جامعة المعرفة
المصدر المعتمد للمعلومات البحثية والمخرجات هو قاعدة بيانات سكوبس (Elsevier Scopus) مع تدقيق بيانات الباحثين من عمادة البحث العلمي.

Research outputs

المخرجات البحثية

مقالات ومراجعات وأوراق مؤتمرات وفصول كتب، مفهرسة برقم DOI ومربوطة بباحثي الجامعة.

مقالوصول مفتوح20234استشهاد· Semantic Scholar

Adaptive Rectified Linear Unit (Arelu) for Classification Problems to Solve Dying Problem in Deep Learning

International Journal of Advanced Computer Science and Applications · مجلد 14 (2)

A convolutional neural network (CNN) is a subset of machine learning as well as one of the different types of artificial neural networks that are used for different applications and data types. Activation functions (AFs) are used in this type of network to determine whether or not its neurons are activated. One non-linear AF named as Rectified Linear Units (ReLU) which involves a simple mathematical operations and it gives better performance. It avoids rectifying vanishing gradient problem that inherents older AFs like tanh and sigmoid. Additionally, it has less computational cost. Despite these advantages, it suffers from a problem called Dying problem. Several modifications have been appeared to address this problem, for example; Leaky ReLU (LReLU). The main concept of our algorithm is to improve the current LReLU activation functions in mitigating the dying problem on deep learning by using the readjustment of values (changing and decreasing value) of the loss function or cost function while number of epochs are increased. The model was trained on the MNIST dataset with 20 epochs and achieved lowest misclassification rate by 1.2%. While optimizing our proposed methods, we received comparatively better results in terms of simplicity, low computational cost, and with no hyperparameters.

leaky ReLUactivation functionsconvolutional neural networksMNIST classification
مقالوصول مفتوح20234استشهاد· Semantic Scholar

Predicting Functional Recovery of Stroke Rehabilitation Using a Deep Learning Technique

Journal of Disability Research · مجلد 2 (3)

Stroke survivors have access to a wide range of drug and non-drug treatments for the resulting physiological and functional problems. However, comprehensive therapies typically fail to meet the demands of a large percentage of patients. The recent clinical studies to improve protocol scientific evidence have resulted in a new development phase for rehabilitation medicine. Stroke rehabilitation supports individuals to lead a normal life. It assists the physicians in offering an effective environment to the patients. The evaluation of a patient’s progress in rehabilitation is based on the clinician’s subjective observations and the patient’s self-reported data. Deep learning techniques offer novel forms of individualized treatment. Nonetheless, missing data is one of the crucial factors that reduces the performance of data classification techniques. Thus, there is a demand for functional recovery prediction models for supporting stroke patients (SPs) to improve their quality of life. In this study, the researchers intend to build a framework for predicting functional outcomes using the electronic health record data of SPs. An attention-based bidirectional gated recurrent unit is used for developing the data imputation model. In addition, a shallow-convolutional neural network is employed for predicting the functional outcomes based on the modified Barthel Index. Data from 356 SPs were utilized for evaluating the performance of the proposed framework with the benchmark metrics and baseline models. The findings reveal that the proposed framework outperforms the state-of-the-art classification by achieving an average accuracy, precision, recall, F1-measure, specificity, and sensitivity of 98.18, 97.48, 98, 97.74, 96.74, and 97.24, respectively. The proposed framework can be implemented in real time to support SPs.

stroke rehabilitationfunctional recovery predictionelectronic health recordsmissing data imputation
مقالوصول مفتوح20234استشهاد· Semantic Scholar

The Impact of Recombinant Human Erythropoietin Administration in Critically ill COVID-19 Patients: A Multicenter Cohort Study

Clinical and Applied Thrombosis/Hemostasis · مجلد 29 · 10760296231218216-10760296231218216

