RadStation: client-based digital dictation system and integrated clinical information display with an embedded Web-browser.

RadStation is a digital dictation system having an integrated display of clinical information. The three-tiered system architecture provides robust performance, with most information displayed within one second after a request. The multifunctional client tier is a unique client/browser hybrid. A Web browser display window functions as the client application's data display window for clinical information, radiology reports, and laboratory and pathology results. RadStation provides a robust platform for digital dictation functionality. The system's internal status checks ensure operational integrity in a clinical environment. Also, the programmable dictation microphone and bar-code reader supplant the mouse as the system's primary input device. By merging information queries into existing work flow, radiologist's interpretation efficiency is maintained with instant access to essential clinical information. Finally, RadStation requires minimal training and has been enthusiastically accepted by our radiologists in an active clinical practice.

Radiologist's clinical information review workstation interfaced with digital dictation system.

Efficient access to information systems integrated into the radiologist's interpretation workflow will result in a more informed radiologist, with an enhanced capability to render an accurate interpretation. We describe our implementation of radStation, a radiologist's clinical information review workstation that combines a digital dictation station with a clinical information display. radStation uses client software distributed to the radiologist's workstation and central server software, both running Windows NT (Microsoft, Redmond, WA). The client system has integrated digital dictation software. The bar-code microphone (Boomerang, Dictaphone Corp, Stratford, CT) also serves as a computer input device forwarding the procedure's accession number to the server software. This initiates multiple queries to available legacy databases, including the radiology information system (RIS), laboratory information system, clinic notes, hospital discharge, and operative report system. The three-tier architecture then returns the clinical results to the radStation client for display. At the conclusion of the dictation, the digital voice file is transferred to the dictation server and the client notifies the RIS to update the examination status. The system is efficient in its information retrieval, with queries displayed in about 1 second. The radStation client requires less than 5 minutes of radiologist training in its operation, given that its control interface integrates with the well-learned dictation process. The telephone-based dictation system, which this new system replaced, remains available as a back-up system in the event of an unexpected digital dictation system failure. This system is well accepted and valued by the radiologists. The system interface is quickly mastered. The system does not interrupt dictation workflow with the display of all information initiated with examination bar-coding. This system's features could become an accepted model as a standard tool for radiologists.

Integration of radiologist peer review into clinical review workstation.

Professional peer review of random prior radiologist's interpretations is mandated by the Joint Commission on Accreditation of Healthcare Organizations (JCAHO). The JCAHO expects documentation of 5% rate of random peer-review cases. Countless hours are spent in departments fulfilling these requirements. The integration of the peer-review process into the radiologist's interpretation workflow was expected to increase the percentage of documented peer review, yet decrease the time and effort for this documentation. radStation clinical review workstations are deployed at every reading station. When a requisition is bar-coded, radStation retrieves the patient's clinical information and automatically displays the prior comparison report. If the radiologist agrees with the prior report, a single click on a "quality assurance' agree box documents the agreement. In the case of a discordance, an additional dialog box automatically appears and the radiologist enters the reason for disagreement and then submits the case as a discrepancy. The system holds the discordance for 3 to 5 working days, then notifies the original radiologist via E-mail that a prior interpretation has been submitted for peer review, lists the submitted discrepancy reason, and provides a link to display the discordant report. The peer-review database is separate from the existing radiology information system (RIS). At the end of every month, summary reports of all peer-review activity are generated automatically. Initial benchmarks of our deployed system anticipate documentation of long-term random peer-review rate at greater than 50% of interpreted cases. The system enhances the peer-review process by integrating it with the normal interpretation workflow. The time to complete peer review using radStation is less than 1 second per normal case and less than 60 seconds for a discordant case. The E-mail notification system is fully automated, eliminating the need for secretarial involvement in the data collection. This system has completely replaced a manual paper-based system. The integration of peer review directly into the radiologist's interpretation workstation greatly enhances the capability to easily exceed JCAHO standards. The overall increase in peer-review documentation should continue to improve the ability to document a consistent high quality of patient care.

A digital imaging and communications in medicine (DICOM) print service for chest imaging.

Large-scale picture archiving and communication systems (PACS) have not been widely implemented in this or other countries. In almost all radiology departments film remains the medium for diagnostic interpretation and image archive. Chest imaging is the dominant screening examination performed within most imaging departments and as such, is an extremely high-volume, low-margin examination. Digital technologies are being applied to chest imaging to overcome limitations of screen-film receptors (limited latitude) and current film management systems (single-image copy). Efficient management of images and information is essential to the success of a chest imaging program. In this article we report on a digital imaging and communications in medicine (DICOM)-based centralized printing network for chest imaging. The system components and their operational characteristics are described. Our experience integrating DICOM-compliant equipment supplied by several vendors is described. We conclude that the print model supported by DICOM is adequate for cross-sectional (eg, computed tomography and magnetic resonance) imaging but is too simplistic to be generally applied to projection radiography.