Navigating Healthcare – Patient Safety and Personal Healthcare Management

Virtual Assistants in your Future – Personal Healthcare Delivered

You can always rely on Hollywood to take concepts and extend them into the future – sometimes correctly (cloaking, holographic TV, forcefields and eco skeletons with mind control), sometimes incorrectly (aluminum dresses, atmosphere that is completely controlled, suspension bridge apartment housing). We have had speech recognition and Spock’s request:

So it was no surprise to find the latest Hollywood idea is the “Her” – a lonely writer develops a relationship with a newly developed operation system

Intriguing and challenging our current concepts with an exploration of artificial intelligence, voice and natural language technologies. These new styled avatars understand, listen and decipher what we say and something that Nuance has been developing and reinventing the relationship that people and technology can have. We can engage with our devices on our own terms and we have show these concepts in healthcare with our very own Florence – who is getting ready to launch in 2014

Ambitious you say – maybe but imagine the environment with intelligent personal assistants that hear you, understand you, know your likes and preferences – and in our world exist across your doctors office, the phone, surgery, hospital and elderly care and hospice. Cool? Liberating? Impossible?

If you’re Nuance, the idea is not only brilliant – it’s our focus and drive as we reinvent the relationship between people and technology. It is the chance to connect with your devices on human terms and presents infinite possibilities for intuitive interfaces that adapt to you.

Liberating our clinicians to focus on the patient and providing patients with someone they can talk to, interact with and who does have time for them. That future – coming to a doctors office near you:


Treatment Creep in Medicine – sucking Decency out of Patients

This recent post on the Atlantic: How CPR Became So Popular reminded me of a piece I wrote some time back – Doctors Die Differently. As I said then:

Its not that doctors don’t want to die, its just that they knwo they know enough about modern medicine to know its limits, importantly they have talked about this with their families as they want to be sure that no heroic measures will be used during their last moments in this reality

And the chart demonstrating the big discrepancy between what doctors want in life saving measures vs the general public pretty much said it all

So this piece in the Atlantic took it a step further – tracing the history of CPR from the 1960 at Johns Hopkins where the surgeons had

…successfully resuscitated every one of the first 20 patients they treated, 14 of whom (70 percent) survived without brain damage or other ill effects

But their source patients were not typical (young and mostly healthy) and when you extrapolate that out to an elderly population survival can fall to as low as 0% a variation in the effectiveness when performed in the real world
But it was Hollywood adn the media that pushed these procedures into the general awareness suggesting

…that two-thirds of all (fictional) cardiac arrests portrayed on ER (and other doctor shows) involved young patients who had suffered rare events like drowning or lightning strikes, rather than old people with heart disease (who account for 90 percent of cardiac arrests in real-life settings…..most of these fictional TV patients did well, unlike the vast majority of CPR recipients in real life

Dr Peter Benton was well known as all in life saving heroics

In fairness Hollywood was dramatizing some real life events – and they applied their pixie dust to this as they have to many other things.

But the problem remains and health care professionals need to help their patients understand their disease and make good choices, bearing in mind that heroics and life saving may well be a significant driver as it was for Stephen Jay Gould who was diagnosed with a rare and deadly cancer with a median survival of eight months…but as he said in his essay “The Median Isn’t the Message“.

this median survival means that one-half of patients die within eight months but the other half live longer. Most important, because the mesothelioma survival curve has a very long “tail,” a few lucky patients will live a lot longer

In his case his experimental treatment may have contributed to his 20 year survival past the original diagnosis…leaving a legacy of hope.

Florence – the Intelligent Virtual Assistant for the #EHR [Video] #MHealth

Video of the presentation from the Health2.0 show in October 2013 of the Florence Demonstration
You can see Florence in action at the site
or in the video below

Must we Move to ICD10 – Short Answer is Yes

Posted in Clinical Documentation, CLU, HealthIT, icd10, NLP, SNOMED CT by drnic on November 4, 2013

The short answer is yes – but I hear occasional stories and push back from clinicians and sometimes other healthcare staff – is it worth the spend and investment. Why not just wait for ICD-11 (Check out the beta draft of ICD-11 here). Why not just use SNOMED CT

For the individual doctor taking care of the patients they often see no direct benefit from ICD-10….or from SNOMED CT, LOINC, RxNorm, APR-DRG’s, ICD-9, APC’s, HCC’s, etc. But in the healthcare continuum that requires more than a single patient to be cared for and whole populations to be considered we need evidence and data to manage populations that has enough detail that has kept up with the explosion of medical knowledge. Yes capturing the codes may be difficult but the good news is there is technology to help clinicians to capture it at the point of care – anywhere and offers realtime feedback to the doctor with the unique and innovative Computer Assisted Physician Documentation (CAPD). ICD-10 is no longer to be feared but should be embraced as a bright new future that will start to code information in sufficient detail that is more representative of the complex nature of patients and their clinical condition. No longer grouped together in broad categories that do not adequately take account of the complex cases offering a much more nuanced view of the severity of illness.

