Wednesday, September 21, 2011

BayScribe and Perfect Search Corporation Partner to Bring NLP Powered Semantic Search to Healthcare

BayScribe will utilize Perfect Search’s unique indexing and search technology to enhance their Semantic Interoperability platform. Able to index and search structured EMR data, unstructured free text, NLP processed records, DICOM radiology data, lab tests, and more in real time.

Quote startBy combining the supercharged search engine from Perfect Search with the powerful semantic processing through BayScribe, we are giving cost-effective and high speed access to critical patient data that has been difficult and expensive to get beforehand.Quote end 
Charlotte, NC (PRWEB) September 16, 2011
With this partnership BayScribe will utilize Perfect Search’s unique indexing and search technology to enhance their Semantic Interoperability platform. Able to index and search structured EMR data, unstructured free text, NLP processed records, DICOM radiology data, lab tests, and more in real time, clients will be provided with unparalleled access to critical data.

Steve Bonney, Vice President of Business Development at BayScribe, stated, “Clinicians are being told that they have to adopt EMR technology for the advancement of healthcare in America, and we agree, fundamentally. We disagree that physicians should have to change the way they interact with patients in order for the healthcare facility and community at large to obtain Semantically Interoperable data." CDI Nurses, Case Managers and Quality Directors all benefit from this partnership and the companies believe that facilities in search of efficiency, especially in a difficult economy, will be particularly excited with the partnership.

James Watanabe, Healthcare Business Development at Perfect Search agreed, stating, “With this partnership with BayScribe, we are bringing a combined solution to the healthcare industry that has never been seen before. By combining the supercharged search engine from Perfect Search with the powerful semantic processing through BayScribe, we are giving cost-effective and high speed access to critical patient data that has been difficult and expensive to get beforehand.”
Through the partnership BayScribe clients will utilize the solution to improve quality scores, better facilitate Clinical Documentation Improvement & Case Management, help mitigate fraud risk, research critical issues, and increase EMR satisfaction levels.

About BayScribe
Established in 1999, BayScribe provides Clinical Documentation Solutions – Dictation, Digital Ink, Speech Recognition, Transcription, Structured/Encoded Data extraction & Document Distribution – for anywhere, anytime access of Clinical Reports with unparalleled performance and reliability. Every month, more than one hundred thousand clinicians in over 400 healthcare facilities rely on the BayScribe platform.

For more information visit the company website at: BayScribe, Inc. | 10800 Sikes Place, Suite 300 | Charlotte, NC 28277 T: 888-801-0106 - info(at)bayscribe(dot)com.

About Perfect Search
Perfect Search Corporation’s patented technology delivers its customers the industry’s fastest, most precise, most scalable, most cost-effective enterprise search technology. Offering both search engine SDK for OEM and search appliance solutions, Perfect Search enables enterprises to find the information they need when they need it, with speed and bulls-eye relevance. Learn more at

Saturday, June 11, 2011

Creating better users by focusing on the experience

We are in the midst of a fundamental shift in the way that payers, physicians, hospital systems, and suppliers exchange and share information. Consumers are becoming more active in their diagnosis and treatment choices.  Providers need to capture and move data more efficiently to meet new regulatory and reporting requirements.  Payors want to ensure that best practices and evidence-based medicine is being used to minimize costs.  Drug makers and researchers are keen to leverage experience to improve research.  And everyone in the process is interested in ensuring that data is being mined to ensure the best outcomes. As a result, all of the stakeholders in healthcare must learn how to best utilize the new technologies and networks being deployed to meet the needs described above, and potentially adopt and integrate them into their business and technology strategies.
Knowledge becomes Guidance
Traditionally science gives knowledge to clinicians, who in turn use this knowledge to inform and treat patients. However, in a modern healthcare setting providers and patients need assistance in the acquisition of knowledge relevant to their conditions, treatment and the opportunity to discuss this knowledge with their peers, friends, family, advocates and other clinicians.

