文献速递医学人工智能与信息学流行病学与生物统计基础与转化研究

利用自动整编电子健康记录数据开发与验证识别高风险手术患者的机器学习模型(Pythia):回顾性单中心研究

Development and validation of machine learning models to identify high-risk surgical patients using automatically curated electronic health record data (Pythia): A retrospective, single-site study.
PubMed 文献 · PLoS Med · 2018-11-27

本研究基于大型多院区健康机构电子健康记录(EHR)构建自动化手术数据管道Pythia,提取并整编194个临床特征,纳入2014年1月1日至2017年1月31日间66,370例患者共99,755次侵入性操作 encounters。训练lasso惩罚逻辑回归、随机森林和极端梯度提升决策树模型预测14组术后结局,在最后5个月数据的样本外测试集上AUC为0.747至0.924;lasso模型预测术后休克AUC最高为0.924(95%CI: 0.901, 0.946),预测泌尿生殖结局AUC最低为0.780(95%CI: 0.752, 0.810)。以任何并发症风险15%为高风险阈值时模型敏感度76%、特异度76%,表现优于临床专家启发式规则和ACS NSQIP计算器。

要点

  • 基于EHR自动整编的194个特征可训练出预测术后并发症的机器学习模型,样本外AUC为0.747至0.924。
  • lasso模型预测术后休克AUC为0.924(95%CI: 0.901, 0.946),预测泌尿生殖结局AUC为0.780(95%CI: 0.752, 0.810)。
  • 以任何并发症风险15%为高风险阈值时,模型敏感度和特异度均为76%,优于ACS NSQIP计算器。

核心结论

  • 提取并整编大型本地机构EHR数据用于机器学习,可得到预测性能较强的术后并发症风险模型。
  • 这些模型可作为临床决策支持工具,用于识别高风险手术患者以及患者评估和照护管理。
  • 仍需进一步评估Pythia风险计算器在临床工作流中对术后结局的影响,并优化数据流以支持未来机器学习。

研究设计与样本

  • 回顾性单中心研究,数据来自大型四级多院区健康机构EHR,通过自动SQL和R代码提取并处理37百万次临床 encounters。
  • 构建并聚合194个临床特征,包括人口学(年龄、性别、种族)、吸烟状态、用药、合并症、手术信息和手术复杂度代理变量。
  • 研究队列为2014年1月1日至2017年1月31日间接受99,755次侵入性操作 encounters 的66,370例患者,用于预测术后并发症。
  • 训练lasso惩罚逻辑回归、随机森林和极端梯度提升决策树模型,对14个特定术后结局分组进行交叉验证,并在最后5个月数据的样本外测试集上计算AUC。

主要发现

  • 队列平均并发症发生率为16.0%,30天术后死亡率为0.51%。
  • 模型在样本外测试集上的AUC范围为0.747至0.924。
  • lasso惩罚回归被识别为高性能模型,可提供临床可解释的可操作洞察。
  • 表现最高和最低的lasso模型分别预测术后休克和泌尿生殖结局,AUC分别为0.924(95%CI: 0.901, 0.946)和0.780(95%CI: 0.752, 0.810)。

关键数值与推荐

  • 高风险阈值定为任何并发症风险15%,用于识别高风险手术患者。
  • 该阈值下模型敏感度为76%,特异度为76%。
  • 与临床专家开发的启发式高风险患者识别方法和ACS NSQIP计算器相比,该工具表现更优。
  • 创建了仅需输入9个数据字段的计算器,用于生成14组术后结局的风险评估。

临床怎么用

  • 可将该模型作为决策支持工具,用于识别高风险手术患者并辅助患者评估与照护管理。
  • 计算器仅需9个数据字段即可输出14组术后结局的风险评估,便于临床使用。
  • 模型表现优于ACS NSQIP计算器,可提供改进的术后风险估计方法。
  • 在临床工作流中应用前,仍需评估该风险计算器对术后结局的实际影响。

局限性

  • 研究存在数据缺失,缺失数据在分析时被移除。
  • 研究为回顾性单中心设计。
  • 尚需进一步评估Pythia风险计算器在临床工作流中对术后结局的影响。
  • 需优化该数据流以支持未来机器学习工作。

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: Pythia is an automated, clinically curated surgical data pipeline and repository housing all surgical patient electronic health record (EHR) data from a large, quaternary, multisite health institute for data science initiatives. In an effort to better identify high-risk surgical patients from complex data, a machine learning project trained on Pythia was built to predict postoperative complication risk. METHODS AND FINDINGS: A curated data repository of surgical outcomes was created using automated SQL and R code that extracted and processed patient clinical and surgical data across 37 million clinical encounters from the EHRs. A total of 194 clinical features including patient demographics (e.g., age, sex, race), smoking status, medications, comorbidities, procedure information, and proxies for surgical complexity were constructed and aggregated. A cohort of 66,370 patients that had undergone 99,755 invasive procedural encounters between January 1, 2014, and January 31, 2017, was studied further for the purpose of predicting postoperative complications. The average complication and 30-day postoperative mortality rates of this cohort were 16.0% and 0.51%, respectively. Least absolute shrinkage and selection operator (lasso) penalized logistic regression, random forest models, and extreme gradient boosted decision trees were trained on this surgical cohort with cross-validation on 14 specific postoperative outcome groupings. Resulting models had area under the receiver operator characteristic curve (AUC) values ranging between 0.747 and 0.924, calculated on an out-of-sample test set from the last 5 months of data. Lasso penalized regression was identified as a high-performing model, providing clinically interpretable actionable insights. Highest and lowest performing lasso models predicted postoperative shock and genitourinary outcomes with AUCs of 0.924 (95% CI: 0.901, 0.946) and 0.780 (95% CI: 0.752, 0.810), respectively. A calculator requiring input of 9 data fields was created to produce a risk assessment for the 14 groupings of postoperative outcomes. A high-risk threshold (15% risk of any complication) was determined to identify high-risk surgical patients. The model sensitivity was 76%, with a specificity of 76%. Compared to heuristics that identify high-risk patients developed by clinical experts and the ACS NSQIP calculator, this tool performed superiorly, providing an improved approach for clinicians to estimate postoperative risk for patients. Limitations of this study include the missingness of data that were removed for analysis. CONCLUSIONS: Extracting and curating a large, local institution's EHR data for machine learning purposes resulted in models with strong predictive performance. These models can be used in clinical settings as decision support tools for identification of high-risk patients as well as patient evaluation and care management. Further work is necessary to evaluate the impact of the Pythia risk calculator within the clinical workflow on postoperative outcomes and to optimize this data flow for future machine learning efforts.

来源:PLoS Med,查看原文。版权归原作者所有。

引用

  1. Corey KM, Kashyap S, Lorenzi E, et al. Development and validation of machine learning models to identify high-risk surgical patients using automatically curated electronic health record data (Pythia): A retrospective, single-site study. PLoS Med. 2018. PMID: 30481172. doi:10.1371/journal.pmed.1002701

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。