A Framework for Social Network-Based Dynamic Modeling and Prediction of Communicable Diseases

Abstract

It was published lately in 2016 that there are approximately 3.7 million of deaths caused by communicable diseases annually. Unfortunately, currently there is no automated method for the detection and tracking of communicable diseases progression. In this paper, a framework is proposed, that is based on social network analysis, different biological sensors, and big data analytics as for predicting and analyzing communicable disease and to facilitate the process of managing, preventing and predicting risks of communicable disease progression. The proposed framework is largely based on graph theory and social network analysis algorithms to model and dynamically predict communicable disease risk for diagnosed and non-diagnosed patients. In this research, a global graph structure that maps a whole friendship network is proposed, and the suitable algorithms to identify and continuously monitor a certain communicable disease progression rate. This research can potentially be useful for forming a methodology for early intervention and prevention policies targeted at patients that can potentially divert them from the disease pathway. The interpretation and dynamic utilities offered by the framework and its predictive capability are considered a remarkable and promising broad model highlighting potential pathways linking social support, biological sensors and data sciences to physical health.

An Accurate Clinical Implication Assessment for Diabetes Mellitus Prevalence Based on a Study from Nigeria

“…There is considerable interest in determining how different classification techniques from machine learning can be utilized as disease prediction tools [17][18][19][20][21]. These tools have been used to diagnose diabetes [22], glaucoma [23], meningitis [24], coronary artery disease [25], asthma [26], cancer [27], hypertension [28], heart arrhythmia [29], tuberculosis [30], and other diseases [31,32].…”