Objetivo: Cuantificar la repercusión de un sistema de reconocimiento del habla integrado en un PACS/RIS en el tiempo invertido en los informes radiológicos y su disponibilidad en una Clínica Universitaria. Material y métodos: Estudio piloto prospectivo; en 669 radiografías se registró el tiempo invertido por dictado con cinta y sistemas PACS/RIS de reconocimiento (dictado por lotes o dictado en línea) y el Report Turnaround Time, intervalo de tiempo desde la introducción de imagen en PACS hasta tener informe disponible en RIS/CIS. En análisis retrospectivo de base de datos de RIS se estudió 11/2002-02/2003 y 11/2003-02/2004. Se calculó la media y el aumento relativo de la disponibilidad de informes a mediano y corto plazo tras la finalización del estudio. Resultados: Se observaron importantes diferencias en el tiempo invertido para cada modalidad (0,44/0,54/0,62 s por palabra e imagen) y del RTT medio (10,47/6,65/1,27 h). Se evaluaron retrospectivamente 37.898/39.680 informes de los períodos mencionados. En CR/TC, se observó un aumento medio del 20% en la disponibilidad de informes a corto plazo y en todas las modalidades fue más del triple en las primeras 24 h. En el caso de CR/TC/RM, el primer día hubo un aumento máximo de la disponibilidad a mediano plazo (factor 3,1/5,8/4,0) y en el caso de XA/DS, en el segundo día (factor 2,0). Conclusión: Cuando se utiliza un sistema de reconocimiento del habla se modifica el flujo de trabajo y se invierte inicialmente más tiempo para la elaboración de informes. Los sistemas de reconocimiento integrados en PACS/RIS mejoran considerablemente la disponibilidad de los informes a corto y mediano plazo, redundando en la calidad de la atención de los pacientes.

Objetivo: Cuantificar la repercusión de un sistema de reconocimiento del habla integrado en un PACS/RIS en el tiempo invertido en los informes radiológicos y su disponibilidad en una Clínica Universitaria. Material y métodos: Estudio piloto prospectivo; en 669 radiografías se registró el tiempo invertido por dictado con cinta y sistemas PACS/RIS de reconocimiento (dictado por lotes o dictado en línea) y el Report Turnaround Time, intervalo de tiempo desde la introducción de imagen en PACS hasta tener informe disponible en RIS/CIS. En análisis retrospectivo de base de datos de RIS se estudió 11/2002-02/2003 y 11/2003-02/2004. Se calculó la media y el aumento relativo de la disponibilidad de informes a mediano y corto plazo tras la finalización del estudio. Resultados: Se observaron importantes diferencias en el tiempo invertido para cada modalidad (0,44/0,54/0,62 s por palabra e imagen) y del RTT medio (10,47/6,65/1,27 h). Se evaluaron retrospectivamente 37.898/39.680 informes de los períodos mencionados. En CR/TC, se observó un aumento medio del 20% en la disponibilidad de informes a corto plazo y en todas las modalidades fue más del triple en las primeras 24 h. En el caso de CR/TC/RM, el primer día hubo un aumento máximo de la disponibilidad a mediano plazo (factor 3,1/5,8/4,0) y en el caso de XA/DS, en el segundo día (factor 2,0). Conclusión: Cuando se utiliza un sistema de reconocimiento del habla se modifica el flujo de trabajo y se invierte inicialmente más tiempo para la elaboración de informes. Los sistemas de reconocimiento integrados en PACS/RIS mejoran considerablemente la disponibilidad de los informes a corto y mediano plazo, redundando en la calidad de la atención de los pacientes.Purpose: Quantification of the impact of a PACS/RIS-integrated speech recognition system (SRS) on the time expenditure for radiology reporting and on hospital-wide report availability (RA) in a university institution. Material and methods: In a prospective pilot study, the following parameters were assessed for 669 radiographic examinations (CR): 1. time requirement per report dictation (TED: dictation time (s)/number of images (examination) x number of words (report)) with either a combination of PACS/ tape-based dictation (TD: analog dictation device/ minicassette/transcription) or PACS/RIS/speech recognition system(RR: remote recognition/transcription and OR: online recognition/self-correction by radiologist), respectively, and 2. the ReportTur-naround Time (RTT) as the time interval from the entryof the first image into the PACS to the available RIS/HIS report. Two equal time periods were chosen retrospectively from the RIS database: 11/2002-2/2003 (only TD) and 11/2003-2/2004 (only RR or OR with speech recognition system (SRS)). The midterm (> 24 h, 24 h intervals) and short-term (< 24 h, 1 h intervals) RA after examination completion were calculated for all modalities and for CR, CT, MR andXA/DS separately. The relative increase in the mid-term RA (RIMRA: related to total number of examinations in each time period) and increase in the short-term RA (ISRA: ratio of available reports during the 1st to 24th hour) were calculated. Results: Prospectively there was a significant difference between TD/RR/OR (n = 151/257/261) regarding mean TED (0.44/0.54/0.62 s (per word and image)) and mean RTT.

