Extraction of information on elder motor ability from clinical and biomechanical data through data mining.

This study aimed at evaluating the additional knowledge provided by a biomechanical test coupled with clinical tests for motor ability assessment. A database including clinical test scores and sit-to-stand test variables obtained from 110 medically stable elderly subjects was submitted to data mining by searching for association rules. The presence of rules revealed some redundancies due to sample homogeneity, as mainly observed in the joint analysis of a questionnaire for daily activities assessment (Nottingham test) and the sit-to-stand, and due to similar evaluated information, as resulted from the joint analysis of a balance and gait scale (Tinetti test) and the sit-to-stand. Conversely, when no association rules were found, the tests carried unrelated information. The associations mined while analysing these clinical tests encouraged the integration of biomechanical tests, increasing significantly its clinical applicability and reducing the information redundancy. The information extracted also allowed to highlight rules typical of elderly persons that may serve as a knowledge-based tool for the detection of possible deviation from normality.