Phenotypes defined by the "Vienna Classification" in 100 Hungarian patients with Crohn's disease

BACKGROUND

standardisation of subgroup in Crohńs disease (CD) could help to design, and to compare studies performed in different populations. However, due to the lack of a uniformly used classification, data is scarce and difficult to interpret on the frequency of specific subtypes and disease behaviour in different ethnicities.

METHODS

analysis was performed using the Vienna classification on an unselected Hungarian population of 100 CD patients diagnosed according to Lennard- Jones criteria at least three years before the data was collected.

RESULTS

disease behaviour and location was strongly associated (p= 0.008); ileocolonic location presented most commonly with penetrating disease (49%), while colonic location with non-stricturing, non-penetrating disease behaviour (48%). Operations were more frequent in patienys with penetrating disease (p<0,0001). Among patients with extraintestinal manifestations penetrating disease was more common (49 vs 30%) and structuring less frequent (16 vs 38%) than in the group of patients who did not have extraintestinal symptoms (p=0.001). In patients whose disease involved the colon, among those with structuring disease, than men (OR=4.18 CI=1. 07-16.32). Morever, less operation were performed in women, than in men (OR=2.3 CI=1.02-5.19). Smoking had influence on the disease location and severity, while not on the disease behaviour.

CONCLUSIONS

these results point to different disease characteristics between men and women. They support the concept that distinct phenotypes have different complications and prognosis. Therefore, the Vienna classification provides a simple tool to standardise.

Development of a speech-based dialogue system for report dictation and machine control in the endoscopic laboratory

BACKGROUND AND STUDY AIMS

Reporting and machine control based on speech technology can enhance work efficiency in the gastrointestinal endoscopy laboratory.

MATERIALS AND METHODS

The status and activation of endoscopy laboratory equipment were described as a multivariate parameter and function system. Speech recognition, text evaluation and action definition engines were installed. Special programs were developed for the grammatical analysis of command sentences, and a rule-based expert system for the definition of machine answers. A speech backup engine provides feedback to the user. Techniques were applied based on the "Hidden Markov" model of discrete word, user-independent speech recognition and on phoneme-based speech synthesis. Speech samples were collected from three male low-tone investigators.

RESULTS

The dictation module and machine control modules were incorporated in a personal computer (PC) simulation program. Altogether 100 unidentified patient records were analyzed. The sentences were grouped according to keywords, which indicate the main topics of a gastrointestinal endoscopy report. They were: "endoscope", "esophagus", "cardia", "fundus", "corpus", "antrum", "pylorus", "bulbus", and "postbulbar section", in addition to the major pathological findings: "erosion", "ulceration", and "malignancy". "Biopsy" and "diagnosis" were also included. We implemented wireless speech communication control commands for equipment including an endoscopy unit, video, monitor, printer, and PC. The recognition rate was 95%.

CONCLUSIONS

Speech technology may soon become an integrated part of our daily routine in the endoscopy laboratory. A central speech and laboratory computer could be the most efficient alternative to having separate speech recognition units in all items of equipment.