Dragon Medical is up to 99% accurate out-of-the-box, and includes medical vocabularies covering nearly 80 medical specialties and subspecialties. Using Dragon Medical 10, physicians dictate in real-time into their EHR in their own words – letting them instantly review, sign, and make their notes available for other clinicians.

• Improves financial performance by eliminating transcription costs and by increasing physician productivity compared to typing or “point and click” data entry into an EHR. Clinicians can now spend more time with patients or increase their patient load — leading to higher practice revenue — and dictate more detailed “medical decision-making” for each patient encounter.
• Raises the quality of care by enabling clinicians to dictate, review and sign medical records in one step, allowing them to communicate clinical information more quickly to referring clinicians and patients alike. Faster, more complete medical records lead to care plans being put in place more quickly.
• Increases clinician satisfaction by making the EHR easier to use by eliminating typing or “point and click” data entry of patient information.

**Nuance has recently changed their channel focus for Dragon Medical and now requires their channel partners to adhere to a strict Market Map (market segmentation strategy).  This new strategy, which went into effect October 1, 2010, allows resellers to sell into the small physician practice market only.  The small physician practice market is defined as independent practices or clinics with 1-24 total physicians, not owned by a hospital or health system.  The large physician practice market (25+ physicians), practices owned by hospitals or health systems, and the enterprise healthcare market (hospitals and health systems) will be sold by the Dragon Medical Direct sales team.

Please check out these links

http://www.nuance.com/healthcare/landing/speech.asp

http://www.nuance.com/healthcare/products/dragon_medical.asp

Microsoft rolls out encrypted e-mail features in its HealthVault personal health platform in collaboration with the federal Direct Project health record exchange initiative.

 Microsoft Teams with U.S. Direct Project on HealthVault Expansion - Health Care IT - News & Reviews - eWeek.com
Source: eweek.com

Agency for Healthcare Quality – Medicare Shared Savings Program: Accountable Care Organizations Proposed Rules-Comments

File code CMS–1345–P

Before offering my comments on the measurement of quality in the transition from transaction-based medicine to accountable care I first must note that the concepts presented in these proposed statutory requirements are in the whole necessary, achievable and well designed to achieve accountability in our healthcare system. While we expect there will be promotional activities forthcoming from CMS that will emphasize the role of the patient and their responsibilities for achieving optimized and affordable healthcare we will not address this issue in our comments below.

In order to facilitate the context of the comments we will first reference the proposed verbiage which will be in bold and refer to external sources as and where possible.

With the exception of exchanging information electronically through the use of an electronic health record the emphasis on measurement of clinical processes, the caregiver experience and outcomes seem to be focused on surveys for measurement and additional reports that the ACO must generate and forward to the government. While measuring quality of care is a complex and difficult task, it appears that the government, through these proposed regulations, has decided it is too difficult to measure quality beginning with the first patient – PHP encounter and has chosen to begin the measurement of quality after the visit has been coded for payment. If the initial diagnosis of the patient's disease or/problem is incorrect, but all the coding is correct, then the patient will proceed down a path of sub optimized care which may go undetected until or unless a specialist is called in to review said diagnosis or, the patient experiences repeated and significant problems requiring a return to their PHP. After recognizing the patient's reaction to their first treatment plan including medications prescribed, the provider has another opportunity to readdress their diagnosis and subsequent treatment plan. While one might argue that patient safety was not risked from our point of view, it might be argued, even when this incident remains undocumented by the various surveys required for ACOs, there could still be a problem. Physicians that have excellent communication skills are not likely to be scored poorly by the patient who has experienced such a situation.

Rather than increasing the reporting burden for PHPs and patients, we suggest leveraging data already gathered by the PHP and residents in their EHR system. ACOs, which transmit in batch mode the patient's medical history, the symptoms they presented, diagnosis and treatment plan, should be very careful when analyzing this unstructured data. This unstructured data (text) could be analyzed more completely using sensitive qualitative measurement. Converting the unstructured (text), part of the medical record into structured information, which is not granular enough to access the quality of the diagnosis and treatment, leads to measurement of events such as did the provider exchange information with a specialist or did the provider use e-prescribe, etc. These events by themselves do not improve the patient’s care, yet translating this information into codes or reports for discrete numerical information, places considerable burden on providers.

While not commonly known or used in the medical field unstructured (text) content analysis has been used for many years in the intelligence gathering market and in most recently the road legal market. Application of this technology has reduced costs of large litigation most significantly and reduced the time required for discovery by orders of magnitude. This same sort of tool is directly applicable to measuring quality within the healthcare process.

