文献速递儿科与产科急症重症综合管理与镇静镇痛

可解释机器学习算法简化儿童死亡指数3评分

Simplified Pediatric Index of Mortality 3 Score by Explainable Machine Learning Algorithm.
PubMed 文献 · Crit Care Explor · 2021-10-19
一句话结论单中心回顾性研究显示,用5个变量(机械通气、极高危诊断、非心脏手术恢复、低危诊断、碱剩余)的机器学习模型可近似预测PIM3死亡风险。

机器学习模型在输入变量减少至4个时仍保持相似预测误差;5变量模型(机械通气第一小时、极高危诊断、非心脏手术恢复、低危诊断、碱剩余)表现最佳,平均均方根误差1.49(95%CI 1.05-1.93),R平方0.73(95%CI 0.6-0.86),平均绝对误差0.43(95%CI 0.35-0.5)。结论认为可解释机器学习简化PIM3评分在单中心数据集中可行。

要点

  • 5个变量为:PICU入科第一小时机械通气、极高危诊断、非心脏手术术后恢复、低危诊断、碱剩余。
  • 机器学习模型输入变量减少至4个时仍保持与11变量模型相似的预测误差。
  • 该研究为单中心回顾性队列,结论需外部验证,不能直接作为床旁决策阈值。
  • 原文未提及该简化模型在急诊或院前场景的应用。

适用人群与场景

  • 场景为PICU,非急诊抢救室或院前。

诊断标准与关键阈值

  • PIM3原始模型包含11个变量,用于评估PICU患者死亡风险。
  • 简化模型使用5个输入变量:PICU入科第一小时机械通气、极高危诊断、非心脏手术术后恢复、低危诊断、碱剩余。
  • 原文未提及简化模型的诊断界值或启动/停止阈值。

处置流程与药物剂量

  • 原文未提及

红旗征与不能漏的情况

  • 原文未提及

研究设计与关键结果

  • 5变量模型表现最佳:平均均方根误差1.49(95%CI 1.05-1.93),R平方0.73(95%CI 0.6-0.86),平均绝对误差0.43(95%CI 0.35-0.5)。
  • 机器学习模型输入变量减少至4个时仍保持相似预测误差。

证据类型、等级与局限

  • 证据类型:单中心、回顾性队列研究。

对床旁实践的改变

  • 原文提示可解释机器学习方法可能简化PIM3评分的数据收集,减少时间和人力,但仅基于单中心回顾性数据,不能直接改变床旁实践。
  • 适用人群为PICU患者,不适用于急诊或院前场景。
  • 常见陷阱:将模型预测值误作决策阈值,或 extrapolate 至其他中心人群。

指南或共识出处

  • 原文未提及

以上提炼依据论文摘要(全文未开放获取,或许可不允许翻译转载);全文请点「阅读原文」。

英文原文(摘要)· 点击展开

UNLABELLED: Pediatric Index of Mortality 3 is a validated tool including 11 variables for the assessment of mortality risk in PICU patients. With the recent advances in explainable machine learning algorithms, we aimed to assess feasibility of application of these machine learning models to simplify the Pediatric Index of Mortality 3 scoring system in order to decrease time and labor required for data collection and entry for Pediatric Index of Mortality 3.

DESIGN: Single-center, retrospective cohort study. Data from the Virtual Pediatric Systems for patients admitted to Cleveland Clinic Children`s PICU between January 2008 and December 2019 was obtained. Light Gradient Boosting Machine Regressor (a gradient boosting decision tree algorithm) was used for building the machine learning models. Variable importance was analyzed by SHapley Additive exPlanations. All of the 11 Pediatric Index of Mortality 3 variables were used as input variables in the machine learning models to predict Pediatric Index of Mortality 3 risk of mortality as the outcome variable. Mean absolute error, root mean squared error, and R-squared were calculated for each of the 11 machine learning models as model performance parameters.

SETTING: Quaternary children's hospital.

PATIENTS: PICU patients.

INTERVENTIONS: None.

MEASUREMENTS AND MAIN RESULTS: Five-thousand sixty-eight patients were analyzed. The machine learning models were able to maintain similar predictive error until the number of input variables decreased to four. The machine learning model with five input variables (mechanical ventilation in the first hour of PICU admission, very-high-risk diagnosis, surgical recovery from a noncardiac procedure, low-risk diagnosis, and base excess) produced lowest mean root mean squared error of 1.49 (95% CI, 1.05-1.93) and highest R-squared of 0.73 (95% CI, 0.6-0.86) with mean absolute error of 0.43 (95% CI, 0.35-0.5) among all the 11 machine learning models.

CONCLUSIONS: Explainable machine learning methods were feasible in simplifying the Pediatric Index of Mortality 3 scoring system with similar risk of mortality predictions compared to the original Pediatric Index of Mortality 3 model tested in a single-center dataset.

来源:Crit Care Explor,查看原文。版权归原作者所有。

参考来源

  1. Baloglu O, Nagy M, Ezetendu C, et al. Simplified Pediatric Index of Mortality 3 Score by Explainable Machine Learning Algorithm. Crit Care Explor. 2021. PMID: 34693292. doi:10.1097/CCE.0000000000000561

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。