Aim: To investigate out-of-hospital cardiac arrest (OHCA) trend, provided advanced life support (ALS) measures, automated external defibrillator (AEDs) utilization and by-standers involvement in cardiopulmonary resuscitation (CPR) during OHCA incidents. Methods: This cross-sectional study encompassed data pertaining to all OHCA incidents attended to by the Emergency Medical Service of Canton Sarajevo, Bosnia and Herzegovina, covering the period from January 2018 to December 2022. Results: Among a total of 1131 OHCA events, 236 (20.8 %) patients achieved return of spontaneous circulation (ROSC); there were 175 (74.1%) males and 61 (25.9%) females. The OHCA incidence was 54/100.000 inhabitants per year. After a 30-day period post-ROSC, 146 (61.9%) patients fully recovered, while 90 (38.1%) did not survive during this timeframe. Younger age (p<0.05), initial rhythm of ventricular fibrillation (VF) or pulseless ventricular tachycardia (VT) (p<0.05) and faster emergency medical team (EMT) response time (p<0.05) were significantly associated with obtaining ROSC. Only 38 (3.3%) OHCA events were assisted by bystanders, who were mostly medical professionals, 25 (65.7%), followed by close family members, 13 (34.3%). There was no report of AED usage. Conclusion: This follow-up study showed less ROSC achievement, similar bystanders’ involvement, similar factors associated with achieving ROSC (age, EMT response time) and a decline in OHCA events (especially in year 2021 and 2022) comparing to our previous study (2015-2019). There was an extremely low rate of bystander engagement and no AEDs usage. Governments and health organizations must swiftly improve public awareness, promote better practice (basic life support), and actively encourage bystander participation.

Introduction: Neovascular glaucoma (NVG) is a severe type characterized by forming new blood vessels on the iris and the anterior chamber angle, often resulting from ischemic retinal diseases. Pars plana vitrectomy (PPV) is a standard surgical procedure for treating various retinal and vitreous conditions. Understanding the risk factors associated with NVG development following PPV is crucial for improving patient outcomes. Objective: To identify and evaluate demographic, clinical, and surgical risk factors associated with developing NVG following PPV. Patients and methods: A prospective cohort study was conducted over two years, involving 60 type 2 diabetes mellitus (T2DM) patients (31 males and 29 females; mean age 60.48±9.63 years) who underwent PPV at the Eye Clinic and Department of Clinical Immunology, University Clinical Center Sarajevo, Sarajevo, Bosnia and Herzegovina. Patients were thoroughly informed about the study, and written informed consent was obtained. Comprehensive data collection included demographic information, medical history, preoperative and postoperative eye examinations, and intraoperative details. Statistical analyses were performed using IBM SPSS Statistics for Windows, Version 21 (Released 2012; IBM Corp., Armonk, New York, United States). Results: Within 12 months postoperatively, 17 patients (28.3%) developed NVG. Significant preoperative risk factors for NVG included prolonged duration of T2DM (p=0.037), elevated preoperative intraocular pressure (IOP) (p=0.024), and higher levels of vascular endothelial growth factor (VEGF) (p=0.011). Intraoperative factors, such as sharp dissection (p=0.000) and operative complications (p=0.004), were also significantly associated with NVG development. Multivariate logistic regression analysis identified prolonged T2DM duration (OR 1.132, p=0.023), increased preoperative IOP (OR 1.192, p=0.029), elevated VEGF levels (OR 1.002, p=0.016), and intraoperative sharp dissection (OR 0.114, p=0.006) as independent risk factors. Conclusions: Multiple preoperative and intraoperative factors influence the development of NVG post-PPV. Prolonged T2DM duration, elevated preoperative IOP, high VEGF levels, and specific intraoperative techniques significantly increase the risk of NVG. These findings underscore the importance of careful preoperative assessment and tailored intraoperative strategies to mitigate NVG risk in PPV patients.

Chylothorax represents the accumulation of chyle in the pleural cavity due to leakage from the thoracic duct or its tributaries. Intraoperative intrathoracic lymphatic injury is a common cause, but it can also occur on its own. Management of chylothorax involves both medical therapy and, in some cases, surgery for postoperative patients and those who haven't responded to medical therapy. We describe a case of a one-month-old female infant with right-sided chylothorax following primary esophageal atresia repair, who underwent successful thoracic duct ligation by open thoracotomy after unsuccessful medical treatment. Minimally invasive radiology is now the standard treatment for traumatic chylothorax because it is safe and effective. However, surgical ligation of the thoracic duct remains an effective option for treating high-output or recurring chylothorax in countries with limited resources.