So what is the difference between the two systems and what makes ICD-10 the right choice? Some of this relates to terminology and classification – nicely explained here by Dr Peter Johnson explaining the SNOMED CT system. As he says

Classification system,
A classification scheme could be thought of as a collection of buckets into which a care provider throws a particular concept or record. And since there can only be one bucket into which a concept fits, the process of labeling the buckets often leads to catch-all terms like: ‘Disease X, unspecified’ or ‘Y, not elsewhere classified’. As a result, accurately classifying records is rightly seen by most care providers as a separate process from record creation and is typically carried out by specially trained coders who know how to apply the process.

Terminology System
..a terminology allows the user to specify precisely what they want to record. Specifically, a terminology doesn’t have any ‘not elsewhere classified’ bucket terms, but is designed to have the terms that a user needs to record what actually happened.

Which brings me to the problem with SNOMED CT as a replacement for ICD-XX – clearly described by Carl Natale’s in his post: Why SNOMED cannot replace the ICD-10-CM/PCS code sets. As Carl rightly points out:

Physicians are going to have to learn how to communicate with EHRs — which will be based upon SNOMED — to comply with Meaningful Use. So the transition to SNOMED-CT already is in the works.

We do need more specific documentation but as a colleague of mine has pointed out this is not the onerous task that it first appears to be – much of the data is already information we capture as part of a normal clinical interaction and the additional data requirement may only be one clinical element.
For the construct of an ICD-10 code we have 7 characters made up as follows

  • Section,
  • Body System,
  • Root Operation,
  • Body Part,
  • Approach,
  • Device,
  • Qualifier

In a single specialty building up the code is part of the natural clinical content that we capture when documenting the patent encounter. The clinicians should not be expected to construct the code but does need to include all the details to allow the coding to be completed accurately. For example:

Open reduction internal fixation distal phalanx right index finger with K wire
contains everything necessary to code this as
0PST04Z – which is made up of:

  • 0 – Medical Surgical
  • P – Upper Bones
  • S – Reposition
  • T – Finger Phalanx R
  • 0 – Open
  • 4 – Internal Fixation Device
  • Z – No Qualifier

As Carl points out

Basically, ICD-10 codes aren’t the problem. It’s the specificity of documentation that will be required one way or another. SNOMED should make it easier to document to the required specificity. It is then up to the EHR system to convert that data to ICD information. Hopefully the physicians won’t know what level of ICD is being used. They will just need to know what needs to be recorded.

So what does this look like in the clinical setting – this video offers a peek into the new world of documentation and how Healthcare technology, Clinical Language Understanding and integrated solutions will start to ease the documentation burden, allowing clinicians to focus on care and the patient and not documentation coding

Technology as an Aid vs Hinderance to Doctors

A recent article in Becker Hospital Review:  Technology Should Aid Human Interaction: Q&A with Dr. Nick Terheyden, CMIO of Nuance featured some important points to make

Health IT needs to fade into the background. It needs to become part of the fabric of the office rather than the focal point, and then the interaction will change

  • Using the tools to allow the clinician to focus on the patient not the technology
  • Human beings deal in narrative and stories, patients want to tell their story and clinicians need the richness of the narrative to help guide medical decision making
  • Remove the Physical Barriers to the clinicians patient interaction
  • Healthcare is not the focus – the patient is

The key to our future and to the successful use of health IT will be turning the focus back on patient and the physician.

Intensive Care Information retrieval system

Posted in Clinical Documentation, CLU, EHR, NLP by drnic on January 14, 2013

Intensive Care Information retrieval system from our friends down under showing the value of Natural Language Processing to get into the detail of clinical notes, understanding the underlying content. The demo shows the ability to get to information even when there have been typographical errors or use of abbreviations that either have multiple meanings or are not approved/recommended for use.
This technology is now being applied at the point fo clinical data capture ot correct these errors and others and clarify the clinical documentation prior to commitment to the clinical database and Electronic Health Record

Adding Voice Recognition To Mobile EHRs

Posted in #hcsm, Cerner, CLU, EHR, Epic, HealthIT by drnic on October 29, 2012

The new world of Mobile Healthcare will include an integral component in efficiency – the power of he clinicians voice. Cerner and Epic are

