Ellis-van Creveld syndrome presenting with ruptured hemorrhagic cyst of right ovary: A rare clinical entity Authors : Bhatta Sunil1, Awasthi Pusp Raj2, Pandit Sukriti2, Paudel Pratigya2, Bist Omkar3.1-Department of Anesthesia and Critical Care, Nisarga Hospital and Research Center Pvt. Ltd.Email:bhattasunil26@gmail.com(Corresponding author)2-Department of Pediatrics and adolescent medicine, Nisarga Hospital and Research Center Pvt. Ltd.3-Department of Orthopedic surgery, Nisarga Hospital and Research Center Pvt. Ltd.Data availability statement : Data described to support the findings is openly accessible in the article.

Oral Erythema Multiforme attributed to Herpes Simplex Virus: A less recognized variantSantosh Dharel1, Bandana Koirala1, Mamta Dali11Department of Pedodontics and Preventive Dentistry, College of Dental Surgery, B.P. Koirala Institute of Health Sciences, Dharan, Koshi Province, Nepal.Correspondence: Santosh Dharel, Department of Pedodontics and Preventive Dentistry, College of Dental Surgery, B.P. Koirala Institute of Health Sciences, Dharan, Koshi Province, Nepal.E-mail: drdharelsantosh@gmail.com

A document by Muhammad Hanif. Click on the document to view its contents.

Data assimilation (DA) reconstructs and forecasts the dynamics of geophysical processes based on available observations and on physical a priori. Recently, the hybridization of DA and deep learning has opened new perspectives to address model-data interactions. In this paper, we investigate its potential contribution to the analysis of a chaotic oceanic phenomenon: an idealized model representing the centennial to millennial variability of the North Atlantic ocean circulation during the last glacial period. The implemented neural approach – 4DVarNet – yields large relative improvements over a classical variational DA method on the reconstruction of the regime shifts of the Atlantic Meridional Overturning Circulation (AMOC). These gains are even more significant when the density of observations decreases. The results also exhibit that the explicit exploitation of the a priori dynamical model does not necessarily lead to the best performance compared to a data-driven model. Additionally, we compare four different sampling strategies to assess the impact of the observations on the capture of the unstable phases of the AMOC. We highlight the gain of regular over random sampling strategies, reaching an error of reconstruction below 2% with a sampling period of 100 years. The error on the reconstruction of regime shifts can even be divided by 5 when acquiring clusters of three consecutive observations, sometimes more suited in an operational framework. This study on an idealised, nonetheless complex, physical model suggests that neural approaches trained on observations wisely acquired could improve the monitoring of regime shifts in the context of climate change.

Predicting software defects can improve software assurance reliability and reduce development costs. Traditional predictions usually lack precision. The early detection of fault-prone modules helps software project managers allocate developers' limited time for testing the defect-prone modules more intensively. Traditional methods for predicting software defects often lack precision, highlighting the need for enhanced techniques. The proposed solution introduces an ensemble learning algorithm based on clustering for software defect prediction, aiming to handle imbalanced datasets and manage redundant features. The method incorporates clustering and oversampling for data preparation, followed by cost-sensitive feature selection and ensemble learning for improved classification. By employing clustering to group similar data and addressing imbalanced datasets through K-member fuzzy clustering algorithms, the strategy enhances the accuracy of defect prediction. The optimization stage involves selecting the best classifier, features for each cluster, and their hyper-parameters using the NSGA-II algorithm. Experiments conducted on real-world datasets demonstrate better performance of the suggested approach in contrast to other established approaches in the software defect detection literature.

With the growing recognition of the unique advantages of reinforcement learning and genetic algorithms in addressing combinatorial optimization problems, this study aims to integrate these two methods to collectively tackle the classic combinatorial optimization challenge of the Traveling Salesman Problem (TSP). The Traveling Salesman Problem (TSP) stands as a quintessential combinatorial optimization challenge, tasked with determining the shortest path among designated cities. This paper introduces an innovative approach by amalgamating reinforcement learning’s path selection prowess with genetic algorithms’ global search strategy, aiming to uncover superior solutions in TSP. Specifically, the experiment employs a dual Q-learning algorithm within reinforcement learning to identify multiple optimal paths, serving as progenitors for the genetic algorithm to further enhance performance. The paper meticulously outlines the problem modeling process, elucidating TSP instance definitions, descriptions, and precise objective function definitions. Experimental findings underscore the substantial enhancements achievable in TSP optimization through this comprehensive approach, offering a fresh perspective and methodology for tackling combinatorial optimization challenges.