Ziele: Retrospektiver Vergleich der Befundverfügbarkeit bei Einsatz eines RIS/PACS-integrierten Spracherkennungssystems (SES) mit und ohne Befundeditierung durch Schreibkräfte Methode: In einer retrospektiven Auswertung der RIS/PACS-Datenbank wurde die kumulative Befundverfügbarkeit (BV; %) für 2 vergleichbare Zeiträume ausgewertet.

Ziele: Erfassung des langfristigen Effektes eines PACS/RIS-integrierten Spracherkennungssystems (SES) auf die Verfügbarkeit radiologischer Befunde in einer universitären Umgebung Methode: In einer retrospektiven RIS-Datenbank-Analyse wurde die Befundverfügbarkeit (Report Turnaround Time [RTT]: Zeitintervall vom Untersuchungsende bis zum verfügbaren Befund im klinischen Informationssystem) für 3 gleiche Zeiträume berechnet:

PURPOSE:Quantification of the impact of a PACS/RIS-integrated speech recognition system (SRS) on the time expenditure for radiology reporting and on hospital-wide report availability (RA) in a university institution.MATERIAL AND METHODS:In a prospective pilot study, the following parameters were assessed for 669 radiographic examinations (CR): 1. time requirement per report dictation (TED: dictation time (s)/number of images [examination] x number of words [report]) with either a combination of PACS/tape-based dictation (TD: analog dictation device/mini-cassette/transcription) or PACS/RIS/speech recognition system (RR: remote recognition/transcription and OR: online recognition/self-correction by radiologist), respectively, and 2. the Report Turnaround Time (RTT) as the time interval from the entry of the first image into the PACS to the available RIS/HIS report. Two equal time periods were chosen retrospectively from the RIS database: 11/2002 - 2/2003 (only TD) and 11/2003 - 2/2004 (only RR or OR with speech recognition system [SRS]). The mid-term (> or = 24 h, 24 h intervals) and short-term (< 24 h, 1 h intervals) RA after examination completion were calculated for all modalities and for CR, CT, MR and XA/DS separately. The relative increase in the mid-term RA (RIMRA: related to total number of examinations in each time period) and increase in the short-term RA (ISRA: ratio of available reports during the 1st to 24th hour) were calculated.RESULTS:Prospectively, there was a significant difference between TD/RR/OR (n = 151/257/261) regarding mean TED (0.44/0.54/0.62 s [per word and image]) and mean RTT (10.47/6.65/1.27 h), respectively. Retrospectively, 37 898/39 680 reports were computed from the RIS database for the time periods of 11/2002 - 2/2003 and 11/2003 - 2/2004. For CR/CT there was a shift of the short-term RA to the first 6 hours after examination completion (mean cumulative RA 20 % higher) with a more than three-fold increase in the total number of available reports within 24 hours (all modalities). The RIMRA for CR/CT/MR was 3.1/5.8/4.0 in the first 24 hours, and 2.0 for XA/DS in the second 24-hour interval.CONCLUSION:In comparison to tape-based dictation, an SRS results in a significantly higher primary time expenditure and a modified report dictation workflow. In a university institution, a PACS/RIS-integrated SRS achieves a marked improvement in both short- and mid-term RA which eventually results in an improvement in patient care.

