Thursday, February 17, 2011

Dr Watson Takes on Healthcare

Watson Emerges Champion in Jeopardy

Watson emerged the Jeopardy Champion last night with a resounding $ 77,147, beating both competitors (Ken Jennings:$ 24,000 and Brad Rutter:$21,600) by over 300% ($53,147/$55,547).
2011-02-16WatsonWinningTotal.jpg
Hats off to Ken Jennings and Brad Rutter for taking on the challenge and doing such a great job
2011-02-16WatsonThreeScores.jpg

This was followed today with the joint Nuance/IBM Press Release: "IBM to Collaborate with Nuance to Apply IBM’s Watson Analytics Technology to Healthcare" (here on IBM and Nuance's site) that recognizes the tremendous value that Watson can bring to healthcare. Watson showed last night the major advances that have been made by IBM's “Deep Question Answering” (QA) research team:
the ability of a computer to understand natural human speech inquiries that pertain to a limitless range of topics, and to make informed judgments about requests
There was plenty of coverage as evidenced by the 15 Million hits in Google for the search (Jeopardy/Watson) with the vast majority highlighting Watson's superiority (Time Magazine: Winner, Dr Watson I presume, ZDNet: Watson's Next Adventure - Healthcare with Nuance, Information Week: IBM Nuance Envision Watson Helping Doctors, NY Times: Computer Wins on Jeopardy, Trivial It's Not andIBM Moving Watson Supercomputer Beyond 'Jeopardy' To Health-Care. Stephen Wolfram of Wolfram Alpha weighed in with this thoughtful post (Jeopardy IBM and Wolfram Alpha) comparing Watson and Wolfram Alpha and this more light hearted post If Google Played Jeopardy: Smartest Search Engine, But It’s No Ken Jennings where he challenged search engines with the simplified task of entering the same Jeopardy Clues

Google showed well
Leading them to suggest that
Either he’s (Ken Jennings) an immediate acquisition candidate in Mountain View and Redmond, or he should just start his own search engine and answer queries as they come in
There were other dissenters including this post Could Google Play Jeopardy Like IBM's Watson. Google has certainly cornered search and access of data but even if the data can be found with a google search and there are certainly some shared concepts in the search technologies I'm not sure that finding the data in a search page is the same as answering the question and really understanding the question. But the summary and analysis of Natural Langauge:
Natural Language Reality Check: The reality is that the technology that Watson demonstrates, while amazing in a game show, is overkill for what most people need. Those behind “natural language” search technologies have long trotted out sentences like the “Who’s in the pajamas” example above to demonstrate how “smart” their search tools are. And yet, most searches people do on search engines are only two or three words long.
Missed the mark and the analogy is flawed on several counts.  I would suggest that our interactions are deliberately simplified when we interact with Google - we work around the lack of understanding of the Google search engine. And while Watson may be overkill for "most people" the potential application in multiple areas dealing with ever increasing volumes of unstructured data it is healthcare that has been struggling with the challenge of overwhelming clinical knowledge and our inability to access and apply this at the time of care delivery. In this discussion on the possible healthcare applications of Wtason/DeepQA


Dr Herbert Chase (Professor of Clinical of Medicine at Columbia University) says:
For at least 30 years it has been impossible for a physician to master all the material to practice medicine at the highest level. Biomedical literature has doubled in size every seven years but patients want those facts at the doctors finger tips when they see him (the doctor)
It is this challenge of data that clinicians face every day as they attempt to deliver the best possible care to each and every patient at the time of the consultation and something their patients expect. Definitely not overkill for patients or doctors and given the Tsunami of medical knowledge and the challenge of sharing clinical data. DeepQA will add a new level of medical intelligence to support to clinicians is with the application of Natural Language Processing taken to a new level of understanding.

