Prediction of Hypertension Outcomes Based on Gain Sequence Forward Tabu Search Feature Selection and XGBoost
For patients with hypertension, serious complications, such as myocardial infarction, a common cause of heart failure, occurs in the late stage of hypertension. Hypertension outcomes can lead to complications, including death. Hypertension outcomes threaten patients’ lives and need to be predicted....
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/11/5/792 |
| _version_ | 1797536044460015616 |
|---|---|
| author | Wenbing Chang Xinpeng Ji Yiyong Xiao Yue Zhang Bang Chen Houxiang Liu Shenghan Zhou |
| author_facet | Wenbing Chang Xinpeng Ji Yiyong Xiao Yue Zhang Bang Chen Houxiang Liu Shenghan Zhou |
| author_sort | Wenbing Chang |
| collection | DOAJ |
| description | For patients with hypertension, serious complications, such as myocardial infarction, a common cause of heart failure, occurs in the late stage of hypertension. Hypertension outcomes can lead to complications, including death. Hypertension outcomes threaten patients’ lives and need to be predicted. In our research, we reviewed the hypertension medical data from a tertiary-grade A class hospital in Beijing, and established a hypertension outcome prediction model with the machine learning theory. We first proposed a gain sequence forward tabu search feature selection (GSFTS-FS) method, which can search the optimal combination of medical variables that affect hypertension outcomes. Based on this, the XGBoost algorithm established a prediction model because of its good stability. We verified the proposed method by comparing other commonly used models in similar works. The proposed GSFTS-FS improved the performance by about 10%. The proposed prediction method has the best performance and its AUC value, accuracy, F1 value, and recall of 10-fold cross-validation were 0.96. 0.95, 0.88, and 0.82, respectively. It also performed well on test datasets with 0.92, 0.94, 0.87, and 0.80 for AUC, accuracy, F1, and recall, respectively. Therefore, the XGBoost with GSFTS-FS can accurately and effectively predict the occurrence of outcomes for patients with hypertension, and can provide guidance for doctors in clinical diagnoses and medical decision-making. |
| first_indexed | 2024-03-10T11:54:01Z |
| format | Article |
| id | doaj.art-59985cbeeaa54c63b29274fe40d79fa1 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T11:54:01Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-59985cbeeaa54c63b29274fe40d79fa12023-11-21T17:27:59ZengMDPI AGDiagnostics2075-44182021-04-0111579210.3390/diagnostics11050792Prediction of Hypertension Outcomes Based on Gain Sequence Forward Tabu Search Feature Selection and XGBoostWenbing Chang0Xinpeng Ji1Yiyong Xiao2Yue Zhang3Bang Chen4Houxiang Liu5Shenghan Zhou6School of Reliability and Systems Engineering, Beihang University, Beijing 100191, ChinaSchool of Reliability and Systems Engineering, Beihang University, Beijing 100191, ChinaSchool of Reliability and Systems Engineering, Beihang University, Beijing 100191, ChinaSchool of Reliability and Systems Engineering, Beihang University, Beijing 100191, ChinaSchool of Reliability and Systems Engineering, Beihang University, Beijing 100191, ChinaSchool of Reliability and Systems Engineering, Beihang University, Beijing 100191, ChinaSchool of Reliability and Systems Engineering, Beihang University, Beijing 100191, ChinaFor patients with hypertension, serious complications, such as myocardial infarction, a common cause of heart failure, occurs in the late stage of hypertension. Hypertension outcomes can lead to complications, including death. Hypertension outcomes threaten patients’ lives and need to be predicted. In our research, we reviewed the hypertension medical data from a tertiary-grade A class hospital in Beijing, and established a hypertension outcome prediction model with the machine learning theory. We first proposed a gain sequence forward tabu search feature selection (GSFTS-FS) method, which can search the optimal combination of medical variables that affect hypertension outcomes. Based on this, the XGBoost algorithm established a prediction model because of its good stability. We verified the proposed method by comparing other commonly used models in similar works. The proposed GSFTS-FS improved the performance by about 10%. The proposed prediction method has the best performance and its AUC value, accuracy, F1 value, and recall of 10-fold cross-validation were 0.96. 0.95, 0.88, and 0.82, respectively. It also performed well on test datasets with 0.92, 0.94, 0.87, and 0.80 for AUC, accuracy, F1, and recall, respectively. Therefore, the XGBoost with GSFTS-FS can accurately and effectively predict the occurrence of outcomes for patients with hypertension, and can provide guidance for doctors in clinical diagnoses and medical decision-making.https://www.mdpi.com/2075-4418/11/5/792hypertension outcomesbiomedical engineeringfeature selectiongain sequence forward tabu searchdisease predictionXGBoost |
| spellingShingle | Wenbing Chang Xinpeng Ji Yiyong Xiao Yue Zhang Bang Chen Houxiang Liu Shenghan Zhou Prediction of Hypertension Outcomes Based on Gain Sequence Forward Tabu Search Feature Selection and XGBoost Diagnostics hypertension outcomes biomedical engineering feature selection gain sequence forward tabu search disease prediction XGBoost |
| title | Prediction of Hypertension Outcomes Based on Gain Sequence Forward Tabu Search Feature Selection and XGBoost |
| title_full | Prediction of Hypertension Outcomes Based on Gain Sequence Forward Tabu Search Feature Selection and XGBoost |
| title_fullStr | Prediction of Hypertension Outcomes Based on Gain Sequence Forward Tabu Search Feature Selection and XGBoost |
| title_full_unstemmed | Prediction of Hypertension Outcomes Based on Gain Sequence Forward Tabu Search Feature Selection and XGBoost |
| title_short | Prediction of Hypertension Outcomes Based on Gain Sequence Forward Tabu Search Feature Selection and XGBoost |
| title_sort | prediction of hypertension outcomes based on gain sequence forward tabu search feature selection and xgboost |
| topic | hypertension outcomes biomedical engineering feature selection gain sequence forward tabu search disease prediction XGBoost |
| url | https://www.mdpi.com/2075-4418/11/5/792 |
| work_keys_str_mv | AT wenbingchang predictionofhypertensionoutcomesbasedongainsequenceforwardtabusearchfeatureselectionandxgboost AT xinpengji predictionofhypertensionoutcomesbasedongainsequenceforwardtabusearchfeatureselectionandxgboost AT yiyongxiao predictionofhypertensionoutcomesbasedongainsequenceforwardtabusearchfeatureselectionandxgboost AT yuezhang predictionofhypertensionoutcomesbasedongainsequenceforwardtabusearchfeatureselectionandxgboost AT bangchen predictionofhypertensionoutcomesbasedongainsequenceforwardtabusearchfeatureselectionandxgboost AT houxiangliu predictionofhypertensionoutcomesbasedongainsequenceforwardtabusearchfeatureselectionandxgboost AT shenghanzhou predictionofhypertensionoutcomesbasedongainsequenceforwardtabusearchfeatureselectionandxgboost |