Machine learning-based prediction of in-hospital mortality for critically ill patients with sepsis-associated acute kidney injury
AbstractObjectives This study aims to develop and validate a prediction model in-hospital mortality in critically ill patients with sepsis-associated acute kidney injury (SA-AKI) based on machine learning algorithms.Methods Patients who met the criteria for inclusion were identified in the Medical I...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-12-01
|
| Series: | Renal Failure |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/0886022X.2024.2316267 |
| _version_ | 1797231028462419968 |
|---|---|
| author | Tianyun Gao Zhiqiang Nong Yuzhen Luo Manqiu Mo Zhaoyan Chen Zhenhua Yang Ling Pan |
| author_facet | Tianyun Gao Zhiqiang Nong Yuzhen Luo Manqiu Mo Zhaoyan Chen Zhenhua Yang Ling Pan |
| author_sort | Tianyun Gao |
| collection | DOAJ |
| description | AbstractObjectives This study aims to develop and validate a prediction model in-hospital mortality in critically ill patients with sepsis-associated acute kidney injury (SA-AKI) based on machine learning algorithms.Methods Patients who met the criteria for inclusion were identified in the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database and divided according to the validation (n = 2440) and development (n = 9756, 80%) queues. Ensemble stepwise feature selection method was used to screen for effective features. The prediction models of short-term mortality were developed by seven machine learning algorithms. Ten-fold cross-validation was used to verify the performance of the algorithm in the development queue. The area under the receiver operating characteristic curve (ROC-AUC) was used to evaluate the differentiation accuracy and performance of the prediction model in the validation queue. The best-performing model was interpreted by Shapley additive explanations (SHAP).Results A total of 12,196 patients were enrolled in this study. Eleven variables were finally chosen to develop the prediction model. The AUC of the random forest (RF) model was the highest value both in the Ten-fold cross-validation and evaluation (AUC: 0.798, 95% CI: 0.774–0.821). According to the SHAP plots, old age, low Glasgow Coma Scale (GCS) score, high AKI stage, reduced urine output, high Simplified Acute Physiology Score (SAPS II), high respiratory rate, low temperature, low absolute lymphocyte count, high creatinine level, dysnatremia, and low body mass index (BMI) increased the risk of poor prognosis.Conclusions The RF model developed in this study is a good predictor of in-hospital mortality for patients with SA-AKI in the intensive care unit (ICU), which may have potential applications in mortality prediction. |
| first_indexed | 2024-03-07T23:51:32Z |
| format | Article |
| id | doaj.art-e48252384d584a5387307a228d2b5bb5 |
| institution | Directory Open Access Journal |
| issn | 0886-022X 1525-6049 |
| language | English |
| last_indexed | 2024-04-24T15:37:52Z |
| publishDate | 2024-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Renal Failure |
| spelling | doaj.art-e48252384d584a5387307a228d2b5bb52024-04-02T01:21:13ZengTaylor & Francis GroupRenal Failure0886-022X1525-60492024-12-0146110.1080/0886022X.2024.2316267Machine learning-based prediction of in-hospital mortality for critically ill patients with sepsis-associated acute kidney injuryTianyun Gao0Zhiqiang Nong1Yuzhen Luo2Manqiu Mo3Zhaoyan Chen4Zhenhua Yang5Ling Pan6Department of Nephrology, The First Affiliated Hospital of Guangxi Medical University, Nanning City, PR ChinaDepartment of Nephrology, The First Affiliated Hospital of Guangxi Medical University, Nanning City, PR ChinaDepartment of Nephrology, The First Affiliated Hospital of Guangxi Medical University, Nanning City, PR ChinaDepartment of Nephrology, The First Affiliated Hospital of Guangxi Medical University, Nanning City, PR ChinaDepartment of Critical Care Medicine, The First Affiliated Hospital of Guangxi Medical University, Nanning City, PR ChinaDepartment of Nephrology, The First Affiliated Hospital of Guangxi Medical University, Nanning City, PR ChinaDepartment of Nephrology, The First Affiliated Hospital of Guangxi Medical University, Nanning City, PR ChinaAbstractObjectives