基于电子健康记录与迁移学习的个体化急性肾损伤风险估计模型的开发与验证
这项诊断研究利用1家三级医院2007年11月1日至2016年12月31日期间住院≥2天的成人电子健康记录数据,采用机器学习和逻辑回归开发并验证全局、亚组和个体化急性肾损伤风险估计模型,并用迁移学习增强个体化模型。主要结局为任何严重程度的急性肾损伤,按肾脏病改善全球结局(KDIGO)血清肌酐标准定义。共纳入76957例次住院,患者平均(SD)年龄55.5(17.4)岁,男性42159例(54.8%)。采用迁移学习的个体化模型在一般住院患者中的AUROC为0.78(95%CI 0.77-0.79),优于全局模型的0.76(95%CI 0.75-0.76),P<.001;在高危亚组中为0.79(95%CI 0.78-0.80)对0.75(95%CI 0.74-0.77),P<.001;在低危亚组中为0.74(95%CI 0.73-0.75)对0.71(95%CI 0.70-0.72),P<.001。高危亚组(如肝移植和心脏手术患者)AUROC提升达0.13,且该模型在研究充分的急性肾损伤亚组中表现优于或相当于已发表的最佳模型。预测因素的结局在不同患者间差异显著,交互分析发现了预测因素结局的修饰因素。作者认为,采用迁移学习的个体化建模是一种改进的急性肾损伤风险估计方法,可跨不同患者亚组使用;风险因素的异质性和个体层面的交互作用凸显了敏捷、个体化照护的需求。
要点
- 采用迁移学习的个体化模型在一般住院患者中估计急性肾损伤的AUROC为0.78(95%CI 0.77-0.79),优于全局模型的0.76(95%CI 0.75-0.76),P<.001。
- 在高危亚组中个体化模型AUROC为0.79(95%CI 0.78-0.80),全局模型为0.75(95%CI 0.74-0.77),P<.001;低危亚组中分别为0.74(95%CI 0.73-0.75)和0.71(95%CI 0.70-0.72),P<.001。
- 高危亚组(如肝移植和心脏手术患者)AUROC提升达0.13。
- 预测因素的结局在不同患者间差异显著,交互分析发现了预测因素结局的修饰因素。
- 作者认为,采用迁移学习的个体化建模是一种改进的急性肾损伤风险估计方法,可跨不同患者亚组使用;风险因素异质性和个体层面交互作用凸显敏捷、个体化照护的需求。
适用人群与场景
- 纳入2007年11月1日至2016年12月31日期间在1家三级医院住院2天或以上的成人。
- 排除入院时存在中度或重度肾功能不全的患者。
诊断标准与关键阈值
- 急性肾损伤定义为任何严重程度,采用肾脏病改善全球结局(KDIGO)血清肌酐标准。
研究设计与关键结果
- 研究类型为诊断研究,分析1家三级医院的电子健康记录数据,使用机器学习和逻辑回归开发并验证全局、亚组和个体化风险估计模型,并用迁移学习增强个体化模型。
- 研究队列包含76957例次住院,患者平均(SD)年龄55.5(17.4)岁,男性42159例(54.8%)。
- 采用迁移学习的个体化模型在一般住院患者中估计急性肾损伤的AUROC为0.78(95%CI 0.77-0.79),全局模型为0.76(95%CI 0.75-0.76),P<.001。
- 在高危亚组中,个体化模型AUROC为0.79(95%CI 0.78-0.80),全局模型为0.75(95%CI 0.74-0.77),P<.001。
- 在低危亚组中,个体化模型AUROC为0.74(95%CI 0.73-0.75),全局模型为0.71(95%CI 0.70-0.72),P<.001。
- 高危亚组(如肝移植和心脏手术患者)AUROC提升达0.13。
- 个体化模型在研究充分的急性肾损伤亚组中表现优于或相当于已发表的最佳模型。
- 预测因素的结局在不同患者间差异显著,交互分析发现了预测因素结局的修饰因素。
证据类型、等级与局限
- 证据类型:诊断研究(模型开发与验证)。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为,采用迁移学习的个体化建模是一种改进的急性肾损伤风险估计方法,可跨不同患者亚组使用。
- 作者认为,风险因素异质性和个体层面的交互作用凸显了敏捷、个体化照护的需求。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「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
IMPORTANCE: Acute kidney injury (AKI) is a heterogeneous syndrome prevalent among hospitalized patients. Personalized risk estimation and risk factor identification may allow effective intervention and improved outcomes.
OBJECTIVE: To develop and validate personalized AKI risk estimation models using electronic health records (EHRs), examine whether personalized models were beneficial in comparison with global and subgroup models, and assess the heterogeneity of risk factors and their outcomes in different subpopulations.
DESIGN, SETTING, AND PARTICIPANTS: This diagnostic study analyzed EHR data from 1 tertiary care hospital and used machine learning and logistic regression to develop and validate global, subgroup, and personalized risk estimation models. Transfer learning was implemented to enhance the personalized model. Predictor outcomes across subpopulations were analyzed, and metaregression was used to explore predictor interactions. Adults who were hospitalized for 2 or more days from November 1, 2007, to December 31, 2016, were included in the analysis. Patients with moderate or severe kidney dysfunction at admission were excluded. Data were analyzed between August 28, 2019, and May 8, 2022.
EXPOSURES: Clinical and laboratory variables in the EHR.
MAIN OUTCOMES AND MEASURES: The main outcome was AKI of any severity, and AKI was defined using the Kidney Disease: Improving Global Outcomes serum creatinine criteria. Performance of the models was measured with area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve, and calibration.
RESULTS: The study cohort comprised 76 957 inpatient encounters. Patients had a mean (SD) age of 55.5 (17.4) years and included 42 159 men (54.8%). The personalized model with transfer learning outperformed the global model for AKI estimation in terms of AUROC among general inpatients (0.78 [95% CI, 0.77-0.79] vs 0.76 [95% CI, 0.75-0.76]; P < .001) and across the high-risk subgroups (0.79 [95% CI, 0.78-0.80] vs 0.75 [95% CI, 0.74-0.77]; P < .001) and low-risk subgroups (0.74 [95% CI, 0.73-0.75] vs 0.71 [95% CI, 0.70-0.72]; P < .001). The AUROC improvement reached 0.13 for the high-risk subgroups, such as those undergoing liver transplant and cardiac surgery. Moreover, the personalized model with transfer learning performed better than or comparably with the best published models in well-studied AKI subgroups. Predictor outcomes varied significantly between patients, and interaction analysis uncovered modifiers of the predictor outcomes.
CONCLUSIONS AND RELEVANCE: Results of this study demonstrated that a personalized modeling with transfer learning is an improved AKI risk estimation approach that can be used across diverse patient subgroups. Risk factor heterogeneity and interactions at the individual level highlighted the need for agile, personalized care.
参考来源
- Liu K, Zhang X, Chen W, et al. Development and Validation of a Personalized Model With Transfer Learning for Acute Kidney Injury Risk Estimation Using Electronic Health Records. JAMA Netw Open. 2022. PMID: 35796212. doi:10.1001/jamanetworkopen.2022.19776
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。