Artificial intelligence technology is rapidly advancing year by year, and thus the possibilities of using artificial intelligence in every branch of science. The importance of artificial intelligence and its components has been known for a long time. They are seen as tools and techniques that make the world a better place With their simple and everyday techniques, they make the world a mistake-free place. These technologies and applications are not only related to our general and everyday life, but also affect and have significance for other domains as well. The paper will analyze the application of artificial intelligence and its influence today.

The Sarajevo Canton Winter Field Campaign 2018 (SAFICA) was a project that took place in winter 2017–2018 with an aim to characterize the chemical composition of aerosol in the Sarajevo Canton, Bosnia and Herzegovina (BiH), which has one of the worst air qualities in Europe. This paper presents the first characterization of the metals in PM10 (particulate matter aerodynamic diameters ≤10 μm) from continuous filter samples collected during an extended two-months winter period at the urban background Sarajevo and remote Ivan Sedlo sites. We report the results of 18 metals detected by inductively coupled plasma mass spectrometry (ICP-MS) and electrothermal atomic absorption spectrometry (ETAAS). The average mass concentrations of metals were higher at the Sarajevo site than at Ivan Sedlo and ranged from 0.050 ng/m3 (Co) to 188 ng/m3 (Fe) and from 0.021 ng/m3 (Co) to 61.8 ng/m3 (Fe), respectively. The BenMAP-CE model was used for estimating the annual BiH health (50% decrease in PM2.5 would save 4760+ lives) and economic benefits (costs of $2.29B) of improving the air quality. Additionally, the integrated energy and health assessment with the ExternE model provided an initial estimate of the additional health cost of BiH’s energy system.

Estimating conditional average treatment effects (CATE) is challenging, especially when treatment information is missing. Although this is a widespread problem in practice, CATE estimation with missing treatments has received little attention. In this paper, we analyze CATE estimation in the setting with missing treatments where unique challenges arise in the form of covariate shifts. We identify two covariate shifts in our setting: (i) a covariate shift between the treated and control population; and (ii) a covariate shift between the observed and missing treatment population. We first theoretically show the effect of these covariate shifts by deriving a generalization bound for estimating CATE in our setting with missing treatments. Then, motivated by our bound, we develop the missing treatment representation network (MTRNet), a novel CATE estimation algorithm that learns a balanced representation of covariates using domain adaptation. By using balanced representations, MTRNet provides more reliable CATE estimates in the covariate domains where the data are not fully observed. In various experiments with semi-synthetic and real-world data, we show that our algorithm improves over the state-of-the-art by a substantial margin.

INTRODUCTION Additive production refers to the process of prototyping, which allows the production of highly complex medical devices and products. Interpretation of additive manufacturing (AM) material in Computed Tomography (CT) has not been widely investigated. The aim of this study was to determine the CT number values of commercially available fused deposition modelling (FDM) and stereolithography (SLA) AM materials. METHODS Total of 15 AM materials, 7 FMD and 8 SLA, were selected and scanned on CT to determine the HU value and appearance on the images. All test object were designed as rectangular blocks and after their production physical description were calculated. AM materials were scanned on CT operating at 80, 100, 120 and 135 kV. RESULTS All materials correspond to a certain human tissue and they have uniformity when printed with 100% infill. CT number ranged from a minimum of -188.0 HU to a maximum of 189.1 HU, for FDM materials, and from -15.8 HU to 167.3 HU, for SLA materials. CONCLUSION Knowing the CT number of an AM materials can allow the design of medical or rehabilitation products with a specific appearance on CT images. Analysed and collected data can find application in the design and manufacture of immobilization devices that can be easily distinguished from other materials or human tissue. IMPLICATIONS FOR PRACTICE This study provides information that can be used in the design and fabrication of anthropomorphic diagnostic and therapeutic phantoms. There is significant potential for the use of AM material for sophisticated test objects when used in medical image modality testing. Knowing actual CT numbers of frequently used AM materials allows manufacturing anthropomorphic phantoms to investigate radiation doses in diagnostic radiology and radiotherapy.