The new mobile-native electronic health records (EHRs) systems of Epic and Cerner are being voice-enabled via recent deals with Nuance Communications

Not only easy access to the world’s leading speech recognition platform but as Joe Petro (SVP for R&D at Nuance) puts it:

it’s form-factor neutral and can be used with iOS, Android, or other mobile or desktop devices, as well as thick- and thin-client systems

Great news for the mobile platform making these devices as productive as they can be

Will Nuance’s Nina Do What Apple’s Siri Won’t? – Forbes

Posted in #hcsm, CLU, EHR, EMR, HealthIT, NLP by drnic on October 24, 2012

A series of  Forbes Insights profiles of thought leaders changing the business landscape: Gary Clayton, Chief Creative Officer, Nuance

Apple’s Siri iPhone voice-based App interface has forever changed consumer expectations of how to interact with their computing devices.  But Nuance’s Nina may represent an even bigger transformation—the consumerization of IT.  Nuance has over 10,000 employees, $1.4 billion in revenue in FY ‘11, $7.65 billion market cap company, headquartered in Burlington, Massachusetts and is best known for its Dragon Naturally Speaking voice recognition software. They just might be the biggest, most successful company you never heard of before. They describe themselves as “focused on developing the most human, natural intuitive ways to use your voice to take command of information.”

Gary Clayton, Chief Creative Officer, Nuance

Gary Clayton, Chief Creative Officer, Nuance

Siri is cool.  But Nina may represent a true leap forward in man-machine learning and artificial intelligence. I recently spoke with Gary Clayton, Nuance’s Chief Creative Officer about his role in bringing Nina to life and his thoughts on how Nina is already bringing a welcome change into how businesses put the tool he helped to create to work to better serve their customers.  He’s the guy responsible for turning some of the world’s most sophisticated software algorithms and artificial intelligence into engaging and user-friendly interfaces.  He also oversees innovation, strategy and design at Nuance.  “I wear a lot of hats,” said the understated Clayton.

The major innovation behind Nina is its capability to retain context over time.  People can interact with Nina, the virtual assistant for customer service apps, and carry on a complex set of instructions within the same conversation flow.  Its artificial intelligence learns and anticipates the user’s interests and requests over time—using natural language understanding.  For example: a person can ask Nina what their checking account balance is, then a person can ask Nina to show them the charges over $200 and then for the month of August, or one could go through the bill paying process by simply stating “I would like to pay the balance on my cable bill on Friday from my savings account.” Humans communicate through context, not through complex, detailed step-by-step instructions that have always been the hallmark of human to computer interaction.

Imagine calling your insurance company and having a pleasant and successful interaction with an always friendly voice.  No more yelling and swearing into the phone “Operator”!!  Nina can also interact across devices and applications, so that customers can choose to connect by voice, mobile device or web page or any combination and still retain the context of the interaction.  In fact, one such enlightened financial services company USAA, is implementing Nina to create a better customer experience.  “USAA is extraordinarily responsive to their customers; one of the very best in their field and represent a gold standard in managing the customer experience,” said Clayton.

“People like to anthropomorphize technology,” stated Clayton. He knows it’s a basic human need to understand and control the world around us. Nina is one expression of meeting that need. That’s what drives Clayton in what he calls his never-ending quest to understand the creativity behind science and art. He started his quest as a physics undergrad at SUNY and later ventured to San Francisco for interdisciplinary studies and eventually earned his BA in communication from San Francisco StateUniversity.  He sees creativity as the synthesis of art and science.

This led to a fascinating career path that began with the explosion of Silicon Valley technology drawing the film business toNorthern California. There, Francis Ford Coppola, George Lucas and others set up shop. Clayton worked with all of them but most notably Lucas and his Skywalker Ranch studios inMarin County,California, where he engineered sound recordings, which included the first recordings at Skywalker Sound with the San Francisco Ballet Orchestra.  He founded and ran his own multi-media production company from 1985 to 2000 and worked on many Academy Award winning films, Grammy winning albums and Emmy winning TV shows. There he worked on projects with Michael Jackson, Dave Brubeck, The Cure, Brian Eno, David Bowie, Mel Torme, Sam Shepard, David Byrne, Norman Mailer, Apple Computer (Knowledge Navigator,Newton) and many others. After a succession of consulting projects at Pacific Bell and a start-up gig at TellMe, (acquired by Microsoft for a reported $800 million in 2007) he spent time at Yahoo where he headed up their speech strategy.  From there he landed at Nuance in 2008.  Clayton is the owner of eight patents and is considered one of the leaders in the digital speech recognition movement.

