ABSTRACT
Institutions of higher learning have made persistent efforts to provide students with a high-quality education. Educational data mining (EDM) enables academic institutions to gain insight into student data in order to extract information for making predictions. COVID-19 represents the most catastrophic pandemic in human history. As a result of the global pandemic, all educational systems were shifted to online learning (OL). Due to issues with accessing the internet, disinterest, and a lack of available tools, online education has proven challenging for many students. Acquiring accurate education has emerged as a major goal for the future of this popular medium of education. Therefore, the focus of this research was to identifying attributes that could help in students' performance prediction through a generalizable model achieving precision education in online education. The dataset used in this research was compiled from a survey taken primarily during the academic year of COVID-19, which was taken from the perspective of Pakistani university students. Five machine learning (ML) regressors were used in order to train the model, and its results were then analyzed. Comparatively, SVM has outperformed the other methods, yielding 87.5% accuracy, which was the highest of all the models tested. After that, an efficient hybrid ensemble model of machine learning was used to predict student performance using NB, KNN, SVM, decision tree, and logical regression during the COVID-19 period, yielding outclass results. Finally, the accuracy obtained through the hybrid ensemble model was obtained as 98.6%, which demonstrated that the hybrid ensemble learning model has performed better than any other model for predicting the performance of students.
ABSTRACT
With the emergence of the COVID-19 pandemic, access to physical education on campus became difficult for everyone. Therefore, students and universities have been compelled to transition from in-person to online education. During this pandemic, online education, the use of unfamiliar digital learning tools, the lack of internet access, and the communication barriers between teachers and students made precision education more difficult. Customizing models from previous studies that only consider a single course in order to make a prediction reduces the predictive power of the model because it only considers a small subset of the attributes of each possible course. Due to a lack of data for each course, overfitting often occurs. It is challenging to obtain a comprehensive understanding of the student's participation during the semester system or in a broader context. In this paper, a model that is flexible and more generalizable is developed to address these issues. This model resolves the problem of generalized models and overfitting by using a large number of responses from college and university students as a dataset that considered a broader range of attributes, regardless of course differences. CatBoost, an advanced type of gradient boosting algorithm, was used to conduct this research, and enabled the developed model to perform effectively and produce accurate results. The model achieved a 96.8% degree of accuracy. Finally, a comparison was made with other related work to demonstrate the concept, and the experimental results proved that the Catboost model is a viable, accurate predictor of students' performance. © 2023 by the authors.
ABSTRACT
The ongoing pandemic of COVID-19 has changed every aspect of life. Most of the people who become a victim of COVID-19 experience mild to moderate symptoms, but some people may become seriously ill. This illness, sometimes, may lead to a very painful death. The Fréchet distribution is one of the flexible distribution for survival time. Hence, in this article, the recovery time of COVID-19 patients is modeled by a new Fréchet-exponential (FE) distribution, and the parameters of the distribution are estimated in the classical and Bayesian paradigms. Since the Bayes estimators using informative priors are not in the closed form, the Lindley and Tierney–Kadane approximation methods are used for their evaluation. The results obtained through simulation studies and the COVID-19 data set assess the superiority of the Bayes estimators over the classical estimators in terms of minimum risks. Mathematically and graphically, it is shown that our proposed model appropriately fits the data set. The minimum values of Akaike information criterion, Bayesian information criterion, corrected Akaike information criterion, and Hannan-Quinn information criterion proves that the FE distribution better fit than the competitors' distribution for the data set about the recovery time of COVID-19 patients. © 2022 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group on behalf of the University of Bahrain.
