Predictive Analytics (PA) is becoming a trusted methodology for evaluating large complex public health datasets.

Public health surveillance covers all fields of public health, ranging from epidemiology, health promotion, health impact assessment, research, environmental and human wellness, and many more. Public health surveillance can be used for the following:

• Measure patterns and characterize diseases
• Estimate degree and scope of wellbeing issues
• Identify epidemics, scourges, wellbeing issues, changes in health behaviors
• Monitor changes in contagious, natural, and environmental agents
• Pinpoint patients and their contacts for treatment and mediations
• Assess the viability of programs and control measures
• Develop hypotheses and fortify research

How can predictive analytics be used to help public health surveillance? It can be used to build predictive models to analyze data coming in from public health surveillance systems effectively. Some of the critical applications of predictive analytics in health surveillance are:

• predict the onset and spread of an infectious disease outbreak,
• environment health surveillance,
• pharmacovigilance,
• predict the probability of a natural disaster,
• determine the amount and types of vaccines required in various demographics,
• predict the likelihood of a biological or chemical attack,
• provide an estimate of multiple parameters in a clinical setting: health insurance risk profiling, staffing requirements, medical errors, appointments
• detect aberrations, which are recognizable proof of strange incidents or patterns in information, with clinical pertinence.