One of the hottest debates in medical transcription is the quality of documentation completed domestically versus that done overseas.  I asked him if there was a similar debate in the manufacturing arena.  He nodded eagerly, “Yes, there is a noticeable difference from what we produce today to what we produced years ago here in the US.  We replace more devices than we did ten years ago, and we receive more complaints from unhappy customers.”  It was obvious to me that he had given this subject some thought, so I asked him why there was a difference in quality of the medical devices today than those produced a few years ago?  “The workers don’t care,” he answered immediately.  “And why should they?  The workers at these overseas plants will never use one of these devices.  Neither will any of their family or friends or their neighbors.  It doesn’t matter to them if the device fails – it’s not going to save or improve the life of someone they care about.”

A couple of weeks before my friend’s wedding, and this conversation, my family and I moved to a new home where we inherited a fairly new dishwasher… which we have just recently replaced.  Why did we replace a new-ish dishwasher?  Well, the wheels had all fallen off of the bottom tray.  Every single one of them.  (There were 6 of them.)  Any time you wanted to run the dishwasher, you needed to locate and replace the wheels – otherwise, the water would not circulate properly.  But they would all fall off again, forcing you to pick up the basket of semi-clean dishes, scoop out the wheels from the bottom and replace the wheels before running the dishwasher again.  Since the wheels would fall off during the cycle, most of the dishes came out only semi-clean, forcing us to run the dishwasher two or three times to clean one load of dirty dishes.

The dishwasher with the falling-off-wheels was a GE dishwasher.  GE manufactures all of its appliances overseas, many in China, but they recently announced that they will return much of their appliance manufacturing to the US.  Maybe they got tired of replacing poorly constructed dishwasher wheels??  Needless to say, we didn’t consider replacing this dishwasher with another GE dishwasher.  Instead, we opted for a dishwasher from a European manufacturer that was made in Europe (the fact that they offered a special rebate helped in making that decision!).

As my dinner partner lamented the lack of quality in the devices he and his team designed, I told him of the longstanding debate in the quality of medical transcription completed domestically versus overseas.  Just like manufacturing, many transcription companies moved their production to cheaper overseas outlets, like India and the Philippines, years ago. But with the lowering value of the dollar, economic uncertainty, and rising costs overseas, could medical transcription return to the US, much like manufacturing is starting to return?  “I don’t expect my company to bring back any manufacturing to the US,” he commented.  “Even though they have to replace more faulty devices and deal with more customer complaints, the amount of money they save in overhead, salary and healthcare costs will keep them in Latin America for the foreseeable future.”  And if a recent interview with the CEO of the largest medical transcription service provider is anything to go by, the same is probably true for medical transcription.

“As an engineer who designs something meant to last years, it’s heartbreaking to see them fall apart due to poor construction,” I can remember that engineer saying as dessert was served.  “The American workers who used to make our products breathed something into what they created.  And why not?  That device could one day save their life, or their mother’s life or the life of their neighbor down the street.  When you are creating something for a complete stranger, you don’t put your heart into it.  Americans care about what they are creating because they are creating it for other Americans, not some stranger thousands of miles away.”

The buzz this year was natural language processing (NLP) and the role it will play in transforming healthcare documentation.  From computer-assisted-coding (CAC) to data extraction and data mining, NLP has been used for a variety of purposes in healthcare for years.  So why the buzz now?

Major changes in healthcare documentation, like ICD-10 and Meaningful Use, have led to a momentum in the development of robust NLP technologies.  NLP promises many new advancements, and we’ll cover more of those in future posts.  In thinking about how NLP can radically change healthcare documentation is its potential for eliminating (or at least decreasing) the amount of pointing and clicking in an EMR interface done today by physicians. 

When I speak with physicians and in much of what I’ve read on the subject, I hear time and again how much they hate to point and click in an EMR interface.  It’s intrusive to the patient/doctor relationship, because the doctor is staring at a computer screen, rather than talking to the patient.  Pointing and clicking is also cumbersome and a restrictive way of encoding data. 

That’s the reason for the pointing and clicking – it’s so the data elements are tagged in such a way the EMR system can report on that data.  Here is a simplified example.  When an EMR user types in a field box, selects an option from a drop-down menu, or chooses a radio button, he is encoding data.  For example, by typing in the word penicillin in a field box marked “allergies,” the physician just tagged <allergies=penicillin>.  This process makes the data readable by computer software.

If data is going to be encoded via an interface, then the data to be encoded needs to be predicted at the time of development.  When developing an EMR, you have to predict the data elements you want to track and encode so you can create the interface around them.  That means that if you suddenly decide you want to also encode a new data element, you have to re-develop your interface, which is time consuming and expensive.  Plus, only data that is entered after the new interface is released will be encoded properly.  Past data will be lost.

NLP on the other hand works outside of an interface.  Instead, it looks at free-form text and extracts data elements automatically.  For example, let’s say the following sentence was contained in a patient record:

The patient states he is allergic to penicillin and has never been hospitalized.

