Decision support and expert systems are information systems assisting in data analysis meant for decision making. Decision support systems rely on straightforward and simpler knowledge while expert systems deal with complex and substantial facts, rules and policies representations. The main goal of these systems is to incorporate external knowledge in data analysis process with the effort to improve on speed, consistency and accuracy of human decision making.
Three basic reasons exist as to why decision support and expert systems are required in public health. For one, they are required to increase quantity of data (O’Carroll, 2003). Secondly, they are needed in betterment of dissemination of best practices. In the current period, public health is under the threat of bioterrorism. Thus, these systems are required so that such threats are detected before they strike. This will help to limit mortality and morbidity. In decision support and expert systems, tabular knowledge is that which has been tabulated.
It represents forecasting parameters of every dose like minimum wait-intervals from past doses, recommended minimum age and minimum acceptable age. On the other hand, rule-based knowledge applies “if-then” rule in storing clinical logic to determine the time a dose should be given and the set of tabular parameters that may apply to a given patient at a time. This is a rule that also determines several factors like what vaccine preparation must be recommended where alternatives do exist. Rules are commonly used by decision support systems in public health in encoding small atomistic “chunks” of logic.
In public health, decision support systems use procedural logic also referred to as conventional computer programs in representing certain aspects of immunization knowledge which may be complex and is not expected to change over time (O’Carroll, 2003). Decision support and expert systems may only thrive in an organization with certain characteristics. These systems may only thrive in an environment that has diversity in its background, goals, and skills; uncertainty, complete and clear information dissemination, ambiguity, mutual respect, trust and putting individual views second to those of the team.
There must also be a reward organization structure which promotes shared accountability and responsibility. In public health, when developing these systems, the team must take into consideration the availability of internet that has a common network in addition to the user interface. This may reduce system development cost and make it easy for widespread deployment. The team must also improve compliance in preventive medicine guidelines. Developing decision support and expert system calls for the team to consider not only the kind of problem to be solved but also the appropriate and needed computational tools (O’Carroll, 2003).
Objectives must be defined; model structuring that incorporates identifying relationships between cost factors, parameters and value judgments. Moreover, they must consider how they will gather and present their case studies the moment their decision support and expert system is developed. References Convis, C. The Nature of Geographic Information Systems, 1996. Retrieved from http://www. conservationgis. org/gishistory/gishistry2. html Nbdpn. org. Use of Geographic Information Systems (GIS) to map data, 2008.
Retrieved from http://www. nbdpn. org/current/resources/sgm/Appendix11-2. pdf O’Carroll, P. W. (2003). Public health informatics and information systems, Berlin: Springer. Smith, R. & Dircks, C. J. Maximizing Value through GIS Organizational Design, 2007. Retrieved from http://www. directionsmag. com/article. php? article_id=2416 Tanser, F. C. , & Sueur, D. L. The application of geographical information systems to important public health problems in Africa, 2002. Retrieved from http://www. ncbi. nlm. nih. gov/pmc/articles/PMC149399/