Smart Healthcare Using Data-Driven Prediction of Immunization Defaulters in Expanded Program on Immunization (EPI)

Abstract

Immunization is a noteworthy and proven tool for eliminating life-threating infectious diseases, child mortality and morbidity. Expanded Program on Immunization (EPI) is a nation-wide program in Pakistan to implement immunization activities, however the coverage is quite low despite the accessibility of free vaccination. This study proposes a defaulter prediction model for accurate identification of defaulters. Our proposed framework classifies defaulters at five different stages: defaulter, partially high, partially medium, partially low, and unvaccinated to reinforce targeted interventions by accurately predicting children at high risk of defaulting from the immunization schedule. Different machine learning algorithms are applied on Pakistan Demographic and Health Survey (2017-18) dataset. Multilayer Perceptron yielded 98.5% accuracy for correctly identifying children who are likely to default from immunization series at different risk stages of being defaulter. In this paper, the proposed defaulters' prediction framework is a step forward towards a data-driven approach and provides a set of machine learning techniques to take advantage of predictive analytics. Hence, predictive analytics can reinforce immunization programs by expediting targeted action to reduce dropouts. Specially, the accurate predictions support targeted messages sent to at-risk parents' and caretakers' consumer devices (e.g., smartphones) to maximize healthcare outcomes.