Predicting Prolonged Length of ICU Stay through Machine Learning
This study aimed to construct machine learning (ML) models for predicting prolonged length of stay (pLOS) in intensive care units (ICU) among general ICU patients. A multicenter database called eICU (Collaborative Research Database) was used for model derivation and internal validation, and the Medi...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/11/12/2242 |
| _version_ | 1797505487231516672 |
|---|---|
| author | Jingyi Wu Yu Lin Pengfei Li Yonghua Hu Luxia Zhang Guilan Kong |
| author_facet | Jingyi Wu Yu Lin Pengfei Li Yonghua Hu Luxia Zhang Guilan Kong |
| author_sort | Jingyi Wu |
| collection | DOAJ |
| description | This study aimed to construct machine learning (ML) models for predicting prolonged length of stay (pLOS) in intensive care units (ICU) among general ICU patients. A multicenter database called eICU (Collaborative Research Database) was used for model derivation and internal validation, and the Medical Information Mart for Intensive Care (MIMIC) III database was used for external validation. We used four different ML methods (random forest, support vector machine, deep learning, and gradient boosting decision tree (GBDT)) to develop prediction models. The prediction performance of the four models were compared with the customized simplified acute physiology score (SAPS) II. The area under the receiver operation characteristic curve (AUROC), area under the precision-recall curve (AUPRC), estimated calibration index (ECI), and Brier score were used to measure performance. In internal validation, the GBDT model achieved the best overall performance (Brier score, 0.164), discrimination (AUROC, 0.742; AUPRC, 0.537), and calibration (ECI, 8.224). In external validation, the GBDT model also achieved the best overall performance (Brier score, 0.166), discrimination (AUROC, 0.747; AUPRC, 0.536), and calibration (ECI, 8.294). External validation showed that the calibration curve of the GBDT model was an optimal fit, and four ML models outperformed the customized SAPS II model. The GBDT-based pLOS-ICU prediction model had the best prediction performance among the five models on both internal and external datasets. Furthermore, it has the potential to assist ICU physicians to identify patients with pLOS-ICU risk and provide appropriate clinical interventions to improve patient outcomes. |
| first_indexed | 2024-03-10T04:19:17Z |
| format | Article |
| id | doaj.art-b9e6a6f1ae71482283378a3ba190717c |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T04:19:17Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-b9e6a6f1ae71482283378a3ba190717c2023-11-23T07:53:23ZengMDPI AGDiagnostics2075-44182021-11-011112224210.3390/diagnostics11122242Predicting Prolonged Length of ICU Stay through Machine LearningJingyi Wu0Yu Lin1Pengfei Li2Yonghua Hu3Luxia Zhang4Guilan Kong5National Institute of Health Data Science, Peking University, Beijing 100191, ChinaDepartment of Medicine and Therapeutics, LKS Institute of Health Science, The Chinese University of Hong Kong, Hong Kong, ChinaAdvanced Institute of Information Technology, Peking University, Hangzhou 311215, ChinaDepartment of Epidemiology and Biostatistics, School of Public Health, Peking University, Beijing 100191, ChinaNational Institute of Health Data Science, Peking University, Beijing 100191, ChinaNational Institute of Health Data Science, Peking University, Beijing 100191, ChinaThis study aimed to construct machine learning (ML) models for predicting prolonged length of stay (pLOS) in intensive care units (ICU) among general ICU patients. A multicenter database called eICU (Collaborative Research Database) was used for model derivation and internal validation, and the Medical Information Mart for Intensive Care (MIMIC) III database was used for external validation. We used four different ML methods (random forest, support vector machine, deep learning, and gradient boosting decision tree (GBDT)) to develop prediction models. The prediction performance of the four models were compared with the customized simplified acute physiology score (SAPS) II. The area under the receiver operation characteristic curve (AUROC), area under the precision-recall curve (AUPRC), estimated calibration index (ECI), and Brier score were used to measure performance. In internal validation, the GBDT model achieved the best overall performance (Brier score, 0.164), discrimination (AUROC, 0.742; AUPRC, 0.537), and calibration (ECI, 8.224). In external validation, the GBDT model also achieved the best overall performance (Brier score, 0.166), discrimination (AUROC, 0.747; AUPRC, 0.536), and calibration (ECI, 8.294). External validation showed that the calibration curve of the GBDT model was an optimal fit, and four ML models outperformed the customized SAPS II model. The GBDT-based pLOS-ICU prediction model had the best prediction performance among the five models on both internal and external datasets. Furthermore, it has the potential to assist ICU physicians to identify patients with pLOS-ICU risk and provide appropriate clinical interventions to improve patient outcomes.https://www.mdpi.com/2075-4418/11/12/2242prolonged length of ICU staymachine learningclinical decision rulesmedical informatics |
| spellingShingle | Jingyi Wu Yu Lin Pengfei Li Yonghua Hu Luxia Zhang Guilan Kong Predicting Prolonged Length of ICU Stay through Machine Learning Diagnostics prolonged length of ICU stay machine learning clinical decision rules medical informatics |
| title | Predicting Prolonged Length of ICU Stay through Machine Learning |
| title_full | Predicting Prolonged Length of ICU Stay through Machine Learning |
| title_fullStr | Predicting Prolonged Length of ICU Stay through Machine Learning |
| title_full_unstemmed | Predicting Prolonged Length of ICU Stay through Machine Learning |
| title_short | Predicting Prolonged Length of ICU Stay through Machine Learning |
| title_sort | predicting prolonged length of icu stay through machine learning |
| topic | prolonged length of ICU stay machine learning clinical decision rules medical informatics |
| url | https://www.mdpi.com/2075-4418/11/12/2242 |
| work_keys_str_mv | AT jingyiwu predictingprolongedlengthoficustaythroughmachinelearning AT yulin predictingprolongedlengthoficustaythroughmachinelearning AT pengfeili predictingprolongedlengthoficustaythroughmachinelearning AT yonghuahu predictingprolongedlengthoficustaythroughmachinelearning AT luxiazhang predictingprolongedlengthoficustaythroughmachinelearning AT guilankong predictingprolongedlengthoficustaythroughmachinelearning |