Optimierung der Bereitstellung von exakten Morbiditäts- und Mortalitätsdaten für einen Klinikkonzern. Eine randomisierte kontrollierte Studie zur Kostenreduktion im Datenformationsprozess.

Abstract

This master's thesis addresses the optimization of clinical quality management by employing machine learning (ML) methods and predefined contextual information to collect complications that are often recorded unstructured as free text in patient records. The focus is on the hypotheses whether the collection time per case and the time to identify a complication (time-to-complication) can be reduced using ML models and contextual information. Given the increasing challenges such as a shortage of skilled workers, demographic changes, and rising healthcare costs, more efficient data collection is crucial for improving patient safety and care. The thesis is divided into several main chapters. First, the basics of quality management and clinical quality management are explained. This is followed by a presentation of quality management in practice, particularly information logistics in healthcare. The randomized, controlled study, conducted from August to September 2023, included the collection of 391 cases. The methodology involved the implementation of ML models for the retrospective identification of complication cases, including assessments of the suspected type of complication. Additionally, context information was provided, which included structured data on the patients, such as primary and secondary diagnoses during the main stay. The results show that the intervention using ML models and contextual information leads to a significant reduction in collection time and a faster identification of a complication. The average collection time in the intervention group was 14.22 minutes compared to 16.53 minutes in the control group, which is a significant difference (p-value

Date of Award	2024
Original language	German (Austria)
Supervisor	Gerhard Halmerbauer (Supervisor)