Search

Abstract Background Distinguishing between middle ear cholesteatoma and chronic suppurative otitis media (CSOM) is an ongoing challenge. While temporal bone computed tomography (CT) scan is highly accurate for diagnosing middle ear conditions, its specificity in discerning between cholesteatoma and CSOM is only moderate. To address this issue, we utilized trained machine learning models to enhance the specificity of temporal bone CT scan in diagnosing middle ear cholesteatoma. Our database consisted of temporal bone CT scan native images from 122 patients diagnosed with middle ear cholesteatoma and a control group of 115 patients diagnosed with CSOM, with both groups labeled based on surgical findings. We preprocessed the native images to isolate the region of interest and then utilized the Inception V3 convolutional neural network for image embedding into data vectors. Classification was performed using machine learning models including support vector machine (SVM), k-nearest neighbors (k-NN), random forest, and neural network. Statistical metrics employed to interpret the results included classification accuracy, precision, recall, F1 score, confusion matrix, area under the receiver operating characteristic curve (AUC), and FreeViz diagram. Results Our training dataset comprised 5390 images, and the testing dataset included 125 different images. The neural network, k-NN, and SVM models demonstrated significantly higher relevance in terms of classification accuracy, precision, and recall compared to the random forest model. For instance, the F1 scores were 0.974, 0.987, and 0.897, respectively, for the former three models, in contrast to 0.661 for the random forest model. Conclusion The performance metrics of the presented trained machine learning models hold promising prospects as potentially clinically useful aids.

Objective:. To evaluate the feasibility, safety, and effectiveness of a comprehensive regional program, including the Minimally Invasive Recovery and Empowerment Care (MIREC) pathway, that can significantly reduce hospital stays after laparoscopic gastrectomy without increasing adverse events. Background:. Cost-effectiveness and improving patient outcomes are crucial in providing quality gastric cancer care worldwide. Methods:. To compare the outcomes of gastric cancer surgery using 2 different models of care within an integrated healthcare system from February 2012 to March 2023. The primary endpoint was the length of hospital stay. The secondary endpoints were the need for intensive care unit care, emergency room (ER) visits, readmission, reoperation, and death within 30 days after surgery. Results:. There were 553 patients, 167 in the pre-(February 2012–April 2016) and 386 in the post-MIREC period (May 2016–March 2023). Perioperative chemotherapy utilization increased from 31.7% to 76.4% (P < 0.0001). Laparoscopic gastrectomy increased from 17.4% to 97.7% (P < 0.0001). Length of hospitalization decreased from 7 to 2 days (P < 0.0001), with 32.1% and 88% of patients discharged home on postoperative day 1 and postoperative day 2, respectively. When comparing pre- and post-MIREC, intensive care unit utilization (10.8% vs. 2.9%, P < 0.0001), ER visits (34.7% vs. 19.7%, P = 0.0002), and readmission (18.6% vs. 11.1%, P = 0.019) at 30 days were also considerably lower. In addition, more patients received postoperative adjuvant chemotherapy (31.4% to 63.5%, P < 0.0001), and the time between gastrectomy and starting adjuvant chemotherapy was also less (49–41 days; P = 0.002). Conclusion:. This comprehensive regional program, which encompasses regionalization care, laparoscopic approach, modern oncologic care, surgical subspecialization, and the MIREC pathway, can potentially improve gastric cancer surgery outcomes. These benefits include reduced hospital stays and lower complication rates. As such, this program can revolutionize how gastric cancer surgery is delivered, leading to a higher quality of care and increased value to patients.

Objective: Streptococcus pneumoniae (S. pneumoniae) nasopharyngeal carriage has significantly decreased after the generalization of pneumococcal vaccination worldwide. This study sought to investigate changes in S. pneumoniae carriage rates, serotype distribution and penicillin non-susceptibility following the generalization of 10-valent pneumococcal conjugate vaccine. Methods: A prospective study was conducted in Marrakesh, Morocco, between 2017 and 2018, among healthy children attending vaccination centers. We collected nasopharyngeal swabs and questionnaire data for each child. Using univariate logistic regression, we analyzed the association between S. pneumoniae carriage and various risk factors. Comparisons of serotype diversity and penicillin resistance between 2017 and 2018 and the period before introduction of vaccination (2008–2009, n = 660) were performed using Simpson index and the chi-squared test, respectively. Results: During 2017–2018, 515 children aged between 6 and 36 months participated. The S. pneumoniae carriage rate was 43.3%. Looking at the distribution serotypes, the rate of PCV10 serotypes rate was only 9.6%. Among non-vaccine serotypes, an increase in serotypes 6C/6D (22; 14%), 19B/19C (17; 10.8%), and 15B/15C (11; 7%) was observed. A particular increase in serotype diversity was also observed after the generalization of PCV10 (p

