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

Ottenbacher, Kenneth J.; Linn, Richard T.; Smith, Pamela M.; Illig, Sandra B.; Mancuso, Melodee G.; Granger, Carl V.

doi:10.1016/j.annepidem.2003.10.005

Cited by 51 publications

(45 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The receiver operating characteristic (ROC) curve analysis has been widely applied as a useful tool to evaluate performances of classifiers (Lin et al, 2006;Ottenbacher et al, 2001;Ottenbacher et al, 2004;Yeh et al, 2009). In this study, the ROC curve analysis was also applied to estimate the discrimination power of the prediction models.…”

Section: Evaluation Of the Predictive Performancementioning

confidence: 99%

“…Eller-Vainicher et al (2011) identified the promising role of ANN in predicting osteoporotic fracture among postmenopause osteoporosis women. For the comparison of the characteristics between ANNs and logistic regression applied to this epidemiological research field, a study has established prediction models for predicting living setting after hip fracture by ANNs and logistic regression, and shown that ANN is slightly better than logistic regression (Ottenbacher et al, 2004). Lin et al found ANN algorithm could reliably predict the mortality of hip fractured patients and outperforms the logistic regression method .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Ensemble artificial neural networks applied to predict the key risk factors of hip bone fracture for elders

Liu

Cui

Chou

et al. 2015

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

Hip bone fracture is one of the most important causes of morbidity and mortality in the elder adults. It is necessary to establish a prediction model to provide suggestions for elders. A total of 725 subjects were involved, including 228 patients with first low-trauma hip fracture and 497 ages-, sex-, and living area-matched controls (215 from the same hospital and 282 from community). All the subjects were interviewed with the same questionnaire, and the answers of the interviewees were recorded to be the database. Three-layer back-propagation Artificial Neural Networks (ANN) models were applied for females and males separately in this study to predict the risk of hip bone fracture for elders. Furthermore, to improve the accuracies and the generalizations of the models, the ensemble ANNs method was applied. To understand variables contributions and find the important variables for predicting hip fracture, sensitivity analysis and connection weights approach were applied. In this study, three ANNs prediction models were tested with different architectures. With the fivefold crossvalidation method evaluating the performances, one of the three models turned out to be the best prediction model and achieved a big success of prediction. The best area under the receiver operating characteristic (ROC) curve and the accuracy of the prediction model are 0.91 ± 0.028 (mean ± SD) and 0.85 ± 0.029 for females, while for males are 0.99 ± 0.015 and 0.93 ± 0.020. With the method of sensitivity analysis and connection weights, input variables were ranked according to contributions/importance, and the top 10 variables show great proportion of contribution to predict hip fracture. The top 10 important variables causing hip fracture for both females and males are similar to our previous results got from logistic regression model and other related researches. In conclusion, ANNs has successfully been to establish prediction models for predicting the risk of hip bone fracture for both female and male elder adults respectively and identified the top 10 important variables from 74 input variables to predict hip bone fracture of elders. This study verified the performance of ANNs to be a highly complex prediction model. Sept 2014Dear Prof. R. Allen, I use the electronic version to send this manuscript to you. The manuscript title is: "Ensemble back-propagation neural networks for predicting the risk of hip bone fracture for elders in Taiwan". We are submitting this material for possible publication in "Biomedical Signal Processing and Control". This material has not been submitted for publication or published elsewhere in whole or part. We believe this manuscript represents an original and significant contribution to the field of "Neural networks for predicting the risk of hip bone fracture" and therefore would like to be considered for publication in "Original Articles". AbstractHip bone fracture is one of the most important causes of morbidity and mortality in the elder adults. It is necessary to establish a prediction mod...

show abstract

Section: Evaluation Of the Predictive Performancementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Ensemble artificial neural networks applied to predict the key risk factors of hip bone fracture for elders

Liu

Cui

Chou

et al. 2015

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

show abstract

“…A number of recent works [9,10] have applied machinelearning techniques to predicting various rehabilitation outcomes. Although some of these results have been promising [9], others have been equivocal [10].…”

