Sample: this helps to slim down the processing time by selection of a representative sample to get a crucial information. Some of the strategies include simple random and the stratification of samples that is a representation of the needed subgroups. It enables extraction of information that are critical. It obviates the problems of data validation, production of substandard results. This could be related to the program to determine the number of cases of individuals moved by the Ebola virus and hence the data should be the number of the great unwashed who are already with the virus.
Explore: one of the means of exploration is visualization, and its standard method is decided where the data is linked to a peculiar area. If the given data are not right for visualization then, there is the option of summarization that uses the advanced statistical methods. This relates to the studying and investigation of a situation that a disease has already spread to. The information gathered can be used to quarantine.
Modify: this can be used when a lot of data is missing by replacing them with a mean, median or a data by the user preference. This at times helps to improve a model set. This can be effected in a scenario where a set of drugs utilized for the cure of a particular disease run out, then an alternative can be provided that has the same result.
Model: this helps in the recognition of what induces a peculiar form in a gifted problem. In one case the rules have been planted, then they can be worked through, modelling techniques. In the case of an outbreak of chicken pox, let's say in a school environment that happens in a particular time of the year and so this can be habituated. It will help figure out why it recurs the same time.
Assess: a model can be measured through the application of providing data sets obtained during the sampling point, and if the model is valid then it is expected to operate for all samples. In the instance of an outbreak, a model proposed can be valued by giving medication to a sample taken to examine if the model works or not before going along.
References
Armoni, A. (2000). Healthcare information systems (1st ed.). Hershey, Pa.: Idea Group Pub.
Dave Smith, S., & Marlow, U. (2007). Data Mining in the Clinical Research Environment. Phuse.
Obenshain, M. (2004). Application of data mining techniques to healthcare data. Infection Control And Hospital Epidemiology, 25(8), 690--695.
Rohanizadeh, S., & Moghadam, M. (2009). A proposed data mining methodology and its application to industrial procedures. J. Industr. Eng, (4), 37--50.
