Search

Within the theory of thermo-elasticity, the temperature field of thin plates is commonly defined via two parameters: temperature in the mid-plane and linear temperature gradient normal to the mid-plane. First, the paper analytically proves the justification of that assumption in machine structures. Then, in an analytical closed form, applying the integral transformation method, the thin plate deflection caused by a constant temperature gradient is defined. It is shown that, in that case, the plate deflection does not depend on its thickness but only on the plate dimensions in the mid-plane. Analytically defined values are compared to corresponding values obtained by applying the thin plate finite element, where the temperature field is described using the two mentioned parameters. This finite element is defined and programmed within the Komips program package. The influence of the temperature gradient on the behavior of constructions mostly depends on the type of material. That is why the behavior of some structural elements made of brass, steel, and concrete is analyzed in this paper.

Background/Aim. Acute kidney injury (AKI) is a frequent and serious complication after aortic surgery, which increases the length of hospital stay, costs, morbidity, and mortality. The aim of the study was to investigate the incidence of AKI and the most important preoperative and intraoperative predictive factors for AKI 72 hrs after elective infrarenal aortic surgery (IAS). Methods. This prospective observational study was performed at the Clinic of Anesthesia, Intensive Care and Pain Therapy, University Clinical Center of Vojvodina (UCCV), from October 2017 to April 2019. It included 140 adult patients who underwent an elective IAS. The occurrence of AKI was noted according to the Acute Kidney Injury Network (AKIN) criteria. A multivariate logistic regression model was used for potential predictive factors. Results. The incidence of AKI after the elective IAS at the Clinic of Anesthesia, Intensive Care and Pain Therapy, UCCV, was 28.56%. According to the receiver operating characteristic (ROC) curve analysis, the cut-off value of cystatin C serum concentration of 1.14 mg/L had the highest sensitivity (82.5%) and specificity (76%) in the differentiation of patients who will develop AKI. The final model contained the following variables: the presence of chronic kidney disease, the preoperative serum concentration of cystatin C > 1.14 mg/L, the application of colloid solutions in volume > 500 mL during the operation, and the total intra-vascular fluid replacement volume > 59 mL/kg in the intraoperative period. Conclusion. The incidence of AKI at the Clinic of Anesthesia, Intensive Care and Pain Therapy, UCCV, is somewhat higher compared to the literature data. A presurgical value of cystatin C above 1.14 mg/L is a good predictor of AKI after the elective IAS.

Background/Aim. When it comes to anesthesia, patient satisfaction (PS) is more difficult to assess than in any other medical specialty. The aim of this study was to construct a tool for assessing PS with anesthesia and then examine the effects of postoperative care provided by anesthesiologists on PS. Methods. The study included patients undergoing general anesthesia due to the reconstruction of the anterior cruciate knee ligament who were considered the American Society of Anesthesiologists (ASA) 1 and ASA 2 classes. Patients were divided into three groups: group 1 included 74 patients who had a postoperative visit performed by an attending anesthesiologist; group 2 included 70 patients who had a postoperative visit performed by a nurse anesthetist after surgery; group 3 included 74 patients who did not have postoperative visit during postoperative care by an anesthesiologist nor a nurse anesthetist. The tools used in the research were the Anesthesia Patient Satisfaction questionnaire specially designed for this study and the Post Anesthetic Recovery Scoring System (PAS). ANOVA and Pearson’s correlation coefficient were used to estimate the statistical significance of the obtained results between the groups. Results. Association between an objective assessment of the postoperative status of patients on day zero and satisfaction with the anesthesiologist’s patient management showed statistical significance (p < 0.05). Patients who had a postoperative visit by an anesthesiologist tolerated better preoperative and postoperative physical symptoms. Patients visited by an anesthesiologist were most satisfied with postoperative care (p < 0.05). Conclusion. The use of a highly reliable questionnaire for the evaluation of PS with anesthesia could improve the postoperative condition of patients and enable faster recovery during the postoperative period.

