Speech Solutions abound at HIMSS
Speech vendors pulled out all the stops at HIMSS. New systems provide greater flexibility and further accelerate speech workflow to drop report turnaround times to mere minutes. At HIMSS, it was clear that speech recognition is moving beyond conventional approaches. Vendors showed various applications designed for mobile devices and smart phones that allow physicians and care providers to dictate and document on the fly. Other new solutions wed speech and structured reporting to further bump productivity. 

Crescendo launched a front-end speech recognition module of its MD Center-XL application. The company also highlighted an HL7 bidirectional interface between its dictation/speech recognition system and PACS.
With the launch of this foreground module, MD Center-XL allows physicians to oversee the entire documentation workflow, from dictation and correction to sign-off and final report distribution, using one single interface.
In the front-end workflow, this system automatically produces text as the doctor dictates. Once the dictation is complete, the physician can use voice commands to navigate, edit, format, spell, play, fast forward, rewind, select and sign-off the report without using the mouse or keyboard. Personal voice glossaries can be created for word expansion to further accelerate the correction process. The saved voice glossary expansion can support any formatting, including numbering, attributes and positioning.
Automatic template fill-in further shortens the entire report creation process to a few clicks or voice commands. When a doctor creates a new dictation, the system creates the database record, recalls the template, populates the demographics and displays information on the screen in less than one second; the system then populates the database record accordingly. This feature is particularly useful for "normal findings" and is configurable by work type.
The ability for users to use back-end or front-end speech recognition allows healthcare facilities to leave their document creation options open: switching from back-end to front-end recognition may compensate for transcription resource shortage or periodic peaks of activity. A facility may also decide that short reports can be reviewed by authors in foreground mode, while more complex and detailed work can be routed to transcription for correction as a standard or on the fly. Authors can switch from front-end to back-end mode while logged in, so users don't have to exit the application and log on again. If they lack time or are interrupted in the middle of the correction process, they can save ongoing work for later completion or decide to send the report to transcription. Authors can sign off the report using the same application once the correction phase is complete. Finally, even once a job has been sent to transcription, it is still possible to edit it using voice commands. Automatic and predefined distribution occurs after the report has been signed off, and is configurable by work type, author, department and facility.
The Crescendo HL7 bidirectional interface between its dictation/speech recognition system and PACS allows all information to be exchanged electronically (x-ray, voice, and patient report/data), contributing to increased efficiency and reliability of data. Completed results are uploaded from the dictation database to the PACS or RIS where they will be centrally stored. From a user’s perspective, the integrated PACS dictation eliminates duplication of efforts, manual data entry and related errors. Radiologists can begin their dictation immediately without the need to log on twice or manually enter details such as bar codes. Patient information is automatically passed on each time a new image is brought to the screen thereby ensuring optimal data integrity.

MedQuist Inc. and IQMax Inc. announced their partnership to deliver point-of-care clinical documentation and dictation solutions. The companies highlighted PhysAssist IQ and DocQment Ovation.

MedQuist’s PhysAssist IQ, powered by IQMax, allows caregivers to manage their daily workflow by delivering patient list and demographic information to physicians on their mobile devices, so that they can dictate and document patient encounters at the point of care or in between appointments, at the time and place most convenient for them.
With PhysAssist IQ, physicians can synchronize their dictated patient encounters securely in a wireless or wired environment across any care setting, whether acute or ambulatory. PhysAssist IQ is certified on more than 40 different mobile devices utilizing the Microsoft Windows Mobile or Palm Operating Systems.
As part of the strengthened partnership between MedQuist and IQMax, IQMax is more tightly integrating its mobile solutions with MedQuist’s technology and services solutions. For example, PhysAssist IQ mobile solutions will be integrated into MedQuist’s new dictation platform, DocQment Ovation, to provide healthcare customers with a total end-to-end documentation solution. Ovation is a Web-based enterprise digital voice capture and document management solution that provides centralized administration and management from a single point and allows healthcare organizations to increase efficiency, decrease turnaround times and realize an immediate ROI. 