Abstract This paper introduces a novel method that leverages artificial neural networks to estimate magnetic flux density in the proximity of overhead transmission lines. The proposed method utilizes an artificial neural network to estimate the parameters of a mathematical model that describes the magnetic flux density distribution along the lateral profile for various configurations of overhead transmission lines. The training target data is acquired using the particle swarm optimization algorithm. A performance comparison between the proposed method and the Biot-Savart law-based method is conducted using an extensive test dataset. The resulting coefficient of determination and mean square error values demonstrate the successful application of the proposed method for a range of different spatial arrangements of phase conductors. Furthermore, the performance of the proposed method is thoroughly assessed on multiple test cases. The practical relevance of the proposed method is highlighted by contrasting its results with the field measurements obtained in the proximity of a 400 kV overhead transmission line.

Background: Lactate dehydrogenase (LDH) isoenzyme assay was used widely in the past to diagnose myocardial infarction (MI). Recent studies show that lactate dehydrogenase seems to be a promising biomarker of adverse left ventricular remodeling. Objectives: Higher levels of these biomarkers were associated with lower odds for favorable reverse remodeling in patients with MI. Methods: The study was performed on patients with the first occurrence of acute myocardial infarction (ST-elevation myocardial infarction (STEMI) or non-ST-elevation myocardial infarction (NSTEMI)), aged 34 to 80 years who underwent catheterization at the admission or during their hospital stay depending on indications. In this study, we compared peak levels of lactate dehydrogenase (LDH) and left ventricular ejection fraction (LVEF). Peak values of LDH were used from the second to the fourth day of hospitalization. Echocardiography has been done in the first 72 hours, which represents an early phase of cardiac remodeling. The ejection fraction was evaluated using the Simpson method. Results: Spearman's rank test showed a negative, statistically significant correlation between LDH and ejection fraction ρ(80)=−0.543, p<0.001. Weighted least squares regression model included LDH concentration, age, and type of myocardial infarction (STEMI/NSTEMI), and the slope coefficient for the LDH level was −0.010 (95% confidence interval (CI): −0.013 to −0.006). With each unit of LDH increase, there was a decrease of 0.01% in left ventricular ejection fraction when age and type of myocardial infarction were held constant. Conclusion: The increased LDH level could be a new predictor for early myocardial remodeling after the first occurrence of myocardial infarction independent of age and type of myocardial infarction.

The deployment of diverse data-generating technologies in livestock farming holds the promise of early disease detection and improved animal well-being. In this paper, we combine routinely collected dairy farm and herd data with weather and high frequency sensor data from 6 farms to predict new lameness events in various future periods, spanning from the following day to 3 weeks. A Random Forest classifier, using input features selected by the Boruta Algorithm, was used for the prediction task; effects of individual features were further assessed using partial dependence plots. We achieve precision scores of up to 93% when predicting lameness for the next 3 weeks and when using information from the last 3 weeks, combined with a balanced accuracy of 79%. Removing sensor data results have tendency to reduce the precision for predictions, especially when using information from the last one,2 or 3 weeks. Moving to a larger data set (without sensor data) of 44 farms keeps the similar balanced accuracy but reduces precision by more than 30%, revealing a substantial a trade-off in model quality between false positives (false lameness alerts) and false negatives (missed lameness events). Sensor data holds promise to further improve the precision of these models, but can be partially compensated by high resolution data from other systems, such as automated milking systems.

Although deep learning (DL) algorithms have been proved to be effective in diverse research domains, their application in developing models for tabular data remains limited. Models trained on tabular data demonstrate higher efficacy using traditional machine learning models than DL models, which are largely attributed to the size and structure of tabular datasets and the specific application contexts in which they are utilized. Thus, the primary objective of this paper is to propose a method to use the supremacy of Stacked Bidirectional LSTM (Long Short-Term Memory) deep learning algorithms in pattern discovery incorporating tabular data with customized 3D tensor modeling in feeding neural networks. Our findings are empirically validated using six diverse, publicly available datasets each varying in size and learning objectives. This paper proves that the proposed model based on time-sequence DL algorithms, which were generally described as inadequate when dealing with tabular data, yields satisfactory results and competes effectively with other algorithms specifically designed for tabular data. An additional benefit of this approach is its ability to preserve simplicity while ensuring fast model training also with large datasets. Even with extremely small datasets, models can be applied to achieve exceptional predictive results and fully utilize their capacity.

