Knowledge discovery in databases of biomechanical variables: application to the sit to stand motor task

Abstract

ABSTRACT : BACKGROUND : The interpretation of data obtained in a movement analysis laboratory is a crucial issue in clinical contexts. Collection of such data in large databases might encourage the use of modern techniques of data mining to discover additional knowledge with automated methods. In order to maximise the size of the database, simple and low-cost experimental set-ups are preferable. The aim of this study was to extract knowledge inherent in the sit-to-stand task as performed by healthy adults, by searching relationships among measured and estimated biomechanical quantities. An automated method was applied to a large amount of data stored in a database. The sit-to-stand motor task was already shown to be adequate for determining the level of individual motor ability. METHODS : The technique of search for association rules was chosen to discover patterns as part of a Knowledge Discovery in Databases (KDD) process applied to a sit-to-stand motor task observed with a simple experimental set-up and analysed by means of a minimum measured input model. Selected parameters and variables of a database containing data from 110 healthy adults, of both genders and of a large range of age, performing the task were considered in the analysis. RESULTS : A set of rules and definitions were found characterising the patterns shared by the investigated subjects. Time events of the task turned out to be highly interdependent at least in their average values, showing a high level of repeatability of the timing of the performance of the task. CONCLUSIONS : The distinctive patterns of the sit-to-stand task found in this study, associated to those that could be found in similar studies focusing on subjects with pathologies, could be used as a reference for the functional evaluation of specific subjects performing the sit-to-stand motor task.

Figure 1

A scheme of the KDD process. Input data are initially selected and target data are isolated. Pre-processing and transformation are performed to ensure the database reliability. Data mining is the core analysis. The knowledge discovery process ends with the interpretation of the results.

Figure 2

Example of a discretisation process of a quantitative attribute. Grey areas represent the different partitions, i.e. the items. Vertical lines represent the values of the quantitative attribute.

Figure 3

The Apriori algorithm applied to the database under analysis. The two phases of the Apriori algorithm are highlighted. The first, referred as "join step" phase, aimed at the generation of the candidate itemsets C_k built starting from L_k-1, the frequent itemset of the previous phase. In the second phase the C_k itemsets underwent to a "pruning" procedure that selected the frequent itemsets L_k on the base of the support check.

Figure 4

Graphic cluster representation of both the rules and the definitions found in the study. The first ones, marked with a single-ended arrow, were found to have a confidence ranging from 86% to 96%. The second ones, marked with a double-ended arrow, both presented a confidence of 95%. Involved items are positioned according to the STS time subdivision (BSO and ASO phases and seat-off timing).