Purpose: Quantification of the impact of a PACS/RIS-integrated speech recognition system (SRS) on the time expenditure for radiology reporting and on hospital-wide report availability (RA) in a university institution. Material and Methods: In a prospective pilot study, the following parameters were assessed for 669 radiographic examinations (CR): 1. time requirement per report dictation (TED: dictation time (s)/number of images [examination] x number of words [report]) with either a combination of PACS/tape-based dictation (TD: analog dictation device/minicassette/transcription) or PACS/RIS/speech recognition system (RR: remote recognition/transcription and OR: online recognition/self-correction by radiologist), respectively, and 2. the Report Turnaround Time (RTT) as the time interval from the entry of the first image into the PACS to the available RIS/HIS report. Two equal time periods were chosen retrospectively from the RIS database: 11 /2002 - 2/2003 (only TD) and 11/2003 - 2/2004 (only RR or OR with speech recognition system [SRS]). The midterm (>= 24 h, 24 h intervals) and short-term (< 24 h, 1 h intervals) RA after examination completion were calculated for all modalities and for CR, CT, MR and XA/DS separately. The relative increase in the mid-term RA (RIMRA: related to total number of examinations in each time period) and increase in the short-term RA (ISRA: ratio of available reports during the 1st to 24th hour) were calculated. Results: Prospectively, there was a significant difference between TD/RR/OR (n = 151/257/261) regarding mean TED (0.44/0.54/0.62s [per word and image]) and mean RTT (10.47/6.65/1.27 h), respectively. Retrospectively, 37898/39680 reports were computed from the RIS database for the time periods of 11/2002 - 2/2003 and 11/2003 - 2/2004. For CR/CT there was a shift of the short-term RA to the first 6 hours after examination completion (mean cumulative RA 20% higher) with a more than three-fold increase in the total number of available reports within 24 hours (all modalities). The RIMRA for CR/CT/MR was 3.1/5.8/4.0 in the first 24 hours, and 2.0 for XA/DS in the second 24-hour interval. Conclusion: In comparison to tape-based dictation, an SRS results in a significantly higher primary time expenditure and a modified report dictation workflow. In a university institution, a PACS/RIS-integrated SRS achieves a marked improvement in both short- and mid-term RA which eventually results in an improvement in patient care.

Die bisherige Erstattung stationärer Krankenhausleistungen auf Basis tagesgleicher Pflegesätze, Fallpauschalen und Sonderentgelte ist durch das Diagnosis-related-groups- (DRG-)System abgelöst worden. Operationen- und Prozeduren- (OPS-)Schlüssel 301 konnten in der Radiologie bis 2004 mit entsprechender Anpassung des „Radiologie-Informations-System“ (RIS) vollautomatisiert erfasst werden. Durch die immer feinere Differenzierung der OPS-Codes in der Version 2005 ist eine eindeutige Ermittlung der OPS-Codes jedoch nicht mehr vollautomatisch möglich. Ziel ist es, diese zusätzlichen Aufgaben mit so wenig Mehraufwand wie möglich zu erbringen.

With ongoing technical refinements speech recognition systems (SRS) are becoming an increasingly attractive alternative to traditional methods of preparing and transcribing medical reports. The two main components of any SRS are the acoustic model and the language model. Features of modern SRS with continuous speech recognition are macros with individually definable texts and report templates as well as the option to navigate in a text or to control SRS or RIS functions by speech recognition. The best benefit from SRS can be obtained if it is integrated into a RIS/RIS-PACS installation. Report availability and time efficiency of the reporting process (related to recognition rate, time expenditure for editing and correcting a report) are the principal determinants of the clinical performance of any SRS. For practical purposes the recognition rate is estimated by the error rate (unit "word"). Error rates range from 4 to 28%. Roughly 20% of them are errors in the vocabulary which may result in clinically relevant misinterpretation. It is thus mandatory to thoroughly correct any transcribed text as well as to continuously train and adapt the SRS vocabulary. The implementation of SRS dramatically improves report availability. This is most pronounced for CT and CR. However, the individual time expenditure for (SRS-based) reporting increased by 20-25% (CR) and according to literature data there is an increase by 30% for CT and MRI. The extent to which the transcription staff profits from SRS depends largely on its qualification. Online dictation implies a workload shift from the transcription staff to the reporting radiologist.

