Predictive Analytic Model for Classifying the Health State of Fetal Heart Using Ensemble Model

The field of healthcare has witnessed tremendous change after the advent of artificial intelligence and predictive analytics. Many researchers have shown their interest in developing frameworks and algorithms to assist the clinical diagnosis and treatment procedures. Fetal mortality is considered as one of the significant factor in assessing the performance of a country's medical infrastructure. Leveraging day cutting edge technologies like machine learning and deep learning has facilitated the development of novel and smart methods for prognosis and predictive monitoring of many health conditions. The proposed work focuses on developing a predictive analytical model as an ensemble of multiple heterogeneous ML algorithms. The results of the individual based learners used in the proposed model are they aggregated using soft majority voting technique, which is a probabilistic approach to get the final outcome. The efficiency of the proposed model is assessed using standard classification metrics. The results indicate that the proposed methodology outperforms the individual based learners and in future more number of base learners can be integrated to form the ensembles.