Voice Recognition Roars Into Chicago
Image courtesy of Crescendo 

Speech recognition and reporting solutions are making themselves heard. As the pressure to decrease report turnaround time and cut costs continues to mount—and PACS-speech integration gets smoother—more sites are turning to speech recognition systems. And vendors are ready.
At RSNA, companies are touting speech recognition systems and new features to boost workflow and enhance patient safety and care. What’s more, tighter integrations with PACS providers and other vendors are on the rise, streamlining implementations and workflow. Several products that are the fruit of company alliances are making integration even tighter. Make some time to peruse the latest speech options on display around McCormick Place.


3M Health Information Systems (Booth 5955) and Philips Speech Recognition Systems are highlighting the integration of Philips SpeechMagic into 3M’s document creation suite of products.
The integration provides 3M customers with documentation solutions for medical reporting. It includes front-end and back-end speech recognition, designed to significantly reduce document turnaround time and transcription costs and leverages 3M’s voice management system, document creation tools and automated document distribution solutions, according to the companies.

Commissure (Booth 7154), recently acquired by Nuance, is releasing RadWhere 2.0 structured speech reporting/workflow/communication system.    
The new version updates the RadWhere Assisted Diagnosis (AD) module with additional content and anatomical atlases and integrates third- party hosted content, such as Amirsys STATdx. RadWhere 2.0 also includes RadWhere Peer Review. The integrated Peer Review feature is designed to comply with the American College of Radiology’s new peer review guidelines, save time and reduce clicks. Peer reviews are performed at site-defined intervals and validation is managed from the new administrator portal. The new version allows RadWhere Notes to serve as a "chat session" between radiologists collaborating on a study. The improved RadWhere Workflow Orchestrator solves the problem of managing multisite workflow with disparate systems in heterogeneous work environments. Worklist management and single workstation control simplify the interpretation and communication of diagnostic imaging studies. The "Smart Template" includes an enhanced "Finding-only Mode" that eases structured reporting by automating the process and not changing the radiologist’s dictation style. RadWhere 2.0 features a speech engine update that improves recognition accuracy and profile management. A web-based administrative portal features a Boolean worklist builder, a peer review validation tool and new real-time dashboard. Finally, RadWhere 2.0 can be integrated with RadCube data mining and analysis tool.

Crescendo (Booth 6451) is highlighting Clinical Notes, an interactive speech recognition module for clinical notes as part of MD Center-XL.
The new module allows physicians to process clinical notes in real-time via customized templates, macros, drop-down menus, check boxes, voice commands, front-end speech recognition and electronic signature. All features are integrated into a single application. Resulting electronic reports can be stored and shared with other healthcare professionals. Upon selecting a patient, the system loads a clinical notes template with bookmarks, such as length of stay or allergies, to guide the physician during the dictation process. The physician can navigate from one bookmark to another using voice commands. Text is populated on screen as the physician dictates via Crescendo front-end speech recognition system powered by SpeechMagic. The new module also supports HL7 ADT integration to automate the import of patient demographics directly into the report. Once the report is complete, the physician can sign off within the same application. Automatic and predefined distribution occurs after the report has been signed off, and is configurable by work type, author, department and facility. The Clinical Notes module offers seamless interfaces with major PACS and RIS, and supports thin-client infrastructures and terminals.

Dictaphone, (Booth 2117) a division of Nuance, at RSNA is unveiling Dictaphone PowerScribe 5.0.
PowerScribe Workstation 5.0 is a new version of company’s speech recognition reporting solution for radiology. It includes: speech engine upgrades; system architecture enhancements; a redesigned user interface; enhanced, patent-pending, critical-alert technology to improve high-priority communication and infrastructure upgrades to support multiple radiology information systems.
PowerScribe 5.0 features customer-driven system enhancements designed to give radiologists more control of their reports with the goal of making the dictation process faster, more accurate and easier to maintain. PowerScribe 5.0 is expected to drive faster report turnaround time, reduce transcription costs, increase satisfaction levels from referring physicians and enhance patient care.

Grundig Business Systems (Booth 1977) is demonstrating its DigtaSonic x420 mobile dictation recorder and DigtaSonic xMic digital dictation microphone, and spotlighting its Digta CordEx wireless dictation microphone.
The x420 recorder features 128 MB internal memory for up to 20 hours of voice recording and the DigtaCard memory cards provide extra capacity. It can be used as a desktop USB microphone via the USB interface. Both the DigtaSonic x420 and DigtaSonic xMic support the improved DS SPro voice standard. The Digta CordEx comes in a rubberized coating and allows for movement up to 25 feet away while dictating.

RIS Concepts (Booth 8731) is introducing its RadSpeak feature that utilizes templates and macros to streamline web-based dictation. When accessed, RadSpeak presents the user with a range of exam report templates. Through verbal commands, the user simply selects which standard paragraphs from the template to include in the report, makes any necessary changes and calls for a digital signature. Radiologists also can create an unlimited number of custom voice-controlled templates.

ScImage (Booth 2551) is highlighting integrations with speech recognition products from PowerScribe, Lanier, ViaVoice and Dragon Naturally Speaking and PicomDOC, its own customizable reporting and workflow documentation solution.
PicomDOC uses a standards-based approach to report design and customization. PicomDOC incorporates the DICOM Structured Reporting (SR) standard and uses rich-text formatting and smart macros to complete a variety of reports. The solution also boasts automatic creation of an Adobe PDF document upon final signature that is subsequently saved to the Electronic Patient Folder within PicomEnterprise. PicomDOC further supports workflow needs by automatically changing the status of the study to “report created” and “report signed.” PicomDOC supports locking of documents: once a document is signed, it is locked and the user is prompted to create an addendum. These generated reports can be automatically distributed by using ScImage’s workflow engine via HL7 message or other file formats.