Ensemble machine learning algorithm for predicting acute kidney injury in patients admitted to the neurointensive care unit following brain surgery
Abstract Acute kidney injury (AKI) is a common postoperative complication among patients in the neurological intensive care unit (NICU), often resulting in poor prognosis and high mortality. In this retrospective cohort study, we established a model for predicting AKI following brain surgery based o...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-04-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-33930-5 |
| _version_ | 1797836446317412352 |
|---|---|
| author | Muying Wu Xuandong Jiang Kailei Du Yingting Xu Weimin Zhang |
| author_facet | Muying Wu Xuandong Jiang Kailei Du Yingting Xu Weimin Zhang |
| author_sort | Muying Wu |
| collection | DOAJ |
| description | Abstract Acute kidney injury (AKI) is a common postoperative complication among patients in the neurological intensive care unit (NICU), often resulting in poor prognosis and high mortality. In this retrospective cohort study, we established a model for predicting AKI following brain surgery based on an ensemble machine learning algorithm using data from 582 postoperative patients admitted to the NICU at the Dongyang People's Hospital from March 1, 2017, to January 31, 2020. Demographic, clinical, and intraoperative data were collected. Four machine learning algorithms (C5.0, support vector machine, Bayes, and XGBoost) were used to develop the ensemble algorithm. The AKI incidence in critically ill patients after brain surgery was 20.8%. Intraoperative blood pressure; postoperative oxygenation index; oxygen saturation; and creatinine, albumin, urea, and calcium levels were associated with the postoperative AKI occurrence. The area under the curve value for the ensembled model was 0.85. The accuracy, precision, specificity, recall, and balanced accuracy values were 0.81, 0.86, 0.44, 0.91, and 0.68, respectively, indicating good predictive ability. Ultimately, the models using perioperative variables exhibited good discriminatory ability for early prediction of postoperative AKI risk in patients admitted to the NICU. Thus, the ensemble machine learning algorithm may be a valuable tool for forecasting AKI. |
| first_indexed | 2024-04-09T15:10:08Z |
| format | Article |
| id | doaj.art-dc524589057b4b14b55b23d264d0c6c4 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-09T15:10:08Z |
| publishDate | 2023-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-dc524589057b4b14b55b23d264d0c6c42023-04-30T11:16:56ZengNature PortfolioScientific Reports2045-23222023-04-011311910.1038/s41598-023-33930-5Ensemble machine learning algorithm for predicting acute kidney injury in patients admitted to the neurointensive care unit following brain surgeryMuying Wu0Xuandong Jiang1Kailei Du2Yingting Xu3Weimin Zhang4Intensive Care Unit, Affiliated Dongyang Hospital of Wenzhou Medical UniversityIntensive Care Unit, Affiliated Dongyang Hospital of Wenzhou Medical UniversityIntensive Care Unit, Affiliated Dongyang Hospital of Wenzhou Medical UniversityIntensive Care Unit, Affiliated Dongyang Hospital of Wenzhou Medical UniversityIntensive Care Unit, Affiliated Dongyang Hospital of Wenzhou Medical UniversityAbstract Acute kidney injury (AKI) is a common postoperative complication among patients in the neurological intensive care unit (NICU), often resulting in poor prognosis and high mortality. In this retrospective cohort study, we established a model for predicting AKI following brain surgery based on an ensemble machine learning algorithm using data from 582 postoperative patients admitted to the NICU at the Dongyang People's Hospital from March 1, 2017, to January 31, 2020. Demographic, clinical, and intraoperative data were collected. Four machine learning algorithms (C5.0, support vector machine, Bayes, and XGBoost) were used to develop the ensemble algorithm. The AKI incidence in critically ill patients after brain surgery was 20.8%. Intraoperative blood pressure; postoperative oxygenation index; oxygen saturation; and creatinine, albumin, urea, and calcium levels were associated with the postoperative AKI occurrence. The area under the curve value for the ensembled model was 0.85. The accuracy, precision, specificity, recall, and balanced accuracy values were 0.81, 0.86, 0.44, 0.91, and 0.68, respectively, indicating good predictive ability. Ultimately, the models using perioperative variables exhibited good discriminatory ability for early prediction of postoperative AKI risk in patients admitted to the NICU. Thus, the ensemble machine learning algorithm may be a valuable tool for forecasting AKI.https://doi.org/10.1038/s41598-023-33930-5 |
| spellingShingle | Muying Wu Xuandong Jiang Kailei Du Yingting Xu Weimin Zhang Ensemble machine learning algorithm for predicting acute kidney injury in patients admitted to the neurointensive care unit following brain surgery Scientific Reports |
| title | Ensemble machine learning algorithm for predicting acute kidney injury in patients admitted to the neurointensive care unit following brain surgery |
| title_full | Ensemble machine learning algorithm for predicting acute kidney injury in patients admitted to the neurointensive care unit following brain surgery |
| title_fullStr | Ensemble machine learning algorithm for predicting acute kidney injury in patients admitted to the neurointensive care unit following brain surgery |
| title_full_unstemmed | Ensemble machine learning algorithm for predicting acute kidney injury in patients admitted to the neurointensive care unit following brain surgery |
| title_short | Ensemble machine learning algorithm for predicting acute kidney injury in patients admitted to the neurointensive care unit following brain surgery |
| title_sort | ensemble machine learning algorithm for predicting acute kidney injury in patients admitted to the neurointensive care unit following brain surgery |
| url | https://doi.org/10.1038/s41598-023-33930-5 |
| work_keys_str_mv | AT muyingwu ensemblemachinelearningalgorithmforpredictingacutekidneyinjuryinpatientsadmittedtotheneurointensivecareunitfollowingbrainsurgery AT xuandongjiang ensemblemachinelearningalgorithmforpredictingacutekidneyinjuryinpatientsadmittedtotheneurointensivecareunitfollowingbrainsurgery AT kaileidu ensemblemachinelearningalgorithmforpredictingacutekidneyinjuryinpatientsadmittedtotheneurointensivecareunitfollowingbrainsurgery AT yingtingxu ensemblemachinelearningalgorithmforpredictingacutekidneyinjuryinpatientsadmittedtotheneurointensivecareunitfollowingbrainsurgery AT weiminzhang ensemblemachinelearningalgorithmforpredictingacutekidneyinjuryinpatientsadmittedtotheneurointensivecareunitfollowingbrainsurgery |