Back in June I talked about this technology and the potential for application in healthcare (NLP in Healthcare). In October Nuance announced our strategic partnership with IBM and I covered the news in this post: Clinical Documentation Challenges and then again building towards the Jeopardy challenge NLP in Healthcare Part 2 and most recently this week as part of the potential solution to the challenge of shareable clinical data and clinical data models (The PCAST Opportunity, HL7 CDA, UEL and SAGE)

The announcement today builds on a deep research and technology partnership that already exists in multiple areas between the companies. As one person pointed out in a note to me yesterday
"I cannot understand that Watson cannot 'hear' an opponents wrong answer. They text in the question and then Watson parses the english, algorithms swirl, etc. However, when an opponent speaks it cannot hear. So when a bad answer is spoken it is bound to repeat it.. "
That is part of the innovation and solutions that Nuance will contribute to the partnership which will also include the Clinical Language Understanding (CLU) Technology that will be used create new solutions that provide hospitals, physicians and caregivers access to critical and timely information expanding from recognizing what was said and parsing data to now understanding the intent and providing guidance. This will push us one step closer to intelligent medical analysis real time with the clinician to assist hospitals to utilize facts and knowledge as they migrate toward evidence-based and accountable care models:
Recognizing the tremendous value that Watson can bring to healthcare, Nuance and IBM have teamed to co-develop solutions that will transform vast amounts of clinical data into actionable information across the continuum of care. This endeavor is intended to unlock important medical knowledge and facts buried within huge volumes of data repositories, providing healthcare provider organizations, payers and individual physicians a new level of medical intelligence
It has been yet another exciting day in the world of healthcare technology


If you want to see the Jeopardy games you can watch them below
Part 1:

Part 2:

and Part 3:



And it is not just healthcare:

Wednesday, February 16, 2011

Computer Assisted Physician Documentation

It was an exciting news day today with the announcement of a Strategic partnership between Nuance and 3M. Lots of coverage and keen interest from the press and healthcare industry as evidenced by the 290,000 search results in Google by 15:30 ET. While many of the news links were picking up 3M's Press Release and Nuance's Press Release it was the interview on HISTalk that provided a detailed look into the tremendous synergies between the two companies and excitement surrounding the concept of Computer-Assisted Physician Documentation. As John Lindekugel said
In a nutshell, we’re taking 3M’s industry-leading Clinical Documentation Improvement approach, which a lot of hospitals rely on today in their HIM and documentation improvement departments, and applying all the technology that Nuance brings and its industry-leading technology to deliver that content to the point of care, to the physician.
Replacing the manual time consuming and painful follow up process today with an automated tool that provides immediate feedback to the clinician at the point of care.....as one CMO put it "that's huge!".

For clinicians CAPD's immediate feedback adds up to

  • More accurate and specific documentation that is more effective in assessing and communicating the patient's condition
  • Reducing the burden of disruptive follow up questions and queries for Clinical Documentation Improvement (CDI) staff
  • Improving the overall quality and detail of the Clinical document without excessive change in behavior or effort
  • Achieving appropriate reimbursement with more accurate quality and detailed clinical reporting
  • Ease the burden of the ICD10 transition

For any healthcare facility in the US CAPD means there are now automated tools to reduce the administrative burden on clinicians which will have a positive effect on clinician satisfaction and retention. More accurate information flowing through the clinical systems translates to accurate clinical risk and severity, reducing compliance risk and reducing administrative costs

All this will be on show at HIMSS next week in Orlando at 3M's Booth 3547 and Nuance's Booth 2744. If you will be at the show stop by and take a look. It will be a busy few days but there should be plenty of opportunities to talk to the folks involved in developing the solution and we are keen to get feedback from as wide arrange of stakeholders as possible.