The NLP software will extract ‘allergic to penicillin’ and encode that as a positive allergy, <allergies=penicillin>.  In computer language, it’s the same as if a human being typed it into a field box.  So in a case like this, the physician would not have needed to interact at all with the EMR.  Instead, he could have picked up his iPhone and dictated, comfortably, quickly, efficiently, with no intrusive interface to get in the way of the relationship with his patient.  Plus, in the future, if we wanted to track a patient’s history of hospitalizations, we could modify the NLP to also look for phrases like ‘never been hospitalized,’ which would encode it as <hospitalizations=none>.  If we wanted to track that information with an EMR interface, we would have to add a new field box or drop-down menu, further cluttering the display of the EMR.

Many years ago, I started graduate research in NLP and conversational speech recognition. I left that program after being recruited by a start-up company and have been more or less away from NLP development ever since.  Things have certainly progressed since then, and I can’t say enough about how excited I am by the buzz happening with the potential for how NLP can assist physicians to comfortably complete patient stories, while still generating data that can be reliably and routinely extracted for the improvement of patient care.

The advent of ICD-10 will require changes to IU Bloomington’s physicians existing documentation habits, Rob explained.  ICD-10 is much more specific than ICD-9, and may require more documentation than what physicians today are used to documenting to ensure proper billing. Essentially, current documentation may not provide enough support to continue billing at today’s ICD-9 rates.

One of the reasons dictation (and, therefore, traditional transcription) has historically been a key element to healthcare is that it is arguably the only way to provide a comprehensive patient narrative quickly and efficiently.  In recent years, some dictation (and, therefore, traditional transcription) has been replaced with front-end voice recognition and electronic medical records (EMRs).  If ICD-10 will require increases in documentation, I asked Rob, could the hospital see physicians returning to traditional transcription?

Theoretically, yes, Rob agreed, increases in transcription could be forthcoming as EMRs may not allow the physician to document to the level of specificity required under ICD-10.  Or, documenting to meet the specificity required for ICD-10 may make EMR input too clunky for some physicians.  Physicians may find it easier to pick up the phone and dictate than to type or click through an EMR for cases requiring additional documentation under ICD-10.  And those physicians using front-end voice recognition today may find it too time-consuming to self-edit when dictating the additional information required for ICD-10.  As physicians struggle to document appropriately for ICD-10, they could turn back to dictation and transcription as the quickest and most efficient documentation method – now that’s not such a nonchalant comment to those of us in the transcription industry.

What does that mean for a hospital like IU Health Bloomington?  According to Rob, the hospital will continue to do what it has always done – support physicians with options.  IU Health Bloomington currently provides its physicians with a combination of front-end speech recognition, traditional transcription, and direct (keyboard) EMR input.  Physicians have the choice to select the method quickest and most efficient for them, given the uniqueness of the patient’s story and visit.

As SpeechMotion’s product manager, I was encouraged by my conversation with Rob, for it reminded me that SpeechMotion is moving in the right direction by providing physicians and hospitals with what they need – options.  Our product suite includes front-end speech recognition, back-end speech recognition, traditional transcription, and a value-add/structured data product.  If the advent of ICD-10 leads to increases in documentation, then, hey, SpeechMotion is ready for it.

The winds of change are blowing these days when it comes to the business of healthcare documentation. The companies that provide service and software for the purpose of improving efficiency of workflow, critical cost savings and added accuracy of data to healthcare institutions are merging, changing and reacting at increased pace recently. So what has changed in the industry that has shifted things from a mere storm in gulf into a full blown hurricane?

The industry has activated and there are several recent shifts and events that are the catalyst. First, it is now clear that doctors do not expect to be data entry professionals. Whatever productivity ratio you believe to be true, clinical professionals cannot work as efficiently and see as many patients when keyboarding patient histories as when they have a good transcriptionist at their back, or using other technology such as Front-End Speech Recognition (FESR). Next, speech recognition workflow technology is now considered by many as a proven ROI for MTSO’s and facilities that employ it. These two reasons are all the validation industry players needed to bet the bank on their acquisitions. One only need to look at the MedQuist acquisition of Speech Understanding company M*Modal in order to be convinced of these factors. At five or six times earnings, it’s a good bet that MedQuist is very satisfied that their 130 Million Dollar investment will be paying off for them for many years to come.

The storm has washed the writing off the wall and the demise of medical transcription services has been cancelled. Outsourced transcription companies are jockeying for position and continue to grow through the acquisition of smaller organizations. During the process, they continue to make decisions that they hope will complete their enterprise portfolios. In the meantime, the industry has been transformed from a mature industry into a vibrant new technology filled industry with exciting ROI.

These industry changes cause validation that there is much success on the horizon for the clinical documentation business. A KLAS report earlier this year suggested that merely one in four hospitals has even implemented speech recognition. This combined with the fact that all of this technology is yet difficult to employ by healthcare providers without assistance, suggests that outsourcers and technology businesses in this space are making wise investments. The storm is just beginning.

An EHR, on the other hand, is more comprehensive in scope and application. NAHIT defines EHR as “the aggregate electronic record of health-related information on an individual that is created and gathered cumulatively across more than one health care organization and is managed and consulted by licensed clinicians and staff involved in the individual’s health and care.”

A door also provides security to that which is protected inside. Entry is limited to those that have the key. Access to protected health information must also be secured to those that should have permission. All gateways and transfer points that are trusted with this important and very personal information must be function securely.

As we open the door on this new publication, we offer the analogy of SpeechMotion as a “door” for healthcare documentation. We invite you to follow our blog as we explore everything that is centric to healthcare documentation in the constant effort to improve process quality and leverage better patient care.