Page 19569, Section II E. Quality and Other Reporting Requirements, 2. Proposed Measures To Assess the Quality of Care Furnished by an ACO, b. Considerations in Selecting Measures, 1. Use of Measures, third bullet in second column states,

· “The collection of information should minimize the burden on providers to the extent possible. As part of that effort, we have begun and will continuously seek to align Shared Savings Program measures with the methods and measures included in the Medicare and Medicaid EHR Incentive Programs to enable the collection and reporting of performance information to be a seamless part of care delivery and the meaningful use of certified EHR technology.”

Again as mentioned earlier in the comments above the burden on providers of generating reports, filling out surveys is quickly diminishing the productivity gains they realized through installing electronic health records. We suggest that the agency for healthcare quality examine the use of an application for unstructured content analysis. We are not talking about technology from Google which counts the number of links, nor are we talking about full-text Boolean searches, we are talking about content analysis based upon 300+ mathematical algorithms. This measuring tool is most accurate with large volumes of information; terabytes and above.

Page 19570 Section II E. c. Proposed Quality Measures for Use in Establishing Quality Performance Standards That ACOs Must Meet for Shared Savings states,

“Based upon the principles described, we are proposing 65 measures (see Table 1 pages 19571-19591) for use in the calculation of the ACO Quality Performance Standard. We propose that ACOs will submit data on these measures using the process described later in this proposed rule and meet defined quality performance thresholds.”

While measuring quality outcomes in healthcare is much like measuring beauty, in both cases a definition can be developed and then some quantitative measures established that will assist in a numerical comparison between multiple judges. Inherent in this complexity is the fact that measuring quality in a healthcare setting is a qualitative rather than a quantitative process. The American Society of quality control can provide numerous tests for quality inspection and reporting based on defects per unit or level I level II or level III type defects. Unfortunately these techniques cannot be translated to measuring healthcare quality which has been extraordinarily large possibilities of good and bad quality. The research performed by Stanford University and the Center for primary care and outcomes research reported the risks associated with implementing the patient quality index. While their research highlighted challenges regarding selecting the indicators, the numerator or the denominator of the statistic used for a quality measure, they also highlighted policy implications that should be considered. Their research poses the question, will the measurements which are presented in table 1, insure true quality improvement or will it simply improve coding and shift the burden of the case management to the PHP from specialists and other healthcare providers? They also pose the question, does this focus on avoidance of hospitalization really reflect quality or, is it simply an attempt to reduce costs at the expense of the patient's healthcare? One of the recommendations made by this research group was that the government should identify interventions and link usefulness of indicators with true quality improvement.

The measurement of true quality, infers a relevancy and risk assessment not answered through statistical analysis. Statistical significance, without practical significance, appears to be where these measurements are headed. While qualitative research often involves validated surveys, this method is not preferred to direct sampling of the research populations’ experiences. Unfortunately few researchers have access to/or knowledge of the latest content analysis tools that would significantly increase the quality of their conclusions based upon an ability to quickly and reliably analyze thousands of published research articles which may have been impractical to analyze given their research budgets.

Page 19570 Section II E. 3. Requirements for Quality Measures Data Submission by ACOs, b. GPRO Tool, first paragraph, states “We propose that the existing GPRO tool be built out, refined, and upgraded to support clinical data collection and measurement reporting and feedback to ACOs under the Shared Savings Program.”

Page 19592 Section II E. 3. Requirements for Quality Measures Data Submission by ACOs, b. GPRO Tool, first column, fourth paragraph, states Quality Performance Standards, “In the GPRO audit process, we plan to abstract a random sample of 30 beneficiaries previously abstracted for each of the quality measure domains/ measure sets. The audit process would include up to three phases, depending on the results of the first two phases. Although each sample would include 30 beneficiaries per domain, only the first eight beneficiaries’ medical records would be audited for mismatches during the first phase of the audit…”

We suggest that, before the government build out the GPRO tool, a pilot project containing the 50 or more collections of medical records of 5,000 beneficiaries for one of the quality domains/measure sets be analyzed using a content analysis tool. This tool should be able to search and retrieve information based upon concepts and ideas they contain and should be able to link relationships between patient history, symptoms, diagnosis and outcomes. Using thousands of published research articles and best practice documentation a library of several gigabytes of information up to a terabyte of information should be used to judge the efficacy of this measurement process.