Ziele: Quantifizierung der verbesserten Verfügbarkeit radiologischer Befunde in einem Universitätsklinikum nach Einführung eines Spracherkennungssystems mit integrierter PACS/RIS-Kopplung und digitaler Bild- und Befundverteilung Methode: Als Parameter für die Befundverfügbarkeit wurde die Report Turnaround Time (RTT=Zeitintervall zwischen PACS-Import des ersten Bildes und erster Verfügbarkeit des zugehörigen radiologischen Befundes im RIS/HIS) herangezogen. In einer prospektiven Analyse wurden von 12 Radiologen aller Ausbildungsgrade je 240 Befunde aus konventionellem Röntgen (CR) und Computertomographie (CT) erstellt. Die Befunderstellung erfolgte für beide Modalitäten zur Hälfte mit konventionellem Banddiktat (KD), zur Hälfte mit einem Spracherkennungssystem (SE). Es wurden jeweils Hintergrundspracherkennung (HGSE) mit Korrektur des Diktates durch Schreibkräfte bzw. Onlinespracherkennung (OLSE) mit Selbsteditierung des Diktates durch den Radiologen gleichermaßen eingesetzt. Retrospektiv erfolgte für die Zeiträume 11/02–02/03 (KD vor Einführung des SE) sowie 11/03–02/04 (HGSE bzw. OLSE) ebenfalls eine RTT-Analyse der RIS-Datenbank. Die Befundverfügbarkeit (RTT) wurde in drei Kategorien unterteilt: (I) Befundverfügbarkeit (BV) in weniger als einem Tag, (II) BV in bis zu 5 Stunden, (III) BV in bis zu 1 Stunde. Ergebnis: Prospektiv betrug die mittlere RTT im CR 21,1/25,1/8,9h (KD/HGSE/OLSE), im CT 23,8/29,6/7,6h (KD/HGSE/OLSE). In der retrospektiven Analyse wurden 37898 bzw. 39680 Datensätze für beide Zeiträume ausgewertet. Die Zahl der Befunde in weniger als einem Tag betrug 3485/11453, in <5 Stunden 2410/9710, in <1 Stunde 352/2050 für 2002–03/2003–04. Dies entspricht einem Verbesserungsfaktor der Befundverfügbarkeit in einem Tag von 3,1, in <5 Stunden von 3,9, in <1 Stunde von 5,6. Schlussfolgerung: Die Einführung eines Spracherkennungssystems mit Integration in ein vorbestehendes PACS/RIS-System ermöglicht eine deutlich verbesserte klinikweite Befundverfügbarkeit.

Film-based teaching files require a substantial investment in human, logistic, and financial resources. The combination of computer and network technology facilitates the workflow integration of distributing radiologic teaching cases within an institution (intranet) or via the World Wide Web (Internet).A digital teaching file (DTF) should include the following basic functions: image import from different sources and of different formats, editing of imported images, uniform case classification, quality control (peer review), a controlled access of different user groups (in-house and external), and an efficient retrieval strategy. The portable network graphics image format (PNG) is especially suitable for DTFs because of several features: pixel support, 2D-interlacing, gamma correction, and lossless compression. The American College of Radiology (ACR) "Index for Radiological Diagnoses" is hierarchically organized and thus an ideal classification system for a DTF.Computer-based training (CBT) in radiology is described in numerous publications, from supplementing traditional learning methods to certified education via the Internet. Attractiveness of a CBT application can be increased by integration of graphical and interactive elements but makes workflow integration of daily case input more difficult. Our DTF was built with established Internet instruments and integrated into a heterogeneous PACS/RIS environment. It facilitates a quick transfer (DICOM_Send) of selected images at the time of interpretation to the DTF and access to the DTF application at any time anywhere within the university hospital intranet employing a standard web browser.A DTF is a small but important building block in an institutional strategy of knowledge management.

Reimbursement for inpatient services rendered based on comparable daily care rates, case-based flat rates, and special fees as practiced until now has been replaced by the system of diagnosis-related groups. Up until 2004, operation and procedure system (OPS 301) codes could be processed completely automatically by appropriate adaptation of the radiology information system (RIS). Because of further differentiation of OPS codes in the 2005 version, it is no longer possible to unambiguously determine OPS codes automatically. Our goal was to fulfill these additional requirements with as little extra effort as possible. In 36 of 2138 procedures during an observation period of 12 days, i.e., 4/day, manual input on the part of the radiology technical assistant and quality assurance by the diagnosing physician were necessary. This is only needed in complicated procedures for which the minor added effort is negligible in comparison to the entire effort expended for the procedure. We were thus able to achieve the goal of near automation of ascertaining OPS codes.

Reimbursement for inpatient services rendered based on comparable daily care rates, case-based flat rates, and special fees as practiced until now has been replaced by the system of diagnosis-related groups. Up until 2004, operation and procedure system (OPS 301) codes could be processed completely automatically by appropriate adaptation of the radiology information system (RIS). Because of further differentiation of OPS codes in the 2005 version, it is no longer possible to unambiguously determine OPS codes automatically. Our goal was to fulfill these additional requirements with as little extra effort as possible. In 36 of 2138 procedures during an observation period of 12 days, i.e., 4/day, manual input on the part of the radiology technical assistant and quality assurance by the diagnosing physician were necessary. This is only needed in complicated procedures for which the minor added effort is negligible in comparison to the entire effort expended for the procedure. We were thus able to achieve the goal of near automation of ascertaining OPS codes.

Mit der voranschreitenden technischen Entwicklung werden Spracherkennungssysteme (SES) — gerade vor dem Hintergrund der aktuell unabweisbaren Kostenreduktion bei gleichbleibender Qualität in der Patientenversorgung — eine zunehmend attraktive Alternative zur traditionellen Befunderstellung.