Age estimation has become inordinately significant for human beings for many reasons, such as detecting legal and criminal responsibility and other social events like a marriage license, birth certificate, etc. This paper aims to decide on the most desirable machine learning algorithm (from conventional machine learning algorithms to deep learning) for dental age estimation based on buccal bone level. The database consisted of 150 CBCT images (73 males and 77 females) from an existing base of the Faculty of Dental Medicine with Clinics, University of Sarajevo, aged 20-69. Results were obtained using the Waikato Environment for Knowledge Analysis (Weka), machine learning software in Java. Left and Right Buccal Alveolar Bone Levels are increasing with age, so they showed to be the most important attributes, especially the latter. Random Forest classifier provided the greatest result with the correlation coefficient of 0.803 and the mean absolute error of 6.022. We have also shown that considering sinus-related features can be a significant addition to the databases. Our paper is probably one of the first studies where regression algorithms based on the Support Vector Machines and Random Forest were utilized.

Abstract Sweet chestnut forests in Bosnia and Herzegovina are underrepresented in the total forest fund, and their area is declining today. The research aims to determine the correlation relations of morphological traits of chestnut leaves, fruit and cupule in the population of Bosnian Krajina (northwestern Bosnia and Herzegovina) to undertake selection and breeding activities. Eleven traits of fruits, leaves and cupules were measured, seven assessed and six calculated. A mutual correlation for the researched traits was calculated using the Pearson correlation coefficient r. When the fruit traits and cupule traits were compared, the needle length showed a statistically significant correlation with most of the fruit traits. The traits of the number of fruits in the cupule and needle length had a statistically significant correlation coefficient with leaf blade width and leaf petiole length. The correlated traits can be distinguished as important for further selection and breeding of sweet chestnuts. The research results indicate that the genetic material of sweet chestnut is a rich source of genetic diversity and can be used in selection to obtain new varieties and cultivars in Bosnia and Herzegovina and for the protection of the indigenous gene pool.

Benzophenone (BP) type UV filters are common environmental contaminants that are posing a growing health concern due to their increasing presence in water. Different studies have evidenced the presence of benzophenones (BP, BP-1, BP-2, BP-3, BP-4, BP-9, HPB) in several environmental matrices, indicating that conventional technologies of water treatment are not able to remove them. It has also been reported that these compounds could be associated with endocrine-disrupting activities, genotoxicity, and reproductive toxicity. This review focuses on the degradation kinetics and mechanisms of benzophenone-type UV filters and their degradation products (DPs) under UV and solar irradiation and in UV-based advanced oxidation processes (AOPs) such as UV/H2O2, UV/persulfate, and the Fenton process. The effects of various operating parameters, such as UV irradiation including initial concentrations of H2O2, persulfate, and Fe2+, on the degradation of tested benzophenones from aqueous matrices, and conditions that allow higher degradation rates to be achieved are presented. Application of nanoparticles such as TiO2, PbO/TiO2, and Sb2O3/TiO2 for the photocatalytic degradation of benzophenone-type UV filters was included in this review.

Origanum compactum, an endemic Moroccan medicinal herb, possesses many different activities such as antibacterial, antifungal, antioxidant and anticancer. The aim of this study was to investigate the stability and antifungal activity of liposomal dispersion with this essential oil. Liposomal dispersion stability was evaluated by testing the vesicle size, polydispersity index and zeta potential. It was also examined the in vitro release of thymol and carvacrol from liposomal dispersion. The major components of this essential oil were carvacrol (58.4%), thymol (12.5%) and γ-terpinene (10.7%). Origanum compactum essential oil showed a strong antifungal activity, and the inhibition zones ranged from 24 to 45 mm. After 210 minutes, 80.88% thymol and 16.67% carvacrol were released. Stability assessment was performed for three months and the liposomal dispersion showed a good stability.

Objectives The study aimed to compare the color stability of two different light-cured composites after immersion in three liquids and the effectiveness of 16% carbamide peroxide (CP) in removing the discoloration. Material and methods Color stability of a microhybrid (Z250, 3M ESPE) and nanocomposite (Z550, 3M ESPE) was evaluated after immersion in instant coffee, tea, Coca-Cola, and deionized water as a control group (n=5). Samples were kept in liquids for four hours daily at 37°C for 30 days. Furthermore, 16% CP was applied for the following 14 days, simulating night whitening. A digital spectrophotometer was used for color measurement based on the CIEL*a*b* color coordinates. The color changes (∆E) were measured at baseline, after immersion in the beverages, and also after the teeth whitening procedure. Mixed and factorial ANOVA followed by Bonferroni’s post-hoc test were used for statistical evaluation (p≤0.05). Results Tested resin composites showed a color change over the acceptability threshold (ΔE*> 3.48) after immersion in coffee and tea. Nanocomposite reported a significant increase in discoloration in coffee after 30 days (p <0.05). The color of both materials significantly changed (p<0.05) along all three L*a*b* axes in coffee and tea to darker, yellow, and red. Whitening with 16% CP was effective in removing external discoloration in both examined composite materials. Conclusion Coffee and tea induced clinically detectable color changes in dental composites tested, with cumulative effects. Whitening represents an efficient method for the removal of surface discoloration in composite restorations.