Aims: The purpose of this study is to establish a novel diagnosis system in early acute coronary syndrome (ACS) using Probe Electrospray Ionization-Mass Spectrometry (PESI-MS) and machine learning (ML) and to validate the diagnostic accuracy. Methods: Total 32 serum samples derived of 16 ACS patients and 16 control patients were analyzed by PESI-MS. The acquired mass spectrum dataset was subsequently analyzed by partial least squares (PLS) regression to find the relationship between two groups. Support vector machine (SVM), a method of machine learning, was applied on the dataset to construct the diagnostic algorithm. Results: Control and ACS groups were separated into the two clusters in PLS plot, indicating ACS patients differed from the control in the profile of serum composition obtained by PESI-MS. The sensitivity, specificity and accuracy of our diagnostic system were all 93.8%, and the area under the receiver operating characteristic curve showed 0.965 (95%CI: 0.84-1). Conclusion: The PESI-MS and ML-based diagnosis system is likely an optimal solution to assist physicians in ACS diagnosis with its remarkably predictive accuracy.

Background: Multiple myeloma (MM) has different complications, including renal failure, anemia, infections, metabolic complications, and skeletal problems. Hypercalcemia is the most common metabolic complication, and the presence of hypercalcemia indicates worse outcomes. Aims: The study aims to examine outcomes such as hospitalization costs, length of stay, survival rates, and the incidence of complications of hypercalcemia in multiple myeloma patients admitted in the United States from 2017 to 2020. Methods: We performed a retrospective analysis using the National Inpatient Sample database to determine the incidence of hypercalcemia in patients admitted to United States hospitals from 2017 to 2020. Univariate and multivariate logistic regression were used to calculate the odds ratio. We used STATA software 17 to perform the analysis. Results: We found that the total number of patients with MM was 437799, out of which 8.6% had hypercalcemia. The mean age of the patients was 69 years, and hypercalcemia was found to be more common in males (55%) than females (45%). The presence of hypercalcemia was also associated with increased mortality (adjusted odds ratio 1.3, p-value 0.00). It was also seen that MM patients who had hypercalcemia had a higher risk of complications, including acute kidney injury (OR 3, p<0.05), hyperkalemia (OR 1.8, p-value <0.05), metabolic acidosis (1.4, p-value <0.05), spinal cord compression (OR 0.9, p-value >0.05), increased length of stay (OR 3, p-value <0.05), and higher cost of hospitalizations (p-value <0.05). Conclusion: The data is also limited to the demographic characteristics, impact, and outcomes of hypercalcemia on patients with MM. This study contributes valuable insights into the clinical implications of hypercalcemia in patients with multiple myeloma (MM). It fills existing gaps in the literature by utilizing a large population-based dataset.

This paper is dedicated to establishing regularity criteria for the 3D generalized Navier-Stokes equations that include a nonlinear damping term. Our primary focus is on examining how the damping term influences these regularity criteria and contributes to the global existence of solutions.

Thymic neuroendocrine tumors are rare malignant tumors with neuroendocrine functions located in the anterior mediastinum thymic region. They exhibit a high degree of malignancy and can early invade surrounding fat,pericardium, pleura, major blood vessels, and lungs,posing a significant risk of recurrence.Here, we report a case of recurrent thymic cancer treated with complete surgical resection, replacement of the innominate vein, superior vena cava formation, and iodine ion insertion.A 51-year-old male diagnosed with stage lllA malignant thymoma in November 2021, accompanied by lymph node metastasis,involving the peripheral left lung.The patient underwent six cycles of adjuvant immunotherapy with pembrolizumab and cisplatin plus etoposide, along with one course of radiotherapy postoperatively.Subsequently, the patient received regular immunotherapy and follow-up at our hospital. In October 2023,chest CT revealed tumor recurrence, with infiltration into the pericardium, bilateral innominate veins, superior vena cava, and brachiocephalic artery.Subsequently, the patient underwent a midline thoracotomy for extensive resection of recurrent thymic tumor,enlargement of pericardial resection, left innominate vein-to-right atrial artificial grafting,superior vena cava formation,and iodine-125radioisotope brachytherapy.Aggressive surgical intervention combined with adjuvant therapy is an essential treatment modality for locally advanced thymic cancer involving the superior vena cava and surrounding blood vessels.

