Department of Medicine.
Precision and Intelligent Systems in Medicine (PrismaP), University of Florida, Gainesville, Florida, USA.
Curr Opin Crit Care. 2021 Dec 1;27(6):560-572. doi: 10.1097/MCC.0000000000000887.
Acute kidney injury (AKI) affects nearly 60% of all patients admitted to ICUs. Large volumes of clinical, monitoring and laboratory data produced in ICUs allow the application of artificial intelligence analytics. The purpose of this article is to assimilate and critically evaluate recently published literature regarding artificial intelligence applications for predicting, diagnosing and subphenotyping AKI among critically ill patients.
Among recent studies regarding artificial intelligence implementations for predicting, diagnosing and subphenotyping AKI among critically ill patients, there are many promising models, but few had external validation, clinical interpretability and high predictive performance. Deep learning techniques leveraging multimodal clinical data show great potential to provide continuous, accurate, early predictions of AKI risk, which could be implemented clinically to optimize preventive and early therapeutic management strategies.
Use of consensus criteria, standard definitions and common data models could facilitate access to machine learning-ready data sets for external validation. The lack of interpretability, explainability, fairness and transparency of artificial intelligence models hinder their entrustment and clinical implementation; compliance with standardized reporting guidelines can mitigate these challenges.
急性肾损伤（AKI）影响近 60%入住 ICU 的患者。ICU 中产生的大量临床、监测和实验室数据可应用人工智能分析。本文旨在综合并批判性评估最近发表的关于人工智能在重症患者 AKI 预测、诊断和亚表型中的应用的文献。
在最近关于人工智能在重症患者 AKI 预测、诊断和亚表型中的应用的研究中，有许多有前途的模型，但很少有模型具有外部验证、临床可解释性和高预测性能。利用多模态临床数据的深度学习技术具有提供 AKI 风险连续、准确、早期预测的巨大潜力，这可在临床上实施，以优化预防和早期治疗管理策略。
使用共识标准、标准定义和通用数据模型可以方便地访问可用于机器学习的数据集进行外部验证。人工智能模型缺乏可解释性、可说明性、公平性和透明度，这阻碍了它们的委托和临床实施；遵守标准化报告指南可以减轻这些挑战。
