Machine learning models for early prediction of potassium lowering effectiveness and adverse events in patients with hyperkalemia
Abstract The aim of this study was to develop a model for early prediction of adverse events and treatment effectiveness in patients with hyperkalemia. We collected clinical data from patients with hyperkalemia in the First Hospital of Zhejiang University School of Medicine between 2015 and 2021. Th...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-024-51468-y |
| _version_ | 1827388650025910272 |
|---|---|
| author | Wei Huang Jian-Yong Zhu Cong-Ying Song Yuan-Qiang Lu |
| author_facet | Wei Huang Jian-Yong Zhu Cong-Ying Song Yuan-Qiang Lu |
| author_sort | Wei Huang |
| collection | DOAJ |
| description | Abstract The aim of this study was to develop a model for early prediction of adverse events and treatment effectiveness in patients with hyperkalemia. We collected clinical data from patients with hyperkalemia in the First Hospital of Zhejiang University School of Medicine between 2015 and 2021. The least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression were used to analyze the predictors on the full dataset. We randomly divided the data into a training group and a validation group, and used LASSO to filter variables in the training set. Six machine learning methods were used to develop the models. The best model was selected based on the area under the curve (AUC). Shapley additive exPlanations (SHAP) values were used to explain the best model. A total of 1074 patients with hyperkalemia were finally enrolled. Diastolic blood pressure (DBP), breathing, oxygen saturation (SPO2), Glasgow coma score (GCS), liver disease, oliguria, blood sodium, international standardized ratio (ISR), and initial blood potassium were the predictors of the occurrence of adverse events; peripheral edema, estimated glomerular filtration rate (eGFR), blood sodium, actual base residual, and initial blood potassium were the predictors of therapeutic effect. Extreme gradient boosting (XGBoost) model achieved the best performance (adverse events: AUC = 0.87; therapeutic effect: AUC = 0.75). A model based on clinical characteristics was developed and validated with good performance. |
| first_indexed | 2024-03-08T16:21:56Z |
| format | Article |
| id | doaj.art-f627166a15584f92822489497922fa6d |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-08T16:21:56Z |
| publishDate | 2024-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-f627166a15584f92822489497922fa6d2024-01-07T12:20:28ZengNature PortfolioScientific Reports2045-23222024-01-0114111010.1038/s41598-024-51468-yMachine learning models for early prediction of potassium lowering effectiveness and adverse events in patients with hyperkalemiaWei Huang0Jian-Yong Zhu1Cong-Ying Song2Yuan-Qiang Lu3Department of Emergency Medicine, The First Affiliated Hospital, School of Medicine, Zhejiang UniversityDepartment of Emergency Medicine, The First Affiliated Hospital, School of Medicine, Zhejiang UniversityDepartment of Emergency Medicine, The First Affiliated Hospital, School of Medicine, Zhejiang UniversityDepartment of Emergency Medicine, The First Affiliated Hospital, School of Medicine, Zhejiang UniversityAbstract The aim of this study was to develop a model for early prediction of adverse events and treatment effectiveness in patients with hyperkalemia. We collected clinical data from patients with hyperkalemia in the First Hospital of Zhejiang University School of Medicine between 2015 and 2021. The least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression were used to analyze the predictors on the full dataset. We randomly divided the data into a training group and a validation group, and used LASSO to filter variables in the training set. Six machine learning methods were used to develop the models. The best model was selected based on the area under the curve (AUC). Shapley additive exPlanations (SHAP) values were used to explain the best model. A total of 1074 patients with hyperkalemia were finally enrolled. Diastolic blood pressure (DBP), breathing, oxygen saturation (SPO2), Glasgow coma score (GCS), liver disease, oliguria, blood sodium, international standardized ratio (ISR), and initial blood potassium were the predictors of the occurrence of adverse events; peripheral edema, estimated glomerular filtration rate (eGFR), blood sodium, actual base residual, and initial blood potassium were the predictors of therapeutic effect. Extreme gradient boosting (XGBoost) model achieved the best performance (adverse events: AUC = 0.87; therapeutic effect: AUC = 0.75). A model based on clinical characteristics was developed and validated with good performance.https://doi.org/10.1038/s41598-024-51468-y |
| spellingShingle | Wei Huang Jian-Yong Zhu Cong-Ying Song Yuan-Qiang Lu Machine learning models for early prediction of potassium lowering effectiveness and adverse events in patients with hyperkalemia Scientific Reports |
| title | Machine learning models for early prediction of potassium lowering effectiveness and adverse events in patients with hyperkalemia |
| title_full | Machine learning models for early prediction of potassium lowering effectiveness and adverse events in patients with hyperkalemia |
| title_fullStr | Machine learning models for early prediction of potassium lowering effectiveness and adverse events in patients with hyperkalemia |
| title_full_unstemmed | Machine learning models for early prediction of potassium lowering effectiveness and adverse events in patients with hyperkalemia |
| title_short | Machine learning models for early prediction of potassium lowering effectiveness and adverse events in patients with hyperkalemia |
| title_sort | machine learning models for early prediction of potassium lowering effectiveness and adverse events in patients with hyperkalemia |
| url | https://doi.org/10.1038/s41598-024-51468-y |
| work_keys_str_mv | AT weihuang machinelearningmodelsforearlypredictionofpotassiumloweringeffectivenessandadverseeventsinpatientswithhyperkalemia AT jianyongzhu machinelearningmodelsforearlypredictionofpotassiumloweringeffectivenessandadverseeventsinpatientswithhyperkalemia AT congyingsong machinelearningmodelsforearlypredictionofpotassiumloweringeffectivenessandadverseeventsinpatientswithhyperkalemia AT yuanqianglu machinelearningmodelsforearlypredictionofpotassiumloweringeffectivenessandadverseeventsinpatientswithhyperkalemia |