The Chinese Pangolin (Manis pentadactyla) is typically conserved as a flagship species, but its ecological functions, particularly regarding avian interactions, remain underexplored. Using infrared camera traps, this study investigated the ecological interactions between the Chinese Pangolin and bird species. Results revealed higher bird species diversity and biodiversity indices in the experimental group compared to the control group, especially among non-Galliformes birds. The Chinese Pangolin exhibited nocturnal activity, while birds were active during the day, indicating temporal segregation. Among the observed bird species, none exhibited burrow-entry behavior, but nine demonstrated foraging behavior, with a significantly higher foraging ratio among non-Galliformes birds. This study provides the first evidence of non-Galliformes birds being attracted to soil mounds created by Chinese Pangolin burrows, suggesting the pangolin’s potential role as a keystone species in the local ecosystem. Further research is necessary to explore the mechanisms of this attraction.

With the renewable energy continuously access to the microgrid, the microgrid itself does not have the disadvantages of the inertia of the synchronous generator in the traditional grid is increasingly apparent, for which the generalized droop control (GDC) strategy is proposed. In the normal operation of the system, GDC has the advantages of large inertia and small active power overshoot, but when subjected to external frequency perturbations, the grid-supporting inverter with large virtual inertia is prone to large transient active power overshoot and oscillation. To address this problem, the article establishes small-signal models under different perturbations based on the GDC compared with the virtual synchronous generator (VSG) and further proposes two adaptive inertia control strategies: GDC adaptive inertia (GDCAI) and adaptive inertia for operation mode switching (AIOMS). By adjusting the virtual inertia appropriately, the rate of change of frequency (RoCoF) is maintained in the set range while improving the transient performance of the system, the methods of reduce-order of the system model and control parameter design is given, to reduce the frequency fluctuation while greatly reducing the active power overshoot and improving the response speed of the system. The effectiveness of the two control strategies is verified by MATLAB/Simulink simulation and StarSim hardware-in-the-loop (HIL) experiment.

Entropically Secure Encryption (ESE) offers unconditional security with shorter keys compared to the One-Time Pad. In this paper, we present the first implementation of ESE for bulk encryption. The main computational bottleneck for bulk ESE is a multiplication in a very large finite field. This involves multiplication of polynomials followed by modular reduction. We have implemented polynomial multiplication based on the gf2x library, with some modifications that avoid inputs of vastly different length, thus improving speed. Additionally, we have implemented a recently proposed efficient reduction algorithm that works for any polynomial degree. We investigate two use cases: X-ray images of patients and human genome data. We conduct entropy estimation using compression methods whose results determine the key lengths required for ESE. We report running times for all steps of the encryption. We discuss the potential of ESE to be used in conjunction with Quantum Key Distribution (QKD), in order to achieve full information-theoretic security of QKD-protected links for these use cases.

To achieve efficient and rapid optimization for high torque and low noise permanent magnet synchronous motors, this paper proposes a multi-layer surrogate model-based optimization method for IPMSM (Interior Permanent Magnet Synchronous Motor) based on sensitivity classification of structural parameters. Firstly, using a hybrid model of “FEM + Unit Force Wave Response,” the key order electromagnetic forces causing electromagnetic noise in various operating conditions of the motor are obtained. Their amplitudes, along with the motor’s average output torque and torque ripple, are taken as optimization objectives. By analyzing the sensitivity of structural parameters using the random forest algorithm, the selection and classification of structural parameters are achieved. A hierarchical optimization is then performed using a combination of a multi-island genetic algorithm, a multi-objective particle swarm optimization algorithm, and parameterized scanning. Compared with traditional multi-field coupled optimization methods, this method saves computational resources while reducing calculation time by 54.9%. After optimization, the average output torque is increased by 34.6% compared to before optimization, the amplitude of key order electromagnetic forces of the motor is reduced by 13.7%, and torque ripple is reduced by 67.8%.

