文献速递心脑血管急症重症综合管理与镇静镇痛

卒中患者住院时长与30天死亡率预测:巴西17,000例ICU入住患者的机器学习分析

Hospital Length of Stay and 30-Day Mortality Prediction in Stroke: A Machine Learning Analysis of 17,000 ICU Admissions in Brazil.
PubMed 文献 · Neurocrit Care · 2022-04-06
一句话结论在巴西130个ICU的卒中患者中,随机森林模型利用常规ICU数据即可较好预测住院时长与30天院内死亡率,无需卒中特异性量表或影像数据。

本研究基于巴西43家医院130个ICU于2011年1月至2020年12月连续收治的成人卒中(缺血性或非创伤性出血性)患者,回顾性分析17,115例ICU入住记录,最终纳入16,592例(缺血性13,258例、出血性3,334例)。采用七种机器学习模型在训练集与测试集上开发住院时长与30天院内死亡率预测模型,以随机森林表现最佳:住院时长>14天预测的Brier分数=0.17、曲线下面积=0.73、阳性预测值=0.61、阴性预测值=0.78;30天死亡率预测的Brier分数=0.05、曲线下面积=0.90、阳性预测值=0.66、阴性预测值=0.94。作者认为,即使缺乏美国国立卫生研究院卒中量表评分或神经影像等卒中特异性数据,机器学习方法仍能准确预测上述结局,所提方法可用于资源分配规划与ICU绩效评估。

要点

  • 在16,592例卒中ICU患者中,26%(4,298例)住院时长延长(>14天),30天院内死亡率为8%(n=1,392)。
  • 随机森林预测住院时长>14天:Brier分数=0.17、曲线下面积=0.73、阳性预测值=0.61、阴性预测值=0.78。
  • 随机森林预测30天院内死亡率:Brier分数=0.05、曲线下面积=0.90、阳性预测值=0.66、阴性预测值=0.94。
  • 两个模型最强的20个贡献变量包括病前状态(如功能受损)、多器官功能障碍参数(如低血压、机械通气)及卒中急性神经学方面(如入院格拉斯哥昏迷评分、卒中类型)。
  • 作者认为,即使没有卒中特异性数据(如美国国立卫生研究院卒中量表评分或神经影像),机器学习方法仍能准确预测住院时长与30天死亡率。

适用人群与场景

  • 2011年1月至2020年12月连续入住ICU的成人卒中患者(缺血性或非创伤性出血性),来自巴西43家医院的130个ICU。

研究设计与关键结果

  • 研究类型:回顾性多中心队列研究,纳入16,592例成人卒中患者(缺血性13,258例、出血性3,334例),来自130个ICU、43家巴西医院。
  • 主要终点:住院时长延长(>14天)见于4,298例(26%);30天院内死亡率为8%(n=1,392)。
  • 住院时长预测:随机森林模型表现最佳,Brier分数=0.17、曲线下面积=0.73、阳性预测值=0.61、阴性预测值=0.78。
  • 死亡率预测:随机森林模型区分度与校准最佳,Brier分数=0.05、曲线下面积=0.90、阳性预测值=0.66、阴性预测值=0.94。
  • 两个模型最强的20个贡献变量包括:病前状态(如功能受损)、多器官功能障碍参数(如低血压、机械通气)、卒中急性神经学方面(如入院格拉斯哥昏迷评分、卒中类型)。

证据类型、等级与局限

  • 证据类型:回顾性多中心队列研究,采用数据驱动的机器学习方法(七种模型)。
  • 局限:作者指出,更详细的急性神经学与管理数据以及长期功能结局可能提高未来机器学习预测算法的准确性与适用性。

对床旁实践的改变

  • 作者认为,所提出的使用通用重症监护数据库的方法可用于资源使用分配规划和治疗卒中的ICU绩效评估。
  • 作者指出,即使缺乏卒中特异性数据(如美国国立卫生研究院卒中量表评分或神经影像),机器学习方法仍能准确预测住院时长与30天死亡率。
  • 作者认为,更详细的急性神经学与管理数据以及长期功能结局可能提高未来机器学习预测算法的准确性与适用性。

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: Hospital length of stay and mortality are associated with resource use and clinical severity, respectively, in patients admitted to the intensive care unit (ICU) with acute stroke. We proposed a structured data-driven methodology to develop length of stay and 30-day mortality prediction models in a large multicenter Brazilian ICU cohort.

METHODS: We analyzed data from 130 ICUs from 43 Brazilian hospitals. All consecutive adult patients admitted with stroke (ischemic or nontraumatic hemorrhagic) to the ICU from January 2011 to December 2020 were included. Demographic data, comorbidities, acute disease characteristics, organ support, and laboratory data were retrospectively analyzed by a data-driven methodology, which included seven different types of machine learning models applied to training and test sets of data. The best performing models, based on discrimination and calibration measures, are reported as the main results. Outcomes were hospital length of stay and 30-day in-hospital mortality.

RESULTS: Of 17,115 ICU admissions for stroke, 16,592 adult patients (13,258 ischemic and 3334 hemorrhagic) were analyzed; 4298 (26%) patients had a prolonged hospital length of stay (> 14 days), and 30-day mortality was 8% (n = 1392). Prolonged hospital length of stay was best predicted by the random forests model (Brier score = 0.17, area under the curve = 0.73, positive predictive value = 0.61, negative predictive value = 0.78). Mortality prediction also yielded the best discrimination and calibration through random forests (Brier score = 0.05, area under the curve = 0.90, positive predictive value = 0.66, negative predictive value = 0.94). Among the 20 strongest contributor variables in both models were (1) premorbid conditions (e.g., functional impairment), (2) multiple organ dysfunction parameters (e.g., hypotension, mechanical ventilation), and (3) acute neurological aspects of stroke (e.g., Glasgow coma scale score on admission, stroke type).

CONCLUSIONS: Hospital length of stay and 30-day mortality of patients admitted to the ICU with stroke were accurately predicted through machine learning methods, even in the absence of stroke-specific data, such as the National Institutes of Health Stroke Scale score or neuroimaging findings. The proposed methods using general intensive care databases may be used for resource use allocation planning and performance assessment of ICUs treating stroke. More detailed acute neurological and management data, as well as long-term functional outcomes, may improve the accuracy and applicability of future machine-learning-based prediction algorithms.

来源:Neurocrit Care,查看原文。版权归原作者所有。

参考来源

  1. Kurtz P, Peres IT, Soares M, et al. Hospital Length of Stay and 30-Day Mortality Prediction in Stroke: A Machine Learning Analysis of 17,000 ICU Admissions in Brazil. Neurocrit Care. 2022. PMID: 35381967. doi:10.1007/s12028-022-01486-3

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。