Alexander Brenner

With increasing digitalization in healthcare, there is growing potential for the use of Mixed Reality (MR) in medicine. In response to this, we developed a course to provide students with hands-on experience in MR and familiarize them with the technology. Utilizing the HoloLens 2, we designed an application enabling multiple users to interact with virtual objects overlaid on the real world and shared across devices. We used 3D heart anatomy models to let students discuss cardiovascular diseases together. We conducted a preliminary evaluation of our prototype, involving ten participants. The first test indicated a positive reception of the course, with students expressing keen interest in MR. With this work we share our experience to contribute to the field of MR applications.

We addressed the limitations of subjective clinical tremor assessment by comparing routine neurological evaluation with a Tremor Occurrence Score derived from smartwatch sensor data, among 142 participants with Parkinson disease and 77 healthy controls. Our findings highlight the potential of smartwatches for automated tremor detection as a valuable addition to conventional assessments, applicable in both clinical and home settings.

The utilisation of smart devices, such as smartwatches and smartphones, in the field of movement disorders research has gained significant attention. However, the absence of a comprehensive dataset with movement data and clinical annotations, encompassing a wide range of movement disorders including Parkinson’s disease (PD) and its differential diagnoses (DD), presents a significant gap. The availability of such a dataset is crucial for the development of reliable machine learning (ML) models on smart devices, enabling the detection of diseases and monitoring of treatment efficacy in a home-based setting. We conducted a three-year cross-sectional study at a large tertiary care hospital. A multi-modal smartphone app integrated electronic questionnaires and smartwatch measures during an interactive assessment designed by neurologists to provoke subtle changes in movement pathologies. We captured over 5000 clinical assessment steps from 504 participants, including PD, DD, and healthy controls (HC). After age-matching, an integrative ML approach combining classical signal processing and advanced deep learning techniques was implemented and cross-validated. The models achieved an average balanced accuracy of 91.16% in the classification PD vs. HC, while PD vs. DD scored 72.42%. The numbers suggest promising performance while distinguishing similar disorders remains challenging. The extensive annotations, including details on demographics, medical history, symptoms, and movement steps, provide a comprehensive database to ML techniques and encourage further investigations into phenotypical biomarkers related to movement disorders.

UNSTRUCTURED We addressed the limitations of subjective clinical tremor assessment by comparing routine neurological evaluation with a Tremor Occurrence Score derived from smartwatch sensor data, among 142 participants with Parkinson disease and 77 healthy controls. Our findings highlight the potential of smartwatches for automated tremor detection as a valuable addition to conventional assessments, applicable in both clinical and home settings.

A growing number of studies have been researching biomarkers of Parkinson’s disease (PD) using mobile technology. Many have shown high accuracy in PD classification using machine learning (ML) and voice records from the mPower study, a large database of PD patients and healthy controls. Since the dataset has unbalanced class, gender and age distribution, it is important to consider appropriate sampling when assessing classification scores. We analyse biases, such as identity confounding and implicit learning of non-disease-specific characteristics and present a sampling strategy to highlight and prevent these problems.

Automation solutions for manufacturing processes have no mass market. Engineering costs, therefore, are often far beyond the actual hardware costs. Special hardware has to be designed to meet computing power and I/O requirements. Traditional solutions estimate these requirements a priori leading to expensive oversized or unusable undersized systems. A design process as such often yields inflexible monolithic and not scaleable hardware. This paper introduces an object oriented hardware design paradigm that can greatly benefit from modularity, scaleability, reusability and shorter time to the market. The object oriented concept drastically reduces engineering costs as basic modular "objects" are used in place of static complex monoliths. It is shown that cost and time efficiency can already be highly influenced at the level of board hardware design. The paper gives also an example implementation of an object oriented hardware for signal processing purposes in industrial applications, e.g. vision systems. The presented hardware object is designed to be part of a whole "class library" comprising an industrial PC and I/O module series. The hardware system can be easily extended by adding new objects and offers natural flexibility in connecting the parts together. The paper clearly figures out how to save time and money using interconnected hardware objects rather than once used specialised circuitry.

This paper discusses a colour camera based vision system for temperature measurement. Usually, visual imaging and infrared image sensing are treated as seperate disciplines. We will show, that a well selected colour camera device might be a cheaper, more robust and more sophisticated solution for optical temperature measurement in several cases. Herein, only implementation fragments and important restrictions for the sensing element will be discussed. Our aim is to draw the readers attention to the use of visual image sensors for measuring thermal radiation and temperature. With AVL-List, our partner of industry, we successfully used the proposed sensor to perform temperature measurement for flames inside the combustion chamber of diesel engines; the AVL Engine VideoScope 513D allows a triggered acquisition of transient temperature phenomena at an integration time as low as 64µs. The achieved results for temperature measurement will be shown for this sample application.

Machine learning algorithms become increasingly prevalent in the field of medicine, as they offer the ability to recognize patterns in complex medical data. Especially in this sensitive area, the active usage of a mostly black box is a controversial topic. We aim to highlight how an aggregated and systematic feature analysis of such models can be beneficial in the medical context. For this reason, we introduce a grouped version of the permutation importance analysis for evaluating the influence of entire feature subsets in a machine learning model. In this way, expert-defined subgroups can be evaluated in the decision-making process. Based on these results, new hypotheses can be formulated and examined.