The problem is not a lack of will or incentive. Cutting through this Gordian Knot involves getting enough information from the physician, nurse and patients to ensure the proper outcome. Clinical databases are scarce in healthcare today and most analytical tools have trouble extracting meaningful information from free text, claims and pharmacy data.  Most EMR’s have not been designed as clinical systems and have trouble sending or accepting 3rd party clinical data.  Every day the US generates millions of dictated and typed medical reports each requiring a laborious and time-consuming process of data entry and manipulation, where highly trained and expensive experts manually cull the needed information from each report. Many HIT vendors can’t support the granular clinical data culled out of these reports to meet meaningful use and other regulatory requirements put in place by the Federal Government. 

With this guidance in mind clinicians now use a combination of Data Capture methods and devices along with Natural Language Processing, Semantic Search and knowledge driven software to solve the myriad of logistical, technological, financial and administrative challenges inherent in the clinical documentation and care giving process. The Health Information Technology for Economic and Clinical Health (HITECH) Act brings together, for the first time, a focus on clinical documentation standards (CDA), interoperability of healthcare data (Snomed, ICD-9, ICD-10), EHR Adoption, Portability of Data (HIE, RHIO), and physicians incentives designed to speedily and accurately match disparate patients information when and where it’s needed, securely.   Natural Language Processing (NLP) allows clinicians to document care any way they chose (pen, keyboard, and dictation) by providing a solution that can identify, encode and extract a meaningful set of appropriate healthcare data into a Certified EMR without changing their workflow. This unique solution combines front end data capture, NLP and Semantic Search supported by a Semantic Knowledge Base and a XML based Common Application Framework required to ascertain this goal. 
Natural Language Processing
The information within a clinical note is not solely contained within fixed highly structured fields we normally associate with a database – such as name, address, phone number, etc. The description of the chronic problems, current medications, plan, HPI, and the specific Past Medical History, Review of Systems, Vitals, Labs, Social/Family History, Assessment, and plan are often expressed in free text narratives that require a skilled clinician or abstractor to interpret. This facet of clinical documentation makes up the “black art” of deciphering the active diagnosis against which to match a patient’s condition or status.  

The description, storage and classification of patient information are a fundamental component of the clinical documentation process. Patient information must be gathered from multiple sources (the patient interview, the medical history, admission report and radiology reports) and be placed in a normalized or “canonical” format so that a match against meaningful use criteria and passed into an EMR. 

Natural language Processing is a multi-step process, starting with the lexical analysis of free text into its grammatical components: nouns, verbs, adjectives, etc. and its syntactic architecture of phrases, sentences, tables etc. In order to move beyond the specific language based elements of vocabulary, grammar and syntax one needs to “understand” meaning. Meaning is expressed in terms of concepts and relationships.

In order to extract meaning from “free text” one needs to associate subjects, verbs and objects with previously defined concepts. For example, “amoxicillin is an antibiotic” and by storing this concept of “what amoxicillin is” in a computer one can “interpret” the text containing these words (amoxicillin, antibiotic…). The most common relationship is an “is a” relationship, that is pharyngitis “is a” disease, tamoxifen “is a” estrogen antagonist and so on. Similarly one can build a list of diseases such adenosarcoma, small cell carcinoma, etc. or a hierarchy or taxonomy of diseases.

By parsing, the text for words in the taxonomy the computer can deduce that the word is a disease and then by utilizing the syntax, decide if a relationship exists. By classifying the word as either the subject or object of a phrase, the computer can extract a concept. Finally, by adding synonyms to the taxonomy the computer can greatly enhance its extraction of meaning from free text because it understands more words that are similar to those for which it “knows” a concept.
Once all the Clinically Relevant data has been normalized and tagged it is housed in a Common Application Framework the process of interpreting and analyzing the data it contains can begin.  Once encoded, the information is easily available and accessible for further clinical processes like billing, reimbursement, quality assurance analytics, Pharmacovigilance, Clinical trial identification, registry population, Adverse Event Identification, suspicious findings, and data mining.  The whole process takes place with little or no change to existing workflows supporting front end data capture, near real time decision support and retrospective analysis.   One of the expected results of the PCAST report.
Semantic Search
A natural language query based on a Semantic Output enables either patients, physicians or administrators answers to natural language questions to identify a select body of data. (Patient medical information in the case of the patient is used to screen and/or match patients to trials. For Meaningful Use, Core Measures, PQRI, Infection Control, Registry Population) Finally, by extracting meaning from the clinical narrative data the VA will be able to categorize the clinical data  parameters into a canonical form that may be used for matching or screening of patients with appropriate conditions. The power, specificity, and flexibility of semantic search allows for the discovery and dissemination of clinical information for optimal decision making.  