Tuesday, February 15, 2011

Playing Games with ONC Certification - Guest Post

Certification remains one of the basic building blocks of the incentive program from the Government. CMS provides a tool for finding certified EHR technology for practices as part of the EHR incentive program. As Houston Neal Director of Marketing at Software Advice points out "Certified" is the $44,000 buzzword. In this guest posting he drills down into the details of certification and provides a list of 5 key questions to ask to help avoid the pitfalls and make sure you will be eligible to receive the incentive payments:



Playing Games with ONC Certification

“Certified” is the $44,000 buzzword prefixing electronic health records (EHR) software. To qualify for Health Information Technology for Economic and Clincal Health (HITECH) Act incentive payments, you must use an EHR that is certified by the government. Additionally, you must use a system - or systems - that offer 100% of the functional and security capabilities required to meet “Meaningful Use” criteria.

Many EHR vendors are promoting their products as “certified,” but the claim can be misleading. There are three ways they could lead you astray:

Alternative Certifications
Before the HITECH Act, two organizations certified medical software:

      Certification Commission for Health Information Technology (CCHIT) - CCHIT began certifying EHR software in 2006. Since then they have released 10 certification programs for ambulatory and inpatient EHRs.
      KLAS - KLAS is a private organization that has gathered ratings on EHRs since 1997. Every year they rank EHR vendors and bestow a “Best in KLAS” award on the top 20.

In an effort to stand out from the other 300+ EHR systems on the market, vendors widely promote their CCHIT or KLAS credentials. They may even tack the word “certified” onto their CCHIT or KLAS approved product. This muddies the water for providers. They have to distinguish between CCHIT, KLAS and certification from an ONC-Authorized Testing and Certification Body (ONC-ATCB). While CCHIT and KLAS are meaningful credentials, they’re not the certifications that qualify for incentive funds.

This is especially confusing because CCHIT is now one of six organizations approved to certify EHRs for the HITECH Act. So, if an EHR vendor claims they have CCHIT certification, you’ll need to clarify which one. Is it ONC-ATCB certification, or one of CCHIT’s independent credentials?

Complete EHR vs EHR Module
Software vendors can receive ONC-ATCB certification for a complete EHR or an EHR module. This means a product doesn’t need to meet all criteria for Meaningful Use - instead, it can be partially certified if one or more functions meet a subset of requirements. For example, a vendor could certify their e-prescribing application or their patient portal.

This under-publicized detail could cost you thousands of dollars; by itself, a certified EHR module won’t make you eligible for incentive payments. You must use two or more modular EHRs that, combined, meet 100% of the ONC criteria. So while vendors can officially promote a module as having ONC-ATCB certification, it may fall short of making you eligible.

Guaranteed Incentive Payments
Be mindful of guaranteed incentive payments. It is reasonable for a vendor to guarantee they’ll meet certification criteria. In fact, you might make it a requirement in your purchase decision.

However, guaranteeing incentive payments is altogether different. Technology alone won’t make you eligible. EHRs are just a means to an end. Ultimately, you are responsible for achieving Meaningful Use status. So be wary of this type of guarantee. Read the fine print and find out how you are reimbursed if you don’t qualify for incentive payments. Does the vendor reimburse you the full amount of lost incentive payments? Or do you just get reimbursed for the cost of the software? You shouldn’t purchase a system based on this guarantee alone.

Five Key Questions to Ask Vendors
To help you avoid thse pitfalls, we put together a list of 5 questions to ask vendors. Answering these will put you in a good position to become eligible for incentive payments.

1.     Which certification does the EHR have: CCHIT, KLAS or ONC-ATCB? You must use an EHR that is ONC-ATCB certified in order to be eligible for incentive payments.
2.     Which product version has been certified? Ask the vendor for complete details of their ONC-ATCB 2011/2012 certification, including: product name and version, date certified, unique product identification number, the criteria for which they are certified, and the clinical quality measures for which they were tested.
3.     Does the vendor have certification for a complete EHR or an EHR module? If module, you will need to use more than one to be eligible for incentive payments. The ONC has created a handy website that allows you to build a list of EHR modules that meet 100% of ONC criteria.
4.     Will the vendor resubmit their EHR for final certification in 2012? The current certification is temporary and only lasts through 2011. Make sure your vendor has plans to reapply in 2012, and find out if they will certify a complete EHR or just a module.
5.     Are you purchasing through a reseller or other business partner that renamed the product? If so, make sure the renamed product has been approved by the ONC-ATCB. Even if it is the same version with identical features and functionality, it won’t make their Certified HIT Products List unless the original vendor reports it to an ONC-ATCB.