In this study, a novel array electrospinning collector was devised to generate two distinct regenerated silk fibroin (SF) fibrous membranes: ordered and disordered. Leveraging electrostatic forces during the electrospinning process allowed precise control over the orientation of SF fiber, resulting in the creation of the membranes comprising both aligned and randomly arranged fiber layers. This innovative approach resulted in the development of large-area membranes featuring exceptional stability due to their alternating patterned structure, achievable through expansion using the collector. The study delved into exploring the potential of these membranes in augmenting wound healing efficiency. Conducting in vitro toxicity assays with Adipose Tissue-Derived Mesenchymal Stem Cells (AD-MSCs) and Normal Human Dermal Fibroblasts (NHDFs) confirmed the biocompatibility of the SF membranes. Notably, AD-MSCs exhibited the ability to discern distinct microenvironments established by electrospun SF membranes, translating this recognition into a conditioned medium (CM). Evaluations focused on the paracrine effects of AD-MSCs in promoting migration via CM, drawing comparisons with secretions from NHDFs. The study employed two distinct strategies: firstly, the utilization of paracrine secretion by AD-MSCs to encourages cellular migration, particularly on SF flat membranes where their secretion enhanced cellular migration while elevating the protein concentration of the CMs. Secondly, the exploitation of physical cues from SF electrospun membranes to guide and augment cell recruitment, thereby enhancing wound healing. Observations centered on monitoring cell migration and documenting the influence of SF materials on inducing morphological changes in both AD-MSCs and NHDFs., The ordered membrane, in particular, exhibited pronounced effectiveness in guiding directional cell migration. This research underscores the revelation that customizable microenvironments facilitated by SF membranes optimize the paracrine products of MSCs and offer valuable physical cues, presenting novel prospects for enhancing wound healing efficiency.

This study investigates miRNA impact on lung, colorectal, and epithelial cancers, emphasizing Wnt3’s role in breast tumor growth through WNT signaling and its influence on mammary stem cells. WNT pathway inactivation induces drug-insensitive, quiescent states in breast cancer stem cells, resulting in resistance to multiple drugs. Tamoxifen-resistant breast carcinoma cells activate both canonical and noncanonical WNT signaling, with Wnt3a enhancing tamoxifen resistance in ER+ carcinoma cells. The study also explores breast cancer immunotherapy, highlighting immune checkpoint blockade targeting PD-1/PD-L1 and CTLA-4 as promising avenues. Additionally, the study explores the NOTCH signaling pathways impact on cancer proliferation, apoptosis, invasion and metastasis. Elevated NOTCH receptor and ligand expression particularly in aggressive triple negative breast cancer correlate with poorer treatment outcome, serving as a predictor for adverse results in breast tumors. The review discusses the relevance of Notch signaling in therapy resistance and breast cancer recurrence. The article encapsulates therapeutic advancements targeting the Notch signaling pathway, weighing merits and demerits in the context of breast cancer treatment. Our study provides a comprehensive understanding of the complex interactions within the WNT and Notch signaling pathways in breast cancer, shedding light on potential therapeutic targets and strategies for personalized treatment. This research significantly contributes to the current body of knowledge, offering promise for improved outcomes in breast cancer patients. The findings underscore the importance of WNT and Notch signaling modulation in developing effective therapeutic interventions for breast cancer.

Studies of the utilization of different landscape types by bird communities can provide insights into the relationship between landscape types and bird strike risks, which is important for preventing bird strikes at airports. In this study, we conducted a survey of bird communities in four different landscapes (urban area, farmland, woodland, and water) using the line transect sampling method in and around Lincang Boshang Airport in Yunnan Province, China, from October 2019 to July 2020. We surveyed a total of 17 transects. We used bird species diversity indices including species richness, Shannon-Wiener diversity index, Simpson diversity index, and evenness index to characterize the species diversity of bird communities. We also used estimates of functional and phylogenetic diversity to elucidate differences in bird community diversity among the four landscapes during the four seasons. We also calculated the phylogenetic distance, mean pairwise distance, and mean nearest taxon distance to characterize the phylogenetic structure of bird communities, explore mechanisms of community assembly, and quantify correlations among different diversity indices. A total of 151 wild bird species belonging to 52 families and 15 orders were recorded in this study. Significant differences were observed in both phylogenetic and functional diversity among the different landscapes; functional richness was highest for woodland and lowest for water. The phylogenetic distance was highest in woodland and lowest in the urban area. Standardized effect size analysis indicated that the assembly of bird communities in the four landscapes (farmland, urban area, woodland, and water) was primarily affected by landscape filtering. Our findings suggest that understanding the diversity of bird communities and their relationships with landscape factors can aid the management of bird communities around airports and environmental governance.