Semantic Search is helping users:
       Unlock unstructured clinical data for real time coding and extraction of information
       Uncover trends and patterns to reach organizational goals 
       Anticipate business changes and needs
       Reduce operational risk by anticipating clinical events
       Identify candidates for clinical trials
       Develop early warning systems for Infection Control across all facilities or geographic regions -
       Federate searches across all systems, file directories, journals & web sites across all data types
Semantic Knowledge Base
An adult human rarely has to think hard in order to realize that a dog is an animal, which is a living thing, which is a material biological entity that therefore can eat, move, and procreate. In order to “understand” a document, first one has to map out concepts into a knowledge base or ontology. Quite simply an ontology is the description of knowledge about a certain domain (e.g. medicine, genomics, and clinical trials) as expressed in precisely defined terms that are interconnected through their relationships. The implications of such knowledge are easily available to the human mind but computers, as fast and powerful as they are, have no knowledge of this sort and can make no such inferences. However, we must rely on computers to do much of our searching and thinking and we must, therefore, know how to get computers to understand what we want. This in part means getting computers to understand and act on what we know about our world.
In the field of medicine, these efforts have been sponsored by the NIH for over 20 years and medical ontology’s and taxonomies are many and varied. There are many tools for managing ontological databases – both commercial and open source.
Common Application Framework
A Common Application Framework (CAF) is a platform that provides a set of services used to build applications and support business processes based on content. A CAF native data format is XML. XML content is accepted in “as is” form. Content in other formats is converted to an XML representation when loaded into the server. A CAF manages its own content repository and is accessed using the W3C–standard XQuery language or Semantic Search Engine. (By analogy, a relational database is a specialized server that manages its own repository and is accessed through SQL.)
The next generation EMR will have a CAF which should do much more than just store documents. It must be a secure, infinitely extensible platform for building content–driven applications. It needs to be flexible, granular, portable and modular in nature.  To support secondary data use it should have the ability to redact identifiable information while creating a longitudinal record.  Foster a Simi Open Architecture allowing for easy collaboration with other solutions vendors that can add value with no or little integration cost to the end user.  Smart problem lists driven via NLP and dictation. Adverse event identification and notification Medication reconciliation, identification of best practices based on clinical documentation, identification and notification when a physician’s patient meets the criteria for a clinical trial and make that information available to care givers providing a 360 degree view to all stakeholders. 

Tuesday, April 19, 2011

Clinical Trial

The problem
To be brief the problem with the clinical trial system from the perspective of someone seeking alternative or adjust therapy is that is not part of the nation's health care system but part of the pharma industry pipeline. This problem is so severe that while there maybe two million people looking for clinical trial information using Internet search alone easily 100,000+ Americans will die prematurity while there was a trial looking for them within a few zip-codes that could have saved or at least extended their lives.   

Who there are
Clinical Trial Select is a small 501c3 nonprofit group that has been working on this problem for over 8 years. The project was launched with the nonprofit equivalent of seed funding from the American Cancer Society this has been an entirely all volunteer effort. 

In addition to my friend Etienne, the CEO the core group includes a renown data architect,  who designed the original HL7 electronic medical record document architecture and was the  data architect at Lexus|Nexus for over 20 years. We also lucky enough to have one of the top Perl developers anywhere, and a equally well known bio-statistician.

