文献速递主动脉疾病

机器学习与惩罚逻辑回归预测破裂腹主动脉瘤院内死亡比较

Machine Learning versus Penalized Logistic Regression for Predicting In-Hospital Mortality in Ruptured Abdominal Aortic Aneurysm: A Comparison Using a Uniform Validation Framework.
PubMed 文献 · Ann Vasc Surg · 2026-08-19

该回顾性单中心队列纳入196例破裂腹主动脉瘤患者,使用5个入院预测变量比较惩罚逻辑回归、梯度提升和多层感知机的预测效能。梯度提升与惩罚逻辑回归的AUC相当(0.739对0.729),多层感知机较低(0.643)。时间验证中梯度提升AUC为0.800,但所有模型均高估绝对死亡风险。

要点

  • 梯度提升与惩罚逻辑回归预测效能相当,AUC差异无统计学意义。
  • 多层感知机预测效能较低,未显示增量获益。
  • 时间验证中模型高估死亡风险,需外部验证后再临床使用。

核心结论

  • 在统一内部与时间验证框架下,梯度提升数值上表现最佳但未证明优于惩罚逻辑回归。
  • 多层感知机未提供增量预测获益,增加算法复杂性不一定改善死亡预测。
  • 支持可解释的回归作为基本基准,临床实施前需外部多中心验证和更完整的前瞻性数据收集。

研究设计与样本

  • 回顾性单中心队列,纳入2006至2024年管理的196例破裂腹主动脉瘤患者。
  • 评估5个预设入院预测变量:年龄、低血容量性休克、最大动脉瘤直径、血红蛋白和收缩压。
  • 采用嵌套五折交叉验证重复5次比较惩罚逻辑回归、梯度提升和多层感知机,缺失数据在各训练分区内独立插补。
  • 时间验证在181例可恢复治疗年份的患者中进行:2006-2018年队列(n=110)开发模型,2019-2024年队列(n=71)评估且不重新拟合或校准。

主要发现

  • 院内死亡99/196例(50.5%)。
  • 梯度提升和惩罚逻辑回归达到相当的中等区分度,AUC分别为0.739(95%CI 0.666-0.805)和0.729(95%CI 0.654-0.796),配对AUC差异0.010(95%CI -0.024至0.045)。
  • 多层感知机区分度较低(AUC 0.643,95%CI 0.563-0.719),与惩罚逻辑回归配对差异-0.086(95%CI -0.160至-0.013)。
  • 时间验证中AUC分别为梯度提升0.800(95%CI 0.686-0.904)、惩罚逻辑回归0.739(95%CI 0.607-0.858)、多层感知机0.632(95%CI 0.496-0.762)。
  • 时间校准显示绝对死亡风险高估,观察死亡率40.8%,平均预测死亡率分别为49.9%、50.0%和63.4%。

临床怎么用

  • 可考虑将惩罚逻辑回归作为预测破裂腹主动脉瘤院内死亡的基线模型。
  • 梯度提升数值上表现较优但未显示明确优势,不宜仅因算法复杂而优先选用。
  • 多层感知机预测效能较低,不推荐用于该场景的死亡预测。
  • 临床实施前需外部多中心验证,并注意模型可能高估绝对死亡风险。

局限性

  • 回顾性单中心设计,样本量有限。
  • 部分患者治疗年份不可恢复,时间验证仅纳入181例。
  • 时间验证中模型高估绝对死亡风险,校准欠佳。
  • 缺乏外部多中心验证和更完整的前瞻性数据。

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

BACKGROUND: Ruptured abdominal aortic aneurysm (rAAA) remains associated with substantial in-hospital mortality. Although machine-learning methods can model complex nonlinear relationships between admission characteristics and outcome, their incremental value over conventional regression remains uncertain. We compared 3 prediction models using identical admission variables and a uniform validation framework. METHODS: This retrospective single-center cohort included 196 unique patients with rAAA managed between 2006 and 2024. Five prespecified admission predictors were evaluated: age, hypovolaemic shock, maximal aneurysm diameter, hemoglobin, and systolic blood pressure. Missing data were imputed independently within each training partition. Penalized logistic regression, gradient boosting, and a multilayer perceptron (MLP) were compared using nested five-fold cross-validation repeated 5 times. Secondary temporal validation was performed in the 181 patients with a recoverable treatment year: models were developed in the 2006-2018 cohort (n = 110) and evaluated, without refitting or recalibration, in the 2019-2024 cohort (n = 71). RESULTS: In-hospital mortality occurred in 99/196 patients (50.5%). Gradient boosting and penalized logistic regression achieved comparable moderate discrimination, with area under the curves (AUCs) of 0.739 (95% confidence interval [CI] 0.666 to 0.805) and 0.729 (95% CI, 0.654 to 0.796), respectively. Their paired AUC difference was 0.010 (95% CI, -0.024 to 0.045). The MLP showed lower discrimination (AUC, 0.643; 95% CI, 0.563-0.719), with a paired difference versus penalized logistic regression of -0.086 (95% CI, -0.160 to -0.013). In temporal validation, AUCs were 0.800 (95% CI, 0.686 to 0.904) for gradient boosting, 0.739 (95% CI, 0.607 to 0.858) for penalized logistic regression, and 0.632 (95% CI, 0.496 to 0.762) for the MLP. Temporal calibration demonstrated overprediction of absolute mortality risk, with observed mortality of 40.8% compared with mean predicted mortality of 49.9%, 50.0%, and 63.4%, respectively. CONCLUSION: Using a uniform internal and temporal validation framework, gradient boosting achieved the highest numerical performance but did not demonstrate a conclusive advantage over penalized logistic regression. The MLP provided no incremental predictive benefit. These findings indicate that increasing algorithmic complexity does not necessarily improve mortality prediction in modest-sized emergency vascular datasets and support interpretable regression as an essential benchmark. External multicenter validation and more complete prospective data collection are required before clinical implementation.

来源:Ann Vasc Surg,查看原文。版权归原作者所有。

引用

  1. Lourdes Del Río-Solá M, de la Torre-Casaseca C, Jiménez-Caja M, et al. Machine Learning versus Penalized Logistic Regression for Predicting In-Hospital Mortality in Ruptured Abdominal Aortic Aneurysm: A Comparison Using a Uniform Validation Framework. Ann Vasc Surg. 2026. PMID: 42617692. doi:10.1016/j.avsg.2026.08.006

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。