Multivariate prediction of upper limb prosthesis acceptance or rejection

Objective. To develop a model for prediction of upper limb prosthesis use or rejection. Design. A questionnaire exploring factors in prosthesis acceptance was distributed internationally to individuals with upper limb absence through community-based support groups and rehabilitation hospitals. Subjects. A total of 191 participants (59 prosthesis rejecters and 132 prosthesis wearers) were included in this study. Methods. A logistic regression model, a C5.0 decision tree, and a radial basis function neural network were developed and compared in terms of sensitivity (prediction of prosthesis rejecters), specificity (prediction of prosthesis wearers), and overall cross-validation accuracy. Results. The logistic regression and neural network provided comparable overall accuracies of approximately 84 ± 3%, specificity of 93%, and sensitivity of 61%. Fitting time-frame emerged as the predominant predictor. Individuals fitted within two years of birth (congenital) or six months of amputation (acquired) were 16 times more likely to continue prosthesis use. Conclusions. To increase rates of prosthesis acceptance, clinical directives should focus on timely, client-centred fitting strategies and the development of improved prostheses and healthcare for individuals with high-level or bilateral limb absence. Multivariate analyses are useful in determining the relative importance of the many factors involved in prosthesis acceptance and rejection.

[1]  Jing Peng,et al.  Classifying Unbalanced Pattern Groups by Training Neural Network , 2006, ISNN.

[2]  A. Agresti.  An introduction to categorical data analysis , 1997 .

[3]  Zihua Hu,et al.  Utilization of two sample t-test statistics from redundant probe sets to evaluate different probe set algorithms in GeneChip studies , 2006, BMC Bioinformatics.

[4]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[5]  E. Biddiss,et al.  Upper-Limb Prosthetics: Critical Factors in Device Abandonment , 2007, American journal of physical medicine & rehabilitation.

[6]  A Mauro,et al.  Depression is the main determinant of quality of life in multiple sclerosis: A classification-regression (CART) study , 2006, Disability and rehabilitation.

[7]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[8]  Yves Chauvin,et al.  Backpropagation: theory, architectures, and applications , 1995 .

[9]  Tom Chau,et al.  The roles of predisposing characteristics, established need, and enabling resources on upper extremity prosthesis use and abandonment , 2007, Disability and rehabilitation. Assistive technology.

[10]  G. V. Kass.  An Exploratory Technique for Investigating Large Quantities of Categorical Data , 1980 .

[11]  David Biggs,et al.  A method of choosing multiway partitions for classification and decision trees , 1991 .

[12]  David W. Hosmer,et al.  Applied Logistic Regression , 1991 .

[13]  H. White,et al.  Logistic regression in the medical literature: standards for use and reporting, with particular attention to one medical domain. , 2001, Journal of clinical epidemiology.

[14]  R. Andersen.  Revisiting the behavioral model and access to medical care: does it matter? , 1995, Journal of health and social behavior.

[15]  J. Keating,et al.  An investigation of factors predictive of independence in transfers and ambulation after hip fracture. , 2002, Archives of physical medicine and rehabilitation.

[16]  Werner Dubitzky,et al.  Instance-based concept learning from multiclass DNA microarray data , 2005, BMC Bioinformatics.

[17]  E. Biddiss,et al.  Upper limb prosthesis use and abandonment: A survey of the last 25 years , 2007, Prosthetics and orthotics international.

[18]  Manuel Mazo,et al.  Hardware implementation of a new neurocontrol wheelchair-guidance system , 2002, Neurocomputing.

[19]  Harry J. P. Timmermans,et al.  Measuring the goodness-of-fit of decision-tree models of discrete and continuous activity-travel choice: methods and empirical illustration , 2003, J. Geogr. Syst..

[20]  Lipo Wang,et al.  Training RBF neural networks on unbalanced data , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[21]  Peter C Austin,et al.  Automated variable selection methods for logistic regression produced unstable models for predicting acute myocardial infarction mortality. , 2004, Journal of clinical epidemiology.

[22]  Jenny Strong,et al.  Factors that predict the post-discharge use of recommended assistive technology (AT) , 2006, Disability and rehabilitation. Assistive technology.

[23]  K M Means,et al.  Obstacle course performance and risk of falling in community-dwelling elderly persons. , 1998, Archives of physical medicine and rehabilitation.

[24]  Lianfen Qian,et al.  Regularized Radial Basis Function Networks: Theory and Applications , 2002, Technometrics.

[25]  R. Andersen,et al.  Understanding the context of healthcare utilization: assessing environmental and provider-related variables in the behavioral model of utilization. , 1998, Health services research.

[26]  Tom Chau,et al.  A radial basis classifier for the automatic detection of aspiration in children with dysphagia , 2006, Journal of NeuroEngineering and Rehabilitation.

[27]  Taeho Jo,et al.  A Multiple Resampling Method for Learning from Imbalanced Data Sets , 2004, Comput. Intell..

[28]  Marcus J Fuhrer,et al.  Rehabilitation medicine summit: building research capacity Executive Summary , 2006, Journal of NeuroEngineering and Rehabilitation.

[29]  Fong Chan,et al.  Predicting employment outcomes of rehabilitation clients with orthopedic disabilities: A CHAID analysis , 2006, Disability and rehabilitation.

[30]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[31]  S.D. Iftime,et al.  Automatic determination of synergies by radial basis function artificial neural networks for the control of a neural prosthesis , 2005, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[32]  Dong Ha Lee,et al.  Data mining approach to policy analysis in a health insurance domain , 2001, Int. J. Medical Informatics.

[33]  Yi Lu,et al.  Robust neural learning from unbalanced data samples , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[34]  Ulla Johansson,et al.  Predicting return to work after brain injury using occupational therapy assessments , 2001, Disability and rehabilitation.

[35]  David W. Hosmer,et al.  Best subsets logistic regression , 1989 .

[36]  D L Patrick,et al.  Correlates of exercise maintenance among people with mobility impairments. , 1999, Disability and rehabilitation.