While the life you help save may not be your own simply helping people speak to their own doctors about their clinical trial options will change the practice of health care in America.

Monday, February 14, 2011

Positive Impact of Multiple Input Devices for EHR Adoption: Department of Veterans Affairs

The Department of Veterans Affairs, MedLEE NLP, Bayscribe and RoverINK will demonstrate the result of an innovation prototype resulting from the CONNECT EHR Special Interest Group. This demonstration supports a complete usability framework for clinicians' that works the way they do by incorporating handwriting, keyboards, Tablets, iPads and dictation into electronic records.  

By incorporating clinicians' existing work flow, EHRs support the meaningful use of EHRs without impeding processes. The information collected from the multiple input devices are exportable XML to MedLEE Natural Language Processor (NLP) and data coded to standards. Discreet data elements are generated, including free form notes to produce interoperable formats. This demonstration will populate an NLP based Semantic Search and enterprise content management system for easy health information analysis and document retrieval. This helps eliminate objections regarding the method of input allowing clinicians to continue in their personal work flow. 

Tuesday, January 18, 2011

Transcription Today: Transcription is back.

From HIStalk on Monday 1/17

Transcription Today 
By Diligent Monk
As EMR adoption picks up in response to Meaningful Use, it is worth noting that lurking in the shadows is a familiar enemy to EMR companies: transcription. The age-old practice of dictating for capturing clinical observation is the most efficient, accurate, and preferred method for physicians to document a patient encounter.
Over the past few months, announcements from large organizations have signaled a return to relevancy for the transcription industry. IBM, Nuance, 3M, HealthStory Project, major universities from around the globe, and many other dominant players in the transcription service industry have made significant strides in utilizing technology to create more value from transcripts.
Enter the transcription technology revolution.
Partnering the skilled labor of transcriptionists with technology produces a rich and accurate dataset from a traditional transcript. Whether labeled natural language processing (NLP) or discrete reportable transcription (DRT), the concept is quick, simple to understand, and the value is just now being seen by the industry at large.
Using extensible mark-up language (XML), data is pulled from transcripts and provided in common transport standards (CCR, CCD, CDA) to be used in EMR systems and reports. A physician can dictate his/her notes and collect all of the data required for meeting the objectives and measures for incentive payment per the HITECH Act without purchasing an EMR.
Historically, the EMR sale was built on an ROI derived from transcription savings. Looking at a practice or hospital balance sheet, the transcription bill seemed to be the easiest to pick on, and with the point-and-click interface promoted by EMR vendors, it was a straight replacement for clinical documentation. EMR adoption would eliminate transcription costs. As an industry, the transcript was losing its relevancy in an age of electronic records, but physicians and practices weren’t thrilled with the results. And back to the revolution.
Permitting a physician to dictate in their preferred and normal manner, coupled with the ability to ‘tag’ the data elements of importance from the note, provides the best of both worlds.
Unfortunately, this does nothing to eliminate that pesky transcription charge, which is still the focal point of many EMR pitches. The transcription industry, however, counters that the prevention of productivity loss will more than cover the cost of their services and therefore be a win-win for all involved. As well, the risk of errors in reports is significantly decreased by the medical language specialists that review documents for clinical quality and integrity before submitting back for approval from the physicians.
As crazy as this sounds, and as hard to believe as it may be, transcribing may be the best way for practitioners to achieve Meaningful Use and the most cost-effective for their practice. The technology continues to improve and adoption continues to be strong, so yes, transcription doesn’t appear to be going away, and that may be a good thing.

Tuesday, July 6, 2010

BayScribe and NLP International enter into Strategic Partnership

BayScribe takes next step in developing end-to-end web-based
Clinical Documentation System with the MedLEE Portal

Edgewater, MD — June 24, 2010 BayScribe enters into a strategic partnership to integrate and develop applications that leverage the unique capabilities of the MedLEE™ Natural Language Processing (NLP) technology from NLP International.  NLP International has created a universal SaaS portal to give healthcare facilities, MTSOs and Clinical Documentation Systems, like BayScribe’s Cloud-based platform, access to a broad range of applications designed to support automated, low-cost healthcare solutions to improve Quality, EHR Adoption and accelerate Meaningful Use.

