Microbiology laboratory is a type of medical laboratory and should be safe and efficient environment. Even it is not a mandatory for the accreditation in most of the countries, ISO/IEC 15189 remains the most common reference for quality of work in medical laboratories. It is mostly based on good laboratory practices and is oriented to support accurate clinical decisions. ISO/IEC 15189 has potential to become very effective instrument for development and improvement of medical laboratories. Results from laboratory should guide the majority of clinical decisions and help in providing adequate patient care. This article provides a simple approach to meet the minimum requirements set. To achieve intended goal and strictly follow the requirements proposed in the standard, the trained and well-motivated laboratory staff is necessary to implement the system. The objective of this article is for it to be used as a guideline for evaluation and implementation of the ISO 15189.

This paper presents the results of development of Artificial Neural Networks (ANNs) for prediction of medical device performance based on conformity assessment data. Conformity assessment data of medical devices was obtained from periodical inspections conducted by ISO 17020 accredited laboratory during 2015–2019 period. For the development of ANNs, 1738 samples of conformity assessment of infusion and perfusor pumps was used. Out of the overall number of samples, 1391 (80%) of them were used during system development and 346 (20%) samples were used for subsequent validation of system performance. During system development, the impact on overall system accuracy of different number of neurons in hidden layer and the activation functions was tested. Also, two neural network architectures were tested: feedforward and feedback. The results show that feedforward neural network architecture with 10 neurons in single hidden layer has the best performance. The overall accuracy of that neural network is 98.06% for performance prediction of perfusor pumps and 98.83% for performance prediction of infusion pumps. The recurrent neural network resulted in accuracy of 98.41% for both infusion pumps and perfusor pumps. The results show that conformity assessment data obtained through yearly inspections of medical devices can successfully be used for prediction of performance of single medical device. This is very important in increasing the safety and accuracy of diagnosis and treatment of patients.

Increasing incidence of cardiovascular disease and their mortality rate render them as second leading cause of death worldwide. Artificial Intelligence (AI) is used in many fields of science and industry, but also has found its use in medicine for diagnosis, treatment and prediction of diseases. This paper presents the review of AI application in cardiology. The review is based on research papers published in Medline database. Findings of the review indicate that, according to accuracy parameter, the overall performance of AI based models for cardiovascular application is above 83%. Based on the results, AI algorithms and deep learning can be rendered as accurate, hence showing possibility to be used as a diagnostic tool now and in the future. New era of modern diagnosing is coming and Artificial Intelligence has the potential to change the way in which medicine is practiced.

PURPOSE OF THE STUDY Decline in length of stay is of growing interest for patients, doctors and health insurances. The aim of our study was to assess the safety and length of stay after omission of casting, start of early mobilization and implementation of functional discharge criteria after total elbow arthroplasty (TEA). MATERIAL AND METHODS We retrospectively reviewed all patients' records who received a Coonrad-Morrey TEA in the period from January 1st, 2011 to December 31st, 2018. From these records, indications, demographic information and complications were derived. Length of stay was calculated from the hospital administration. Patients were divided in three groups to evaluate the two changes in post-operative care. RESULTS In total 125 patients receiving 126 Coonrad-Morrey TEAs were included with a mean length of stay of 5.5 days (range 2- 23) for the entire group. Omitting a post-operative cast led to decline in length of stay from 6.2 to 5.4 days (p < 0.001). Introduction of functional discharge criteria in August 2017 declined mean length of stay to 3.8 days (p < 0.001). The surgical technique (triceps-on versus triceps-off) was not a confounder (p = 0.20). Range of motion after one year was not significantly different between groups. DISCUSSION The length of stay declined after omission of a cast, and declined further after introducing functional discharge criteria. Since no higher complication rates were observed, the shortening of length of stay appears to be safe. This is in line with other fast-track programs, i.e. for hip and knee arthroplasty. The surgical technique used were not a confounder for the shortened length of stay, which further adds to the safety of the functional discharge criteria. CONCLUSIONS Omitting a cast and splint as regular post-operative treatment reduced the length of stay significantly without leading to more complications. Introduction of functional discharge criteria lowered the length of stay further without more complications. Key words: fast track rehabilitation, cast, total elbow arthroplasty, length of stay, discharge, complications.

Abstract Microstructure of austenitic stainless steel is primarily monophasic, i.e. austenitic. However, precipitation of the δ-ferrite in the austenite matrix is possible depending on the chemical composition of steel. δ-Ferrite is stable on room temperature but it transforms into σ-phase, carbides and austenite during heat treatment. In this work, the results of analysis of influence of temperature and time on decomposition of δ-ferrite are presented. Magnetic induction method, microstructure and hardness analyses were used for testing the degree of decomposition of the δ-ferrite. Analysis of results showed that increase in temperature and time increases the degree of decomposition of δ-ferrite.

