Band 18, Heft 1

Objectives Nowadays universities face ever-increasing demands on quality of education, which is crucial from perspective of future graduates. In face of the need of constant quality improvements of medical curricula, it is important to seek strategies for their efficient management. The general trend is to develop electronic support tools to streamline the curricular design, analysis and harmonization. Methods Based on the requirements we have identified by the needs analysis among curriculum designers, teachers and managers at five universities involved in the Building Curriculum Infrastructure in Medical Education (BCIME) project, and evidence published in literature on curriculum development, we have developed methodological guidelines on curriculum innovations and a software-based tools that help manage, map and analyse curricula in the medical and healthcare study fields. Results In this paper, we share our experiences with building and implementation of EDUportfolio, an online platform developed within our consortium and intended to facilitate harmonisation and optimisation of medical outcome-based curricula. Its functionalities and outputs were verified by pilot mapping of Anatomy curricula as taught at partner universities in five European countries. Conclusions The visualisation and the analysis of described curriculum data using natural language processing techniques revealed both the hidden relations between curriculum building blocks and a set of overlaps and gaps in curricula. In addition, we demonstrate both the usability of the platform in the context of the involved academic environments and the capability to map and compare curricula across different institutions and different countries.

Objectives The paper presents preliminary results on the assessment of algorithms used in image processing of the grain damage degree. The purpose of the work is developing a tool allowing to analyse sample cross-sections of rye germs. Methods The analysis of the grain cross-sections was carried out on the basis of a series their photos taken at equal time intervals at a set depth. The cross-sections will be used to create additional virtual cross-sections allowing to analyse the whole sample volume. The ultimate plan is to generate two cross-sections perpendicular to each other. Based on volumetric data read from the sample section, a three-dimensional model of an object will be generated. Results The analysis of model surface will allowed us to detect possible grain damage. The developed method of preparing the research material and the proprietary application allowed for the identification of internal defects in the biological material (cereal grains). Conclusions The presented methodology may be used in the agri-food industry in the future. However, much research remains to be done. These works should primarily aim at significantly reducing the time-consuming nature of individual stages, as well as improving the quality of the reconstructed image.

Objectives In this paper the research on developing convolutional spiking neural networks for traffic signs classification is presented. Unlike classical ones, spiking networks reflect the behaviour of biological neurons much more closely, by taking into account the time dimension and event-based operation. Spiking networks running on dedicated neuromorphic platforms, such as Intel Loihi, can operate with greater energy efficiency, hence they are an interesting approach for embedded solutions. Methods For convolutional spiking neural networks' design and simulation, Nengo and NengoDL libraries for Python language were used. Numerous experiments using the Leaky-Integrate-and-Fire (LIF) neuron model were conducted. The training results, with different augmentation methods and number of time steps for input image presentation were compared. Results Finally, an accuracy of up to 97% on the test set was achieved, depending on the number of time steps the input was presented to the SNN. Conclusions The proposed experiments show that using simple convolutional spiking neural network, one can achieve accuracy comparable to the classical network with the same architecture and trained on the same dataset. At the same time, running on dedicated neuromorphic hardware, such solution should be characterized by low latency and low energy consumption.

Objectives Due to the diversity, volume, and distribution of ingested data, the majority of current healthcare entities operate independently, increasing the problem of data processing and interchange. The goal of this research is to design, implement, and evaluate an electronic health record (EHR) interoperability solution – prototype – among healthcare organizations, whether these organizations do not have systems that are prepared for data sharing, or organizations that have such systems. Methods We established an EHR interoperability prototype model named interoperability smart lane for electronic health record (islEHR), which comprises of three modules: 1) a data fetching APIs for external sharing of patients’ information from participant hospitals; 2) a data integration service, which is the heart of the islEHR that is responsible for extracting, standardizing, and normalizing EHRs data leveraging the fast healthcare interoperability resources (FHIR) and artificial intelligence techniques; 3) a RESTful API that represents the gateway sits between clients and the data integration services. Results The prototype of the islEHR was evaluated on a set of unstructured discharge reports. The performance achieved a total time of execution ranging from 0.04 to 84.49 s. While the accuracy reached an F-Score ranging from 1.0 to 0.89. Conclusions According to the results achieved, the islEHR prototype can be implemented among different heterogeneous systems regardless of their ability to share data. The prototype was built based on international standards and machine learning techniques that are adopted worldwide. Performance and correctness results showed that islEHR outperforms existing models in its diversity as well as correctness and performance.