We present the case of a 39-years old man who underwent three surgeries because of spinal ependymoma located in cauda equina region. He presented at the Oncology Institute of Vojvodina for combined adjuvant chemoand radiotherapy after the second surgery. An MRI examination performed after six cycles of therapy showed no signs of disease. 26 months later, a follow-up MRI showed recurrence of disease in the form of small drop metastasis. Six months later, the patient underwent the third surgery. The patient is currently receiving another cycle of radiotherapy, and is scheduled for additional cycles of chemotherapy. Ependymomas are the most common spinal cord malignancy in adults. The symptoms are nonspecific which often causes a delay in diagnosis. An MRI examination of the spine with contrast admission is the study of choice for detecting spinal cord masses. Surgery is the first-line therapy for ependymomas. Recurrence rate is associated with the extent of surgical resection, with en bloc and gross-total resection being associated with lower rates of disease recurrence. In children under 3 years, adjuvant chemotherapy is advocated, while older children and adults undergo adjuvant radiotherapy or combined chemoand radiotherapy in cases of subtotal resection or tumor recurrence.

The new global order has yet to be fully established. The process reflects not only a geopolitical struggle but also a set of competitive political models. While it is possible to determine more than two dominant models, it is a contest between the two forms of democracy - liberal and illiberal. A one-party state, or a Chinese model, is an economic model used for geopolitical purposes while Muslim political model, strongly contested within the Muslim world, is restricted to areas dominated by the population of this faith. Some of its forms are reflected in the form of authoritarianism as developed in Turkey. The faith, therefore, is of lesser significance. The regimes in the Western Balkans have been developed and are based on two models of democracy. The resulting hybrid regimes are analysed in the global context of the powerstruggle and ideological contest. The question is whether the hybrid regimes of the Western Balkans are the result of dysfunctional local democracy or whether the search for global stability is resulting in a model of competitive authoritarianism which provides for global security but also supports the regime's desire to remain unchanged in perpetuity? This development might be supportive of international security but is an utterly destabilising factor for societies in the Western Balkans and a substantial obstacle to the development of liberal democracy.

The problem of torsion due to horizontal inertial effects is considered at cantilever beam with variable I-section. Linear variation of height is concerned as most practical one for the design of cantilever beams. The solution for adopted cases of beams is obtained numerically, according to the complexity of the given ordinary differential equation which deals with pure torsion along with warping torsion. The models are based on known tailor-made beams with possibility for application in design of jib cranes, as practical aspect of this work. The comparison of results is done with uniform cantilever beam models which can be used as one way for verification of stress state of variable cantilever beams subjected to bending with torsion. The obtained results show corresponding advantages of usage of variable sections.

Introduction. Hemodynamic instability is a common occurrence during liver transplantation (LT). Hypotension and hemodynamic instability during graft reperfusion are most commonly consequences of the postreperfusion syndrome (PRS). Case Outline. In this report, we present a case of severe cardiovascular collapse leading to cardiac arrest which occurred in the course of graft reperfusion during LT. Persistent hypotension, non-responsive to regular measures such as volume filling and the use of vasopressors, yielded the question of whether other mechanisms were involved in causing it. Diffuse redness of the face and body, swelling of the face, lips and tongue with tongue prolapse, accompanied with severe cardiovascular collapse indicated that it was an anaphylactic reaction. This caused a dilemma as to what instigated the reaction. The trigger may have been the pharmacological substance administered during the graft reperfusion, or the one administered immediately prior to the reperfusion. The substances in question would most likely be either the University of Wisconsin preservation solution (UW), which was administered during the reperfusion, or Hepatect, which the patient received immediately prior to reperfusion. Conclusion. The clinical syndrome resulting from degranulation of mast cells and basophils in anaphylaxis is very similar to the PRS in LT. Clinical features play the most important role in establishing a timely diagnosis and early treatment of anaphylaxis. Swift administration of epinephrine reduces the chances of a fatal outcome. Better information on both donor and recipient can improve the efficiency of therapy and prophylaxis for anaphylaxis.

One approach to the optimization of a thin-walled open section Z-beam subjected to the bending and to the constrained torsion is considered. For given loads, material and geometrical characteristics, the problem is reduced to the determination of minimum mass i.e. minimum crosssectional area of structural thin-walled beam of the chosen shape. The area of the cross-section is assumed to be the objective function. The stress constraints are introduced. The Lagrange multiplier method is applied. Solutions of analitically obtained expressions for the mathematical model, numerical solutions, as well as the saved mass, are calculated for three loading cases.