ABSTRACT
Background: Venetoclax combined with hypomethylating agents is a new standard of care for newly diagnosed patients with acute myeloid leukemia (AML) 75 years or older, or unfit for intensive chemotherapy. As precision therapy in AML expanded with the addition of venetoclax among others in the therapeutic armamentarium of AML, efficacy and safety reports in ethnic minorities are limited, with a background of well recognized inter-ethnic differences in drug response. Phase III data from VIALE-A, as well as VIALE-C, was limited for the Arab population as no site opened in the Arab world. We herein report our experience on the use of venetoclax with azacitidine in patients with newly diagnosed or relapsed/refractory AML in the Arab population. Methods: Retrospective-single center review on the use of Azacitidine with venetoclax in older patients (aged ≥60 years) with newly diagnosed AML, not eligible for intensive chemotherapy;secondary AML and relapsed or refractory AML. All patients self-identified of Arabic ethnicity. Patients who received previous BCL2-inhibitor therapy were excluded. Patients who received at least one dose of treatment (Azacitidine ≥3 days, >14 days of venetoclax) were included in the intention to treat analysis. Patients typically received azacitidine 75 mg/m2 intravenously for 7 days with oral venetoclax 400 mg daily for induction, with appropriate dose adjustment for concomitant use of azoles. This is followed by the same regimen in consolidation, with adjustment according to response and side effects at the treating physician's discretion. The primary endpoint was overall survival. The secondary endpoints include response rate, safety, and relapse-free survival. Results: Between July 2019, and July 2021, we identified 19 patients;13 (68%) had newly diagnosed AML (ND-AML), and 6 (32%) had relapsed or refractory AML (R/R AML). The median age was 70 years (17-82). In the ND-AML, most patients had an adverse ELN 2017 AML (69%) with 23% having either intermediate or adverse AML (Negative for CBF, NPM1, FLT3-ITD and biCEBPA, but missing NGS data for adverse mutations Tp53/ASXL1 and RUNX1). Only one patient was classified as intermediate-risk AML. The overall response rate in the ND-AML was 77%, with 46% achieving complete remission (CR), and 23% CR with incomplete count recovery (CRi) [Table]. One patient achieved PR after the first cycle (blast 7% by morphology and 1.5% by flow cytometry) and did not have a subsequent bone marrow evaluation, however had a full count recovery. Among the responders in the ND-AML cohort, 4 deaths were noted. One death was related to COVID-19 associated pneumonia, one due to graft failure (at day 42 post Haplo-SCT), one due to septic shock, and one was related to relapse disease. The overall survival and relapse-free survival for ND-AML were 5.6 months for both [Figure]. In the R/R AML, 66% had prior HMA exposure, and all patients did receive high-intensity chemotherapy. The median number of prior treatments was 3 (1-5). the response rate was 80% (4/5), with 60% achieving CR. All patients are still alive with a median follow-up of 7.6 months. One patient had progressive disease. One patient is early to evaluate and was not included in the response analysis [Table]. The 30-day mortality was zero in both ND-AML and R/R AML cohorts. Conclusions: In a majority of adverse risk ND-AML, and in heavily pretreated R/R AML, the response rate and overall survival is comparable to what has been previously reported. Our data support the use of this regimen in older patients with newly diagnosed AML, patients with relapsed or refractory disease, and those with adverse-risk features. This analysis is limited by the small number of patients, and by the lack of ELN 2017 favorable-risk AML. Future prospective and randomized studies are needed to clarify activity and safety in the Arab population, as well as in the high-risk AML subset. [Formula presented] Disclosures: No relevant conflicts of interest to declare.
