Chronic Disease Prediction Using Character-Recurrent Neural Network in The Presence of Missing Information
The aim of this study was to predict chronic diseases in individual patients using a character-recurrent neural network (Char-RNN), which is a deep learning model that treats data in each class as a word when a large portion of its input values is missing. An advantage of Char-RNN is that it does no...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/10/2170 |
| _version_ | 1828858212114235392 |
|---|---|
| author | Changgyun Kim Youngdoo Son Sekyoung Youm |
| author_facet | Changgyun Kim Youngdoo Son Sekyoung Youm |
| author_sort | Changgyun Kim |
| collection | DOAJ |
| description | The aim of this study was to predict chronic diseases in individual patients using a character-recurrent neural network (Char-RNN), which is a deep learning model that treats data in each class as a word when a large portion of its input values is missing. An advantage of Char-RNN is that it does not require any additional imputation method because it implicitly infers missing values considering the relationship with nearby data points. We applied Char-RNN to classify cases in the Korea National Health and Nutrition Examination Survey (KNHANES) VI as normal status and five chronic diseases: hypertension, stroke, angina pectoris, myocardial infarction, and diabetes mellitus. We also employed a multilayer perceptron network for the same task for comparison. The results show higher accuracy for Char-RNN than for the conventional multilayer perceptron model. Char-RNN showed remarkable performance in finding patients with hypertension and stroke. The present study utilized the KNHANES VI data to demonstrate a practical approach to predicting and managing chronic diseases with partially observed information. |
| first_indexed | 2024-12-13T01:53:05Z |
| format | Article |
| id | doaj.art-4bb44a13d4ed45a89f38f96baa3f2d2a |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-13T01:53:05Z |
| publishDate | 2019-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-4bb44a13d4ed45a89f38f96baa3f2d2a2022-12-22T00:03:28ZengMDPI AGApplied Sciences2076-34172019-05-01910217010.3390/app9102170app9102170Chronic Disease Prediction Using Character-Recurrent Neural Network in The Presence of Missing InformationChanggyun Kim0Youngdoo Son1Sekyoung Youm2Department of Industrial and Systems Engineering, Dongguk University—Seoul, Seoul 04620, KoreaDepartment of Industrial and Systems Engineering, Dongguk University—Seoul, Seoul 04620, KoreaDepartment of Industrial and Systems Engineering, Dongguk University—Seoul, Seoul 04620, KoreaThe aim of this study was to predict chronic diseases in individual patients using a character-recurrent neural network (Char-RNN), which is a deep learning model that treats data in each class as a word when a large portion of its input values is missing. An advantage of Char-RNN is that it does not require any additional imputation method because it implicitly infers missing values considering the relationship with nearby data points. We applied Char-RNN to classify cases in the Korea National Health and Nutrition Examination Survey (KNHANES) VI as normal status and five chronic diseases: hypertension, stroke, angina pectoris, myocardial infarction, and diabetes mellitus. We also employed a multilayer perceptron network for the same task for comparison. The results show higher accuracy for Char-RNN than for the conventional multilayer perceptron model. Char-RNN showed remarkable performance in finding patients with hypertension and stroke. The present study utilized the KNHANES VI data to demonstrate a practical approach to predicting and managing chronic diseases with partially observed information.https://www.mdpi.com/2076-3417/9/10/2170Human factordeep learningcharacter recurrent neural networkstatistic learninghealth carechronic diseasedata mininganalysis |
| spellingShingle | Changgyun Kim Youngdoo Son Sekyoung Youm Chronic Disease Prediction Using Character-Recurrent Neural Network in The Presence of Missing Information Applied Sciences Human factor deep learning character recurrent neural network statistic learning health care chronic disease data mining analysis |
| title | Chronic Disease Prediction Using Character-Recurrent Neural Network in The Presence of Missing Information |
| title_full | Chronic Disease Prediction Using Character-Recurrent Neural Network in The Presence of Missing Information |
| title_fullStr | Chronic Disease Prediction Using Character-Recurrent Neural Network in The Presence of Missing Information |
| title_full_unstemmed | Chronic Disease Prediction Using Character-Recurrent Neural Network in The Presence of Missing Information |
| title_short | Chronic Disease Prediction Using Character-Recurrent Neural Network in The Presence of Missing Information |
| title_sort | chronic disease prediction using character recurrent neural network in the presence of missing information |
| topic | Human factor deep learning character recurrent neural network statistic learning health care chronic disease data mining analysis |
| url | https://www.mdpi.com/2076-3417/9/10/2170 |
| work_keys_str_mv | AT changgyunkim chronicdiseasepredictionusingcharacterrecurrentneuralnetworkinthepresenceofmissinginformation AT youngdooson chronicdiseasepredictionusingcharacterrecurrentneuralnetworkinthepresenceofmissinginformation AT sekyoungyoum chronicdiseasepredictionusingcharacterrecurrentneuralnetworkinthepresenceofmissinginformation |