Nada Andelic,1 Jan Borre Johansen,1 Erik Bautz-Holter,1,2 Anne Marit Mengshoel,3 Eva Bakke,3 Cecilie Roe1,21Department of Physical Medicine and Rehabilitation, Oslo University Hospital, Oslo, Norway; 2Faculty of Medicine, University of Oslo, Oslo, Norway; 3Department of Health Sciences, Institute of Health and Society, University of Oslo, Oslo, NorwayObjective: To describe commonly reported self-determined functional problems in patients with neck pain and to evaluate their fit to the components of the International Classification of Functioning, Disability, and Health (ICF).Methods: Overall, 249 patients were included in this cross-sectional study that comprised patients with neck pain referred to the outpatient clinic at Oslo University Hospital (2007–2009). Patients were asked to report their three most significant functional problems on the Patient-Specific Functional Scale, a self-determined measure of function. The ICF was used as a tool for analysis. Meaningful concepts within the functional problems were identified, coded, and linked to second-level categories within the components of “body functions,” and “activities and participation.” Two researchers performed coding and linking independently. The ICF categories were presented by percentage of the total number of functional problems linked to the ICF.Results: Of 628 reported functional problems, 13 meaningful ICF domains were identified: four domains belonging to the body functions component (b) and nine domains belonging to activities and participation components (d). Within the 88 second-level ICF classification categories of body functions, the most frequently reported items were sleep function (b134; 27%) and mobility of joint functions (b710; 26%). Within the 538 second-level categories of activities and participation, remunerative employment was reported as the most frequent item (d850; 15%), closely followed by doing housework (d640; 14%), and recreation and leisure activities (d920; 13%). Only two meaningful concepts, described as “be active” and “to function after activities,” were not assigned to a specific ICF category.Conclusion: The majority of the specific functional problems presented by patients in this study showed a good fit with the ICF model. The substantial number of links to the activities and participation categories, such as mobility, domestic life, employment, and social and civic life, suggests that a comprehensive approach, as well as the involvement of a multidisciplinary team, should be present in the rehabilitation of neck pain-related disability.Keywords: neck pain disability, self-determined functional problems, PSFS, ICF

The main purpose of this paper is to present one approach to the optimization of thin-walled I, Z and channel-section beams subjected to constrained torsion. The displacement constraints are introduced: allowable angle of twist and allowable angle of twist per unit length. The area of the cross-section is assumed to be the objective function. Applying the Lagrange multiplier method, the equations whose solutions represent the optimal values of the ratios of the parts of the chosen cross-sections are derived.

An approach to the optimization of the thin-walled cantilever open section beams subjected to the bending and to the constrained torsion is considered. The problem is reduced to the determination of minimum mass, i.e. minimum cross-sectional area of structural thin-walled I-beam and channel-section beam elements for given loads, material and geometrical characteristics. The area of the cross-section is assumed to be the objective function. The stress constraints are introduced. Applying the Lagrange multiplier method the equations, whose solutions represent the optimal values of the ratios of the parts of the chosen cross-section, are formed. The obtained results are used for numerical calculation.

Background and Objectives : The aim of this study was to examine whether the use of an alveolar recruitment maneuver (RM) leads to a significant increase in static lung compliance (Cstat) and an improvement in gas exchange in patients undergoing laparoscopic cholecystectomy. Material and Methods : A clinical prospective intervention study was conducted. Patients were divided into two groups according to their body mass index (BMI): normal-weight (group I) and pre-obese and obese grade I (group II). Lung mechanics were monitored (Cstat, dynamic compliance-Cdin, peak pressure-Ppeak, plateau pressure-Pplat, driving pressure-DP) alongside gas exchange, and hemodynamic changes (heart rate-HR, mean arterial pressure-MAP) at six time points: T1 (induction of anesthesia), T2 (formation of pneumoperitoneum), T3 (RM with a PEEP of 5 cm H 2 O), T4 (RM with a PEEP of 7 cm H 2 O), T5 (desufflation), and T6 (RM at the end). The RM was performed by increasing the peak pressure by +5 cm of H 2 O at an equal inspiration-to-expiration ratio (I/E = 1:1) and applying a PEEP of 5 and 7 cm of H 2 O. Results : Out of 96 patients, 33 belonged to group I and 63 to group II. An increase in Cstat values occurred after all three RMs. At each time point, the Cstat value was measured higher in group I than in group II. A higher increase in Cstat was observed in group II after the second and third RM. Cstat values were higher at the end of the surgical procedure compared to values after the induction of anesthesia. The RM led to a significant increase in PaO 2 in both groups without changes in HR or MAP. Conclusions : During laparoscopic cholecystectomy, the application of RM leads to a significant increase in Cstat and an improvement in gas exchange. The prevention of atelectasis during anesthesia should be initiated immediately after the induction of anesthesia, using protective mechanical ventilation and RM., Competing Interests: The authors declare no conflicts of interest.

