机器学习模型用于急性肾损伤风险分类的系统综述与Meta分析
KEY POINTS: Pooled discrimination metrics were acceptable (area under the receiver operating characteristic curve >0.70) for all AKI risk classification categories in both internal and external validation.…
要点
- 机器学习模型对AKI风险分类的汇总AUC在内部和外部验证中均>0.70,判别能力可接受。
- AKI发病预测的汇总AUC内部验证0.82、外部验证0.78,但异质性高(I2>90%)。
- 86%的研究存在高偏倚风险,人群、定义和预测因子异质性限制临床实施。
核心结论
- 多数外部验证模型在预测住院成人和儿童AKI发病、严重程度及post-AKI并发症方面表现良好,但异质性限制其推广和床旁实施。
主要发现
- 共识别302个模型,最常见为logistic回归(37%)、神经网络(10%)、随机森林(9%)和eXtreme gradient boosting(9%)。
- 住院AKI发病最常报告的预测因子为年龄、性别、糖尿病、血清肌酐和血红蛋白。
- AKI发病的汇总AUC内部验证为0.82(95%CI 0.80–0.84),外部验证为0.78(95%CI 0.76–0.80)。
- 跨多种临床场景、AKI严重程度和post-AKI并发症的汇总AUC内部验证为0.78–0.87,外部验证为0.73–0.84。
- 所有结局的between-study异质性高(I2>90%),86%的研究根据PROBAST评估为高偏倚风险。
关键数值与推荐
- KDIGO-AKI标准是最常用的AKI定义(72%)。
- 内部和外部验证中所有AKI风险分类类别的汇总AUC均>0.70。
- 近期发表和低或不明确偏倚风险的研究中模型性能更好。
临床怎么用
- 机器学习模型可用于住院成人和儿童AKI风险分类的辅助预测,但需注意人群、定义和预测因子异质性。
- 临床实施前应评估模型在本地人群中的外部验证性能和偏倚风险。
局限性
- 患者人群、AKI定义、临床预测因子和方法存在显著异质性,限制真实世界临床应用。
- 所有结局between-study异质性高(I2>90%),多数研究(86%)存在高偏倚风险。
- 儿童人群数据有限,但结果与成人一致。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
KEY POINTS: Pooled discrimination metrics were acceptable (area under the receiver operating characteristic curve >0.70) for all AKI risk classification categories in both internal and external validation. Better performance was observed in most recently published studies and those with a low or unclear risk of bias. Significant heterogeneity in patient populations, definitions, clinical predictors, and methods limit implementation in real-world clinical scenarios. BACKGROUND: Artificial intelligence through machine learning models seems to provide accurate and precise AKI risk classification in some clinical settings, but their performance and implementation in real-world settings has not been established. METHODS: PubMed, Excerpta Medica (EMBASE) database, Web of Science, and Scopus were searched until August 2023. Articles reporting on externally validated models for prediction of AKI onset, AKI severity, and post-AKI complications in hospitalized adult and pediatric patients were searched using text words related to AKI, artificial intelligence, and machine learning. Two independent reviewers screened article titles, abstracts, and full texts. Areas under the receiver operating characteristic curves (AUCs) were used to compare model discrimination and pooled using a random-effects model. RESULTS: Of the 4816 articles initially identified and screened, 95 were included, representing 3.8 million admissions. The Kidney Disease Improving Global Outcomes (KDIGO)-AKI criteria were most frequently used to define AKI (72%). We identified 302 models, with the most common being logistic regression (37%), neural networks (10%), random forest (9%), and eXtreme gradient boosting (9%). The most frequently reported predictors of hospitalized incident AKI were age, sex, diabetes, serum creatinine, and hemoglobin. The pooled AUCs for AKI onset were 0.82 (95% confidence interval, 0.80 to 0.84) and 0.78 (95% confidence interval, 0.76 to 0.80) for internal and external validation, respectively. Pooled AUCs across multiple clinical settings, AKI severities, and post-AKI complications ranged from 0.78 to 0.87 for internal validation and 0.73 to 0.84 for external validation. Although data were limited, results in the pediatric population aligned with those observed in adults. Between-study heterogeneity was high for all outcomes (I2>90%), and most studies presented high risk of bias (86%) according to the Prediction Model Risk of Bias Assessment Tool. CONCLUSIONS: Most externally validated models performed well in predicting AKI onset, AKI severity, and post-AKI complications in hospitalized adult and pediatric populations. However, heterogeneity in clinical settings, study populations, and predictors limits their generalizability and implementation at the bedside.
引用
- Cama-Olivares A, Braun C, Takeuchi T, et al. Systematic Review and Meta-Analysis of Machine Learning Models for Acute Kidney Injury Risk Classification. J Am Soc Nephrol. 2025. PMID: 40152939. doi:10.1681/ASN.0000000702
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。