期刊
INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS
卷 151, 期 -, 页码 -出版社
ELSEVIER IRELAND LTD
DOI: 10.1016/j.ijmedinf.2021.104484
关键词
Acute kidney injury; Machine learning; Artificial intelligence; Logistic regression
The study found that machine learning models perform similarly to logistic regression models in predicting acute kidney injury (AKI), but some machine learning models show exceptional performance, with gradient boosting models performing the best.
Introduction: We aimed to assess whether machine learning models are superior at predicting acute kidney injury (AKI) compared to logistic regression (LR), a conventional prediction model. Methods: Eligible studies were identified using PubMed and Embase. A total of 24 studies consisting of 84 prediction models met inclusion criteria. Independent samples t-test was performed to detect mean differences in area under the curve (AUC) between ML and LR models. One-way ANOVA and post-hoc t-tests were performed to assess mean differences in AUC between ML methods. Results: AUC data were similar between ML (0.736 +/- 0.116) and LR (0.748 +/- 0.057) models (p = 0.538). However, specific ML models, such as gradient boosting (0.838 +/- 0.077), exhibited superior performance at predicting AKI as compared to other ML models in the literature (p < 0.05). Creatinine and urine output, standard variables assessed for AKI staging, were classified as significant predictors across multiple ML models, although the majority of significant predictors were unique and study specific. Conclusions: These data suggest that ML models perform equally to that of LR, however ML models exhibit variable performance with some ML models displaying exceptional performance. The variability in ML prediction of AKI can be attributed, in part, to the specific ML model utilized, variable selection and processing, study and subject characteristics, and the steps associated with model training, validation, testing, and calibration.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据