The diagnosis of extensive pulmonary tuberculosis, especially in young people, should take into account the possibility of an associated systemic autoimmune disease. Infections remain an important cause of morbidity and mortalityin systemic lupus erythematosus. This case illustrates the importance of recognizing the association of systemic autoimmune diseases and infections and the need for a multidisciplinary approach.

Aim: During the pandemic of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), many countries reported a significant decrease in the prevalence of influenza virus cases. The study aimed to characterize the flu seasons from 2018 to 2023 in Sarajevo Canton, Bosnia and Herzegovina (B&amp;H), and to assess the possible impact of the SARS-CoV-2 pandemic on the influenza A and B virus circulation.&nbsp; Methods: The CDC Human Influenza Virus Real-Time RT-PCR Diagnostic Panels were used for the detection of influenza virus A and B, and subtyping of influenza virus A (H1pdm09 virus and H3). The data for this regis-try-based retrospective study were collected at the Clinical Centre of the University of Sarajevo, Unit for Clinical Microbiology (the laboratory that acts as a referral for the detection and characterization of influenza virus and SARS-CoV-2 in Federation B&amp;H). Results: In the 2018/2019 and 2019/2020, an equal percentage of positive cases was recorded (148/410; 36%, and 182/504; 36%, respectively). The absence of the influenza virus was observed in 2020/2021. During 2021/2022, influenza virus was detected among 19/104 (18%) patients and slightly increased in 2022/2023 (45/269; 17%). The switch of the influenza B virus lineage was observed. Conclusion: The SARS-CoV-2 virus had an impact on the prevalence of influenza virus infection among the population of the Sarajevo Canton, B&amp;H. Since the interactions between these two viruses are not entirely clear, awareness of a possible threat to public health is crucial.

AIM To evaluate the clinical impact of corticosteroids (CS) overuse in inflammatory bowel disease (IBD) patients. Excessive use of CS could delay more efficacious treatment and may indicate poor quality of care. METHOD This is a two-phase study that used Steroid Assessment Tool (SAT) to measure corticosteroid exposure in IBD patients. In the first phase, data from 211 consecutive ambulatory patients with IBD (91 with ulcerative colitis, 115 with Crohn's disease, and five with unclassified inflammatory bowel disease) were analysed by SAT. In the second phase, one year after data entry, clinical outcome of patients with corticosteroids overuse was analysed. RESULTS Of the 211 IBD patients, 132 (62%) were not on corticosteroids, 45 (22%) were corticosteroid-dependent, and 34 (16%) used corticosteroids appropriately, according to the European Crohn's and Colitis Organization guidelines. In the group of patients with ulcerative colitis, 57 (63%) were not on corticosteroids, 18 (20%) were corticosteroid-dependent, and 16 (16%) used corticosteroids appropriately; in the group of patients with Crohn's disease 70 (61%), 27 (23%) and 18 (16%), respectively. Overall, 24 (out of 45; 53%) patients with IBD could avoid the overuse of corticosteroids if they had a timely change of the treatment, surgery, or entered a clinical trial. CONCLUSION An excessive corticosteroid use can be recognized on time using the SAT. We have proven that excessive corticosteroid use could be avoided in almost half of cases and thus the overuse of CS may indicate poor quality of care in those patients.

AIM To determine the normative range of ultrasound dimensions for the liver, spleen and kidneys in healthy children according to gender, age, body measurements, body surface area (BSA), and the influence of ethnicity on organ size. METHODS The prospective study included children, ranging from full-term neonates to children aged 15, with normal ultrasonographic (US) findings of the liver, spleen and kidney and no clinical evidence of a disease. Gender, age, as well as body measurements and BSA, were determined for each child along with US measurements, and normative ranges were established. RESULTS US images of the liver and spleen from 372 children and 366 US images of kidneys of 366 children were included. US measurements of the liver, spleen and kidney correlated well with gender, age, body weight and height, and often differed to a greater or lesser extent from the normal range of measurements (5th to 95th percentile) reported in other studies. CONCLUSION Our results differed slightly from other reports conducted in Europe, but larger differences compared to measurements performed on children on other continents were found. Thus, our study confirmed that ethnically appropriate and modern tables of normal ultrasound dimensions for the liver, spleen and kidneys should be used, and that the national nomogram is justified.