Ein filmbasiertes radiologisches Lehrarchiv erfordert einen hohen personellen, logistischen und finanziellen Aufwand. Die Verbindung von Computer- und Netzwerktechnologie erlaubt mittlerweile die sog. „Workflowintegration“ der Verbreitung radiologischer Lehrfälle innerhalb einer Institution (Intranet) oder im World Wide Web (Internet).

Film-based teaching files require a substantial investment in human, logistic, and financial resources. The combination of computer and network technology facilitates the workflow integration of distributing radiologic teaching cases within an institution (intranet) or via the World Wide Web (Internet). A digital teaching file (DTF) should include the following basic functions: image import from different sources and of different formats, editing of imported images, uniform case classification, quality control (peer review), a controlled access of different user groups (in-house and external), and an efficient retrieval strategy. The portable network graphics image format (PNG) is especially suitable for DTFs because of several features: pixel support, 2D-interlacing, gamma correction, and lossless compression. The American College of Radiology (ACR) Index for Radiological Diagnoses is hierarchically organized and thus an ideal classification system for a DTF. Computer-based training (CBT) in radiology is described in numerous publications, from supplementing traditional learning methods to certified education via the Internet. Attractiveness of a CBT application can be increased by integration of graphical and interactive elements but makes workflow integration of daily case input more difficult. Our DTF was built with established Internet instruments and integrated into a heterogeneous PACS/RIS environment. It facilitates a quick transfer (Dl-COM_Send) of selected images at the time of interpretation to the DTF and access to the DTF application at any time anywhere within the university hospital intranet employing a standard web browser. A DTF is a small but important building block in an institutional strategy of knowledge management.

Zusammenfassung Problem. Wie sind Produktivitätsverbesserungen im Zusammenhang mit RIS/PACS zu definieren und wie sind welche erreicht bzw. zu erreichen? Was kosten sie? Zur Problemeingrenzung werden zunächst die Aufgaben der Radiologie und Schwachstellen im Workflow analysiert. Die Frage, wie Produktivitätsverbesserungen festzustellen und zu beurteilen sind, wird diskutiert. Methoden. Das Problem wird anhand des RIS-/PACS-Projekts im Klinikum der Universität München, Standort Großhadern, untersucht. Die Ziele des Projekts werden nochmals vor Augen geführt. Der Stand der Realisierung des Projekts, das noch nicht abgeschlossen ist, wird dargestellt. Insofern stellt dies eine Zwischenbilanz dar. Ergebnisse und Diskussion. Der Stand der Beseitigung der Schwachstellen wird geschildert. Insbesondere werden alle digital erzeugten Bilder (derzeit noch ohne Mammographie) zu beinahe 100% digital archiviert. Sie sind daher auch bei Bedarf in der Radiologie über PACS und im Klinikum über die webbasierte Intranetbildverteilung abrufbar. In einigen Bereichen, z. B. Multischicht-CT (wie MSCT), ist das Befunden am Monitor überhaupt nicht mehr wegzudenken. Bisher kann noch nicht vollständig auf Hardcopies verzichtet werden, da die Verteilung der Bilder an DICOM-Viewer in teurer, beinahe Befundungsqualität für ausgewählte Anforderer noch in der Testphase ist. In der Übergangszeit werden zur Senkung der Filmkosten Bilder auf hochauflösenden Papierdrucker gedruckt, zusätzlich zur Intranetbildverteilung. Bei den Befundberichten werden aus Mangel an Planstellen im Schreibdienst ca. 40% der Befunde durch die Ärzte handgeschrieben. Die diktierten und getippten Befunde sind in der Regel nicht schnell genug im RIS und damit in der Befundverteilung des Klinikums verfügbar. Hier kann nur ein Spracherkennungssystem eine Lösung bringen, um die Befunde sofort nach dem Diktat verfügbar zu machen. Sobald dies ebenso wie die Bildverteilung an DICOM-Viewer funktioniert, werden die Befunde zusammen mit den Bildern innerhalb von Minuten bis zu maximal wenigen Stunden nach der Untersuchung im Intranet abrufbar sein. Zusammenfassung. Die bisher erreichten Ziele wurden aufgrund von nicht vorhergesehenen Problemen und “Fallstricken” mit Verzögerungen erreicht. Insgesamt ist der Arbeitsablauf in der Radiologie ruhiger und daher effizienter geworden, da weniger Nachfragen nach unfertigen Untersuchungen, Bildern und Bildkopien gestellt werden.