This article was written by Houston Neal of Software Advice. To view the original article, visit Playing Games with ONC Certification.

Monday, February 14, 2011

The PCAST Opportunity, HL7 CDA, UEL and SAGE

The recent publication of the PCAST Health Information Technology Report: Realizing the Full Potential of Health Information Technology to Improve Healthcare for Americans: The Path Forward,  published December 8, 2010 (press release and covered in this webcast) and became something of a Piñata for comments. Vince Kuratis did a great job of pulling these comments and responses together in his his blog PCAST HIT Report Becomes a Political Piñata.

But Wes Rishell's post: "PCAST Opportunity: Documents vs. “Atomic Data Elements” that reviews the PCAST recommendations and digs into the details of the development of standards and the basis for the exchange of information (documents vs snippets or Molecules/atoms), exchange formats and Universal ExchangeLanguage (UEL) vs HL7 CDA does an excellent job of dissecting out some of the controversies and homing in on exchange of data and the standards in question as well as highlighting the challenges associated with pre and post coordination of data (read less codes requirements and more code requirements). Interestingly Wes estimates
from 20,000 to 100,000 (data elements) but a number of physicians seem to agree that a very useful collection of molecules and radicals would contain many fewer than 20,000. Stan’s presentation describes several different parallel efforts to enumerate the molecules using siloed methodologies. The one he is working on as identified more than 4,000.
He points to several related posts - this from John Halamka: Detailed Clinical Models that points to multiple other standards in development in other countries (Open EHR in Australia, ISO13972, Tolven's Open Source Clinical Data Definitions  and the National Health Service Logical Record Architecture) which all adds up to a pressing need for a Universal Exchange Language...and in my mind translates to a significant challenge in developing and then keeping up to date.

Both blogs point to an excellent detailed (almost 2 hours) presentation by Stan Huff (CMIO at Intermountain Healthcare): Practical Modeling issues: Representing Coded and Structured Patient Data in EHR Systems

select

And a link to some of the original work "Detailed Clinical Models for Shareable, Excutable Guidelines (pdf from MEDINFO 2004) that detailed the NIST funded multi institutional SAGE research project
sharable, executable clinical guidelines. The project envisions a system that enables the authoring, localization and execution of significant clinical guidelines in a vendor independent manner
One thing is for sure - this is a complex issue requiring much attention and focus since the coordination and sharing of data is a fundamental building block of effective, efficient and safe healthcare. Effective sharing of data appears to require standards and exchange languages. But today is the first of three part episodes of Jeopardy featuring Watson . I talked about this back in June and again in December. Tonight is the first night of the Waston Jeopardy challenge.
In the countdown to Jeopardy


It is clear IBM has pushed the limits of computing technology and "understand" the complex human language which Nuance has partnered to bring this same technology to Healthcare: Clinical Documentation Challenges that will apply a whole new way of looking at clinical documentation that reduces our dependance on codes, structure and defined clinical data models.

If we consider the adeptness of the human mind and our ability to understand the fine nuance detailed of clinical reports without the data being tagged or encoded this suggests that the Watson applied to healthcare concept may hold a critical key to exchange and intelligent use of data. Based on the existing standard of "documents" we can innovate and use these documents that are currently a natural part of clinical care.

So as Wes Rishell stated in his summary:
Documents will continue to be at the heart of information flow for patient care and one primary way of bundling clinical information about people
In conjunction with some form of

  • evolving universal exchange language (UEL),
  • encoding of data, and 
  • reliable and simple ("but only as simple as possible, but not simpler") data representation

In conjunction with machine based understanding that I think we will see tonight has been advanced to new and exciting levels we will have a foundation of sharing data efficiently and intelligently in our healthcare system