As one of the key developers of the Dragon Go! and Nina product lines, he is helping to push Nuance into the forefront of turning mobile device personal assistants into personal advisers.  His vision of the synthesis of art and science may be a never-ending process, but his work on Nina just may be the full fruition of a lifetime of trying.


Imagine that – a User friendly EMR interface that uses the power of your voice and a natural exchange to navigate and interact with. The long term memory (or retaining of context) offers a more natural and engaging exchange

The major innovation behind Nina is its capability to retain context over time. People can interact with Nina, the virtual assistant for customer service apps, and carry on a complex set of instructions within the same conversation flow.

The example cited is for your banking exchange but imagine this in healthcare
“Nina show me my patients for today”
“What are the latest laboratory results for Mr Jones”
“Are there any new results on my patients marked abnormal”

You get the picture

Changing the interaction with technology, especially in the mobile world but also in every human/computer interface shielding the user from the complexity of the technology by providing an easy conversational speech front end.

I can hear Scotty now…”a keyboard…how quaint”

The Impact of RACs on Your Medical Practice – Physicians Practice

Posted in Clinical Documentation, CLU, EHR, NLP, RAC by drnic on October 9, 2012

Please sit down — this will not be an easy article to digest, no matter how carefully I parse my words. Life under the microscope of Recovery Audit Contractors is going to get tougher for physicians. Three recent developments may impact your practice in the next year.

I have written in the past on RACs and documented their growth from a twinkle in Uncle Sam’s eye to the behemoths they have become. Much of the advice offered in prior articles (please see links at the bottom of this article) remains valid and should be heeded.

Audits of Level 5 E&M services

CMS has given approval to Connelly, the Region C RAC, to perform complex medical reviews on level 5, E&M services (e.g., 99215, 99205, and 99255). This is the first time CMS has given any RAC permission to target the coding and documentation of E&M services. One impetus for the focus on level 5 E&M services is a shift in providers’ use of level 4 and 5 codes. According to the Center for Public Integrity, the percentage of Medicare services coded as level 4 or level 5 increased from 25 percent to 40 percent between 2001 and 2010. This, of course, has increased CMS’s financial outlay for these services and made them a much larger budget item (i.e., target).

Connelly is the RAC for thirteen states: Alabama, Arkansas, Colorado, Florida, Georgia, Louisiana, Mississippi, New Mexico, North Carolina, Oklahoma, South Carolina, Tennessee, Texas, Virginia, and West Virginia. Take note: the other three RACs are expected to follow suit.

Since early 2009, the Medical Group Management Association, AMA, and 101 state and specialty societies have actively opposed RAC audits. It is unfortunate for all of us that CMS has not heeded their advice.

There is yet another cause for concern with this initiative. Though it has not been officially confirmed, CMS apparently has given Connelly permission to extrapolate the results of their E&M audits. For instance, if a RAC audit determined that six of twenty (30 percent) level 5 services did not meet coding/documentation guidelines, the RAC would have authority to extrapolate this 30 percent failure rate across all level 5 services provided during the review period.

If you provide level 5 services, it is prudent to have several of them copiously reviewed by a certified professional coder.

9th Circuit Court of Appeals verdict

On September 11, 2012, the U.S. Court of Appeals for the Ninth Circuit rendered a dangerous opinion. It affirmed that RACs are not restricted by regulatory deadlines, statutes of limitations, or time limits. Lead plaintiff attorney Ronald S. Connelly, of Power Pyles Sutter & Verville PC, says “The decision leaves providers with absolutely no finality in their payments from the Medicare program. Contractors could reopen claims that are even 10 or 20 years old, and providers would have no right to challenge the timeliness of the audit.”

Legal minds will weigh in on this opinion in the weeks and months to follow, but again, a scary precedent has been set. It may mean that Medicare patient and billing records should be maintained indefinitely. At a minimum, it means the past is neither safe nor sacred.

I recommend you contact your medical malpractice insurance carrier to determine if this circuit court opinion will change their recommendations for records retention.

EHR automated notes

Last but not least, the HHS’s Office of Inspector General has set its focus on whether providers are using automated note generation appropriately in their EHRs. Also known as “cloned notes,” automated notes and templates use copied and pasted data on multiple patients to record standard information such as a normal review of systems or physical exam.

An observer reviewing several such notes would find virtually identical documentation and very little patient-specific information. Herein lies the OIG’s concern. They are concerned that cloned notes may lead to over-documentation or a lack of patient-specific information. From a medical malpractice liability perspective, the same concerns apply.