Sand flies infect more than one million people annually with Leishmania parasites and other bacterial and viral pathogens. Progress in understanding sand fly adaptations to xenobiotics, such as insecticides has been hampered by the limited availability of genomic resources. Here we sequenced, assembled and annotated the transcriptomes of 11 phlebotomine sand fly species, and used them to generate new evolutionary insights pertaining to their adaptations to xenobiotics, including those contributing to insecticide resistance. We annotated and performed large-scale phylogenetic comparisons of more than 2,700 sand fly genes from the five major detoxification enzyme families, Cytochrome P450s (CYPs), Glutathione-S-Transferases (GSTs), UDP-Glycosyltransferases (UGTs), Carboxyl/Cholinesterases (CCEs) and ATP-Binding Cassette (ABC) Transporters. This comparative approach uncovered that sand flies have evolved diverse CYP and GST repertoires, with striking expansions in gene groups encoding for potential xenobiotic metabolizers. Furthermore, we identified conserved orthologs for two primary insecticide targets, acetylcholinesterase-1 (Ace1) and Voltage Gated Sodium Channel (VGSC). This work provides novel biological insights and valuable genomic resources for enabling sand fly research in xenobiotic adaptation and insecticide resistance.

The pandemic generated by COVID-19 has affected the way of life of citizens of all countries of the world and in all areas of society. Although the health crisis has been global, the different contexts and the different national responses implemented by governments have had heterogeneous results. The objective of this work is to find evidence about the characteristics of the countries associated with a better performance in the scene of Pandemia, similar to COVID-19. In particular, we analyze to what extent the economic freedom and good governance of countries can condition an effective and efficient management of the pandemic. Results The results show a significant influence of Economic Freedom on the Outcomes of the COVID-19: COVID-19 Cases, COVID-19 Deaths, Cases Fataly Ratio and Efficient Covid-19. Such a linear relationship is moderate by The Good Government. In countries with high score in Good Governance, higher economic freedom scores is associated with lower rates of infection by COVID-19, lower rates of COVID-19 deaths, minor ratios of deaths on a case case and greater efficiency in the management of pandemic. Conclusions The present research concludes that economic freedom has a positive effect on the control of the Covid-19 pandemic. In addition, this effect occurs with greater intensity in situations of high Good Government. Scarce economic freedom and the worst governance can make the Covid-19 pandemic be controlled and that its effects are very worse.

Objective Throughout the COVID-19 pandemic, Rhinovirus (RV) remained notable persistence, maintaining its presence while other seasonal respiratory viruses were largely suppressed by pandemic restrictions during national lockdowns. This research explores the epidemiological dynamics of RV infections among pediatric populations on Hainan Island, China, specifically focusing on the impact before and after the zero-COVID policy was lifted. Methods From January 2021 to December 2023, 19,680 samples were collected from pediatric patients hospitalized with acute lower respiratory tract infections (ARTIs) at the Hainan Maternal and Child Health Hospital. The infection of RV was detected by tNGS. RV species and subtypes were identified in 32 RV-positive samples representing diverse time points by analyzing the VP4/VP2 partial regions. Results Among the 19,680 pediatric inpatients with ARTIs analyzed, 21.55% were found to be positive for RV infection, with notable peaks observed in April 2021 and November 2022. A gradual annual decline in RV infections was observed, alongside a seasonal pattern of higher prevalence during the colder months. The highest proportion of RV infections was observed in the 0-1 year age group. Phylogenetic analysis revealed 23 distinct RV subtypes, with a shift in dominance from RV-A to RV-C in 2022, suggesting evolving RV dynamics. Conclusions The research emphasizes the necessity for ongoing surveillance and targeted management, particularly for populations highly susceptible to severe illnesses caused by RV infections.

A knowledge graph (KG) is a multidirectional labelled graph used for the graphical representation of knowledge where each node represents an entity, and the edge connecting the two nodes represents a relationship. There has been a rise in the popularity of using KG in information retrieval, recommender system, dialogue system, and question-answering system (QAS). The QAS can be either over structured data or unstructured data. This article studies the existing techniques for question-answering systems over KG (KGQA). We collect more than 30 articles on the question-answering system over a knowledge graph. We give a brief introduction to KG and QAS. Further, we discuss challenges, datasets and evaluation metrics used to evaluate techniques. Finally, we conclude the article by discussing some open research aspects, highlighting factors of the low-resource language for KGQA task and remarks on existing systems.