In recent advancements in robotics, Artificial Intelligence (AI) methods such as Deep Learning, Deep Reinforcement Learning (DRL), Transformers, and Large Language Models (LLMs) have significantly enhanced robotic capabilities. Key AI models driving advancements in robotic vision include Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), the DEtection Transformers (DETR), the YOLO family of algorithms, segmentation techniques, and 3D vision technologies. Deep Reinforcement Learning (DRL), an AI technique where agents learn optimal behaviors through trial and error interactions with their environment, enables robots to perform complex tasks autonomously. Transformers, originally developed for natural language processing, have been adapted to robotics for tasks involving sequence prediction and data understanding, improving perception and decision-making processes. LLMs leverage vast amounts of text data to enhance robot-human interaction, enabling robots to understand and generate human-like language, thus improving their communicative and collaborative abilities in various applications. The integration of these AI methods enhances the adaptability, efficiency, and overall performance of robotic systems, paving the way for more sophisticated and intelligent autonomous agents.

In the last ten years, the development and research of advanced technologies, as well as their application in all segments of society, have led to major changes and reshaping of the new world. New innovations are occurring on a daily basis, but their application is not going fast enough due to the rigid infrastructure. However, in order to secure an optimal future, we all have to adapt to the changes that are coming. The developed countries have adopted the strict implementation of advanced technologies of Industry 4.0, some of which include: Internet of Things (IoT), Big Data, Cloud Computing, smart sensors, Radio Frequency Identification (RFID), 3D printing, advanced security systems, Virtual and Augmented Reality (VAR), etc. Robotics is the basic and first technology that has been implemented since the 60s of the last century, with artificial intelligence coming in the spotlight in the last ten years. Artificial intelligence is becoming a key to the development of advanced robots, as it enables them to adapt to unpredictable situations, to learn from experience and make intelligent decisions.Robots use AI to process sensor data, navigate, recognize objects, plan paths and interact with the environment. In short, artificial intelligence enables robots to be smart, whereas robotics uses AI to create autonomous and useful devices. This symbiosis contributes to progress in many industries, including healthcare, manufacturing and transportation. Artificial intelligence (AI) and robotics are two key fields that complement each other. The paper presents the trend of applied and approved patents in artificial intelligence and robotics, as well as an example of the use of artificial intelligence in advanced robots to perform certain tasks. Artificial intelligence (AI) is having an increasing impact on robotics, opening up many possibilities.

U radu je predstavljen postupak izbora najpogodnijeg numeričkog modela za utvrđivanje indeksa staništa (SI – site index) kao apsolutne mjere proizvodnog potencijala (boniteta) staništa jednodobnih nenjegovanih sastojina bijelog bora na karbonatnim supstratima u BiH. Objekat istraživanja su predstavljale jednodobne nenjegovane sastojine bijelog bora različitih taksacionih i stanišnih karakteristika. Metodom privremenih oglednih parcela prikupljeno je više općih i taksacionih podataka, a zatim su njihovom obradom i analizom utvrđeni najvažniji strukturni i proizvodni parametri sastojina odvojeno po relativnim visinskim bonitetnim klasama staništa (RB). Za utvrđivanje numeričkog modela za procjenu indeksa staništa (SI) primijenjene su metode korelacione i regresione analize, a za predstavljanje veličina osnovnih taksacionih elemenata prema veličinama SI grafička metoda. U cilju predstavljanja veličina osnovnih taksacionih elemenata po utvrđenim SI klasama uspostavljena je korelaciona veza između SI50 (pri starosti od 50 godina)i postojećih relativnih bonitetnih klasa (RB) jednodobnih sastojina bijelog bora. Ova veza je poslužila za izradu proizvodne diferencijacije staništa jednodobnih sastojina bijelog bora na karbonatnim susptratima u BiH koja omogućava prikaz veličina osnovnih taksacionih elemenata ovih sastojina zavisno od starosti i SI50. Poređenjem utvrđenih rezultata istraživanja s odgovarajućim rezultatima drugih autora zaključeno je da su jednodobne sastojine bijelog bora u BiH srednje produktivne.