Statistics and Deep Belief Network-Based Cardiovascular Risk Prediction
ObjectivesCardiovascular predictions are related to patients' quality of life and health. Therefore, a risk prediction model for cardiovascular conditions is needed.MethodsIn this paper, we propose a cardiovascular disease prediction model using the sixth Korea National Health and Nutrition Exa...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Korean Society of Medical Informatics
2017-07-01
|
| Series: | Healthcare Informatics Research |
| Subjects: | |
| Online Access: | http://e-hir.org/upload/pdf/hir-23-169.pdf |
| _version_ | 1798025701359616000 |
|---|---|
| author | Jaekwon Kim Ungu Kang Youngho Lee |
| author_facet | Jaekwon Kim Ungu Kang Youngho Lee |
| author_sort | Jaekwon Kim |
| collection | DOAJ |
| description | ObjectivesCardiovascular predictions are related to patients' quality of life and health. Therefore, a risk prediction model for cardiovascular conditions is needed.MethodsIn this paper, we propose a cardiovascular disease prediction model using the sixth Korea National Health and Nutrition Examination Survey (KNHANES-VI) 2013 dataset to analyze cardiovascular-related health data. First, statistical analysis was performed to find variables related to cardiovascular disease using health data related to cardiovascular disease. Second, a model of cardiovascular risk prediction by learning based on the deep belief network (DBN) was developed.ResultsThe proposed statistical DBN-based prediction model showed accuracy and an ROC curve of 83.9% and 0.790, respectively. Thus, the proposed statistical DBN performed better than other prediction algorithms.ConclusionsThe DBN proposed in this study appears to be effective in predicting cardiovascular risk and, in particular, is expected to be applicable to the prediction of cardiovascular disease in Koreans. |
| first_indexed | 2024-04-11T18:23:05Z |
| format | Article |
| id | doaj.art-55d7b05306cc495989425e0c6acae860 |
| institution | Directory Open Access Journal |
| issn | 2093-3681 2093-369X |
| language | English |
| last_indexed | 2024-04-11T18:23:05Z |
| publishDate | 2017-07-01 |
| publisher | The Korean Society of Medical Informatics |
| record_format | Article |
| series | Healthcare Informatics Research |
| spelling | doaj.art-55d7b05306cc495989425e0c6acae8602022-12-22T04:09:43ZengThe Korean Society of Medical InformaticsHealthcare Informatics Research2093-36812093-369X2017-07-0123316917510.4258/hir.2017.23.3.169886Statistics and Deep Belief Network-Based Cardiovascular Risk PredictionJaekwon Kim0Ungu Kang1Youngho Lee2Department of Computer and Information Engineering, Inha University, Incheon, Korea.IT Department, Gachon University, Seongnam, Korea.IT Department, Gachon University, Seongnam, Korea.ObjectivesCardiovascular predictions are related to patients' quality of life and health. Therefore, a risk prediction model for cardiovascular conditions is needed.MethodsIn this paper, we propose a cardiovascular disease prediction model using the sixth Korea National Health and Nutrition Examination Survey (KNHANES-VI) 2013 dataset to analyze cardiovascular-related health data. First, statistical analysis was performed to find variables related to cardiovascular disease using health data related to cardiovascular disease. Second, a model of cardiovascular risk prediction by learning based on the deep belief network (DBN) was developed.ResultsThe proposed statistical DBN-based prediction model showed accuracy and an ROC curve of 83.9% and 0.790, respectively. Thus, the proposed statistical DBN performed better than other prediction algorithms.ConclusionsThe DBN proposed in this study appears to be effective in predicting cardiovascular risk and, in particular, is expected to be applicable to the prediction of cardiovascular disease in Koreans.http://e-hir.org/upload/pdf/hir-23-169.pdfcardiovascular diseasesdeep belief networkmachine learningcardiovascular risk predictionknhanes |
| spellingShingle | Jaekwon Kim Ungu Kang Youngho Lee Statistics and Deep Belief Network-Based Cardiovascular Risk Prediction Healthcare Informatics Research cardiovascular diseases deep belief network machine learning cardiovascular risk prediction knhanes |
| title | Statistics and Deep Belief Network-Based Cardiovascular Risk Prediction |
| title_full | Statistics and Deep Belief Network-Based Cardiovascular Risk Prediction |
| title_fullStr | Statistics and Deep Belief Network-Based Cardiovascular Risk Prediction |
| title_full_unstemmed | Statistics and Deep Belief Network-Based Cardiovascular Risk Prediction |
| title_short | Statistics and Deep Belief Network-Based Cardiovascular Risk Prediction |
| title_sort | statistics and deep belief network based cardiovascular risk prediction |
| topic | cardiovascular diseases deep belief network machine learning cardiovascular risk prediction knhanes |
| url | http://e-hir.org/upload/pdf/hir-23-169.pdf |
| work_keys_str_mv | AT jaekwonkim statisticsanddeepbeliefnetworkbasedcardiovascularriskprediction AT ungukang statisticsanddeepbeliefnetworkbasedcardiovascularriskprediction AT youngholee statisticsanddeepbeliefnetworkbasedcardiovascularriskprediction |