Machine learning-based modeling of physical systems has attracted significant interest in recent years. Based solely on the underlying physical equations and initial and boundary conditions, these new approaches allow to approximate, for example, the complex flow of blood in the case of fluid dynamics. Physics-informed neural networks offer certain advantages compared to conventional computational fluid dynamics methods as they avoid the need for discretized meshes and allow to readily solve inverse problems and integrate additional data into the algorithms. Today, the majority of published reports on learning-based flow modeling relies on fully-connected neural networks. However, many different network architectures are introduced into deep learning each year, each with specific benefits for certain applications. In this paper, we present the first comprehensive comparison of various state-of-the-art networks and evaluate their performance in terms of computational cost and accuracy relative to numerical references. We found that while fully-connected networks offer an attractive balance between training time and accuracy, more elaborate architectures (e.g., Deep Galerkin Method) generated superior results. Moreover, we observed high accuracy in simple cylindrical geometries, but slightly poorer estimates in complex aneurysms. This paper provides quantitative guidance for practitioners interested in complex flow modeling using physics-based deep learning.

Electronic health records (EHRs) have been successfully used in data science and machine learning projects. However, most of these data are collected for clinical use rather than for retrospective analysis. This means that researchers typically face many different issues when attempting to access and prepare the data for secondary use. We aimed to investigate how raw EHRs can be accessed and prepared in retrospective data science projects in a disciplined, effective, and efficient way. We report our experience and findings from a large-scale data science project analyzing routinely acquired retrospective data from the Kepler University Hospital in Linz, Austria. The project involved data collection from more than 150,000 patients over a period of 10 years. It included diverse data modalities, such as static demographic data, irregularly acquired laboratory test results, regularly sampled vital signs, and high-frequency physiological waveform signals. Raw medical data can be corrupted in many unexpected ways that demand thorough manual inspection and highly individualized data cleaning solutions. We present a general data preparation workflow, which was shaped in the course of our project and consists of the following 7 steps: obtain a rough overview of the available EHR data, define clinically meaningful labels for supervised learning, extract relevant data from the hospital’s data warehouses, match data extracted from different sources, deidentify them, detect errors and inconsistencies therein through a careful exploratory analysis, and implement a suitable data processing pipeline in actual code. Only few of the data preparation issues encountered in our project were addressed by generic medical data preprocessing tools that have been proposed recently. Instead, highly individualized solutions for the specific data used in one’s own research seem inevitable. We believe that the proposed workflow can serve as a guidance for practitioners, helping them to identify and address potential problems early and avoid some common pitfalls.

Advanced Driver Assistance Systems rely on automated traffic sign recognition. Today, Deep Learning methods outperform other approaches in terms of accuracy and processing time; however, they require vast and well-curated data sets for training. In this paper, we present the Austrian Highway Traffic Sign Data Set (ATSD), a comprehensive annotated data set of images of almost all traffic signs on Austrian highways in 2014, and corresponding images of full traffic scenes they are contained in. Altogether, the data set consists of almost 7500 scene images with more than 28,000 detailed annotations of more than 100 distinct traffic sign classes. It covers diverse environments, ranging from urban to rural and mountainous areas, and includes many images recorded in tunnels. We further evaluate state-of-the-art traffic sign detectors and classifiers on ATSD to establish baselines for future experiments. The data set and our baseline models are freely available online.

Background: Hemodynamics during the growth process of cerebral aneurysms are incompletely understood. We developed a novel fluid–structure interaction analysis method for the identification of relevant scenarios of aneurysm onset. Method: This method integrates both fluid dynamics and structural mechanics, as well as their mutual interaction, for a comprehensive analysis. Patients with a single unruptured cerebral aneurysm were included. Results: Overall, three scenarios were identified. In scenario A, wall shear stress (WSS) was low, and the oscillatory shear index (OSI) was high in large areas within the region of aneurysm onset (RAO). In scenario B, the quantities indicated a reversed behavior, where WSS was high and OSI was low. In the last scenario C, a behavior in-between was found, with scenarios A and B coexisting simultaneously in the RAO. Structural mechanics demonstrated a similar but independent trend. Further, we analyzed the change in hemodynamics between the onset and a fully developed aneurysm. While scenarios A and C remained unchanged during aneurysm growth, 47% of aneurysms in scenario B changed into scenario A and 20% into scenario C. Conclusions: In conclusion, these findings suggest that WSS and the OSI are reciprocally regulated, and both low and high WSS/OSI conditions can lead to aneurysm onset.