Comparison of logistic regression and neural network analysis applied to predicting living setting after hip fracture

• Published in: Annals of epidemiology 2004-09, Vol.14 (8), p.551-559
• Main Authors: Ottenbacher, Kenneth J., Linn, Richard T., Smith, Pamela M., Illig, Sandra B., Mancuso, Melodee, Granger, Carl V.
• Format: Article
• Language: English
• Subjects: Aged; Algorithms; Female; Follow-Up Studies; Hip - physiopathology; Hip Fractures - ethnology; Hip Fractures - rehabilitation; Hip Fractures - therapy; Humans; Insurance, Health; Joint Replacement; Length of Stay; Logistic Models; Male; Marital Status; Middle Aged; Multivariate Analysis; Neural Networks (Computer); Rehabilitation Outcomes; Treatment Outcome
• ISSN: 1047-2797; 1873-2585
• DOI: 10.1016/j.annepidem.2003.10.005

Describe and compare the characteristics of artificial neural networks and logistic regression to develop prediction models in epidemiological research. The sample included 3708 persons with hip fracture from 46 different states included in the Uniform Data System for Medical Rehabilitation. Mean age was 75.5 years (sd=14.2), 73.7% of patients were female, and 82% were non-Hispanic white. Average length of stay was 17.0 days (sd=10.6). The primary outcome measure was living setting (at home vs. not at home) at 80 to 180 days after discharge. Statistically significant variables (p < .05) in the logistic model included follow-up therapy, sphincter control, self-care ability, marital status, age, and length of stay. Areas under the receiver operating characteristic curves were 0.67 for logistic regression and 0.73 for neural network analysis. Calibration curves indicated a slightly better fit for the neural network model. Follow-up therapy and independent bowel and/or bladder function were strong predictors of living at home up to 6 months after hospitalization for hip fracture. No practical differences were found between the predictive ability of logistic regression and neural network analysis in this sample.