Introduction: The health implications of Caesarean section are a significant factor in evaluating the use of Caesarean section as a method of completing childbirth. The increased rate of Cesarean section augmenting in a statistical way the health implications of the use of Cesarean section as a way of operative technique of childbirth finalization. Aim: To investigate the incidence of health implications on mother and child after Cesarian section in comparison to vaginal delivery. Methods: In our study, which was conducted as a retrospective-prospective and targeted study, the observed research period is from 2007 to 2019. The data sources are: medical histories, birth protocols and neonatal medical histories. Group A: represents the number of surveyed patients with a Cesarean section in a one-year period (2018) in General Hospital „Prim.dr A. Nakaš“. Group B: represents a control group of the same number of patients born by Caesarean section in 2007 in General Hospital „Prim.dr A.Nakaš“ with all parameters and variables detected in the research group. Evaluation of the examinee’s findings includes: anamnestic data, sonographic data, gynecological finding, colposcopic finding. PAPA test, HPV typing and laboratory findings due to the extensiveness of the study. Results: A comparison of the number of Caesarean sections in BiH before and now shows a statistically significant increase from about 6 caesareans per year to almost 21 Cesarean section per year (p<0.05). This increase led to a statistically significant decrease in perinatal mortality from 30 per thousand per year to only 6 per thousand per year (p<0.05). Complications after Cesarean section during both observed periods are dominated by subjective problems, followed by early complications after Cesarean section. According to the types of complications after Caesarean section, hemorrhages were the most numerous during both examined years, with 1 case of other complications and without a statistically significant difference between the observed years. There were no statistically significant differences in the duration of hospitalization, although in 2007 somewhat longer stay in the hospital after Caesarean section was recorded. Conclusion: Our study has shown that one of the most visible trends in modern perinatology is a significant increase in number of Cesarean sections. This is the basis of long-term side effects of Caesarean section, the frequency of which correlates with the increase in this surgical procedure.

Renewable diesel fuels have the potential to reduce net CO2 emissions, and simultaneously decrease particulate matter (PM) emissions. This study characterized engine-out PM emissions and PM-induced reactive oxygen species (ROS) formation potential. Emissions from a modern heavy-duty diesel engine without external aftertreatment devices, and fueled with petroleum diesel, hydrotreated vegetable oil (HVO) or rapeseed methyl ester (RME) biodiesel were studied. Exhaust gas recirculation (EGR) allowed us to probe the effect of air intake O2 concentration, and thereby combustion temperature, on emissions and ROS formation potential. An increasing level of EGR (decreasing O2 concentration) resulted in a general increase of equivalent black carbon (eBC) emissions and decrease of NOx emissions. At a medium level of EGR (13% intake O2), eBC emissions were reduced for HVO and RME by 30 and 54% respectively compared to petroleum diesel. In general, substantially lower emissions of polycyclic aromatic hydrocarbons (PAHs), including nitro and oxy-PAHs, were observed for RME compared to both HVO and diesel. At low-temperature combustion (LTC, O2 < 10%), CO and hydrocarbon gas emissions increased and an increased fraction of refractory organic carbon and PAHs were found in the particle phase. These altered soot properties have implications for the design of aftertreatment systems and diesel PM measurements with optical techniques. The ROS formation potential per mass of particles increased with increasing engine O2 concentration intake. We hypothesize that this is because soot surface properties evolve with the combustion temperature and become more active as the soot matures into refractory BC, and secondly as the soot surface becomes altered by surface oxidation. At 13% intake O2, the ROS-producing ability was high and of similar magnitude per mass for all fuels. When normalizing by energy output, the lowered emissions for the renewable fuels led to a reduced ROS formation potential.

In this paper is presented an analysis of gland seals operation and their influence on the performance of low power steam turbine with two cylinders and steam reheating, which can be used in marine applications. Performed analysis presents a comparison of steam turbine main operating parameters when gland seals operation is neglected (as usual in the most of the literature) and when steam mass flow rates leaked through all gland seals are taken into consideration. Steam mass flow rate leakage through all gland seals reduces produced power of the whole turbine and both of its cylinders. Operation of gland seal mounted at the inlet in the first cylinder of any steam turbine (cylinder which operates with the steam of the highest pressure) has the most notable influence on the reduction of the whole turbine produced power. Gland seal mounted at the outlet of the last turbine cylinder (cylinder which operates with the steam of the lowest pressure) did not have any influence on the reduction of steam turbine produced power. In any detail analysis of a steam turbine (especially the complex turbine with multiple cylinders), gland seals operation should be considered due to their notable influence on the turbine performance.

SUMMARY Myxopapillary ependymomas (MPE) of the spinal cord are slow-growing benign tumors most frequently found in adults between 30 and 50 years of age. They arise from the ependyma of the filum terminale and are located in the area of the medullary conus and cauda. The recommended treatment option is gross total resection, while patients undergoing subtotal resection usually require radiotherapy. Complete resection without capsular violation can be curative and is often accomplished by simple resection of the filum above and below the tumor mass. Nevertheless, dissemination and distant treatment failure may occur in approximately 30% of the cases. In this paper, we propose an original MPE classification, which is based upon our personal series report concerned with tumor location and its correlation with the extent of resection. We also provide literature review, discussing surgical technique, tumor recurrence rate and dissemination, and adjuvant treatment. In conclusion, our findings suggest that MPE management based on the proposed 5-type tumor classification is favorable when total surgical resection is performed in carefully selected patients. Yet, further studies on a much broader model is obligatory to confirm this.

Over the course of the last decade, the subfield of artificial intelligence, called deep learning, becomes the main technology that provides breakthroughs in the computer vision area. Likewise, deep learning algorithms made a major impact in the automated driving domain. This research aims to apply and evaluate the performance of two pre-trained deep learning algorithms in order to recognize different street objects. Both RCNN, as well as YOLO algorithms, are used to recognize bikes, cars and pedestrians using the public GRAZ-02 dataset composed of 1476 raw images of street objects. Accuracy greater than 90% is achieved in recognizing all considered objects. The fine-tuning and training of both algorithms is established using databases named ImageNet and COCO, and afterwards, trained models are tried on the test data.