Article
Multidisciplinary Sciences
Debendra Nath Roy, Md. Shah Azam, Ekramul Islam
Summary: This study investigates the acceptance and hesitancy of COVID-19 vaccine booster dose among university teachers and students in Bangladesh. The acceptance rates were higher among teachers compared to students. The study identified multiple factors influencing acceptance, including safety concerns, risk-benefit ratio, variant control, and post-vaccination side effects.
Article
Environmental Sciences
Alimahdi Mohammaddost, Zargham Mohammadi, Mohsen Rezaei, Hamid Reza Pourghasemi, Asadullah Farahmand
Summary: This study assessed the vulnerability of Kabul aquifers in Afghanistan using the DRASTIC, EBF, and LR models, finding that the EBF model was the most compatible with the existing vulnerability zones.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2022)
Article
Engineering, Geological
Ugur Ozturk, Massimiliano Pittore, Robert Behling, Sigrid Roessner, Louis Andreani, Oliver Korup
Summary: Contemporary landslide research often focuses on predicting and mapping susceptibility to slope failure using generalized linear models, however the impact of sample size, location, or time on model performance remains largely untested. Findings suggest that considering only lower parts of landslides can significantly improve model performance, particularly for medium-sized landslides. Additionally, model performance shows marginal variation when progressively updating and adding more landslide data through time.
Article
Computer Science, Information Systems
Mankirat Kaur, Sarbjeet Singh, Naveen Aggarwal
Summary: This study proposes a statistically principled methodology to impute missing traffic data and improve the estimation results of traffic flow analysis. By quantifying the accuracy and uncertainty of imputation, comparing different missing data patterns, and evaluating performance against existing methods, the proposed approach shows robustness in handling missing data and estimating uncertainty.
INFORMATION SCIENCES
(2022)
Article
Ergonomics
Nurten Akgun, Stijn Daniels, Margaret Carol Bell, Nina Nuyttens, Neil Thorpe, Dilum Dissanayake
Summary: This study compared the safety of cyclists at roundabouts between the United Kingdom and Belgium, showing that national differences in speed limits, driver/cyclist behavior, and environmental conditions have an impact on cyclist casualty severity. The analysis found that non-behavioral variables like sociodemographic characteristics, speed limits, and environmental conditions varied significantly between the two countries, indicating differences in road safety measures.
ACCIDENT ANALYSIS AND PREVENTION
(2021)
Review
Orthopedics
Jeffrey W. Chen, David R. Maldonado, Brooke L. Kowalski, Kara B. Miecznikowski, Cynthia Kyin, Jeffrey A. Gornbein, Benjamin G. Domb
Summary: A rigorous and reproducible methodology for controlling bias is crucial in high-quality studies. Propensity score matching (PSM) is a valuable method for controlling bias and achieving pseudo-randomization in retrospective observation studies. This article aims to provide a clear conceptual framework for PSM, recommendations for reporting its use, and practical implementation examples. PSM is an invaluable tool for producing rigorous and reproducible results in observational studies.
ARTHROSCOPY-THE JOURNAL OF ARTHROSCOPIC AND RELATED SURGERY
(2022)
Article
Medicine, General & Internal
Binila Chacko, Lovely Thomas, Roshni Sharma, Bijesh Yadav, Lakshmanan Jeyaseelan, Ashwin O. Arul, Punitha Victor, Vignesh K. Chandiraseharan, Audrin Lenin, Ronald A. B. Carey, Jonathan A. J. Jayakaran, Rajiv K. Krishnaswami, John Victor Peter
Summary: The study investigated the role of noninvasive ventilation in SARS-CoV2 related acute respiratory failure, finding that NIV success rate was 63.6% and factors associated with failure included lower admission PaO2 to FiO2 ratio and higher respiratory rate.
MAYO CLINIC PROCEEDINGS
(2022)
Article
Economics
Jiyang Ren
Summary: Noncompliance is a common issue in randomized experiments. To improve estimations, three model-assisted estimators are proposed for complier average treatment effect with binary outcome. The asymptotic properties are studied, efficiencies are compared with the Wald estimator, and conservative variance estimators are proposed for valid inferences. Simulation studies demonstrate the advantages of model-assisted methods and the analysis is applied to evaluate the effect of academic services or incentives on academic performance in a randomized experiment.
JOURNAL OF BUSINESS & ECONOMIC STATISTICS
(2023)
Article
Computer Science, Information Systems
Deepak Gupta, Ambika Choudhury, Umesh Gupta, Priyanka Singh, Mukesh Prasad
Summary: The research aims to help early identification of diabetes risk and improve medical diagnosis through machine learning methods. In experiments, it was found that logistic regression performed better than other techniques.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Multidisciplinary Sciences
Johannes Honekopp, Audrey Helen Linden
Summary: Meta-analyses are used to quantify the consistency of research results. This study evaluated five heterogeneity estimators using computer simulations and found that biases in the set of primary studies had a greater impact on effect size estimation than on heterogeneity estimation. The REML estimator performed well in most circumstances.
Article
Geosciences, Multidisciplinary
Alvaro Egana, Felipe Navarro, Mohammad Maleki, Francisca Grandon, Francisco Carter, Fabian Soto
Summary: This framework introduces a method for building ensemble spatial interpolation functions by combining weak interpolation functions to produce robust ones. Experiments demonstrate its promising ability to handle large datasets and deal with uncertainty quantifications.
NATURAL RESOURCES RESEARCH
(2021)
Article
Public, Environmental & Occupational Health
Yenesew Fentahun Gebrie
Summary: The study found that the prevalence of household food insecurity in the given district was 59%. Households headed by males, owning farmland, having fertile soil, and receiving agricultural training were less likely to experience food insecurity, while households with large family sizes, small farmland sizes, and few tropical livestock units were more likely to be food insecure.
Article
Medicine, General & Internal
Vivian Goh, Yu-Jung Chou, Ching-Chi Lee, Mi-Chia Ma, William Yu Chung Wang, Chih-Hao Lin, Chih-Chia Hsieh
Summary: This study aimed to establish a predictive model for bacteremia in septic patients using big data in the emergency department. The performance of SVM and RF models was comparable to logistic regression, and these models could help identify high-risk patients and prevent unnecessary antibiotic use.
Article
Computer Science, Information Systems
Manoj Kumar, Aliasgar Moiyadi, Narayan Rangaraj, Santosh Noronha, Prakash Shetty, Vikas Kumar Singh, Amit Kumar Choudhari
Summary: This study investigates the effectiveness of basic and advanced ultrasound technologies in glioma surgery and proposes predictive models for tumor resectability and surgical outcomes. The results show that using ultrasound technologies can predict the extent of tumor removal, and 3D ultrasound seems to offer superior outcomes in certain cases.
INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS
(2023)
Article
Mathematical & Computational Biology
Fei Wan
Summary: It has been found that correctly specified unconditional logistic regression is more efficient than conditional logistic regression in frequency matched designs, especially when continuous matching factors are used. Conditional logistic regression is a more practical approach as it is less dependent on modeling choices.
STATISTICS IN MEDICINE
(2022)