A Machine Learning Model for Predicting Unscheduled 72 h Return Visits to the Emergency Department by Patients with Abdominal Pain
Seventy-two-hour unscheduled return visits (URVs) by emergency department patients are a key clinical index for evaluating the quality of care in emergency departments (EDs). This study aimed to develop a machine learning model to predict 72 h URVs for ED patients with abdominal pain. Electronic hea...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/12/1/82 |
| _version_ | 1797494728604778496 |
|---|---|
| author | Chun-Chuan Hsu Cheng-C.J. Chu Ching-Heng Lin Chien-Hsiung Huang Chip-Jin Ng Guan-Yu Lin Meng-Jiun Chiou Hsiang-Yun Lo Shou-Yen Chen |
| author_facet | Chun-Chuan Hsu Cheng-C.J. Chu Ching-Heng Lin Chien-Hsiung Huang Chip-Jin Ng Guan-Yu Lin Meng-Jiun Chiou Hsiang-Yun Lo Shou-Yen Chen |
| author_sort | Chun-Chuan Hsu |
| collection | DOAJ |
| description | Seventy-two-hour unscheduled return visits (URVs) by emergency department patients are a key clinical index for evaluating the quality of care in emergency departments (EDs). This study aimed to develop a machine learning model to predict 72 h URVs for ED patients with abdominal pain. Electronic health records data were collected from the Chang Gung Research Database (CGRD) for 25,151 ED visits by patients with abdominal pain and a total of 617 features were used for analysis. We used supervised machine learning models, namely logistic regression (LR), support vector machine (SVM), random forest (RF), extreme gradient boosting (XGB), and voting classifier (VC), to predict URVs. The VC model achieved more favorable overall performance than other models (AUROC: 0.74; 95% confidence interval (CI), 0.69–0.76; sensitivity, 0.39; specificity, 0.89; F1 score, 0.25). The reduced VC model achieved comparable performance (AUROC: 0.72; 95% CI, 0.69–0.74) to the full models using all clinical features. The VC model exhibited the most favorable performance in predicting 72 h URVs for patients with abdominal pain, both for all-features and reduced-features models. Application of the VC model in the clinical setting after validation may help physicians to make accurate decisions and decrease URVs. |
| first_indexed | 2024-03-10T01:38:32Z |
| format | Article |
| id | doaj.art-83f88c107f9e4cc484d25e9e59e889c1 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T01:38:32Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-83f88c107f9e4cc484d25e9e59e889c12023-11-23T13:27:55ZengMDPI AGDiagnostics2075-44182021-12-011218210.3390/diagnostics12010082A Machine Learning Model for Predicting Unscheduled 72 h Return Visits to the Emergency Department by Patients with Abdominal PainChun-Chuan Hsu0Cheng-C.J. Chu1Ching-Heng Lin2Chien-Hsiung Huang3Chip-Jin Ng4Guan-Yu Lin5Meng-Jiun Chiou6Hsiang-Yun Lo7Shou-Yen Chen8Department of Emergency Medicine, Chang Gung Memorial Hospital and Chang Gung University, Linkou, Taoyuan City 333, TaiwanCenter for Artificial Intelligence in Medicine, Chang Gung Memorial Hospital, Linkou, Taoyuan City 333, TaiwanCenter for Artificial Intelligence in Medicine, Chang Gung Memorial Hospital, Linkou, Taoyuan City 333, TaiwanNew Taipei City Hospital, New Taipei City Government, New Taipei City 241, TaiwanDepartment of Emergency Medicine, Chang Gung Memorial Hospital and Chang Gung University, Linkou, Taoyuan City 333, TaiwanCenter for Artificial Intelligence in Medicine, Chang Gung Memorial Hospital, Linkou, Taoyuan City 333, TaiwanCenter for Artificial Intelligence in Medicine, Chang Gung Memorial Hospital, Linkou, Taoyuan City 333, TaiwanDepartment of Emergency Medicine, Chang Gung Memorial Hospital and Chang Gung University, Linkou, Taoyuan City 333, TaiwanDepartment of Emergency Medicine, Chang Gung Memorial Hospital and Chang Gung University, Linkou, Taoyuan City 333, TaiwanSeventy-two-hour unscheduled return visits (URVs) by emergency department patients are a key clinical index for evaluating the quality of care in emergency departments (EDs). This study aimed to develop a machine learning model to predict 72 h URVs for ED patients with abdominal pain. Electronic health records data were collected from the Chang Gung Research Database (CGRD) for 25,151 ED visits by patients with abdominal pain and a total of 617 features were used for analysis. We used supervised machine learning models, namely logistic regression (LR), support vector machine (SVM), random forest (RF), extreme gradient