MyMedR

Displaying all 4 publications

Abstract:

Sort:

A hybrid ensemble approach to accelerate the classification accuracy for predicting malnutrition among under-five children in sub-Saharan African countries

Khan MNA, Yunus RM

Nutrition, 2023 Apr;108:111947.
PMID: 36641887 DOI: 10.1016/j.nut.2022.111947

BACKGROUND: The proper intake of nutrients is essential to the growth and maturation of youngsters. In sub-Saharan Africa, 1 in 7 children dies before age 5 y, and more than a third of these deaths are attributed to malnutrition. The main purpose of this study was to develop a majority voting-based hybrid ensemble (MVBHE) learning model to accelerate the prediction accuracy of malnutrition data of under-five children in sub-Saharan Africa.
METHODS: This study used available under-five nutritional secondary data from the Demographic and Health Surveys performed in sub-Saharan African countries. The research used bagging, boosting, and voting algorithms, such as random forest, decision tree, eXtreme Gradient Boosting, and k-nearest neighbors machine learning methods, to generate the MVBHE model.
RESULTS: We evaluated the model performances in contrast to each other using different measures, including accuracy, precision, recall, and the F1 score. The results of the experiment showed that the MVBHE model (96%) was better at predicting malnutrition than the random forest (81%), decision tree (60%), eXtreme Gradient Boosting (79%), and k-nearest neighbors (74%).
CONCLUSIONS: The random forest algorithm demonstrated the highest prediction accuracy (81%) compared with the decision tree, eXtreme Gradient Boosting, and k-nearest neighbors algorithms. The accuracy was then enhanced to 96% using the MVBHE model. The MVBHE model is recommended by the present study as the best way to predict malnutrition in under-five children.
Fulltext Crisis and environmental governance decisions amidst the COVID-19 pandemic: Lessons from European countries

Ismail IHM, Khatib SFA, Abbas AF, Ali Khan MNA, Sulimany HGH, Bazhair AH

Heliyon, 2024 Feb 29;10(4):e25673.
PMID: 38370258 DOI: 10.1016/j.heliyon.2024.e25673

This study investigates the influence of the COVID-19 pandemic crisis on environmental governance decisions within publicly listed European companies. It utilizes a comprehensive analysis of publicly available data regarding these firms and check the environmental governance practices during the pandemic, informed by risk society theory which describes modern societies marked by ongoing risks and uncertainties primarily stemming from technological and scientific advancements. The regression and robustness analysis has been performed on how companies have responded to the crisis, specifically in terms of their approaches to environmental sustainability and governance. Covid-19 has a significantly positive impact on environmental governance (EG), with a coefficient of 18.73 and a p-value of .000. Other variables like human development (HD), size, and free cash flow (FCF) positively affect EG, while corruption (Corrupt) and leverage (Lev) have a negative influence. Robust analysis confirms the negative impact of Covid-19 on EG, with a coefficient of 18.46 and a p-value below .01, consistent across different subsamples. However, it also underscores the challenges companies have encountered in upholding their sustainability efforts amid the crisis. In sum, this research offers valuable insights into how the COVID-19 pandemic has affected environmental governance decisions, with potential implications for policymakers, regulators, and business leaders striving to advance sustainability in the post-pandemic landscape.
Fulltext Knowledge, attitude, and practice of university students towards monkeypox in Bangladesh

Islam MA, Sathi NJ, Setu SP, Nahar MT, Khan MNA, Hasan M, et al.

PLoS One, 2023;18(10):e0287407.
PMID: 37824512 DOI: 10.1371/journal.pone.0287407

The recent outbreak of viral zoonotic disease-monkeypox-caused by the monkeypox virus, has infected many people worldwide. This study aims to explore the knowledge, attitudes, and practices (KAP) concerning monkeypox among university students in Bangladesh. Data were collected using purposive snowball sampling from 887 university students through an online survey using Google Form. The participants were mostly in their twenties (M = 22.33 [SD 2.01] years), and they spent, on average, 2.59 [SD 1.91] hours/day on electronic and social media. The participants generally showed moderate knowledge (39.5%), low attitude (25.1%), and moderate practice (48.6%) toward monkeypox, with 47.6% having had a moderate KAP score. Findings further showed that personal attributes of university students, i.e., age, sex, year of schooling, residence, living status, geographical distribution, e.g., division, were statistically and significantly associated with knowledge, attitudes, and practices regarding monkeypox and overall KAP score. It is also apparent that health status, susceptibility to monkeypox, and exposure to social media were the most common factors significantly associated with knowledge, attitudes, and practices regarding monkeypox and overall KAP score. The current study's findings underscore the need for developing appropriate information, education, and communication (IEC) materials and their dissemination, which could play an important role in reducing the risk of monkeypox and similar other infectious diseases, particularly among students in Bangladesh.
Fulltext Identifying hotspots for antibiotic resistance emergence and selection, and elucidating pathways to human exposure: Application of a systems-thinking approach to aquaculture systems

Brunton LA, Desbois AP, Garza M, Wieland B, Mohan CV, Häsler B, et al.

Sci Total Environ, 2019 Oct 15;687:1344-1356.
PMID: 31412468 DOI: 10.1016/j.scitotenv.2019.06.134

Aquaculture systems are highly complex, dynamic and interconnected systems influenced by environmental, biological, cultural, socio-economic and human behavioural factors. Intensification of aquaculture production is likely to drive indiscriminate use of antibiotics to treat or prevent disease and increase productivity, often to compensate for management and husbandry deficiencies. Surveillance or monitoring of antibiotic usage (ABU) and antibiotic resistance (ABR) is often lacking or absent. Consequently, there are knowledge gaps for the risk of ABR emergence and human exposure to ABR in these systems and the wider environment. The aim of this study was to use a systems-thinking approach to map two aquaculture systems in Vietnam - striped catfish and white-leg shrimp - to identify hotspots for emergence and selection of resistance, and human exposure to antibiotics and antibiotic-resistant bacteria. System mapping was conducted by stakeholders at an interdisciplinary workshop in Hanoi, Vietnam during January 2018, and the maps generated were refined until consensus. Thereafter, literature was reviewed to complement and cross-reference information and to validate the final maps. The maps and component interactions with the environment revealed the grow-out phase, where juveniles are cultured to harvest size, to be a key hotspot for emergence of ABR in both systems due to direct and indirect ABU, exposure to water contaminated with antibiotics and antibiotic-resistant bacteria, and duration of this stage. The pathways for human exposure to antibiotics and ABR were characterised as: occupational (on-farm and at different handling points along the value chain), through consumption (bacterial contamination and residues) and by environmental routes. By using systems thinking and mapping by stakeholders to identify hotspots we demonstrate the applicability of an integrated, interdisciplinary approach to characterising ABU in aquaculture. This work provides a foundation to quantify risks at different points, understand interactions between components, and identify stakeholders who can lead and implement change.