The use of erythropoietin-stimulating agents (ESAs) as adjunctive therapy in critically ill patients with COVID-19 may have a potential benefit. This study aims to evaluate the effect of ESAs on the clinical outcomes of critically ill COVID-19 patients. A multicenter, retrospective cohort study was conducted from 01-03-2020 to 31-07-2021. We included adult patients who were ≥ 18 years old with a confirmed diagnosis of COVID-19 infection and admitted to intensive care units (ICUs). Patients were categorized depending on ESAs administration during their ICU stay. The primary endpoint was the length of stay; other endpoints were considered secondary. After propensity score matching (1:3), the overall included patients were 120. Among those, 30 patients received ESAs. A longer duration of ICU and hospital stay was observed in the ESA group (beta coefficient: 0.64; 95% CI: 0.31-0.97; P = < .01, beta coefficient: 0.41; 95% CI: 0.12-0.69; P = < .01, respectively). In addition, the ESA group's ventilator-free days (VFDs) were significantly shorter than the control group. Moreover, patients who received ESAs have higher odds of liver injury and infections during ICU stay than the control group. The use of ESAs in COVID-19 critically ill patients was associated with longer hospital and ICU stays, with no survival benefits but linked with lower VFDs.

recombinant human erythropoietinerythropoiesis-stimulating agentsCOVID-19 pandemiccritically ill patients
مقالوصول مغلق20233استشهاد· Semantic Scholar

Tree Seed Algorithm-based Feature Selection with Optimal Deep Learning Model for Supply Chain Management

Fluctuation and Noise Letters · مجلد 23 (02)

In recent days, supply chain and logistic industries have been going through a transformational wave of automation and digitization. Supply chain management (SCM) can involve machine learning (ML) abilities and prediction models to ensure that the demands are satisfied at a minimum cost. Intelligent models can be developed to determine whether adequate inventory is accessible to encounter the predictable rise in demands, and if not, the system spontaneously begins to adjust the orders with suppliers to source the raw materials for resolving the predicted future high demand. The conventional ways of SCM can be replaced by the design of recent artificial intelligence (AI) and deep learning (DL) techniques. By this motivation, this research presents a tree seed algorithm-based feature selection with optimum DL technique for supply chain management (TSA-ODLSCM). The proposed TSA-ODLSCM model involves the design of a feature subset selection approach using a tree search algorithm (TSA) algorithm. Besides, a new convolutional neural network with fuzzy cognitive maps (CNN-FCM) technique is designed for the classification process. Moreover, optimal parameter tuning of the CNN-FCM model was performed using the Henry gas solubility optimization (HGSO) technique. To exhibit the improved performance of the TSA-ODLSCM approach, a huge range of simulations were executed and outcomes were examined below several aspects. The experimental validation reported an enhanced 96.52% outcome of the TSA-ODLSCM approach over other methods.

supply chain managementfeature selectiontree seed algorithmconvolutional neural networks
مقالوصول مفتوح20233استشهاد· Semantic Scholar

The Awareness of Sudden Infant Death Among Saudi Arabian Women in 2023

Cureus · مجلد 15 (12) · e50164-e50164

Background Sudden infant death syndrome (SIDS) refers to the unexpected and unexplained death of a child under one year old. The pathogenesis of SIDS remains unclear. However, certain factors such as the child's sleeping position, sleeping on a soft mattress, and maternal smoking have been suggested to contribute to its occurrence. The objective of this study was to evaluate the level of awareness of SIDS among Saudi Arabian women in 2023. Methodology A cross-sectional study was conducted among 300 mothers in Saudi Arabia, over a period of three months, from June to August 2023, using an online questionnaire to gather socio-demographic information from mothers of infants younger than one year old in Saudi Arabia, the sleeping practices of their infants, and their knowledge about SIDS risk factors. Data were coded using the Statistical Package for Social Sciences (SPSS) (IBM SPSS Statistics, Armonk, NY), and statistical significance tests were employed for data analysis. A p-value of <0.05 was considered significant. Results Among the 277 participating mothers, 44% were 31-40 years old, 93% were Saudi, 60% were employed, 65% were nonsmokers, and 64% placed babies in a supine position for sleep. About 37% of mothers used a duvet for bedding during summer, compared to 66% who used a duvet during winter, and 81% utilized a soft mattress cover in their children's beds. Additionally, 67% of mothers reported that their children used a pacifier while sleeping. More than half (54%) of mothers were aware of SIDS with media as their primary source of information. Among those under 21 years old, 50% demonstrated a high level of awareness, compared to 36% of those aged over 50. Conclusion Most women in this study were found to be unaware of SIDS. Among those who were aware, the media was the primary source of information. Higher educational attainment was associated with better understanding.