Abstract Current sessions of multidisciplinary team meetings (MDMs) have several limitations, including increased costs and duration, as well as limited discussion time for each case. To address these issues, we have developed a computer application called OCTOPUS, which helps manage the patients' list for MDMs. The application allows for the generation of automatic MDM decisions based on predetermined criteria filled in by the patient's doctor and algorithms that comply with the latest oncology guidelines from the National Comprehensive Cancer Network. These decisions must be validated by the MDM faculty members. In cases of nonagreement or complex cases, the application proposes a “face‐to‐face MDM.” The internal mailing system connects all members and allows for the request of a second opinion regarding pathology or imaging results. Initial results suggest that this ergonomic tool provides more flexibility in time management and improved uniformity in selecting cases that would most benefit from face‐to‐face MDMs.

Physical attractiveness has an important and great influence in human social life as it was widely linked to the possession of a variety of positive qualities that makes an individual better than the others, as well as offering many advantages to the individual’s life especially in a society obsessed with beauty and attractiveness. As consequences to the attractiveness influence, people tend to look more and more attractive using makeup or in most of the time plastic surgeries. In parallel to the increased need to plastic surgeries, the need to simplify and show how the face will look like after the surgery is recommended, to plan the procedures, verify the satisfaction of the patient, and reduce the risks during the surgery as well. In this paper, we introduce a novel system to analyze and enhance the attractiveness of 3D faces using a Free Form Deformation technique based on the Bézier function. This system was tested on two 3D face datasets and the experimental results show that the edited 3D faces are more attractive compared to the original faces in terms of respecting the beauty canons which are: facial symmetry, golden ration, neoclassical proportions, and the angular profile.

In meat industry, a non-destructive evaluation and prediction of meat quality attributes is highly required. Artificial vision technology is a powerful and widely used tool for meat quality evaluation because of reliability, reproducibility, non-invasiveness, and non-destructiveness. Machine learning methods are a fundamental and crucial part of artificial vision technology. Their choice is critical in determining successfully the quality of meat. The goal of this paper was to compare the performance of three artificial intelligence-based methods to evaluate the beef meat freshness. In this research, a dataset of beef meat samples images was used to extract the color and texture features. Different methods including the support vector machines (SVM), k-nearest neighbor (KNN), and naïve Bayes (NB) algorithms were applied to determine the freshness of samples. The accuracy rates of KNN, SVM and NB algorithms were obtained about 92.59%, 90.12% and 87.65%, respectively. The results show that the KNN provides the highest classification rates against SVM and NB algorithms. [ABSTRACT FROM AUTHOR]

Traffic sign detection is a crucial aspect of advanced driver assistance systems (ADAS) for academic research and the automotive industry. seeing that accurate and timely detection of traffic signs (TS) is essential for ensuring the safety of driving. However, TS detection methods encounter challenges like slow detection speed and a lack of robustness in complex environments. This paper suggests addressing these limitations by proposing the use of the you only look one version 7 (YOLOv7) network to detect and recognize TS in road scenes. Furthermore, the k-means++ algorithm is used to acquire anchor boxes. Additionally, a tiny version of YOLOv7 is used to take advantage of its real-time and low model size, which are required for real-time hardware implementation. So, we conducted an experiment using our proprietary Morocco dataset. According to the experimental results, YOLOv7 achieves 85% in terms of mean average precision (mAP) at 0.5 for all classes. And YOLOv7-tiny obtains 90% in the same term. Afterward, a recognition system for the prohibitive class using the convolutional neural network (CNN) is trained and integrated inside the YOLOv7 algorithm; its model achieves an accuracy of 99%, which leads to a good specification of the prohibitive sign meaning. [ABSTRACT FROM AUTHOR]