boosting (XGB), and voting classifier (VC), to predict URVs. The VC model achieved more favorable overall performance than other models (AUROC: 0.74; 95% confidence interval (CI), 0.69–0.76; sensitivity, 0.39; specificity, 0.89; F1 score, 0.25). The reduced VC model achieved comparable performance (AUROC: 0.72; 95% CI, 0.69–0.74) to the full models using all clinical features. The VC model exhibited the most favorable performance in predicting 72 h URVs for patients with abdominal pain, both for all-features and reduced-features models. Application of the VC model in the clinical setting after validation may help physicians to make accurate decisions and decrease URVs.https://www.mdpi.com/2075-4418/12/1/82unscheduled return visit72 hemergency departmentabdominal pain |
| spellingShingle | Chun-Chuan Hsu Cheng-C.J. Chu Ching-Heng Lin Chien-Hsiung Huang Chip-Jin Ng Guan-Yu Lin Meng-Jiun Chiou Hsiang-Yun Lo Shou-Yen Chen A Machine Learning Model for Predicting Unscheduled 72 h Return Visits to the Emergency Department by Patients with Abdominal Pain Diagnostics unscheduled return visit 72 h emergency department abdominal pain |
| title | A Machine Learning Model for Predicting Unscheduled 72 h Return Visits to the Emergency Department by Patients with Abdominal Pain |
| title_full | A Machine Learning Model for Predicting Unscheduled 72 h Return Visits to the Emergency Department by Patients with Abdominal Pain |
| title_fullStr | A Machine Learning Model for Predicting Unscheduled 72 h Return Visits to the Emergency Department by Patients with Abdominal Pain |
| title_full_unstemmed | A Machine Learning Model for Predicting Unscheduled 72 h Return Visits to the Emergency Department by Patients with Abdominal Pain |
| title_short | A Machine Learning Model for Predicting Unscheduled 72 h Return Visits to the Emergency Department by Patients with Abdominal Pain |
| title_sort | machine learning model for predicting unscheduled 72 h return visits to the emergency department by patients with abdominal pain |
| topic | unscheduled return visit 72 h emergency department abdominal pain |
| url | https://www.mdpi.com/2075-4418/12/1/82 |
| work_keys_str_mv | AT chunchuanhsu amachinelearningmodelforpredictingunscheduled72hreturnvisitstotheemergencydepartmentbypatientswithabdominalpain AT chengcjchu amachinelearningmodelforpredictingunscheduled72hreturnvisitstotheemergencydepartmentbypatientswithabdominalpain AT chinghenglin amachinelearningmodelforpredictingunscheduled72hreturnvisitstotheemergencydepartmentbypatientswithabdominalpain AT chienhsiunghuang amachinelearningmodelforpredictingunscheduled72hreturnvisitstotheemergencydepartmentbypatientswithabdominalpain AT chipjinng amachinelearningmodelforpredictingunscheduled72hreturnvisitstotheemergencydepartmentbypatientswithabdominalpain AT guanyulin amachinelearningmodelforpredictingunscheduled72hreturnvisitstotheemergencydepartmentbypatientswithabdominalpain AT mengjiunchiou amachinelearningmodelforpredictingunscheduled72hreturnvisitstotheemergencydepartmentbypatientswithabdominalpain AT hsiangyunlo amachinelearningmodelforpredictingunscheduled72hreturnvisitstotheemergencydepartmentbypatientswithabdominalpain AT shouyenchen amachinelearningmodelforpredictingunscheduled72hreturnvisitstotheemergencydepartmentbypatientswithabdominalpain AT chunchuanhsu machinelearningmodelforpredictingunscheduled72hreturnvisitstotheemergencydepartmentbypatientswithabdominalpain AT chengcjchu machinelearningmodelforpredictingunscheduled72hreturnvisitstotheemergencydepartmentbypatientswithabdominalpain AT chinghenglin machinelearningmodelforpredictingunscheduled72hreturnvisitstotheemergencydepartmentbypatientswithabdominalpain AT chienhsiunghuang machinelearningmodelforpredictingunscheduled72hreturnvisitstotheemergencydepartmentbypatientswithabdominalpain AT chipjinng machinelearningmodelforpredictingunscheduled72hreturnvisitstotheemergencydepartmentbypatientswithabdominalpain AT guanyulin machinelearningmodelforpredictingunscheduled72hreturnvisitstotheemergencydepartmentbypatientswithabdominalpain AT mengjiunchiou machinelearningmodelforpredictingunscheduled72hreturnvisitstotheemergencydepartmentbypatientswithabdominalpain AT hsiangyunlo machinelearningmodelforpredictingunscheduled72hreturnvisitstotheemergencydepartmentbypatientswithabdominalpain AT shouyenchen machinelearningmodelforpredictingunscheduled72hreturnvisitstotheemergencydepartmentbypatientswithabdominalpain |