An integrated knowledge-based system to guide the physician during structured reporting.

A routinely used system for report generation, based on direct physician data entry, has been combined with a knowledge-based module. The knowledge-based system is operating in the background, and guides the user by dynamically suggesting diagnoses and generating hints regarding the actual and possible further diagnostic procedures. Hybrid technology with neural networks and rules is used. A laboratory evaluation has shown good agreement between diagnoses suggested by the system and confirmed diagnoses, with a kappa coefficient of 0.85 and an area under the ROC curve of 0.92. In a survey following a 14-day test period, physicians stated that the system was both sensible and helpful. The current application domain is ultrasound reporting.

Gallbladder sludge: spontaneous course and incidence of complications in patients without stones.

Although the ultrasonic detection of gallbladder sludge is relatively frequent, its clinical importance remains unclear, partly because of the paucity of reliable investigations regarding its natural course in patients without stones. In a retrospective study we investigated the course and clinical significance of gallbladder sludge in patients without stones or other identified gallbladder abnormalities. The diagnosis of gallbladder sludge was made by ultrasound scan in 286 (1.7%) of 17,021 patients. The mean follow-up period for these patients was 20.3 +/- 11.5 mo. Of this group 56 patients were without both stones and sludge at the initial examination, and gallbladder sludge developed after a mean observation period of 11.2 +/- 10.6 mo. Within 2.0 +/- 3.5 mo after sludge detection, 40 (71.4%) patients were free of sludge and showed normal gallbladder findings. Gallbladder stones without sludge persistence developed in five patients (8.9%) within 2.5 +/- 0.6 mo after diagnosis of sludge, and gallstones with persistence of sludge developed in two other patients (3.6%) after 6.1 and 30.7 mo, respectively. In no cases did the stones become clinically symptomatic in the course of the follow-up period. Acute acalculous cholecystitis developed in four patients (7.1%) from 6.5 to 37.5 mo after the first examination. In five patients, sludge persisted after a mean 22.3 +/- 13.5 mo of follow-up. Although our data show that gallbladder sludge disappeared spontaneously within a relatively short time in 71.4% of patients, gallbladder sludge must be considered an important pathologic entity because gallbladder stones or complications such as acute cholecystitis occurred in 19.6% of patients.(ABSTRACT TRUNCATED AT 250 WORDS)

[Structured documentation of findings and user acceptance--results of a study of abdominal ultrasound]. / Strukturierte Befunderhebung und Benutzerakzaptanz--Ergebnisse einer Studie für die abdominale Sonographie.

Structured reporting of medical findings is known to have positive effects on data quality, whereas user acceptance tends to be low because of time requirements. This paper presents the results of a survey among 19 physicians who worked for 14 months with a computer system using structured data input for abdominal ultrasonography. During this time, they prepared 8.827 reports. The two most important results are that it is feasible to realize well accepted documentation systems with high data quality by using modern computer technology, and that graphic user interfaces tend to increase user acceptance. For comparable systems, evaluation studies are suggested.

Structured data collection and knowledge-based user guidance for abdominal ultrasound reporting.

This paper describes a system for structured data collection and report generation in abdominal ultrasonography. The system is based on a controlled vocabulary and hierarchies of concepts; it uses a graphical user interface. More than 17,000 reports have been generated by 43 physicians using this system, which is integrated into a departmental information system. Evaluations have shown that it is a well accepted tool for the fast generation of reports of comparatively high quality. The functionality is enhanced by two additional components: a hybrid knowledge-based module for "intelligent" user guidance and an interactive tutoring system to illustrate the terminology.

The quality of gastroenterological reports based on free text dictation: an evaluation in endoscopy and ultrasonography.

The majority of physicians consider the use of free dictation for medical reports to be essential in many domains. One of the main criticisms of structured data entry is the possible lack of flexibility and completeness. Electronic documentation systems exist for endoscopy and ultrasonography examinations which are based on structured input as well as on free dictation. Endoscopy and ultrasonography reports based on free dictation were evaluated for omissive errors. The data evaluated was drawn from a database of 18,239 gastroscopy and 3,340 colonoscopy reports dictated by 28 physicians over 74 months, and 18,834 ultrasonography reports dictated by 37 physicians over 42 months. The error rates varied from 0% to 41.8% depending upon the particular feature and the particular examination, but were usually below 15%. The results were independent of the experience of the examiner. This study provides baseline measurements of omissive error rates for selected findings in gastrointestinal endoscopy and abdominal ultrasonography which can be used as standards for the development and evaluation of systems for collection of clinical data.