深度学习模型预测ICU再入院:系统综述与Meta分析
该系统综述与Meta分析检索截至2025年3月4日的PubMed、Embase、Scopus和Web of Science,纳入24项开发或验证深度学习模型预测ICU再入院的研究,共49个模型,多数基于美国数据集,极少外部验证。研究设置、结局定义和时间窗、深度学习架构变异大,偏倚风险高,技术可重复性和模型解释罕见。11项研究AUROC的Meta分析均值为0.78(95%CI 0.72–0.84),异质性极高(I²=99.9%);针对疾病特异性ICU亚群的模型性能显著更高(平均AUROC=0.92,95%CI 0.89–0.95,p=0.002),异质性较低(I²=17.1%)。作者认为证据质量差,阻碍临床适用。
要点
- 11项研究AUROC合并均值0.78(95%CI 0.72–0.84),异质性极高(I²=99.9%),偏倚风险高限制合并性能评估。
- 针对疾病特异性ICU亚群的模型平均AUROC=0.92(95%CI 0.89–0.95,p=0.002),异质性较低(I²=17.1%)。
- 纳入24项研究共49个深度学习模型,多数基于美国数据集训练,极少外部验证。
- 研究间ICU再入院结局定义和时间窗、深度学习架构变异大,技术可重复性与模型解释罕见。
- 作者认为深度学习预测ICU再入院的证据质量差,阻碍其临床适用性。
适用人群与场景
- 开发或验证深度学习模型预测ICU再入院的研究人群,涵盖普通ICU人群及疾病特异性ICU亚群。
研究设计与关键结果
- 系统综述与Meta分析,纳入24项研究共49个深度学习模型,多数基于美国数据集训练,极少外部验证。
- 研究设置变异大,包括ICU再入院结局定义和时间窗、深度学习架构,偏倚风险高,技术可重复性与模型解释罕见。
- 11项研究AUROC的Meta分析均值0.78(95%CI 0.72–0.84),异质性极高(I²=99.9%)。
- 针对疾病特异性ICU亚群的模型平均AUROC=0.92(95%CI 0.89–0.95,p=0.002),异质性较低(I²=17.1%)。
证据类型、等级与局限
- 证据类型:系统综述与Meta分析。
- 局限:技术可重复性和模型解释罕见;过度依赖少数美国数据集;可解释性有限;高异质性和偏倚风险限制通过Meta分析评估合并性能;作者认为证据质量差,阻碍临床适用性。
对床旁实践的改变
- 作者认为深度学习模型在预测ICU再入院方面表现有前景,但存在低可重复性、过度依赖少数美国数据集和可解释性有限等缺陷,证据质量差阻碍临床适用。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开
BACKGROUND: Intensive Care Unit (ICU) readmissions are associated with increased morbidity, mortality, and healthcare costs. Therefore, determining an appropriate timing of ICU discharge is critical. In this context, deep learning (DL) approaches have attracted significant attention. METHODS: We conducted a systematic review of studies developing or validating DL models for ICU readmission prediction, published up to March 4th, 2025, and indexed in PubMed, Embase, Scopus, and Web of Science. We summarised them along multiple dimensions, including outcome and population definition, DL architecture, reproducibility, generalizability, and explainability, and provided a meta-analytic estimate of model performance. RESULTS: We included 24 studies encompassing 49 DL models, predominantly trained on US-based datasets, and rarely subjected to external validation. There was considerable variability across study settings, including the definition and timeframe of the ICU readmission outcome, as well as DL architecture used, alongside a substantial risk of bias. Technical reproducibility and model interpretation were rare. A meta-analysis of AUROC values from 11 studies yielded a mean of 0.78 (95% CI = 0.72–0.84), with very high heterogeneity (I2 = 99.9%). Models targeting disease-specific ICU subpopulations achieved significantly higher performance (mean AUROC = 0.92, 95% CI = 0.89–0.95, p = 0.002), and substantially lower heterogeneity (I2 = 17.1%). CONCLUSIONS: DL models showed promising performances in predicting ICU readmissions, but exhibited several shortcomings, including low reproducibility, over-reliance on a few US-based datasets, and limited explainability. Additionally, the high heterogeneity and risk of bias limited our ability to assess their pooled performance through meta-analysis. Taken together, our observations suggest that the quality of the evidence regarding the application of DL approaches to ICU readmission prediction is poor, thus hindering their clinical applicability.
参考来源
- Koumantakis E, Remoundou K, Colombi N, et al. Deep learning models for ICU readmission prediction: a systematic review and meta-analysis. Crit Care. 2025. PMID: 41107959. doi:10.1186/s13054-025-05642-x
供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。