Breast cancer is a type of cancer with several sub-types. It occurs when cells in breast tissue grow out of control. The accurate sub-type classification of a patient diagnosed with breast cancer is mandatory for the application of proper treatment. Breast cancer classification based on gene expression is challenging even for artificial intelligence (AI) due to the large number of gene expressions. The idea in this paper is to utilize the genetic programming symbolic classifier (GPSC) on the publicly available dataset to obtain a set of symbolic expressions (SEs) that can classify the breast cancer sub-type using gene expressions with high classification accuracy. The initial problem with the used dataset is a large number of input variables (54,676 gene expressions), a small number of dataset samples (151 samples), and six classes of breast cancer sub-types that are highly imbalanced. The large number of input variables is solved with principal component analysis (PCA), while the small number of samples and the large imbalance between class samples are solved with the application of different oversampling methods generating different dataset variations. On each oversampled dataset, the GPSC with random hyperparameter values search (RHVS) method is trained using 5-fold cross validation (5CV) to obtain a set of SEs. The best set of SEs is chosen based on mean values of accuracy (ACC), the area under the receiving operating characteristic curve (AUC), precision, recall, and F1-score values. In this case, the highest classification accuracy is equal to 0.992 across all evaluation metric methods. The best set of SEs is additionally combined with a decision tree classifier, which slightly improves ACC to 0.994.

Fire is usually detected with fire detection systems that are used to sense one or more products resulting from the fire such as smoke, heat, infrared, ultraviolet light radiation, or gas. Smoke detectors are mostly used in residential areas while fire alarm systems (heat, smoke, flame, and fire gas detectors) are used in commercial, industrial and municipal areas. However, in addition to smoke, heat, infrared, ultraviolet light radiation, or gas, other parameters could indicate a fire, such as air temperature, air pressure, and humidity, among others. Collecting these parameters requires the development of a sensor fusion system. However, with such a system, it is necessary to develop a simple system based on artificial intelligence (AI) that will be able to detect fire with high accuracy using the information collected from the sensor fusion system. The novelty of this paper is to show the procedure of how a simple AI system can be created in form of symbolic expression obtained with a genetic programming symbolic classifier (GPSC) algorithm and can be used as an additional tool to detect fire with high classification accuracy. Since the investigation is based on an initially imbalanced and publicly available dataset (high number of samples classified as 1-Fire Alarm and small number of samples 0-No Fire Alarm), the idea is to implement various balancing methods such as random undersampling/oversampling, Near Miss-1, ADASYN, SMOTE, and Borderline SMOTE. The obtained balanced datasets were used in GPSC with random hyperparameter search combined with 5-fold cross-validation to obtain symbolic expressions that could detect fire with high classification accuracy. For this investigation, the random hyperparameter search method and 5-fold cross-validation had to be developed. Each obtained symbolic expression was evaluated on train and test datasets to obtain mean and standard deviation values of accuracy (ACC), area under the receiver operating characteristic curve (AUC), precision, recall, and F1-score. Based on the conducted investigation, the highest classification metric values were achieved in the case of the dataset balanced with SMOTE method. The obtained values of ACC¯±SD(ACC), AUC¯±SD(ACU), Precision¯±SD(Precision), Recall¯±SD(Recall), and F1-score¯±SD(F1-score) are equal to 0.998±4.79×10-5, 0.998±4.79×10-5, 0.999±5.32×10-5, 0.998±4.26×10-5, and 0.998±4.796×10-5, respectively. The symbolic expression using which best values of classification metrics were achieved is shown, and the final evaluation was performed on the original dataset.