ABSTRACT
Introduction: Coronavirus disease 2019 (COVID-19) has resulted in dramatic changes to health-care delivery. Endoscopic activity has had frequent disruptions during this pandemic. The objective of the study was to see the influence of pandemic over the endoscopic activity. Methods: This retrospective analysis of endoscopic activity was undertaken at Nishtar Hospital Multan. Procedural analysis was done in the three months immediately after covid lockdown (1st April till 30th June 2020) and was compared to a similar period one year back. Results: Five hundred and fifty-four (68.5%) patients underwent endoscopic procedures during the three months of pre-COVID era, while this number reduced to half (n=255, 31.5%) patients during the covid pandemic. Even though the absolute number of Esophagogastroduodenoscopies (EGDs) reduced during the pandemic, patients were more likely to undergo EGDs during the COVID pandemic in contrast to the era before the pandemic (79% versus 66%, p = 0.002). The most common indication for EGD was upper gastrointestinal bleeding (UGIB). The percentage of EGDs done for UGIB rose from almost 60% to 80% during the covid pandemic (p < 0.001). The most common findings were esophageal varices and portal gastropathy (non-significant difference during and before the pandemic). Percentage of ERCPs done for obstructive jaundice doubled during the COVID pandemic (33% versus 65%, p = 0.002).The most common indication for sigmoidoscopy or colonoscopy was lower gastrointestinal bleeding. However, no significant difference was found before and during the covid pandemic (41.7% and 45.8% respectively, p=0.72). Internal hemorrhoids were the most common endoscopic finding. Colon cancer diagnosis reduced from 10% to undetected during the pandemic period. Conclusion: COVID pandemic resulted in considerable reduction in all type of endoscopic procedures. Majority of procedures were done for emergency indications like gastrointestinal bleeding. Rates of cancer detection was significantly reduced.
ABSTRACT
Objectives: To determine the safety of Sinopharm Covid-19 vaccine among health care workers of Khyber Teaching Hospital (KTH, Peshawar). Material and Methods: This observational study was carried out to assess the side effects associated with the first dose of Sinopharm vaccine among health care workers in KTH Peshawar, Pakistan. Data was collected using a close ended questionnaire which was filled by the health care workers above 18 years of age. The participants were asked to monitor any side effects up to 1 week after the first dose of Sinopharm vaccine administered to them. Data was analyzed using SPSS version 23 for macbook. Results: A total of 400 health workers were included in the study but only 155 participants responded by completing the questionnaire. It was observed that 63.9% of the participants who were vaccinated experienced at least one symptom after vaccination. The most common symptom was pain at injection site (36.8%) experienced during 15 – 30 minutes after vaccination followed by fatigue (21.3%), headache (18.7%), lightheadedness (12.3%), myalgia (10.3%). Percentage of other symptoms was less than 10%. The occurrence of symptoms after vaccination was greater in age group 24-42 years which was 60.6% while in age group 43-60 years it was 39.4%. Conclusion: Our study concludes that Sinopharm vaccine has no or mild side effects and therefore safe for public use.
ABSTRACT
Background : Cerebral venous sinus thrombosis (CVST) is rare in children. Its risk factors and outcome are largely unknown in low-middle income countries. Some case reports have shown presence of anemia in pediatric CVST as a probable risk factor. Aims : This study was done to determine the frequency of anemia in patients having pediatric CVST and to observe its association with the severity of disease. Methods : Patients between age 0 to 18 years of both genders diagnosed with sinus thrombosis during 2011 to 2020 were identified through international classification of diseases (ICD 9). Data was collected through in-house computerized system and SPSS version 19 was used for analysis. Results : Of 143492 patients who were admitted, 32 (21 males and 11 females) with a median (IQR) age of 4.5 years (0-16) had CVST. This is equivalent to 2.2 CVST events /10,000 pediatric admissions. Overall mortality was 3.4%. Primary underlying disorders were infections (59%), hematological neoplasms (12.5%), thrombotic thrombocytopenic purpura (3%) and antiphospholipid syndrome (3%). Significant laboratory findings were anemia (65%), low protein S (19%), low protein C (19%), low antithrombin III (6%) and activated protein C resistance (25%). Mean(±SD) hemoglobin in anemic patients was 9.0 g/dL (±2.3). SARS-COV2 was negative in patients tested in 2020. Regression analysis showed a positive association of anemia with multiple sinus involvement ( P 0.009) but anemia had no association with the duration of symptoms ( P 0.344), hospital stay ( P 0.466), age ( P 0.863) or gender ( P 0.542) of the patients. Conclusions : Low hemoglobin was observed in a significant proportion of patients with pediatric CVST. Anemia may be an important biomarker along with other clinical variables in the risk assessment of sinus thrombosis in children. Future studies may unveil the role of anemia in coagulopathy and more specifically in pediatric CVST.