Evaluating water-related health risks in East and Central Asian Islamic Nations using predictive models (2020–2030)

• Published in: Scientific reports Vol. 14; no. 1; pp. 16837 - 14
• Main Authors: Cheema, Mahwish Anwer, Hanif, Muhammad, Albalawi, Olayan, Mahmoud, Emad E., Nabi, Muhammad
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 22-07-2024; Nature Publishing Group; Nature Portfolio
• Subjects: 639/705; 692/700; AHWF; Asia - epidemiology; DALYs; Death; Diarrhea; Dysentery; Gastrointestinal diseases; Health promotion; Health risks; Humanities and Social Sciences; Humans; Islam; LOS; Malnutrition; multidisciplinary; Neural networks; Prediction models; Public health; Quality-Adjusted Life Years; Resource management; Sanitation; Science; Science (multidisciplinary); Support Vector Machine; Support vector machines; USWS; Water Pollution; Water Quality; Water resources management; Water Supply; Waterborne diseases; Waterborne Diseases - epidemiology; Asia; AHWF; LOS; Death; DALYs; USWS
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-67775-3

This paper presents a thorough evaluation of health outcomes linked to water-related challenges in Islamic nations across East Asia and Central Asia from 2020 to 2030. It has been examined carefully that the trajectory of deaths and disability-adjusted life years associated with unsafe water sources, lack of sanitation, and absence of handwashing facilities is showing a potential rise in negative health impacts due to water pollution. The direct health influences of water-related problems are thoughtful. The increase in deaths and DALYs due to poor water quality and sanitation leads to a higher occurrence of waterborne diseases such as cholera, diarrhea, and dysentery. These conditions not only cause instant health disasters but also subsidize to long-term health issues which include chronic gastrointestinal disorders and malnutrition that is particularly among susceptible populations like children and the elderly. Employing various predictive models including autoregressive integrated moving average, exponential smoothing, support vector machines, and neural networks. The study evaluates their predictive capabilities by using mean absolute percentage error. Support vector machines is found to be the most accurate in forecasting deaths and disability-adjusted life years which is outperforming autoregressive integrated moving average, exponential smoothing, and neural networks. This research aims to inform stakeholders by providing insights into effective strategies for improving water resource management and public health interventions in the targeted regions.