Passive immunotherapy with convalescent COVID-19 plasma (CCP) is used as a therapeutic procedure in many countries, including Serbia. In this study, we analyzed the association between demographic factors, COVID-19 severity and the reactivity of anti-SARS-CoV-2 antibodies (Abs) in Serbian CCP donors. Individuals ( n = 468) recovered from confirmed SARS-CoV-2 infection, and who were willing to donate their plasma for passive immunization of COVID-19 patients were enrolled in the study. Plasma samples were tested for the presence of IgG reactive to SARS-CoV-2 spike glycoprotein (S1) and nucleocapsid antigens. Individuals were characterized according to age, gender, comorbidities, COVID-19 severity, ABO blood type and RhD factor. Total of 420 candidates (420/468; 89.74%) reached the levels of anti-SARS-CoV-2 IgG that qualified them for inclusion in CCP donation program. Further statistical analysis showed that male individuals ( p = 0.034), older age groups ( p < 0.001), existence of hypertension ( p = 0.008), and severe COVID-19 ( p = 0.000) are linked with higher levels of anti-SARS-CoV-2 Abs. These findings will guide the selection of CCP donors in Serbia. Further studies need to be conducted to assess the neutralization potency and clinical efficiency of CCP collected from Serbian donors with high anti-SARS-CoV-2 IgG reactivity.

Urinary bladder cancer is one of the most common cancers of the urinary tract. This cancer is characterized by its high metastatic potential and recurrence rate. Due to the high metastatic potential and recurrence rate, correct and timely diagnosis is crucial for successful treatment and care. With the aim of increasing diagnosis accuracy, artificial intelligence algorithms are introduced to clinical decision making and diagnostics. One of the standard procedures for bladder cancer diagnosis is computer tomography (CT) scanning. In this research, a transfer learning approach to the semantic segmentation of urinary bladder cancer masses from CT images is presented. The initial data set is divided into three sub-sets according to image planes: frontal (4413 images), axial (4993 images), and sagittal (996 images). First, AlexNet is utilized for the design of a plane recognition system, and it achieved high classification and generalization performances with an AUCmicro¯ of 0.9999 and σ(AUCmicro) of 0.0006. Furthermore, by applying the transfer learning approach, significant improvements in both semantic segmentation and generalization performances were achieved. For the case of the frontal plane, the highest performances were achieved if pre-trained ResNet101 architecture was used as a backbone for U-net with DSC¯ up to 0.9587 and σ(DSC) of 0.0059. When U-net was used for the semantic segmentation of urinary bladder cancer masses from images in the axial plane, the best results were achieved if pre-trained ResNet50 was used as a backbone, with a DSC¯ up to 0.9372 and σ(DSC) of 0.0147. Finally, in the case of images in the sagittal plane, the highest results were achieved with VGG-16 as a backbone. In this case, DSC¯ values up to 0.9660 with a σ(DSC) of 0.0486 were achieved. From the listed results, the proposed semantic segmentation system worked with high performance both from the semantic segmentation and generalization standpoints. The presented results indicate that there is the possibility for the utilization of the semantic segmentation system in clinical practice.

Background and Objectives: Although ML has been studied for different epidemiological and clinical issues as well as for survival prediction of COVID-19, there is a noticeable shortage of literature dealing with ML usage in prediction of disease severity changes through the course of the disease. In that way, predicting disease progression from mild towards moderate, severe and critical condition, would help not only to respond in a timely manner to prevent lethal results, but also to minimize the number of patients in hospitals where this is not necessary., Methods: We present a methodology for the classification of patients into 4 distinct categories of the clinical condition of COVID-19 disease. Classification of patients is based on the values of blood biomarkers that were assessed by Gradient boosting regressor and which were selected as biomarkers that have the greatest influence in the classification of patients with COVID-19., Results: The results show that among several tested algorithms, XGBoost classifier achieved best results with an average accuracy of 94% and an average F1-score of 94.3%. We have also extracted 10 best features from blood analysis that are strongly associated with patient condition and based on those features we can predict the severity of the clinical condition., Conclusions: The main advantage of our system is that it is a decision tree-based algorithm which is easier to interpret, instead of the use of black box models, which are not appealing in medical practice., (Copyright © 2021. Published by Elsevier Ltd.)