sudden infant death syndromematernal knowledgeinfant sleep practicessupine sleeping
مقالوصول مفتوح20233استشهاد· Semantic Scholar

Mechanistic QSAR analysis to predict the binding affinity of diverse heterocycles as selective cannabinoid 2 receptor inhibitor

Journal of Taibah University for Science · مجلد 17 (1)

CB2R are fascinating targets for neuropathic pain and mood disorders because of their improved biological characteristics. Experimental data on 1296 cannabinoid-2 receptor inhibitors with different structural properties were used to develop a QSAR model following OECD guidelines. This study selected the best-predicted model (80:20 splitting ratio) with fitting parameters, such as R2:0.78; F:623.6, Internal validation parameters, such as Q2Loo:0.78; CCCcv: 0.87 and external validation parameters, such as R2ext:0.77; Q2F1:0.7730; Q2F2:0.7730; Q2F3:0.76; CCCext:0.87. Following this, another QSAR model was developed by using a 50:50 split ratio for thetraining and the prediction sets, which were then swapped to evaluate the robustness of the built QSAR model by the 50:50 ratio, which also gives a deeper understanding of the chemical space. In addition, we have confirmed the QSAR result with pharmacophore modelling, and supported by molecular docking, MD simulation, MMGBSA and ADME studies. Thus, this work may enable cannabinoid 2 receptor inhibsitor development.

cannabinoid 2 receptorheterocyclic compoundsbinding affinity predictionQSAR models
مقالوصول مفتوح20233استشهاد· Semantic Scholar

Validation of a Cost-Effective RP-HPLC Method for Quantitative Investigation of Daclatasvir Dihydrochloride in Pharmaceutical Formulations

Journal of Chemistry · مجلد 2023 · 1-9

A well-known direct-acting antiviral (DAA) drug called daclatasvir may be used to treat chronic hepatitis C virus (HCV) infection. Herein, we reported a selective, precise, and a cost-effective analytical method for the measurement of an active pharmaceutical ingredient (API) of daclatasvir dihydrochloride in drug substances as well as drug products via the reversed-phase RP-HPLC technique. To obtain greater separation, the majority of the chromatographic conditions were improved. Best separation findings were achieved under chromatographic conditions with an HPLC column of USP L1 (150 × 4.6 mm, 5 μm) by utilizing a combination of acetonitrile and buffer solution of KH2PO4 (30 : 70, v/v) as a mobile phase at a stream rate of 1 mL.min−1 with a finding at 300 nm and a column temperature of 40°C. Linearity was examined in the range of 90–210 ppm (R2 = 0.999) for daclatasvir dihydrochloride. The new technique has been verified using industry-recognized criteria, including applicability, system precision, accuracy, robustness, specificity, range, linearity, quantification limit, reagent stability, and detection limit. All the measured metrics were determined to be within acceptable limits using the criteria of the Worldwide Council for Harmonisation (ICH). In pharmaceutical labs, daclatasvir dihydrochloride may be analyzed qualitatively and quantitatively using the well-established RP-HPLC technique. Our study also highlights the need to evaluate the greenness of the method developed using a recognized tool ,i.e., Analytical Greenness Metrics (AGREE).

RP-HPLC method validationanalytical method developmentdirect-acting antiviralshepatitis C
مقالوصول مغلق20233استشهاد· Semantic Scholar

Discovery of Anti‐Breast Cancer Thiophene Sulfonamide Derivatives: Design, Synthesis, Molecular Docking against EGFR, MM‐PBSA, MD Simulations, ADME/Tox, and in vitro Studies

ChemistrySelect · مجلد 8 (27)

