IDENTIFYING MOST SUITABLE CLASSIFIER AND RISK FACTORS HIGHLY AFFECT ON LOW BIRTH WEIGHT IN DEVELOPING COUNTRIES: REVIEW
Low birth weight (LBW) is a severe public health concern, especially in developing countries, and is often related to child morbidity and mortality. Identifying the essential factors that affect LBW is beneficial and a significant preventive step. It is also a good predictor of the infant's future health concerns. This research is concerned with identifying substantial risk factors for low birth weight and determining the best enihcam -gmnnacal classifier for LBW data. The study reveals that the most critical factors associated with LBW are the mother's age, education of the mother, sex of infants, preceding birth interval, Antenatal care visits (ANC), residence in rural areas, wealth status, and multiple births. Among several studies using machine learning/data mining approaches (i.e., Logistic Regression, Naive Bayes, Neural Networks, Random Forest, Decision Tree, Random Tree, K-Nearest Neighbor, J-48, and support vector machine), the Random Forest algorithm was shown to be the most suitable predictive modeling technique for LBW data.
Maqola sahifasiga o'tish
Maqola