COVID-19 is one of the greatest challenges humanity has faced recently, forcing a change in the daily lives of billions of people worldwide. Therefore, many efforts have been made by researchers across the globe in the attempt of determining the models of COVID-19 spread. The objectives of this review are to analyze some of the open-access datasets mostly used in research in the field of COVID-19 regression modeling as well as present current literature based on Artificial Intelligence (AI) methods for regression tasks, like disease spread. Moreover, we discuss the applicability of Machine Learning (ML) and Evolutionary Computing (EC) methods that have focused on regressing epidemiology curves of COVID-19, and provide an overview of the usefulness of existing models in specific areas. An electronic literature search of the various databases was conducted to develop a comprehensive review of the latest AI-based approaches for modeling the spread of COVID-19. Finally, a conclusion is drawn from the observation of reviewed papers that AI-based algorithms have a clear application in COVID-19 epidemiological spread modeling and may be a crucial tool in the combat against coming pandemics.

Urinary bladder cancer is one of the most common urinary tract cancers. Standard diagnosis procedure can be invasive and time-consuming. For these reasons, procedure called optical biopsy is introduced. This procedure allows in-vivo evaluation of bladder mucosa without the need for biopsy. Although less invasive and faster, accuracy is often lower. For this reason, machine learning (ML) algorithms are used to increase its accuracy. The issue with ML algorithms is their sensitivity to the amount of input data. In medicine, collection can be time-consuming due to a potentially low number of patients. For these reasons, data augmentation is performed, usually through a series of geometric variations of original images. While such images improve classification performance, the number of new data points and the insight they provide is limited. These issues are a motivation for the application of novel augmentation methods. Authors demonstrate the use of Deep Convolutional Generative Adversarial Networks (DCGAN) for the generation of images. Augmented datasets used for training of commonly used Convolutional Neural Network-based (CNN) architectures (AlexNet and VGG-16) show a significcan performance increase for AlexNet, where AUCmicro reaches values up to 0.99. Average and median results of networks used in grid-search increases. These results point towards the conclusion that GAN-based augmentation has decreased the networks sensitivity to hyperparemeter change.

Estimation of the epidemiology curve for the COVID-19 pandemic can be a very computationally challenging task. Thus far, there have been some implementations of artificial intelligence (AI) methods applied to develop epidemiology curve for a specific country. However, most applied AI methods generated models that are almost impossible to translate into a mathematical equation. In this paper, the AI method called genetic programming (GP) algorithm is utilized to develop a symbolic expression (mathematical equation) which can be used for the estimation of the epidemiology curve for the entire U.S. with high accuracy. The GP algorithm is utilized on the publicly available dataset that contains the number of confirmed, deceased and recovered patients for each U.S. state to obtain the symbolic expression for the estimation of the number of the aforementioned patient groups. The dataset consists of the latitude and longitude of the central location for each state and the number of patients in each of the goal groups for each day in the period of 22nd January 2020-3rd December 2020. The obtained symbolic expressions for each state are summed up to obtain symbolic expressions for estimation of each of the patient groups (confirmed, deceased and recovered). These symbolic expressions are combined to obtain the symbolic expression for the estimation of the epidemiology curve for the entire U.S. The obtained symbolic expressions for the estimation of the number of confirmed, deceased and recovered patients for each state achieved R2 score in the ranges 0.9406-0.9992, 0.9404-0.9998 and 0.9797-0.99955, respectively. These equations are summed up to formulate symbolic expressions for the estimation of the number of confirmed, deceased and recovered patients for the entire U.S. with achieved R2 score of 0.9992, 0.9997 and 0.9996, respectively. Using these symbolic expressions, the equation for the estimation of the epidemiology curve for the entire U.S. is formulated which achieved R2 score of 0.9933. Investigation showed that GP algorithm can produce symbolic expressions for the estimation of the number of confirmed, recovered and deceased patients as well as the epidemiology curve not only for the states but for the entire U.S. with very high accuracy.

COVID-19 represents one of the greatest challenges in modern history. Its impact is most noticeable in the health care system, mostly due to the accelerated and increased influx of patients with a more severe clinical picture. These facts are increasing the pressure on health systems. For this reason, the aim is to automate the process of diagnosis and treatment. The research presented in this article conducted an examination of the possibility of classifying the clinical picture of a patient using X-ray images and convolutional neural networks. The research was conducted on the dataset of 185 images that consists of four classes. Due to a lower amount of images, a data augmentation procedure was performed. In order to define the CNN architecture with highest classification performances, multiple CNNs were designed. Results show that the best classification performances can be achieved if ResNet152 is used. This CNN has achieved AUCmacro¯ and AUCmicro¯ up to 0.94, suggesting the possibility of applying CNN to the classification of the clinical picture of COVID-19 patients using an X-ray image of the lungs. When higher layers are frozen during the training procedure, higher AUCmacro¯ and AUCmicro¯ values are achieved. If ResNet152 is utilized, AUCmacro¯ and AUCmicro¯ values up to 0.96 are achieved if all layers except the last 12 are frozen during the training procedure.