Section: Objectivesmentioning

confidence: 99%

“…Although some of these results have been promising [9], others have been equivocal [10]. In this study, we investigate whether an automatic, data-driven, machinelearning algorithm is capable of accurately assessing a patient's rehabilitation potential.…”

Section: Objectivesmentioning

confidence: 99%

The K-nearest neighbor algorithm predicted rehabilitation potential better than current Clinical Assessment Protocol

Zhu

Chen

Hirdes

et al. 2007

Journal of Clinical Epidemiology

View full text Add to dashboard Cite

Objective: There may be great potential for using computer-modeling techniques and machine-learning algorithms in clinical decision making, if these can be shown to produce results superior to clinical protocols currently in use. We aim to explore the potential to use an automatic, data-driven, machine-learning algorithm in clinical decision making.Study Design and Setting: Using a database containing comprehensive health assessment information (the interRAI-HC) on home care clients (N 5 24,724) from eight community-care regions in Ontario, Canada, we compare the performance of the K-nearest neighbor (KNN) algorithm and a Clinical Assessment Protocol (the ''ADLCAP'') currently used to predict rehabilitation potential. For our purposes, we define a patient as having rehabilitation potential if the patient had functional improvement or remained at home over a follow-up period of approximately 1 year.Results: The KNN algorithm has a lower false positive rate in all but one of the eight regions in the sample, and lower false negative rates in all regions. Compared using likelihood ratio statistics, KNN is uniformly more informative than the ADLCAP.Conclusion: This article illustrates the potential for a machine-learning algorithm to enhance clinical decision making. Ó 2007 Elsevier Inc. All rights reserved.

show abstract

“…Figure 3: Linear regression vs Logistic regression (Sayad, 2012) The assumption is that the predictor variables, Xi, are related linearly to the odds of log ( 1− ) for the outcome of interest (Ottenbacher, Linn, Smith, Illig, Mancuso, & Granger, 2004), and that there exists a hyperplane, or decision boundary, of all points X i that separates successful events from failed events (Dreiseitl & Ohno-Machado, 2002).…”

Section: Logistic Regressionmentioning

confidence: 99%

Utilization of Classification Methods on Bridge Databases in Virginia

Copeland

View full text Add to dashboard Cite

The National Bridge Inventory (NBI) was created in 1972, and stores all the information collected from these inspections. It is the largest collection of bridge data in the world and contains detailed information on more than 600,000 United States highway bridges and large culverts. Pontis is a bridge management system and product of the American Association of State Highway and Transportation Officials (AASHTO). Pontis has the capability of storing and analyzing bridge inspection and inventory data, recommending optimal preservation policies, predicting needs and performance measures for bridges, and developing projects to include in an agency's capital plan.Previously, there has been little analysis performed on the VDOT Pontis and NBI from the perspective of data mining; therefore, the objectives of this study are to consolidate and compile multiple bridge data sets, and to discover previously unknown patterns and trends in the data using data mining and classification methods. The scope of the study includes the application of six classification methods on bridge inspection data to determine when certain bridge types will become structurally deficient. Bridge attributes studied include age, average daily traffic (ADT), truck percentage, district, element condition state, and presence of smart flag elements, and the significance of each is discussed.Overall, classification methods produced strong results as classifiers of structural deficiency of bridges. The comparison of each classification method using the Orange data mining software is conducted and descriptions and performance of bridges in Virginia have been investigated and are presented in the following sections.iv ACKNOWLEDGEMENTS

show abstract

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

Cited by 51 publications

References 25 publications

Ensemble artificial neural networks applied to predict the key risk factors of hip bone fracture for elders

Ensemble artificial neural networks applied to predict the key risk factors of hip bone fracture for elders

The K-nearest neighbor algorithm predicted rehabilitation potential better than current Clinical Assessment Protocol

Utilization of Classification Methods on Bridge Databases in Virginia

Contact Info

Product

Resources

About