Machine Learning-Based Models for Prediction of Critical Illness at Community, Paramedic, and Hospital Stages
Overcrowding of emergency department (ED) has put a strain on national healthcare systems and adversely affected the clinical outcomes of critically ill patients. Early identification of critically ill patients prior to ED visits can help induce optimal patient flow and allocate medical resources ef...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Hindawi Limited
2023-01-01
|
| Series: | Emergency Medicine International |
| Online Access: | http://dx.doi.org/10.1155/2023/1221704 |
| _version_ | 1797780078781792256 |
|---|---|
| author | Sijin Lee Hyun Ji Park Jumi Hwang Sung Woo Lee Kap Su Han Won Young Kim Jinwoo Jeong Hyunggoo Kang Armi Kim Chulung Lee Su Jin Kim |
| author_facet | Sijin Lee Hyun Ji Park Jumi Hwang Sung Woo Lee Kap Su Han Won Young Kim Jinwoo Jeong Hyunggoo Kang Armi Kim Chulung Lee Su Jin Kim |
| author_sort | Sijin Lee |
| collection | DOAJ |
| description | Overcrowding of emergency department (ED) has put a strain on national healthcare systems and adversely affected the clinical outcomes of critically ill patients. Early identification of critically ill patients prior to ED visits can help induce optimal patient flow and allocate medical resources effectively. This study aims to develop ML-based models for predicting critical illness in the community, paramedic, and hospital stages using Korean National Emergency Department Information System (NEDIS) data. Random forest and light gradient boosting machine (LightGBM) were applied to develop predictive models. The predictive model performance based on AUROC in community stage, paramedic stage, and hospital stage was estimated to be 0.870 (95% CI: 0.869–0.871), 0.897 (95% CI: 0.896–0.898), and 0.950 (95% CI: 0.949–0.950) in random forest and 0.877 (95% CI: 0.876–0.878), 0.899 (95% CI: 0.898–0.900), and 0.950 (95% CI: 0.950–0.951) in LightGBM, respectively. The ML models showed high performance in predicting critical illness using variables available at each stage, which can be helpful in guiding patients to appropriate hospitals according to their severity of illness. Furthermore, a simulation model can be developed for proper allocation of limited medical resources. |
| first_indexed | 2024-03-12T23:39:26Z |
| format | Article |
| id | doaj.art-2829a95d82eb43358abc86c626c6eca1 |
| institution | Directory Open Access Journal |
| issn | 2090-2859 |
| language | English |
| last_indexed | 2024-03-12T23:39:26Z |
| publishDate | 2023-01-01 |
| publisher | Hindawi Limited |
| record_format | Article |
| series | Emergency Medicine International |
| spelling | doaj.art-2829a95d82eb43358abc86c626c6eca12023-07-15T00:00:03ZengHindawi LimitedEmergency Medicine International2090-28592023-01-01202310.1155/2023/1221704Machine Learning-Based Models for Prediction of Critical Illness at Community, Paramedic, and Hospital StagesSijin Lee0Hyun Ji Park1Jumi Hwang2Sung Woo Lee3Kap Su Han4Won Young Kim5Jinwoo Jeong6Hyunggoo Kang7Armi Kim8Chulung Lee9Su Jin Kim10Department of Emergency MedicineDepartment of Industrial and Management EngineeringDepartment of Industrial and Management EngineeringDepartment of Emergency MedicineDepartment of Emergency MedicineDepartment of Emergency MedicineDepartment of Emergency MedicineDepartment of Emergency MedicineDepartment of Industrial and Management EngineeringSchool of Industrial and Management EngineeringDepartment of Emergency MedicineOvercrowding of emergency department (ED) has put a strain on national healthcare systems and adversely affected the clinical outcomes of critically ill patients. Early identification of critically ill patients prior to ED visits can help induce optimal patient flow and allocate medical resources effectively. This study aims to develop ML-based models for predicting critical illness in the community, paramedic, and hospital stages using Korean National Emergency Department Information System (NEDIS) data. Random forest and light gradient boosting machine (LightGBM) were applied to develop predictive models. The predictive model performance based on AUROC in community stage, paramedic stage, and hospital stage was estimated to be 0.870 (95% CI: 0.869–0.871), 0.897 (95% CI: 0.896–0.898), and 0.950 (95% CI: 0.949–0.950) in random forest and 0.877 (95% CI: 0.876–0.878), 0.899 (95% CI: 0.898–0.900), and 0.950 (95% CI: 0.950–0.951) in LightGBM, respectively. The ML models showed high performance in predicting critical illness using variables available at each stage, which can be helpful in guiding patients to appropriate hospitals according to their severity of illness. Furthermore, a simulation model can be developed for proper allocation of limited medical resources.http://dx.doi.org/10.1155/2023/1221704 |
| spellingShingle | Sijin Lee Hyun Ji Park Jumi Hwang Sung Woo Lee Kap Su Han Won Young Kim Jinwoo Jeong Hyunggoo Kang Armi Kim Chulung Lee Su Jin Kim Machine Learning-Based Models for Prediction of Critical Illness at Community, Paramedic, and Hospital Stages Emergency Medicine International |
| title | Machine Learning-Based Models for Prediction of Critical Illness at Community, Paramedic, and Hospital Stages |
| title_full | Machine Learning-Based Models for Prediction of Critical Illness at Community, Paramedic, and Hospital Stages |
| title_fullStr | Machine Learning-Based Models for Prediction of Critical Illness at Community, Paramedic, and Hospital Stages |
| title_full_unstemmed | Machine Learning-Based Models for Prediction of Critical Illness at Community, Paramedic, and Hospital Stages |
| title_short | Machine Learning-Based Models for Prediction of Critical Illness at Community, Paramedic, and Hospital Stages |
| title_sort | machine learning based models for prediction of critical illness at community paramedic and hospital stages |
| url | http://dx.doi.org/10.1155/2023/1221704 |
| work_keys_str_mv | AT sijinlee machinelearningbasedmodelsforpredictionofcriticalillnessatcommunityparamedicandhospitalstages AT hyunjipark machinelearningbasedmodelsforpredictionofcriticalillnessatcommunityparamedicandhospitalstages AT jumihwang machinelearningbasedmodelsforpredictionofcriticalillnessatcommunityparamedicandhospitalstages AT sungwoolee machinelearningbasedmodelsforpredictionofcriticalillnessatcommunityparamedicandhospitalstages AT kapsuhan machinelearningbasedmodelsforpredictionofcriticalillnessatcommunityparamedicandhospitalstages AT wonyoungkim machinelearningbasedmodelsforpredictionofcriticalillnessatcommunityparamedicandhospitalstages AT jinwoojeong machinelearningbasedmodelsforpredictionofcriticalillnessatcommunityparamedicandhospitalstages AT hyunggookang machinelearningbasedmodelsforpredictionofcriticalillnessatcommunityparamedicandhospitalstages AT armikim machinelearningbasedmodelsforpredictionofcriticalillnessatcommunityparamedicandhospitalstages AT chulunglee machinelearningbasedmodelsforpredictionofcriticalillnessatcommunityparamedicandhospitalstages AT sujinkim machinelearningbasedmodelsforpredictionofcriticalillnessatcommunityparamedicandhospitalstages |