Abstract With aim of developing the crucial pharmacophoric properties of the reported EGFR inhibitors (EGFRIs), a series of thiophene compounds having ethyl 5‐methylthiophene‐3‐carboxylate core were designed. The designed compounds were subjected to molecular docking studies that indicated the potentialities of compounds AP−A8, A9, A13 and A15 to be EGFRIs. Then, the MD simulations studies confirmed the stability and the correct binding of compound AP−A15 – EGFR complex at both energetic and conformational levels. Furthermore, in silico ADMET prediction revealed that the majority of the proposed compounds had drug‐like characteristics and have minimal toxicity and unfavourable side effects. The designed compounds were synthesized and there in vitro anticancer activity against the cancer cell line (MCF‐7) was measured. Ethyl 5‐methyl‐4‐phenyl‐2‐(2‐(4‐(thiophen‐2‐ylsulfonyl)piperazin‐1‐yl)acetamido)thiophene‐3‐carboxylate (AP−A15) was found to be most potent compound with EC 50 values 3.5 μM, which was very close to Tamoxifen and Brigatinib. Majority compounds showed good to moderate cytotoxic activities ranging from 3.5 μM to 35.9 μM.

EGFR inhibitorsbreast cancermolecular dockingMM-PBSA binding free energy
مقالوصول مفتوح20233استشهاد· Semantic Scholar

Role of Natural Products in the Management of COVID-19: A Saudi Arabian Perspective

Healthcare · مجلد 11 (11) · 1584-1584

The coronavirus disease of 2019 (COVID-19) pandemic has resulted in an unprecedented circumstance that has never previously occurred. This has caused the Saudi Arabian people to recognize the necessity of preventive measures and explore alternative systems, such as using natural products (NPs), for treating their infection. Therefore, the specific objectives of this study were to explore the factors that influence the selection of NPs for COVID-19 management and to know the outcome of using NPs in COVID-19 infection management. This observational cross-sectional study was conducted in Saudi Arabia between February and April 2022. The validated pretested questionnaire was distributed among different regions of the country via a purposive snowball sampling procedure. Both descriptive statistics and stepwise regression analyses were carried out to evaluate the parameters related to the use of medicinal plants for the prevention of COVID-19 and the treatment of respiratory symptoms during the pandemic. The data obtained were statistically analyzed using IBM SPSS Statistics for Windows, version 25 (IBM Corp., Armonk, NY, USA). Of the 677 participants, 65% reported using NPs for themselves or family members during COVID-19. Utilizing NPs is always given priority by a significant (p < 0.001) percentage of survey respondents. Further, a highly significant (p < 0.001) percentage of participants felt that using NPs reduced their COVID-19 symptoms without having any remarkable (p < 0.001) adverse effects. Family and friends (59%) were the most frequent sources of information about utilizing NPs, followed by personal experience (41%). Honey (62.7%) and ginger (53.8%) were the most utilized NP among participants. Moreover, black seeds, garlic and turmeric were used by 40.5%, 37.7% and 26.3% of the surveyors, respectively. Those who used NPs before COVID-19 were 72.9% more likely to use them during COVID-19. NPs are more likely to be used by 75% of people who live in the central part of the country and whose families prefer it. This is true even if other factors are considered, such as the practice of using NPs along with traditional therapies and the fact that some participants’ families prefer it. Our findings show that NPs were commonly used to treat COVID-19 infection among Saudi Arabian residents. Close friends and family members mainly encouraged the use of NPs. Overall, the use of NPs was high among those who participated in our study; such practices are strongly impacted by society. It is essential to promote extensive studies to improve the recognition and accessibility of these products. Authorities should also educate the people about the benefits and risks of using commonly used NPs, especially those reported in this study.

COVID-19 pandemicnatural productsmedicinal plantsherbal medicine
مقالوصول مفتوح20233استشهاد· Semantic Scholar

Outcomes of Cardiopulmonary Resuscitation and Predictors of Its Outcomes in the Emergency Department in King Saud Medical City, Saudi Arabia

