Karlsruhe, University, Diss., 2008.

Univ. of Oxford, Diss.--Oxford, 2000. / Literaturverz. S. [175] - 181.

Zugl.: Stuttgart, Univ., Diss., 2008

Stuttgart, Univ., Fakultät Informatik, Diplomarb., 1998.

Zugl.: Ulm, Universiẗat, Diss., 2003.

University, Diss., 2000--Dortmund.

University, Diss., 2002--Dortmund.

Techn. University, Diss., 2004--Berlin.

Diese retrospektive Studie untersuchte Patientenakten des elektronischen Karteikartensystems einer privaten Zahnarztpraxis von Patienten, welche zur Kontrolluntersuchung oder wegen Schmerzen vorstellig waren. Ziel der Studie war das Entwickeln von Methoden zur Vorhersage der Behandlungszeit für zukünftige Termine anhand verschiedener Patienteninformationen. Mittels statistischer deskriptiver Auswertung wurden die erfassten Daten untersucht und Korrelationen in Hinblick auf die Behandlungsdauer zwischen den verschiedenen Attributen hergestellt. Es wurden verschiedene Methoden zur Vorherbestimmung der Behandlungsdauer aufgestellt und auf ihr Optimierungspotential getestet. Die Methode mit dem höchsten Optimierungswert war ein Ansatz maschinellen Lernens. Der entworfene Algorithmus berechnete Behandlungszeiten der Testgruppe anhand eines Neuronalen Netzes, welches durch Trainieren mit den Daten der Untersuchungsgruppe erstellt wurde. / his retrospective study examined patient records from the electronic medical record system of a private dental practice for patients who presented for routine check-ups or due to pain. The aim of the study was to develop methods for predicting treatment time for future appointments based on various patient information. Through statistical descriptive analysis, the collected data were examined, and correlations were established between different attributes in terms of treatment duration. Various methods for predicting treatment time were proposed and tested for their optimization potential. The method with the highest optimization value was a machine learning approach. The designed algorithm calculated treatment times for the test group using a neural network created by training with the data from the study group.

In this paper we introduce a mixed approach for the semi-supervised data problem. Our approach consists of an ensemble unsupervised learning part where the labeled and unlabeled points are segmented into clusters. Continuing, we take advantage of the a priori information of the labeled points to assign classes to clusters and proceed to predicting with the ensemble method new incoming ones. Thus, we can finally conclude classifying new data points according to the segmentation of the whole set and the association of its clusters to the classes. / Series: Report Series SFB "Adaptive Information Systems and Modelling in Economics and Management Science"