This study aims to develop and validate a prediction model in-hospital mortality in critically ill patients with sepsis-associated acute kidney injury (SA-AKI) based on machine learning algorithms.Methods Patients who met the criteria for inclusion were identified in the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database and divided according to the validation (n = 2440) and development (n = 9756, 80%) queues. Ensemble stepwise feature selection method was used to screen for effective features. The prediction models of short-term mortality were developed by seven machine learning algorithms. Ten-fold cross-validation was used to verify the performance of the algorithm in the development queue. The area under the receiver operating characteristic curve (ROC-AUC) was used to evaluate the differentiation accuracy and performance of the prediction model in the validation queue. The best-performing model was interpreted by Shapley additive explanations (SHAP).Results A total of 12,196 patients were enrolled in this study. Eleven variables were finally chosen to develop the prediction model. The AUC of the random forest (RF) model was the highest value both in the Ten-fold cross-validation and evaluation (AUC: 0.798, 95% CI: 0.774–0.821). According to the SHAP plots, old age, low Glasgow Coma Scale (GCS) score, high AKI stage, reduced urine output, high Simplified Acute Physiology Score (SAPS II), high respiratory rate, low temperature, low absolute lymphocyte count, high creatinine level, dysnatremia, and low body mass index (BMI) increased the risk of poor prognosis.Conclusions The RF model developed in this study is a good predictor of in-hospital mortality for patients with SA-AKI in the intensive care unit (ICU), which may have potential applications in mortality prediction.https://www.tandfonline.com/doi/10.1080/0886022X.2024.2316267Sepsisacute kidney injuryprediction model of prognosismachine learning algorithms |
| spellingShingle | Tianyun Gao Zhiqiang Nong Yuzhen Luo Manqiu Mo Zhaoyan Chen Zhenhua Yang Ling Pan Machine learning-based prediction of in-hospital mortality for critically ill patients with sepsis-associated acute kidney injury Renal Failure Sepsis acute kidney injury prediction model of prognosis machine learning algorithms |
| title | Machine learning-based prediction of in-hospital mortality for critically ill patients with sepsis-associated acute kidney injury |
| title_full | Machine learning-based prediction of in-hospital mortality for critically ill patients with sepsis-associated acute kidney injury |
| title_fullStr | Machine learning-based prediction of in-hospital mortality for critically ill patients with sepsis-associated acute kidney injury |
| title_full_unstemmed | Machine learning-based prediction of in-hospital mortality for critically ill patients with sepsis-associated acute kidney injury |
| title_short | Machine learning-based prediction of in-hospital mortality for critically ill patients with sepsis-associated acute kidney injury |
| title_sort | machine learning based prediction of in hospital mortality for critically ill patients with sepsis associated acute kidney injury |
| topic | Sepsis acute kidney injury prediction model of prognosis machine learning algorithms |
| url | https://www.tandfonline.com/doi/10.1080/0886022X.2024.2316267 |
| work_keys_str_mv | AT tianyungao machinelearningbasedpredictionofinhospitalmortalityforcriticallyillpatientswithsepsisassociatedacutekidneyinjury AT zhiqiangnong machinelearningbasedpredictionofinhospitalmortalityforcriticallyillpatientswithsepsisassociatedacutekidneyinjury AT yuzhenluo machinelearningbasedpredictionofinhospitalmortalityforcriticallyillpatientswithsepsisassociatedacutekidneyinjury AT manqiumo machinelearningbasedpredictionofinhospitalmortalityforcriticallyillpatientswithsepsisassociatedacutekidneyinjury AT zhaoyanchen machinelearningbasedpredictionofinhospitalmortalityforcriticallyillpatientswithsepsisassociatedacutekidneyinjury AT zhenhuayang machinelearningbasedpredictionofinhospitalmortalityforcriticallyillpatientswithsepsisassociatedacutekidneyinjury AT lingpan machinelearningbasedpredictionofinhospitalmortalityforcriticallyillpatientswithsepsisassociatedacutekidneyinjury |