Cureus · مجلد 15 (5) · e39268-e39268

BACKGROUND: Cardiac arrest is a medical emergency marked by the cessation of cardiac mechanical activity and insufficient blood flow. CPR (cardiopulmonary resuscitation) is a life-saving method that involves restoring the essential functions of two vital organs: the heart and lungs. This study was conducted to identify the outcome of CPR in cardiac arrest patients presented to the emergency department (ED) and to identify predictors of CPR outcomes. METHODOLOGY: This was a retrospective, descriptive study. All in-hospital cardiac arrest patients who underwent CPR in the King Saud Medical City (KSMC) ED between January 2017 and January 2020 were analyzed, with a sample size of 351 patients. RESULTS: Overall return of spontaneous circulation (ROSC) and survival to discharge (STD) were achieved in 106 (30.2%) and 40 (11.39%) patients, respectively. When assessing the predictors of ROSC, the analyses showed that patient age, pre-arrest intubation, the method used to deliver oxygen, and CPR duration were all statistically significant predictors for ROSC. Similarly, when assessing predictors associated with STD, the analyses showed that patient age, pre-arrest intubation, the method used to deliver oxygen, and CPR duration were positively associated with STD. CONCLUSION: Comparing the study's findings to those of similar studies, it shows a CPR outcome rate within the range of similar studies. It also highlights that CPR outcomes are highly associated with CPR duration (a maximum of 30 minutes), younger age, and endotracheal intubation.

cardiopulmonary resuscitationin-hospital cardiac arrestreturn of spontaneous circulationsurvival to hospital discharge
مقالوصول مفتوح20233استشهاد· Semantic Scholar

Predictors of Mortality in Adults With Sickle Cell Disease Admitted to the Intensive Care Unit in King Saud Medical City, Saudi Arabia

Cureus · مجلد 15 (5) · e38817-e38817

Background Sickle cell disease (SCD) is the most common genetic blood disorder in Saudi Arabia. A limited number of studies have been conducted on SCD patients regarding their intensive care unit (ICU) admissions. We aimed to identify the cause of ICU admission in SCD patients and to identify predictors of mortality. Methodology We identified 64 patients with SCD, aged 14 years and older, who were admitted to the ICU of King Saud Medical City, Riyadh, Kingdom of Saudi Arabia, from January 1, 2017, to December 31, 2020. Results Acute chest syndrome was the most frequent primary diagnosis for ICU admission in 29 (45.3%) patients followed by vaso-occlusive crisis in 23 (35.9%) patients. Pregnancy in eight (12.5%) patients was the most prevalent co-existing condition. The median age was 29 years, with males comprising 45.3% and females comprising 54.7% of the study population. Arterial blood gas pH less than 7.2 on ICU admission (p= <0.001), hemodialysis support (p= 0.049), the use of vasopressors (p= 0.016), intubation (p= <0.001), and being intubated within the first 24 hours of ICU stay (p= 0.04) had a statistically significant association with mortality at ICU discharge out of all the variables tested. Mortality on ICU discharge was 7 (10.9%). Conclusion This was a retrospective study carried out in King Saud Medical City. Comparing the results of the study to those of similar ones conducted around the world revealed a low SCD ICU mortality rate. This low mortality may be a result of improved overall ICU care. We recommend a multi-center, prospective study in future.

sickle cell diseaseintensive care unit admissionmortality risk factorsacute chest syndrome
مقالوصول مغلق20233استشهاد· Semantic Scholar

Detergent-Compatible Amylases Produced by Fungal Species and Their Applications in Detergent Industry

Science of Advanced Materials · مجلد 15 (5) · 607-616

Detergent enzymes are currently vital and important ingredients of modern powder and liquid detergents. They catalyze various biochemical processes intra-or extracellularly in the detergent industries. Microorganisms are the favored source of detergent compatible fungal amylases compared to plant or animal sources. Detergents cannot be produced in the developed countries without a mixture of detergent enzymes supplementation because they are essential components in the detergent industries. In countries under development, various produced detergents do not have enzymes. Amylases, proteases, pectinases, lipases, mannanases, and cellulases are generally the hydrolytic enzymes used in the detergent industries. They remove all soft, tough and stubborn starchy food, protein, pectin, fatty, mannane and cellulose-based stains attached to the various substrates like fabrics or glassware. A number of review articles on detergent-compatible bacterial and fungal enzymes exists, but none specifically covers detergent-compatible fungal amylases. In the present review, production and aspects of detergent fungal amylases are discussed with an emphasis on the stability of fungal amylases in the presence of detergent constituents. The article will help other worldwide research to study the properties of detergent pectinases and mannanases which are not extensively studied.

fungal amylasedetergent enzymesdetergent additivesstain removal