Predicting child anaemia in the North-Eastern states of India: a machine learning approach

Child anaemia is a serious global health issue and India is one of the highest contributors among the developing nations. Researchers identify many harmful effects of anaemia, which include psychomotor retardation, which in turn decreases the learning ability and causes low intelligence among pre-school children. The effects also include behavioural delays, low immunity, and susceptibility to frequent infections, increased mortality, and disability. The present study aims to predict anaemia among children in North-East India by applying Machine Learning (ML) algorithms to latest available National Family Health Survey (NFHS)-4 data. Out of the total 29,312 eligible children (6–59 months) in North-East India, a total of 21,000 children with demographic variables without any missing observations, wherein 10,460 are anaemic, is considered for this study. Machine learning (ML) algorithms have been applied through 3 different types of penalized regression methods—ridge, least absolute shrinkage and selection operator, and elastic net for predicting anaemia. A systematic assessment of algorithms is performed in terms of accuracy, sensitivity, specificity, F1-Score, and Cohen’s $$k$$ k -Statistics. Having achieved the receiver operating characteristic value of over 70% in training and accuracy of above 64% while testing, it can be safely asserted that factors like mother’s anaemic status, age of the child, social status, mother’s age, mother’s education, religion are important in identifying the child as anaemic.