The fourth part of the Mobility Analysis of AmpuTees (MAAT 4) study, published online February 11 in Disability and Rehabilitation: Assistive Technology, developed a classification tree analysis to determine the probability of a lower-limb prosthesis user’s functional potential. The resultant classification tree can provide the clinical care team with predictive probabilities of a patient’s functional potential, according to the study’s authors.
The researchers conducted a retrospective analysis of a database of outcomes for 2,770 lower-limb prosthesis users to inform a classification and regression tree analysis. Gender, age, height, weight, body mass index adjusted for amputation, amputation level, cause of amputation, comorbid health status, and a Prosthetic Limb Users Survey of Mobility (PLUS-M) T-score were entered as potential predictive variables. Patient K-level was used to assign dependent variable status as an unlimited community ambulator (i.e., K3 or K4) or a limited community/household ambulator (i.e., K1 or K2). The classification tree was initially trained from 20 percent of the sample and subsequently tested with the remaining sample.
The classification tree was able to accurately classify 87.4 percent of individuals within the model’s training group and 81.6 percent within the model’s testing group. Age, PLUS-M T-score, cause of amputation, and body weight were retained within the tree logic.