This paper investigates the possibility of the implementation of Genetic Programming (GP) algorithm on a publicly available COVID-19 data set, in order to obtain mathematical models which could be used for estimation of confirmed, deceased, and recovered cases and the estimation of epidemiology curve for specific countries, with a high number of cases, such as China, Italy, Spain, and USA and as well as on the global scale. The conducted investigation shows that the best mathematical models produced for estimating confirmed and deceased cases achieved R 2 scores of 0.999, while the models developed for estimation of recovered cases achieved the R 2 score of 0.998. The equations generated for confirmed, deceased, and recovered cases were combined in order to estimate the epidemiology curve of specific countries and on the global scale. The estimated epidemiology curve for each country obtained from these equations is almost identical to the real data contained within the data set.

A surveillance study was performed in an intensive care unit in the largest tertiary health care center in Vojvodina, Serbia from 2014 to 2018. Antibiotic prescription data were collated in the WHO anatomical therapeutic chemical (ATC)/defined daily dose (DDD) format, while antibiotic resistance was expressed as incidence density adjusted for total inpatient-days. Individual trends were determined by linear regression, while possible associations between antibiotic prescription and resistance were evaluated using cross-correlation analysis. An overall decrease in antibiotic utilization was observed. The prescription rates of piperacillin-tazobactam increased significantly, while consumption of 3rd and 4th generation cephalosporins and fluoroquinolones decreased. There were rising incidence densities of doripenem resistant Acinetobacter spp., piperacillin-tazobactam resistant Pseudomonas aeruginosa and carbapenem and colistin resistant Klebsiella pneumoniae. These results can serve as a basis for the development of antimicrobial stewardship strategies in the current setting.

Coronavirus (COVID-19) is a highly infectious disease that has captured the attention of the worldwide public. Modeling of such diseases can be extremely important in the prediction of their impact. While classic, statistical, modeling can provide satisfactory models, it can also fail to comprehend the intricacies contained within the data. In this paper, authors use a publicly available dataset, containing information on infected, recovered, and deceased patients in 406 locations over 51 days (22nd January 2020 to 12th March 2020). This dataset, intended to be a time-series dataset, is transformed into a regression dataset and used in training a multilayer perceptron (MLP) artificial neural network (ANN). The aim of training is to achieve a worldwide model of the maximal number of patients across all locations in each time unit. Hyperparameters of the MLP are varied using a grid search algorithm, with a total of 5376 hyperparameter combinations. Using those combinations, a total of 48384 ANNs are trained (16128 for each patient group-deceased, recovered, and infected), and each model is evaluated using the coefficient of determination ( R 2). Cross-validation is performed using K-fold algorithm with 5-folds. Best models achieved consists of 4 hidden layers with 4 neurons in each of those layers, and use a ReLU activation function, with R 2 scores of 0.98599 for confirmed, 0.99429 for deceased, and 0.97941 for recovered patient models. When cross-validation is performed, these scores drop to 0.94 for confirmed, 0.781 for recovered, and 0.986 for deceased patient models, showing high robustness of the deceased patient model, good robustness for confirmed, and low robustness for recovered patient model., Competing Interests: The authors declare that they have no conflicts of interest—financial or otherwise., (Copyright © 2020 Zlatan Car et al.)

In this paper, the urinary bladder cancer diagnostic method which is based on Multi-Layer Perceptron and Laplacian edge detector is presented. The aim of this paper is to investigate the implementation possibility of a simpler method (Multi-Layer Perceptron) alongside commonly used methods, such as Deep Learning Convolutional Neural Networks, for the urinary bladder cancer detection. The dataset used for this research consisted of 1997 images of bladder cancer and 986 images of non-cancer tissue. The results of the conducted research showed that using Multi-Layer Perceptron trained and tested with images pre-processed with Laplacian edge detector are achieving AUC value up to 0.99. When different image sizes are compared it can be seen that the best results are achieved if 50×50 and 100×100 images were used., (Copyright © 2019 The Authors. Published by Elsevier B.V. All rights reserved.)