Nuance Communications, Inc. demonstrated its mobile dictation and voice control solutions and technologies for healthcare organizations including Dictaphone GoMD 3.6 Mobile Dictation, Nuance Voice Control Healthcare Edition and Nuance Mobile Dictation Healthcare Edition. In addition, Dictaphone and Vocera Communications discussed integrated traditional dictation capabilities. Nuance also launched DragonConnect and highlighted an agreement with StructuRad.
GoMD v3.6 is the latest version of Dictaphone’s traditional mobile dictation solution. Using GoMD, a physician can select a patient from a list, dictate a report, and GoMD will automatically deliver it wirelessly to the Dictaphone Enterprise Express documentation system for processing. Transcribed reports can be viewed and electronically signed using GoMD. GoMD 3.6 includes a number of new enhancements, including support for the Microsoft Windows Mobile 5 operating system running on the iPAQ 2490 and 2790 PDAs.
Nuance Voice Control Healthcare Edition allows healthcare providers to instantly access clinical information from their existing healthcare information systems via a Sprint handheld device using simple voice commands. The user simply dictates an information request, and the resulting data is conveniently displayed on the smart phone screen, eliminating the need to locate a computer terminal in the hospital or healthcare facility to obtain pertinent patient information. For providers on the move, this technology represents a productivity boost that can improve patient care. 
Nuance Mobile Dictation Healthcare Edition delivers accurate, real-time transcription to mobile phones based on the technology behind Dragon NaturallySpeaking 9 Medical Edition. This on-demand service brings to the mobile phone speech recognition options that until now had been limited to desktop PC solutions. Using this technology, a physician will be able to dictate narrative clinical notes on a smart phone and have them instantly transcribed.
Vocera Communications and Dictaphone plan to provide integrated traditional dictation capabilities on the Vocera Communications Badge for physicians and nurses. Vocera customers will be able to integrate with the Dictaphone Enterprise Express documentation system to document patient encounters. Provider dictations will be automatically routed through the Dictaphone system for automatic speech recognition, transcription and document distribution.
DragonConnect for Dragon NaturallySpeaking allows medical customers to take advantage of the enterprise wide dictation, transcription and speech recognition capabilities of the Dictaphone Enterprise Express solution to maximize their clinical documentation effectiveness.
With Dragon NaturallySpeaking Medical, healthcare providers dictate directly into third party clinical information and EMR applications to reduce the cost of transcription, improve report turnaround time and increase overall adoption rates of these clinical information systems. DragonConnect provides a software bridge between Dragon NaturallySpeaking Medical and Dictaphone’s Enterprise Express family of integrated dictation and transcription solutions, including EXVoice and EXText. DragonConnect Version 1.0 will support the following integrated workflows:
  • DragonConnect and EXVoice--Dragon NaturallySpeaking Medical users send a full dictated audio report to the EXVoice dictation system using a voice command or microphone control. The dictated report is routed to the appropriate transcriptionist for transcription. The transcribed text can be entered directly into the host clinical information system or other third party application.
  • DragonConnect and EXVoice/EXText--Dragon NaturallySpeaking Medical users send a full dictated report (audio and text recognized by Dragon NaturallySpeaking) to the EXText transcription system using a voice command or microphone control. The draft report is routed to the appropriate transcriptionist for editing and correction within the EXText platform. The transcribed text can then be electronically signed in EXText and uploaded via HL7 to the host application, or it can be uploaded in a preliminary state to be signed electronically with the host application.
DragonConnect will be available in the third Quarter of 2007 for use with Dragon NaturallySpeaking Medical, Dictaphone EXVoice versions 6.5 or 7.0 and Dictaphone EXText versions 6.4 and 7.0.
The agreement between Nuance and StructuRad makes StructuRad reporting tools, including macros and templates, available for Dictaphone PowerScribe and enables PowerScribe users to create reports by voice more quickly by leveraging StructuRad’s macro library to set up the reporting user interface to speed up the reporting process.
StructuRad macros provide a library of normal and abnormal report templates derived from its proprietary radiology knowledge base. As part of the agreement, the customized StructuRad macro library will be sold as an add-on product to PowerScribe. The macro library of report templates has been created to utilize PowerScribe’s voice edit features and will permit PowerScribe users to create reports by calling up a macro and making simple edits.

Philips introduced Digital Pocket Memo and highlighted an agreement with Health Language, Inc.
The redesigned handheld recorder offers enhanced ergonomics and intuitive operation. Features include voice activation and mandatory keyword commands. Enhancements include:
  • A large ergonomic display with three “smart buttons” similar to those on a mobile phone.
  • The handheld recorder can be placed into the optional LAN docking station, allowing dictation to be automatically uploaded to a local area network (LAN) without the need for a PC connection.
  • Dictation is automatically encrypted in real time as it is being recorded. This eliminates the possibility of unauthorized users accessing the Pocket Memo or memory card.
  • The Digital Pocket Memo features two levels of security: a PIN that users enter to activate the device, and a personal user keyword (PUK) that allows IT staff or supervisors to override the lock-out mode.
  • Advanced encryption technology ensures that dictation is compliant with today’s standards for confidentiality and security.
  • The battery can be USB quick-charged in less than 2.5 hours through a USB socket.
  • Sound quality is through upgraded DSS (digital speech standard files) and SpeechExec Pro software. In addition, the Pocket Memo minimizes background noise and allows users the choice of slow or fast-file playback.
The agreement between Philips and Health Language focuses on language standardization. The companies aim to automate the conversion of free text into consistent medical terminology to enable direct storage in the EMR and improve patient care by providing physicians with a central, reliable source of medical information. Interop 6.1 extracts findings, diagnoses, drugs, allergies and other relevant information from dictated reports. Subsequently, the information is formatted for upload to the EMR. The solution generates codes that support the classification of medical conditions and the structuring of clinical data, such as the World Health Organization’s International Classification of Diseases (ICD) codes and the Systematized Nomenclature of Medicine (SNOMED) codes. Interop 6.1 also identifies medical terms from the history of present illnesses (HPI) to be indexed in the EMR. The indexed terms can be used for statistical evaluation, thus helping to improve hospital procedures related to patient safety, medication and continuity of care.