinicians in the system and several great quotes.
They down-code because they are afraid to get audited, afraid that the system will not be reasonable. They are afraid to stand out and afraid that the fact that their patients are ‘sicker’ means that their higher codes will make them stand out. They are afraid — period.
There is enough in the way of pressures without adding more burden to clinicians in worrying about audit's and the veritable army of folks and companies who are employed just to investigate and find discrepancies. Ironically they are probably using more sophisticated tools to identify poor coding than the doctors themselves are using to create the codes.
As Andy says it creates "adversarial culture not only reduces the morale of the physicians, it forces the data to be more flawed than it needs to be"'s true it does, fear is not the answer. It's just like tax returns as described in a recent article in USA Today that suggested there will likely be an increase in tax cheating because of the high profile cases of folks who appear to have gotten away with it but:
Americans are among the most law-abiding taxpayers in the world, in part because the IRS uses computer matching programs that make it difficult to cheat, says Walter Pagano, a former IRS agent who is a partner at accounting firm Eisner.
But this is not clinicians cheating but a fundamentally flawed system cheating them through fear. As Andy said - talked about flawed....
Think about it — the most complex series of events most people endure in their lifetimes are reduced to three-, four- or five-digit codes
The heritage of these codes dates back to Henry VIII and the tabulation methodology used by Graunt to describe the 50 or so causes death that were the precursor to ICD coding system (this is from memory but the original article was in the Journal of Public Health: Public health, data standards, and vocabulary: crucial infrastructure for reliable public health surveillance. and I cannot find the copy of the article so if you have this please send it to me)

But it was this that really struck a cord
Physicians have these well-trained powers of observation and, with the full color of their narrative, describe what is wrong with us and what they are going to do about it. In that language are rich and complex concepts — some of which are negated, historical, related to a family member, or are equivocal because more information is needed. Does all of that valuable information get captured in the medical coding process? Not even a fraction of it. The information captured in the record accurately reflects the actual health of the patients. The information healthcare uses to evaluate the quality of care and outcomes is inaccurate — out of fear and is both measuring and rewarding the wrong things.
Excellent points indeed. To further complicate the issue the content is then dumped into text based files that contain a one dimensional view of much better to start storing this information in a richer more suitable container to capture the full story.... The Healthstory: "Comprehensive electronic clinical records that tell a patient’s complete health story." Such information to include the rich complex concepts and whatever codes are necessary to make the information computer interpretable. It can also include the billing codes and other richer vocabularies including Snomed-CT, Radlex and even ICD-10 should that ever arrive.

The project needs more members, both those providing the capabilities and the information as well as those consuming or using the information. You can sign up here.

I'd love to hear feedback on the Healthstory project - good and bad. If you are not a member - why not?

Why Participating in Blogs is Important

I had the privilege of meeting e-PatientDave at the TEPR conference this week. He was there to bring the patient's views to this conference - wow - that's a novel thought! Getting patient input at a conference on healthcare......this does not happen often enough. It was a commanding performance and one that should have been videoed and then youtubed but I think he has this in the plan based on what I read.

He has his own blog(s) e-PatientDave and is of course on twitter and is an advocate for the inclusion on the patient in the care process (whew - two eureka moments in a single post!). He made many compelling points, delivered an emotional and riveting diary of his incidental finding of an especially aggressive form of Renal Cell Carcinoma that he fought and won. He joined an impromptu tweetup at the evening reception and continued to engage throughout the conference. Much of what he does is on his own coin and time and done with the attitude that given the history every second is a bonus.

A post from last month on why he loves participating in blogs and healthcare is descriptive and a great study of the relevance of this media to our future.....if you are not involved in this media the world is going to pass you by. This post linked to Paul Levy's "Running a Hospital blog that is definitely leading the crowd in communication and openness. He had cited the news of the day on "Check Lists" - I talked about this last year in this post - Simple things save lives crediting Peter Pronovost and congratulating him on his recognition as a newly inducted fellowship. There was a great article in the New Yorker titled "The Checklist" that detailed the concepts and the amazing results

Social media power. Connecting and engaging everyone. If you aren't on board you should be. Do you agree or is this just more "stuff" to distract us form delivering care - you tell me.

There are so many ways to participate and here are some of mine (it's horses for courses - pick the media you like):

RSS Feed - Speech Understanding
RSS Feed - Navigating Healthcare
Follow me on Twitter
DM Reply on the Twitter