Search results

Current healthcare applications produce a complex and inaccessible set of data that often needs to be investigated simultaneously. As such the conflicting software applications and mental effort being demanded from the user result in time‐consuming analysis and diagnosis. The purpose of this paper is to provide a prototype, interactive system for management of multiple data sets, currently used for gait analysis capturing, reconstruction and diagnosis. In summary, this work is concerned with the development of interactive information‐visualisation software that assists medical practitioners in simplifying and enhancing the retrieval, visualisation and analysis of medical data with the intention of improving the overall system leading to an improved service for the user and patient experience.

The design of the proposed system aims to combine all the related existing software currently used for gait analysis and diagnosis under one, user‐friendly package. The latter will have the capacity to offer also real‐time, three dimensional (3D) representations of all the derived data (CT, MRI, motion capture) in an interactive virtual reality (VR) environment.

It is intended that the proposed prototype solutions will enhance interactive systems for management of multiple data sets, currently used for gait analysis capturing, reconstruction and diagnosis. The derived data encapsulate a plethora of multimedia information aiming to enhance medical visualisation.

The proposed system offers simulation capacity and a VR visualisation experience, which enhances the gait analysis diagnostic process. The 3D data can be manipulated in real‐time through a novel human‐computer interface which uses multimodal interaction through the use of graphical user interfaces and gesture recognition. The system aims towards a cost‐effective, clearly presented and timely accessible system that follows a threefold approach; It entails managing the extensive amount of the daily produced medical data, combining the scattered information related to one patient in one interface with a filtering criteria to the required information, and visualising in 3D the data from different sources, in order to improve 3D mental mapping, increase productivity and consequently ameliorate quality of service and management.

To demonstrate the applicability of machine‐learning tools in quality management.

Two popular machine‐learning approaches, decision tree induction and association rules mining, were applied on a set of 960 production case records. The accuracy of results was investigated using randomized experimentation and comprehensibility of rules was assessed by experts in the field.

Both machine‐learning approaches exhibited very good accuracy of results (average error was about 9 percent); however, association rules mining outperformed decision tree induction in comprehensibility and correctness of learned rules.

The proposed methodology is limited with respect to case representation. Production cases are described via attribute‐value sets and the relation between attribute values cannot be determined by the selected machine‐learning methods.

Results demonstrate that machine‐learning techniques may be effectively used to enhance quality management procedures and modeling of cause‐effect relationships, associated with faulty products.

The article proposes a general methodology on how to use machine‐learning techniques to support quality management. The application of the technique in ISDN modem manufacturing demonstrates the effectiveness of the proposed general methodology.