BayScribe plans to jointly advance these applications in cooperation with NLP International, healthcare pundits and other MTSOs to offer these valuable solutions to inpatient and outpatient health providers and organizations. The combination of these technologies creates an end-to-end web services solution available from no other company.

The MedLEE™ Natural Language Processing engine codifies standard text documents for data extraction, thereby enabling Discrete Reportable Transcription (DRT). MedLEE™ was developed over the course of 20 years by Columbia University in New York and is a powerful patented NLP engine that automates analytics, reporting and alerting for outflows such as Core Measures, Present on Admission (POA), PQRI, Patient Summary review, coding and billing support, decision support, clinical trials and more. MedLEE™ has been successfully tested by large hospital systems and government agencies, including Columbia University, the New York Presbyterian Hospital, the National Cancer Institute and the U.S. Department of Defense and is considered the gold standard of Natural Language Processing Solutions. 

"We believe that integrating BayScribe with MedLEE creates an end-to-end Clinical Documentation System that is unparalleled in the healthcare industry,” said Ron Neuenberger, President of BayScribe. "We believe that the physician narrative will continue to be the preferred method of documenting patient encounters for some time because it's quick, easy and supports a thorough analysis. It's our obligation to bring this difference-making technology to Healthcare facilities, directly or indirectly, through NLP International's platform-neutral portal. Dictation and Transcription isn’t dying; it’s evolving, and we believe it will be a critical documentation component for many years, and MedLEE enables the data extraction everyone needs,” added Steven Bonney, V.P. of Business Development at BayScribe.
"A significant proportion of the nation's electronic healthcare records exist in the form of unstructured text - such as word or PDF - and the amount of that data is growing dramatically," noted Bernie Keppler, founder and CEO of NLP International. "MedLEE is a perfect match for the healthcare professionals since it enables physicians to adopt EMR’s with no decrease in their volume.   Healthcare organizations will be able to meet the governmental and economic challenges by significantly reduce costs, by creating interoperable data and have the metrics to report on outcomes. Our partnership with BayScribe is representative of how MTSO are enabling healthcare providers and organizations to realize this value,' added Kyle Silvestro, V.P. of Corporate Strategy and Business Development at NLP International. 

About BayScribe
Established in 1999, BayScribe provides Web-based Dictation & Transcription solutions – anywhere access for Authors and Transcriptionists to dictate, review, approve and distribute reports. Every month, tens of thousands of clinicians rely on BayScribe to capture and deliver their reports. 

For more information visit the company website at: www.BayScribe.comBayScribe, Inc. | 11 Dark Star Court | Edgewater, MD 21037 T: 888-801-0106 - .

About NLP International Corporation
NLP International Corporation offers healthcare professional a patented world-class Natural Language Processing Solution: MedLEE™ .  MedLEE has been successfully commercialized from Columbia University over the past 18 months and is now the market leader in Natural Language Processing technology.  With its unique deployment model NLP International makes this world class solution available for through our MedLEE Portal.   The MedLEE Portal is a SaaS offering the has applications ranging from Quality to Semantic Search and Retrieval to Computer Assisted Coding  and Meaningful use. 

Thursday, May 27, 2010

MTIA: This Week's Webinar Highlight -- Using Natural Language Processing to Achieve Meaningful Use and Promote HIT Adoption

MTIA: This Week's Webinar Highlight -- Using Natural Language Processing to Achieve Meaningful Use and Promote HIT Adoption

This webinar will review current HIT industry trends affecting MTSOs and the path forward into the age of EHR incentives, "meaningful use," and HIT adoption. This will be followed by an introduction in NLP (Natural Language Processing), a leading-edge technology, and how it is currently being used to enable MTSOs to provide solutions to their clinets to address the "meaningful use" requirement and drive secondary data use.

Natural Language Processing using MedLEE