ABSTRACT
Modern public health faces substantial challenges toward predicting exponential rise of communicable and non-communicable diseases (NCDs), unprecedented health crises, lifestyle risk factors and environmental health hazards to populations worldwide. Public health physicians require new and efficient models and resources to tackle, detect and combat infectious disease outbreaks, rare diseases, lifestyle risk factors, mental health repercussions and maternal and child health challenges which not only impacts the overall human health system but also escalates the country’s economic burden and citizen’s quality of life. The integration of big health data, epidemiologic informatics and computational intelligence approaches has created new hopes for people and policy advocates to diagnose and predict diseases at an early stage to prevent further complications, rise in hospital admissions or increased morbidities and mortalities. This chapter will systematically appraise the application of deep learning approaches (a subset of machine learning) and big public health data utilization in predicting diseases across major domains in public health, particularly NCDs, communicable diseases, socio-behavioral medicine, maternal and child health and environmental health.
