用于预测气胸相关急性肾损伤的可解释机器学习框架的开发和外部验证：一项多中心回顾性研究

摘要(中文译文)

背景/目的：重症监护室（ICU）气胸患者由于血流动力学受损和胸内压升高，患急性肾损伤（AKI）的风险增加。早期识别至关重要，但具有挑战性。本研究旨在开发并外部验证一个可解释的机器学习（ML）框架，以预测气胸相关的急性肾损伤。方法：这项多中心回顾性研究利用了来自MIMIC-IV数据库（开发）的数据，以及时间验证队列（MIMIC-III）和独立外部验证队列（eICU）。应用由Boruta、最小绝对收缩和选择算子（LASSO）和递归特征消除（RFE）组成的三算法交集策略来提取最优预测因子。我们系统地评估了九种监督机器学习算法。Shapley Additive exPlanations（SHAP）和限制三次样条（RCS）分析被整合在一起，以揭示决策机制和非线性动力学。最优模型被部署为基于网络的动态列线图。结果：混合特征选择策略确定了7个核心预测因子（BUN、SOFA评分、CKD、PEEP、心力衰竭、白蛋白和年龄）的简约共识。经过综合评估，逻辑回归模型显示出良好的判别性能[曲线下面积（AUC）=0.839（95%CI:0.786-0.891），敏感性=81.5%，特异性=76.0%]和外部普适性（eICU AUC=0.869；MIMIC-III AUC=0.854）。SHAP分析描绘了每个特征的个人贡献。RCS分析揭示了显著的非线性剂量反应关系，突显了BUN升高和PEEP水平升高导致的AKI风险呈指数级上升。决策曲线分析（DCA）表明了该模型在所有验证队列中的潜在净临床效益。结论：我们开发了一个透明的、外部验证的ML框架，用于预测气胸相关的AKI。由此产生的基于网络的列线图为重症监护医生提供了一种实用的、数据驱动的床边工具，以协助进行个性化的风险分层。然而，鉴于在外部队列中观察到的大量校准漂移，在MIMIC衍生人群之外使用之前，局部重新校准是必不可少的，在常规临床实施之前，前瞻性队列验证仍然是必要的。

Abstract

Intensive Care Unit (ICU) patients with pneumothorax face an elevated risk of developing Acute Kidney Injury (AKI) due to compromised hemodynamics and increased intrathoracic pressure. Early identification is crucial but challenging. This study aimed to develop and externally validate an interpretable machine learning (ML) framework to predict pneumothorax-associated AKI. This multicenter retrospective study utilized data from the MIMIC-IV database (development), alongside a temporal validation cohort (MIMIC-III) and an independent external validation cohort (eICU). A tri-algorithm intersection strategy-comprising Boruta, Least Absolute Shrinkage and Selection Operator (LASSO), and Recursive Feature Elimination (RFE)-was applied to extract optimal predictors. We systematically evaluated nine supervised ML algorithms. Shapley Additive exPlanations (SHAP) and Restricted Cubic Spline (RCS) analyses were integrated to unveil decision-making mechanics and non-linear dynamics. The optimal model was deployed as a web-based dynamic nomogram. The hybrid feature selection strategy identified a parsimonious consensus of 7 core predictors (BUN, SOFA score, CKD, PEEP, Heart Failure, Albumin, and Age). Following comprehensive evaluation, the Logistic Regression model demonstrated favorable discriminative performance [Area Under the Curve (AUC) = 0.839 (95% CI: 0.786-0.891), Sensitivity = 81.5%, Specificity = 76.0%] and external generalizability (eICU AUC = 0.869; MIMIC-III AUC = 0.854). SHAP analysis delineated the individual contribution of each feature. RCS analysis revealed significant non-linear, dose-response relationships, highlighting an exponential AKI risk escalation driven by elevated BUN and higher PEEP levels. Decision Curve Analysis (DCA) suggested the potential net clinical benefit of the model across all validation cohorts. We developed a transparent, externally validated ML framework for predicting pneumothorax-associated AKI. The resulting web-based nomogram provides intensive care physicians with a practical, data-driven bedside tool to assist in personalized risk stratification. However, given the substantial calibration drift observed in the external cohort, local recalibration is essential prior to its use outside the MIMIC-derived population, and prospective cohort validation remains necessary before routine clinical implementation.

如何引用

Journal of clinical medicine 的其他文献

• 冠状动脉斑块表征中的人工智能：临床意义、证据差距和未来方向
• 人工智能在食管切除术中的应用：一项系统综述
• 重症患者远程缺血调节期间外周灌注变化的意义
• 评估食管癌和癌症患者生成性人工智能反应的准确性和可读性
• 从再生机制到临床实践：泌尿学和性医学中富血小板血浆的现状、争议和未来前景
• 静脉注射利多卡因对纤维肌痛患者睡眠和生活质量的影响：一项观察性研究
• 基于运动的外周动脉疾病心脏康复
• 匈牙利癌症患者门诊姑息治疗后的症状改善和相关的ESAS领域。
• 济州本地人和移民胆囊息肉的患病率和危险因素：回顾性横断面研究
• 乳腺癌诊断中的简化MRI方案：叙述性综述