Background: In Europe, Omalizumab (anti-IgE) is indicated for the treatment of moderate/severe asthma, but not for IgE-mediated food allergy (FA). Objective: We prospectively assessed the impact of Omalizumab for efficacy, safety, and quality of life (FA-QoL) in patients with moderate/severe asthma and history of anaphylaxis to peanut, tree nuts, fish, egg, milk, and/or wheat. Methods: Food-allergic children (6-18yrs) with moderate/severe asthma underwent oral food challenges (OFCs) to establish the threshold of reaction to the culprit food(s) at baseline (T0) and at four-month intervals (T1, T2, T3) during their first year of treatment with Omalizumab. We recorded the number and severity of food-allergic reactions, Asthma Control Test (ACT), FA-QoL, and total IgE. Results: In 65 patients allergic to 107 foods, the No Observed Adverse Events Level (NOAEL) at T1 increased: 243- and 488-fold for raw and baked milk, respectively; 172 and 134-fold for raw and baked egg; 245-fold for hazelnut; 55-fold for peanut; 31-fold for wheat, and 10-fold for fish. Full tolerance was achieved in 66.4% of OFCs at T1, 58.3% at T2, and 75% at T3. Ninety-five foods were liberalized ad libitum in the diet of 55 patients; the remaining 12 were introduced by 10 patients at least in traces. Throughout the study, 40/65 children got a free diet. ACT increased from 17 (Q1-Q3:15-17) to 23.6 (Q1-Q3:23-25). The FA-QoL score in children ≤ 12 years decreased from 4.63±0.74 to 2.02±1.13, in adolescents from 4.68±0.92 to 1.90±1.50. Conclusions: Omalizumab allows safe reintroduction of allergenic foods. Trial registration number: ClinicalTrials.gov, NCT06316414

The HIV-1 protease is critical for the process of viral maturation, making it an attractive target for antiretroviral therapy. As such it is one of the most well characterised proteins in the Protein Data Bank. There is some evidence to suggest that the HIV-1 protease is capable of accommodating small molecule fragments at several locations on its surface outside of the active site; namely, the Exo site, flap-top pocket, face site, and Eye site. However, some pockets on the surface of proteins remain unformed in the apo structure and these “cryptic sites” have also been known to accommodate small molecule ligands. To date, no cryptic sites have been identified in the structure of the HIV-1 protease. Here, we characterise a novel cryptic cantilever pocket on the surface of the HIV-1 protease through mixed-solvent molecular dynamics simulations using several probes: acetone, benzene, imidazole, isopropanol, and phenol. Structure-based analysis of the cryptic cantilever pocket suggest that the pocket may be amenable to ligand binding. Interestingly, we note that several homologous retroviral proteases exhibit evolutionarily conserved dynamics in the cantilever region and possess a conserved pocket in the cantilever region. Immobilisation of the cantilever region of the HIV-1 protease via disulphide cross-linking resulted in curling-in of the flap tips and the propensity for the protease to adopt a semi-open flap conformation. Together these results suggest that the mobility of the cantilever region plays a key role in the global dynamics of retroviral proteases. Moreover, the cryptic cantilever pocket of the HIV protease may represent an interesting target for future fragment-based ligand screening campaigns.

Stroke is a high-risk neurological condition caused by blockages or bleeding in the brain, leading to death or disability. This study proposes a model to address the imbalance in limited patient data.The proposed model uses the MissForest method, a Random Forest Regression algorithm, to complete missing data and an artificial immune system algorithm whose parameters are updated using the Firefly algorithm to stabilize the data. The One-Sided Selection model is used to improve the performance of the minority class.The model was evaluated in two experiments, one using all features and the other selecting the best features using the Artificial Bee Colony (ABC) algorithm. The models were trained using six different classification algorithms: CatBoost, Light Gradient Boosting Machine (LightGBMBoost), Gradient Boosting (GB), Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), and Logistic Regression (LR). The results were presented using performance metrics. When trained using all features, the model achieved an accuracy of 77%, specificity of 44%, and sensitivity of 77%. When trained using the best features selected by the ABC algorithm, the model achieved an accuracy of 81%, specificity of 61%, and sensitivity of 81%. Compared to previous studies, the proposed model was effective in both experiments.