Monday, January 12, 2009

Plans to Computerize the US Healthcare Records

CNN Money features an article today on the President-elect Obama's Digitizing the US Health Records System featuring the proposal to modernize the health care system by "making all health records standardized and electronic."

The plan calls for computerizing all records withing 5 years and is subject to much discussion in the various communities I participate in that is both positive (great investment and resources allocated to help fix a broken US healthcare system) to negative (are we just spending money on technology rather than spending money on
improving the outcomes and quality)

One observer put it this way:
this is a bit like watching a train wreck that is too late to stop
and more worryingly:
I don’t think that even a free EMR is attractive enough for most docs right now
One source cited came from information published by the AAFP (now restricted to members) that showed substantial variation in satisfaction with current implementations
....substantial variance in physician satisfaction with EMRs by product from “if I could get out I for zero cost I would” to “I’m not happy but my practice couldn’t live without it” to some actual large practices seldom rose above the “not happy, but …” level.
Current penetration and usage cited is at 8% of hospitals and 17% of physicians so there is a long way to go. Estimations for the price tag to achieve this range from $75 - 100 Billion. A Large percentage of any "bail out" that may or may not be approved but a small drop in the ocean of "$2 Trillion a year the industry spends" today.

But it is the usability that is required and ubiquitous access:
Doctors cannot spend hours and hours learning a new system," said Castillo. "It needs to be a ubiquitous, 'anytime, anywhere' solution that has easily accessible data in a simple-to-use Web-based application."
I agree but what is missing from this discussion is how to get this information into these systems. If we had a 100% adoption of EMR's today this would be an enormous mouth to feed with clinical data. It is no use implementing these systems if we don't have the data and the idea that clinicians will interact with the current technology, no matter how good it is with screens, feedback, menus and intuitive interfaces, is just not going to happen.

Providing the tools to capture the data naturally is going to be critical tot he success of these systems and there seems no better method that using voice. All our interactions are based on voice and capturing this as clinical data that can feed the data hungry EMR's. Speech recognition has gone some way to helping and automating this process but these older engines only output text which does not satiate the EMR's needs for structured and encoded clinically actionable data.

Ensuring that technology does not take over the practice of medicine and replace bedside skills is a major concern as detailed in this a New England Journal of Medicine article covered here where Dr Abraham Verghese says:
In short, bedside skills have plummeted in inverse proportion to the available technology. I truly believe that good bedside skills make residents more efficient," Verghese said. Doctors who rely on hands-on skills tend to order tests more judiciously, reducing the number of unnecessary and expensive trips to the radiology department.
To that point allowing for ready voice capture that generates the date required to make these clinical systems useful is essential and is precisely what speech Understanding does. Free form narrative that is converted into structured meaningful clinical documents that contain the full fine detail from the clinicians but also contains encoded structured data that is tagged against relevant controlled medical vocabularies including Snomed, RxNorm, RadLex, LOINC, ICD9 to name a few. All this can be output in CDA format for Common Document Types that has been defined and approved through the HL7 balloting process through the tremendous work being done by the Healthstory Project that creates one document that delivers multiple outputs for different purposes and retains complete and detailed clinical information. Due to the open nature and flexibility of the standard this format allows for ready adoption by multiple stake holders quickly creating immediate value to the participants by generating a flexible rich clinical document that provides useful output.

The conversation on Digital Health Records is going in the right direction and i think it is exciting but must include the capture of information and while speech understanding is not a panacea it is an essential contributor to the equation of making digital records work

No comments: