Machine learning algorithms assist early evaluation of enteral nutrition in ICU patients
BackgroundThis study applied machine learning (ML) algorithms to construct a model for predicting EN initiation for patients in the intensive care unit (ICU) and identifying populations in need of EN at an early stage.MethodsThis study collected patient information from the Medical Information Mart...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-04-01
|
| Series: | Frontiers in Nutrition |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnut.2023.1060398/full |
| _version_ | 1797847227171864576 |
|---|---|
| author | Ya-Xi Wang Xun-Liang Li Ling-Hui Zhang Hai-Na Li Xiao-Min Liu Wen Song Xu-Feng Pang |
| author_facet | Ya-Xi Wang Xun-Liang Li Ling-Hui Zhang Hai-Na Li Xiao-Min Liu Wen Song Xu-Feng Pang |
| author_sort | Ya-Xi Wang |
| collection | DOAJ |
| description | BackgroundThis study applied machine learning (ML) algorithms to construct a model for predicting EN initiation for patients in the intensive care unit (ICU) and identifying populations in need of EN at an early stage.MethodsThis study collected patient information from the Medical Information Mart for Intensive Care IV database. All patients enrolled were split randomly into a training set and a validation set. Six ML models were established to evaluate the initiation of EN, and the best model was determined according to the area under curve (AUC) and accuracy. The best model was interpreted using the Local Interpretable Model-Agnostic Explanations (LIME) algorithm and SHapley Additive exPlanation (SHAP) values.ResultsA total of 53,150 patients participated in the study. They were divided into a training set (42,520, 80%) and a validation set (10,630, 20%). In the validation set, XGBoost had the optimal prediction performance with an AUC of 0.895. The SHAP values revealed that sepsis, sequential organ failure assessment score, and acute kidney injury were the three most important factors affecting EN initiation. The individualized forecasts were displayed using the LIME algorithm.ConclusionThe XGBoost model was established and validated for early prediction of EN initiation in ICU patients. |
| first_indexed | 2024-04-09T18:09:00Z |
| format | Article |
| id | doaj.art-6e1ea59595c244b2bd0fc01971dfffe1 |
| institution | Directory Open Access Journal |
| issn | 2296-861X |
| language | English |
| last_indexed | 2024-04-09T18:09:00Z |
| publishDate | 2023-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Nutrition |
| spelling | doaj.art-6e1ea59595c244b2bd0fc01971dfffe12023-04-14T04:36:24ZengFrontiers Media S.A.Frontiers in Nutrition2296-861X2023-04-011010.3389/fnut.2023.10603981060398Machine learning algorithms assist early evaluation of enteral nutrition in ICU patientsYa-Xi Wang0Xun-Liang Li1Ling-Hui Zhang2Hai-Na Li3Xiao-Min Liu4Wen Song5Xu-Feng Pang6Department of Hospital-acquired Infection Control, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, ChinaDepartment of Nephrology, The Second Hospital of Anhui Medical University, Hefei, Anhui, ChinaSchool of Nursing, Qingdao University, Qingdao, Shandong, ChinaDepartment of Nephrology, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, ChinaDepartment of Critical Care Medicine, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, ChinaDepartment of Endoscopy, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, ChinaDepartment of Hospital-acquired Infection Control, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, ChinaBackgroundThis study applied machine learning (ML) algorithms to construct a model for predicting EN initiation for patients in the intensive care unit (ICU) and identifying populations in need of EN at an early stage.MethodsThis study collected patient information from the Medical Information Mart for Intensive Care IV database. All patients enrolled were split randomly into a training set and a validation set. Six ML models were established to evaluate the initiation of EN, and the best model was determined according to the area under curve (AUC) and accuracy. The best model was interpreted using the Local Interpretable Model-Agnostic Explanations (LIME) algorithm and SHapley Additive exPlanation (SHAP) values.ResultsA total of 53,150 patients participated in the study. They were divided into a training set (42,520, 80%) and a validation set (10,630, 20%). In the validation set, XGBoost had the optimal prediction performance with an AUC of 0.895. The SHAP values revealed that sepsis, sequential organ failure assessment score, and acute kidney injury were the three most important factors affecting EN initiation. The individualized forecasts were displayed using the LIME algorithm.ConclusionThe XGBoost model was established and validated for early prediction of EN initiation in ICU patients.https://www.frontiersin.org/articles/10.3389/fnut.2023.1060398/fullenteral nutritionintensive care unitmachine learninginitiationprediction |
| spellingShingle | Ya-Xi Wang Xun-Liang Li Ling-Hui Zhang Hai-Na Li Xiao-Min Liu Wen Song Xu-Feng Pang Machine learning algorithms assist early evaluation of enteral nutrition in ICU patients Frontiers in Nutrition enteral nutrition intensive care unit machine learning initiation prediction |
| title | Machine learning algorithms assist early evaluation of enteral nutrition in ICU patients |
| title_full | Machine learning algorithms assist early evaluation of enteral nutrition in ICU patients |
| title_fullStr | Machine learning algorithms assist early evaluation of enteral nutrition in ICU patients |
| title_full_unstemmed | Machine learning algorithms assist early evaluation of enteral nutrition in ICU patients |
| title_short | Machine learning algorithms assist early evaluation of enteral nutrition in ICU patients |
| title_sort | machine learning algorithms assist early evaluation of enteral nutrition in icu patients |
| topic | enteral nutrition intensive care unit machine learning initiation prediction |
| url | https://www.frontiersin.org/articles/10.3389/fnut.2023.1060398/full |
| work_keys_str_mv | AT yaxiwang machinelearningalgorithmsassistearlyevaluationofenteralnutritioninicupatients AT xunliangli machinelearningalgorithmsassistearlyevaluationofenteralnutritioninicupatients AT linghuizhang machinelearningalgorithmsassistearlyevaluationofenteralnutritioninicupatients AT hainali machinelearningalgorithmsassistearlyevaluationofenteralnutritioninicupatients AT xiaominliu machinelearningalgorithmsassistearlyevaluationofenteralnutritioninicupatients AT wensong machinelearningalgorithmsassistearlyevaluationofenteralnutritioninicupatients AT xufengpang machinelearningalgorithmsassistearlyevaluationofenteralnutritioninicupatients |