We introduce Sim.DiffProc, an R package for symbolic and numerical computations on scalar and multivariate systems of stochastic differential equations (SDEs). It provides users with a wide range of tools to simulate, estimate, analyze, and visualize the dynamics of these systems in both forms, Itô and Stratonovich. One of Sim.DiffProc key features is to implement the Monte Carlo method for the iterative evaluation and approximation of an interesting quantity at a fixed time on SDEs with parallel computing, on multiple processors on a single machine or a cluster of computers, which is an important tool to improve capacity and speed-up calculations. We also provide an easy-to-use interface for symbolic calculation and numerical approximation of the first and central second-order moments of SDEs (i.e., mean, variance and covariance), by solving a system of ordinary differential equations, which yields insights into the dynamics of stochastic systems. The final result object of Monte Carlo and moment equations can be derived and presented in terms of LATEX math expressions and visualized in terms of LATEX tables. Furthermore, we illustrate various features of the package by proposing a general bivariate nonlinear dynamic system of Haken-Zwanzig, driven by additive, linear and nonlinear multiplicative noises. In addition, we consider the particular case of a scalar SDE driven by three independent Wiener processes. The Monte Carlo simulation thereof is obtained through a transformation to a system of three equations. We also study some important applications of SDEs in different fields.

In analytical systems of Arabic text recognition, segmentation is a critical and decisive stage. In this stage, words after being extracted from the text document are segmented into individual characters to allow the feature extraction and classification. The absence of standard corpus for printed Arabic text does not allow a good and objective comparison between different segmentation systems. In this paper, we propose two contributions. The first one is a multi-font reference corpus of printed Arabic text, in which we grouped all segmentation problems and which can be used as a reference to compare different segmentation systems. The second is a hybrid method for segmentation of printed multi-font Arabic text. The proposed method is based on two of the most known techniques in the field: contour based and Template matching techniques. This method is insensitive to the font variability and the characters overlapping. To evaluate the results of this method, we have studied, implemented and tested other methods in literature by using the proposed corpus. The experimental results show that our method gives better segmentation rates.

Background and Objectives: Streptococcus pneumonia (S. pneumoniae) is one of the most frequent pathogens leading to a variety of clinical manifestations. The effects of S. pneumoniae carriage on acute otitis media (AOM) are poorly studied. The study aimed to assess the serotype’s distribution and antimicrobial susceptibility in children with AOM after the implementation of the pneumococcal conjugate vaccine (PCV) in Morocco. Materials and Methods: We conducted a prospective study of AOM children aged 6 to 36 months who visited pediatric centers in Marrakesh between January to June 2018. Parents were asked to complete a questionnaire and a swab was collected from each child. The S. pneumoniae strains were further identified (Hemolysis, optochin sensitivity, and agglutination test), serogrouped (IMMULEX PNEUMOTEST agglutination test), serotyped (Real time PCR) and tested for antimicrobial susceptibility. Results: The S. pneumoniae carriage rate was 49.7% (87/175). As estimated, non-vaccine serotypes (NVT) were most prevalent (51/63; 81%). The most frequent serotypes were 6C/6D (12.7%), 10 (9.5%), and 19B/19C (9.5%). The S. pneumoniae strains that were isolated showed a diminished susceptibility to penicillin G with a rate of 27.5%. Penicillin non-susceptible pneumococci (PNSP) was mostly associated with NVT. More than 90% of S. pneumoniae isolates were susceptible to chloramphenicol (97.5%), clindamycin (97.5%), erythromycin (97.5%), levofloxacin (97.5%), pristinamycin (97.5%), gentamicin (92.5%), and teicoplanin (92.5%). Conclusion: Important nasopharyngeal carriage prevalence was reported among children with AOM. The study showed that new NVT are emerging, including 6C/6D and 10. Furthermore, susceptibility was significantly higher against all antibiotics tested except for penicillin G and amoxicillin.

