This research delineates a pivotal advancement in the domain of sustainable energy systems, with a focused emphasis on the integration of renewable energy sources—predominantly wind and solar power—into the hydrogen production paradigm. At the core of this scientific endeavor is the formulation and implementation of a deep-learning-based framework for short-term localized weather forecasting, specifically designed to enhance the efficiency of hydrogen production derived from renewable energy sources. The study presents a comprehensive evaluation of the efficacy of fully connected neural networks (FCNs) and convolutional neural networks (CNNs) within the realm of deep learning, aimed at refining the accuracy of renewable energy forecasts. These methodologies have demonstrated remarkable proficiency in navigating the inherent complexities and variabilities associated with renewable energy systems, thereby significantly improving the reliability and precision of predictions pertaining to energy output. The cornerstone of this investigation is the deployment of an artificial intelligence (AI)-driven weather forecasting system, which meticulously analyzes data procured from 25 distinct weather monitoring stations across Latvia. This system is specifically tailored to deliver short-term (1 h ahead) forecasts, employing a comprehensive sensor fusion approach to accurately predicting wind and solar power outputs. A major finding of this research is the achievement of a mean squared error (MSE) of 1.36 in the forecasting model, underscoring the potential of this approach in optimizing renewable energy utilization for hydrogen production. Furthermore, the paper elucidates the construction of the forecasting model, revealing that the integration of sensor fusion significantly enhances the model’s predictive capabilities by leveraging data from multiple sources to generate a more accurate and robust forecast. The entire codebase developed during this research endeavor has been made available on an open access GIT server.

Combining classical educational methods with interactive three-dimensional (3D) visualization technology has great power to support and provide students with a unique opportunity to use them in the study process, training, and/or simulation of different medical procedures in terms of a Human Anatomy course. In 2016, Rīga Stradiņš University (RSU) offered students the 3D Virtual Dissection Table “Anatomage” with possibilities of virtual dissection and digital images at the Department of Morphology. The first 3D models were printed in 2018 and a new printing course was integrated into the Human Anatomy curriculum. This study was focused on the interaction of students with digital images, 3D models, and their combinations. The incorporation and use of digital technologies offered students great tools for their creativity, increased the level of knowledge and skills, and gave them a possibility to study human body structures and to develop relationships between basic and clinical studies.

Educational institutions in several countries state that the education sector should be modernized to ensure a contemporary, individualized, and more open learning process by introducing and developing advance digital solutions and learning tools. Visualization along with 3D printing have already found their implementation in different medical fields in Pauls Stradiņš Clinical University Hospital, and Rīga Stradiņš University, where models are being used for prosthetic manufacturing, surgery planning, simulation of procedures, and student education. The study aimed to develop a detailed methodology for the creation of anatomically correct and optimized models for 3D printing from radiological data using only free and widely available software. In this study, only free and cross-platform software from widely available internet sources has been used—“Meshmixer”, “3D Slicer”, and “Meshlab”. For 3D printing, the Ultimaker 5S 3D printer along with PLA material was used. In its turn, radiological data have been obtained from the “New Mexico Decedent Image Database”. In total, 28 models have been optimized and printed. The developed methodology can be used to create new models from scratch, which can be used will find implementation in different medical and scientific fields—simulation processes, anthropology, 3D printing, bioprinting, and education.

In this technical note, we examine the capabilities of deep convolutional neural networks (DCNNs) for diagnosing osteoporosis through cone-beam computed tomography (CBCT) scans of the mandible. The evaluation was conducted using 188 patients’ mandibular CBCT images utilizing DCNN models built on the ResNet-101 framework. We adopted a segmented three-phase method to assess osteoporosis. Stage 1 focused on mandibular bone slice identification, Stage 2 pinpointed the coordinates for mandibular bone cross-sectional views, and Stage 3 computed the mandibular bone’s thickness, highlighting osteoporotic variances. The procedure, built using ResNet-101 networks, showcased efficacy in osteoporosis detection using CBCT scans: Stage 1 achieved a remarkable 98.85% training accuracy, Stage 2 minimized L1 loss to a mere 1.02 pixels, and the last stage’s bone thickness computation algorithm reported a mean squared error of 0.8377. These findings underline the significant potential of AI in osteoporosis identification and its promise for enhanced medical care. The compartmentalized method endorses a sturdier DCNN training and heightened model transparency. Moreover, the outcomes illustrate the efficacy of a modular transfer learning method for osteoporosis detection, even when relying on limited mandibular CBCT datasets. The methodology given is accompanied by the source code available on GitLab.

Objectives: The integration of machine learning and radiomics in medical imaging has significantly advanced diagnostic and prognostic capabilities in healthcare. This study focuses on developing and validating an artificial intelligence (AI) model using U-Net architectures for the accurate detection and segmentation of spinal metastases from computed tomography (CT) images, addressing both osteolytic and osteoblastic lesions. Methods: Our methodology employs multiple variations of the U-Net architecture and utilizes two distinct datasets: one consisting of 115 polytrauma patients for vertebra segmentation and another comprising 38 patients with documented spinal metastases for lesion detection. Results: The model demonstrated strong performance in vertebra segmentation, achieving Dice Similarity Coefficient (DSC) values between 0.87 and 0.96. For metastasis segmentation, the model achieved a DSC of 0.71 and an F-beta score of 0.68 for lytic lesions but struggled with sclerotic lesions, obtaining a DSC of 0.61 and an F-beta score of 0.57, reflecting challenges in detecting dense, subtle bone alterations. Despite these limitations, the model successfully identified isolated metastatic lesions beyond the spine, such as in the sternum, indicating potential for broader skeletal metastasis detection. Conclusions: The study concludes that AI-based models can augment radiologists’ capabilities by providing reliable second-opinion tools, though further refinements and diverse training data are needed for optimal performance, particularly for sclerotic lesion segmentation. The annotated CT dataset produced and shared in this research serves as a valuable resource for future advancements.

The quality of healthcare varies significantly from one country to another. This variation can be attributed to several factors, including the level of healthcare professionals’ professionalism, which is closely linked to the quality of their education. Medical and healthcare education is unique in its need for students to learn and practice various clinical skills, algorithms, and behaviours for clinical situations. However, it is challenging to ensure these educational experiences do not compromise the quality of healthcare and patient safety. A simulation-based educational (SBE) approach offers a solution to these challenges. However, despite the widespread adoption of the SBE approach in medical and healthcare education curricula; its recognition for its high value among students, educators, and healthcare professionals; and evidence showing its positive impact on reducing risks to both patients and healthcare professionals, there is still an absence of a standardized approach and guidelines for integrating simulations, which includes determining when, how, and to what ex-tent they should be implemented. Currently, there is no regulation on the need for SBE integration in medical and healthcare curricula. However, the framework of this article, based on the results of the analysis of the legal framework, which includes a set of laws, regulations, principles, and standards set by various government, administrations, and authoritative institutions, will determine the fundamental aspects of the integration of the SBE approach that justify and argue the need to (1) incorporate simulation-based education across all levels of medical and healthcare education programs and (2) adhere to certain standards when integrating the SBE approach into medical and healthcare programs. This is an area that needs to be developed with the involvement of legal, health, and education experts.