Predicting the Risk of Osteoporosis Using Decision Tree and Neural Network
Introduction: Osteoporosis is one of the major causes of disability and death in elderly people. The objective of this study was to determine the factors affecting the incidence of osteoporosis and provide a predictive model to accelerate diagnosis and reduce costs. Method: In this fundamental descr...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | fas |
| Published: |
Kerman University of Medical Sciences
2020-12-01
|
| Series: | مجله انفورماتیک سلامت و زیست پزشکی |
| Subjects: | |
| Online Access: | http://jhbmi.ir/article-1-453-en.html |
| _version_ | 1811176324919721984 |
|---|---|
| author | Amin Abedini Efat Jabarpour Abbasali Keshtkar |
| author_facet | Amin Abedini Efat Jabarpour Abbasali Keshtkar |
| author_sort | Amin Abedini |
| collection | DOAJ |
| description | Introduction: Osteoporosis is one of the major causes of disability and death in elderly people. The objective of this study was to determine the factors affecting the incidence of osteoporosis and provide a predictive model to accelerate diagnosis and reduce costs.
Method: In this fundamental descriptive study, a new model was proposed to identify the factors affecting osteoporosis. Data related to 4083 women were investigated with Clementine12, the data mining tool, to discover knowledge. Using data mining algorithms, including decision tree and artificial neural network, some rules were extracted that can be used as a model to predict the condition of patients and finally, the accuracy of the proposed models were compared.
Results: This study examined several models on a number of different characteristics and compared the results in terms of accuracy to find the best predictive model. The classification accuracy of the MLP neural network model was 92.14% which was higher than that of the other algorithms used in this study. According to the identification of factors affecting osteoporosis, the risk of developing this disease can be predicted for a new sample.
Conclusion: Healthcare organizations are always gathering a lot of information while this data is not used properly. This study showed that the hidden patterns and relationships in this data can be discovered and used to improve the quality of diagnostic and treatment services. |
| first_indexed | 2024-04-10T19:51:00Z |
| format | Article |
| id | doaj.art-be01ae9e890c4a619895c1e5e9c464a6 |
| institution | Directory Open Access Journal |
| issn | 2423-3870 2423-3498 |
| language | fas |
| last_indexed | 2024-04-10T19:51:00Z |
| publishDate | 2020-12-01 |
| publisher | Kerman University of Medical Sciences |
| record_format | Article |
| series | مجله انفورماتیک سلامت و زیست پزشکی |
| spelling | doaj.art-be01ae9e890c4a619895c1e5e9c464a62023-01-28T10:30:25ZfasKerman University of Medical Sciencesمجله انفورماتیک سلامت و زیست پزشکی2423-38702423-34982020-12-0173304317Predicting the Risk of Osteoporosis Using Decision Tree and Neural NetworkAmin Abedini0Efat Jabarpour1Abbasali Keshtkar2 M.Sc. in Artificial Intelligence, Computer and IT Engineering, Islamic Azad University of Qazvin, Qazvin, Iran Ph.D. Candidate in Industrial Management, Faculty of Management, University of Tehran, Tehran, Iran Associate Professor, Health Sciences Education Development Dept., Faculty of Public Health, Tehran University of Medical Sciences, Tehran, Iran Introduction: Osteoporosis is one of the major causes of disability and death in elderly people. The objective of this study was to determine the factors affecting the incidence of osteoporosis and provide a predictive model to accelerate diagnosis and reduce costs. Method: In this fundamental descriptive study, a new model was proposed to identify the factors affecting osteoporosis. Data related to 4083 women were investigated with Clementine12, the data mining tool, to discover knowledge. Using data mining algorithms, including decision tree and artificial neural network, some rules were extracted that can be used as a model to predict the condition of patients and finally, the accuracy of the proposed models were compared. Results: This study examined several models on a number of different characteristics and compared the results in terms of accuracy to find the best predictive model. The classification accuracy of the MLP neural network model was 92.14% which was higher than that of the other algorithms used in this study. According to the identification of factors affecting osteoporosis, the risk of developing this disease can be predicted for a new sample. Conclusion: Healthcare organizations are always gathering a lot of information while this data is not used properly. This study showed that the hidden patterns and relationships in this data can be discovered and used to improve the quality of diagnostic and treatment services.http://jhbmi.ir/article-1-453-en.htmlosteoporosisdata miningdecision treeartificial neural networkclementine |
| spellingShingle | Amin Abedini Efat Jabarpour Abbasali Keshtkar Predicting the Risk of Osteoporosis Using Decision Tree and Neural Network مجله انفورماتیک سلامت و زیست پزشکی osteoporosis data mining decision tree artificial neural network clementine |
| title | Predicting the Risk of Osteoporosis Using Decision Tree and Neural Network |
| title_full | Predicting the Risk of Osteoporosis Using Decision Tree and Neural Network |
| title_fullStr | Predicting the Risk of Osteoporosis Using Decision Tree and Neural Network |
| title_full_unstemmed | Predicting the Risk of Osteoporosis Using Decision Tree and Neural Network |
| title_short | Predicting the Risk of Osteoporosis Using Decision Tree and Neural Network |
| title_sort | predicting the risk of osteoporosis using decision tree and neural network |
| topic | osteoporosis data mining decision tree artificial neural network clementine |
| url | http://jhbmi.ir/article-1-453-en.html |
| work_keys_str_mv | AT aminabedini predictingtheriskofosteoporosisusingdecisiontreeandneuralnetwork AT efatjabarpour predictingtheriskofosteoporosisusingdecisiontreeandneuralnetwork AT abbasalikeshtkar predictingtheriskofosteoporosisusingdecisiontreeandneuralnetwork |