Sludge generated in wastewater treatment processes must be treated in an adequate manner, and therefore disposed of in an environmentally friendly manner. The biggest obstacle to the efficient use of sludge is the high water content, therefore the development of methods to accelerate the sludge dewatering process is particularly important. For the purposes of the research, the waste sludge created in the process of purifying ammoniaphenol wastewater in the GIKIL factory was used. Sludge conditioning was performed by adding a commercial flocculant (0.1 % solution) in combination with pyrophyllite, kaolin clay and shredded cardboard. According to earlier research, the volume of waste sludge with the addition of a suitable flocculant could be reduced by more than 5 times compared to the initial amount, leaving behind a large amount of separated water that can be returned to the process. The results show that the addition of commercial flocculant in the amount of 0.8 % gives the best results (reduction of sludge volume by 78.8 %). A lower percentage was found in samples with a mixture of flocculants with pyrophyllite (78 %) and kaolin (77.6 %), while the combination of flocculants with waste cardboard was ineffective (64.4 %). Addition of flocculant to waste sludge resulted in a decrease in specific filtration resistance (1.15x107 s2/g). A decrease in specific resistance was also observed in flocculant/kaolin clay (0.8x107 s2/g) and flocculant/cardboard (1.09x107 s2/g) samples. Sludge conditioning also resulted in a reduction of suspended solids in the neonate compared to settled raw sludge without additives.

Background: Psoriasis can be described as a T-cell-mediated disease, with a complex role for variety of cytokines and other factors. Among the inflammatory molecules influencing the keratinocites, TNF-α appears critical in sustaining most of the clinical manifestations of psoriasis. It is postulated that changes in cytokine production both locally and systemically could be useful in monitoring disease activity. Objective: The aim of the study was to evaluate serum levels of tumor necrosis factor alpha (TNF-α) in patients with psoriasis and the healthy subjects, and also to assess a possible association between TNF-α, clinical type and severity of disease. Methods: We studied the levels of serum TNF-α in 60 patients with psoriasis and in the serum of helthy 20 controls. According to the clinical type of disease, patients with psoriasis were divided into four groups: chronic plaque psoriasis (CPP), erythrodermic psoriasis (EP), pustular psoriasis (PP) and psoriatic arthritis (PA). Blood samples were collected from all psoriasis patients and from healthy control subjects. Serum level of TNF-α were measured by an enzyme-linked immunosorbent assay (ELISA) technique. The severity of CPP was assessed by Psoriasis Area and Severity Index (PASI). Results: Serum levels of TNF-α in patients with psoriasis were significialy higher than in the control group (3.25+1.74 pg/mL vs 0.20+0.01pg/mL, respectively). Significantly elevated serum TNF-α was in patients with PP type (7.39+6.92 pg/mL). There was statistically significant difference between the mean level of TNF-ɑ compared to the clinical type of psoriasis (p<0.05). The mean PASI score in patients with CPP was 0.56±12.45. It was not found statistically significant correlation between serum level of TNF-ɑ and PASI score in patients with CPP (p>0,05). Conclusion: Our results have demonstrated the imortance of determining serum levels of TNF-ɑ in patients with psoriasis. Further investigations are required to clarify the pathogenic role and clinical significance of TNF-ɑ, and these findings may provide important clues to assist in the development of new therapeutic strategies for patients with psoriasis.

Background: Thimerosal is an organomercury compound with high mercury content. Thimerosal is located in the market as an effective bacteriostatic in a series of pharmaceutical products, ophthalmic and nasal products, immunoglobulin preparations, and as a preservative in vaccines. Aims and Objectives: Since it is a compound with living content, this study aimed to examine the genotoxic and cytotoxic potential of thimerosal in human lymphocytes culture. Materials and Methods: We used chromosome aberration analysis and cytokinesis-block micronucleus cytome (CBMN-Cyt) assay to test its genotoxic and cytotoxic potential in human lymphocyte culture. Results: Results showed that the frequency of structural chromosome aberrations and CBMN-cyt assay was significantly increased in treated cultures (1 μg/ml and 0.5 μg/ml) compared to the negative control. Conclusion: Obtained results and statistical analysis show that thimerosal is genotoxic and cytotoxic in human lymphocytes in tested concentrations.