Predicting Pediatric Diarrhea in Pakistan: Impact of Water Quality
Keywords:
Diarrhea, Water Quality, Chi-Square, Naïve Bayes, Logistic Regression, Decision Tree, Random Forest, Support Vector MachineAbstract
According to 2023 study, 45.54% of Pakistan’s population is under 18 years old, with 13.34% being under 5 years old. A 2023 report indicated that there are 6.4 million cases of pediatric diarrhea. Infectious disease account for 70% of mortality in Pakistan, with 60% of these deaths related to diarrhea. This study aims to analyze the impact of poor water quality on the incidence of diarrhea. In environments with inadequate sanitation, hygiene, and access to clean, safe water for drinking, cooking and cleaning, infections are more likely to occur. The hypothesis posists that investing in water infrastructure, strictly enforcing water quality regulations, and expanding access to safe drinking water through purification and treatment techniques will reduce diarrheal cases. Using a Chi-square test to assess associations at a 95% confidence interval, we found a statistically significant association between the use of water in cooking food (CF) and the incidence of diarrhea, with 49.9% of deaths attributed to diarrhea and children aged 0-1 (male) being the most effected. Employing various machine learning techniques, the support vector machine (SVM) emerged as the most accurate, with 88% accuracy, 93% sensitivity, and 83% specificity. These results can inform the development of appropriate policies to ensure the provision of clean water and mitigate the incidence of diarrhea.
Downloads
Published
How to Cite
Issue
Section
License
This is an open Access Article published by Research Center of Computing & Biomedical Informatics (RCBI), Lahore, Pakistan under CCBY 4.0 International License