BackgroundThere is a growing literature showing that critically ill COVID-19 patients have an increased risk of pulmonary co-infections and superinfections. However, studies in developing countries, especially African countries, are lacking. The objective was to describe the prevalence of bacterial co-infections and superinfections in critically ill adults with severe COVID-19 pneumonia in Morocco, the micro-organisms involved, and the impact of these infections on survival.MethodsThis retrospective study included severe COVID-19 patients admitted to the intensive care unit (ICU) between April 2020 and April 2021. The diagnosis of pulmonary co-infections and superinfections was based on the identification of pathogens from lower respiratory tract samples. Co-infection was defined as the identification of a respiratory pathogen, diagnosed concurrently with SARS-Cov2 pneumonia. Superinfections include hospital-acquired pneumonia (HAP) and ventilator-associated pneumonia (VAP). A multivariate regression analysis was performed to identify factors independently associated with mortality.ResultsData from 155 patients were analyzed. The median age was 68 years [62-72] with 87% of patients being male. A large proportion of patients (68%) received antibiotics before ICU admission. Regarding ventilatory management, the majority of patients (88%) underwent non-invasive ventilation (NIV). Sixty-five patients (42%) were placed under invasive mechanical ventilation, mostly after failure of NIV. The prevalence of co-infections, HAP and VAP was respectively 4%, 12% and 40% (64 VAP/1000 ventilation days). The most isolated pathogens were Enterobacterales for HAP and Acinetobacter sp. for VAP. The proportion of extra-drug resistant (XDR) bacteria was 78% for Acinetobacter sp. and 24% for Enterobacterales. Overall ICU mortality in this cohort was 64.5%. Patients with superinfection showed a higher risk of death (OR = 6.4, 95% CI: 1.8-22; p = 0.004).ConclusionsIn this single-ICU Moroccan COVID-19 cohort, bacterial co-infections were relatively uncommon. Conversely, high rates of superinfections were observed, with an increased frequency of antimicrobial resistance. Patients with superinfections showed a higher risk of death.

Streptococcus pneumoniae (S. pneumoniae) remains one of the most important pathogens causing childhood infections. The spread of antibiotic-resistant bacteria is a leading cause of treatment failure in children. The purpose of this investigation is to report the antibiotic and multidrug resistance (MDR) of S. pneumoniae strains isolated from healthy children throughout the years 2020–2022. Antimicrobial susceptibility testing of S. pneumoniae strains in selected antimicrobials was performed using disk diffusion and E-test methods on bloodMueller–Hinton agar. The antimicrobials tested included oxacillin, amoxicillin, ceftriaxone, norfloxacin, gentamicin, vancomycin, erythromycin, clindamycin, pristinamycin, tetracycline, chloramphenicol, and trimethoprim-sulfamethoxazole. A total of 201 S. pneumoniae strains were isolated from the nasopharynx of healthy children in Marrakesh, Morocco. The highest rate of resistance of S. pneumoniae was found in penicillin (57.2%), followed by tetracycline (20.9%), and erythromycin (17.9%). The rates of resistance to clindamycin, trimethoprim-sulfamethoxazole, and chloramphenicol were 14.9%, 4%, and 1.5%, respectively. All isolates were susceptible to norfloxacin, gentamicin, vancomycin, and pristinamycin. Approximately 17% of all S. pneumoniae strains were resistant to at least three different antibiotic families. This study showed a low rate of antibiotics resistance among nasopharyngeal S. pneumoniae strains, and it is thus essential to monitor S. pneumoniae susceptibility in healthy children.

Background: Parvovirus B19 (B19V) infection is ever-present and contagious. It is acquired during childhood and adolescence, but can occur at any age. B19V infection occurs in endemic epidemic mode in temperate zones in winter and spring. B19V infections, although often asymptomatic in pregnant women, can be responsible for hydrop fetalis, fetal anemia, and death in utero. This study will evaluate the seroprevalence of immunoglobulin G (IgG) antiparvovirus in pregnant women in Marrakesh city in Morocco, and to find out the possible risk factors associated with B19V infections. Methods: We randomly selected 100 pregnant women from the Zerktouni hospital in Marrakesh. Socio-demographic characteristics and background were collected using a questionnaire. Serologic tests were carried out by searching for immunoglobulin G antibodies via the ParvovirusVirclia® IgG Chemiluminescencemonotest kits (Vircell Microbiologist, Granada, Spain) at the Bacteriology-Virology laboratory of the Avicenna Military Hospital in Marrakesh. Results: The median age of study participants was 27 (interquartile range (IQR): 17–43) years. Of 100 pregnant women 8%, 38% and 54% were in the first, second and third trimester respectively. The majority 96% of women were from urban areas. Nineteen percent (19%) of them had a history of spontaneous abortion. Of 100 pregnant women, the overall prevalence of IgG was 51 (51%). The average age of participants with positive serology was 26.45 years, and the mean age of those with negative serology was 28.98 years. The immunity against the virus was higher in young pregnant women. Twenty five (25%) women tested positive for B19V antibodies in the third trimester of pregnancy, implying immunity for the virus. The results of logistic regression showed insignificant association between the prevalence of B19V IgG antibodies and the demographic and obstetrical factors except for the having a child under 6 years factor (χ2 = 12.33, p = 0.001). Conclusions: Infection with B19V remains important in pregnant women in our region and virological diagnosis must be sought before any suggestive context.