Knowledge-driven machine learning based framework for early-stage disease risk prediction in edge environment

Abstract

Early-stage disease risk prediction can be beneficial to improve the health of the mass and can reduce the economic burden of late treatment. Machine learning has played a pivotal role in predictive systems, which requires achieving a specific degree of accuracy for healthcare systems. Most recently researchers have found the necessity of bridging between epidemiology and machine learning classifications toward health risk prediction. This work proposes an epidemiology knowledge-driven unique model that follows the principle of association rule-based ontology to select features and classification techniques. The goal of this approach is to generalize a framework for future robust systems to predict the likelihood of diseases, which can be executed in the edge computing environment. The framework introduces epidemiological library and structured attribute set along with the library of precaution to derive the disease risk-prediction process. To investigate the adoption of the epidemiology knowledge-driven model, we considered a real dataset of early-stage likelihood prediction of diabetes and carried out a set of experiments for highlighting the significance of several epidemiological factors. The classification aspect of the framework is further compared with widely accepted approaches for machine learning based healthcare, which shows the novelty of the proposed model.