There is a place for structured notes, and many physicians used them prior to the advent of EHRs. These are acceptable, and EHR-generated notes that contain patient specific documentation should be good to go as well. Your risk lies in over-cloning identical text in your patient notes.

In summary

The United States Department of Justice (DOJ) has three top priorities:

• Terrorism
• Violent crimes
• Healthcare fraud

I wish healthcare fraud were not on this list, but it is, and it is not dropping off the list anytime soon. Government oversight and second-guessing are givens for anyone who practices medicine today; expect fraud identification and enforcement initiatives to grow.

To get a head start on audit-proofing your practice, read the following articles that offer advice and practical tips for protecting both yourself and your practice:

Avoid Medicare Fraud Claims by Coding Correctly

Medicare’s Fraud and Abuse Program

Nine Things to Know About RACs

Lucien W. Roberts, III, MHA, FACMPE, is vice president of Pulse Systems, Inc., and a former practice administrator. For the past 20 years, he has worked in and consulted with physician practices in areas such as compliance, physician compensation, negotiations, strategic planning, and billing/collections. He can be reached at

As the article says – “please sit down, this will not be easy”

As they used to say “up north” in England: “there’s trouble at Mill” and aptly captured in the Monty Python Sketch “”The Spanish Inquisition”

The recent decision in the 9th circuit court:

affirmed that RACs are not restricted by regulatory deadlines, statutes of limitations, or time limits


..the HHS’s Office of Inspector General has set its focus on whether providers are using automated note generation appropriately in their EHRs…They are concerned that cloned notes may lead to over-documentation or a lack of patient-specific information. From a medical malpractice liability perspective, the same concerns apply.

It will be important to provide a balance of information derived form templates and structured content supplemented with narrative generated efficiently and not just stored as narrative but understood to be included in the structured information essential to managing patients

Method of Clinical Documentation and its Relationship to Quality

Posted in #voiceofthedoctor, Clinical Documentation, CLU, EMR, medical intelligence, NLP by drnic on June 18, 2012

So there was a lot of interest in the paper published in JAMIA

Method of electronic health record documentation and quality of primary care published on JAMI this month. A quick summary

They evaluated 18,569 primary care visits, 234 doctors in 2007-08

Note taking Breakdown
62% of free-text notes
29% structured documentation
9% mainly dictated their notes
Quality Measures
15 coronary artery disease and diabetes measures
assessed 30 days after visit
Quality of care was worse on 3 outcome measures for doctors who dictated notes
 anti platelet medication, tobacco use documentation (22% vs 36%) and diabetic eye exam


Their conclusion:

EHR-assessed quality is necessarily documentation-dependent, but physicians who dictated their notes appeared to have worse quality of care than physicians who used structured EHR documentation.

My Conclusions:

I don’t follow that logic – what they appeared to measure was the quality of the documentation not the quality of care? The measures are measures of documentation not of quality of care or clinical outcome.

It was not clear to me if that data might have been in the documents but was not identified (extracted) to if they reviewed all the documents and abstracted that data to determine if the data was missing or not. 

The study was carried out some time ago (2007 – 2008) – 4 years is an eternity in technology advancement. The iPhone was only launched in January 2007….look what that has done to the mobile world and telephones.

As I noted in my most recent VoiceoftheDoctor Radio Show with Dr Ruthann Litman, Dr Sidney Litman and Dr David Eibling it is the integration of solutions in a seamless way that will be successful and is measured by physician satisfaction. Turns out some doctors like dictating, some like using the keyboard and mouse, some like using speech recognition – and in the case study they are presented, some like to have a scribe/librarian/medical specialist do their keyboard interaction under their direction

The overall capture of quality elements was not great so we have not licked this problem yet (well not in 2008 anyway)

The ability to offer all methods but allow for the capture of these elements using technology is available today. This was nicely articulated in a piece just recently in HIT consultant in an interview with Carina Edwards – Understanding Clinical Language Understanding.  

The Reliant Medical Group (formerly the Fallon Clinic) did a study presented at HIMSS in 2010 comparing quality of notes and showed an increase in the quality of notes with a hybrid approach of speech over pure EHR entry and dictation. In many respects I would suggest as similar study and results..just a different interpretation


I maintain that choice for clinicians is the key to success – offering them the right tool that fits their personal requirements and needs adn that includes all variations of documentation capture with NLP and Clinical Language Understanding to provide the bridge between narrative content and structured data essential for the intelligent management of patients and their care