Sequential patterns

Roa and Deigo (No date) state “Sequential Patterns: This technique detects cause-effect relations considering the time periods in which transactions occurred. In health care context, there are many situations that involve periodic controls and patient’s monitoring. As mentioned before, standards, clinical guidelines, and protocols specify sequences of treatments that should be applied in an explicit situation. For this reason, it is feasible to compare the patient’s procedures versus reference guides using sequential patterns. Chronic diseases like hypertension or diabetes require that patients return to the IPS several times with the same diagnosis. This kind of problems involves many variables in each time period. The recommendation is to use sequential patterns to analyze the evolution of patient’s health based on the treatments applied. Based on the concept that, at any given time, a clinical event is the formulation of one or more drugs or procedures we propose the creation of two data sets, drugs and procedures datasets. In this case, the records should be grouped by the patient, ordering clinical events in ascending order by date and time.”

It is very interesting that health care makes use of cluster analysis as well. “In healthcare, is very common to analyze populations based on specific characteristics. In this case, the use of clustering determines subsets based on procedures and demographic information. In addition, there are situations in which data quality is poor. For this reason, it’s impossible to analyze particular issues in the dataset because of the confidence of data. The suggestion is to use clustering techniques to generalize the main characteristics of a specific group. To perform these analyses, a data set must be created which includes patient information such as gender, age, marital status, and race, (among others), as well as drugs and/or procedures provided, grouped into treatments found in the previous section. As in previous algorithms, it is important to analyze the number of people supporting each cluster, before making any conclusions.  (Roa and Deigo, [no date]).”


Roa, D. and Deigo, J. ([No date]) Process model for data mining in health care sector. Available at: http://ceur-ws.org/Vol-729/paper3.pdf (Accessed: 12 June 2017)


Leave a Reply

Your email address will not be published. Required fields are marked *