文献速递创伤与烧伤

机器学习在创伤结局预测中的应用:一项系统评价

Machine Learning in the Prediction of Trauma Outcomes: A Systematic Review.
PubMed 文献 · Ann Emerg Med · 2022-07-13
一句话结论本系统评价发现创伤结局的机器学习模型在开发与报告上高度异质,外部验证、特征选择和正式校准测试均缺乏,作者建议未来模型开发需更多标准化和严谨指南。

该系统评价检索截至2021年5月,从Embase、MEDLINE(通过Ovid)、Web of Science、Google Scholar及相关灰色文献中筛选创伤患者结局预测的机器学习应用,由2名独立评审员完成筛选和数据提取。共筛查14,694篇文章,纳入67篇进行数据提取。人工神经网络是最常用的模型,死亡率是最常见的关注结局。模型开发方面,缺乏采用外部验证、特征选择方法和进行正式校准测试的研究;不同机器学习模型、患者人群、性能指标和所用特征之间报告异质性显著。作者认为这些模型作为临床决策辅助存在机会,但建议未来模型开发需更多标准化和严谨指南。

要点

  • 共筛查14,694篇文章,最终纳入67篇进行数据提取。
  • 人工神经网络是最常用的模型,死亡率是最常见的关注结局。
  • 缺乏采用外部验证、特征选择方法和进行正式校准测试的研究。
  • 不同机器学习模型、患者人群、性能指标和所用特征之间报告异质性显著。
  • 作者认为这些模型作为临床决策辅助存在机会,建议未来模型开发需更多标准化和严谨指南。

适用人群与场景

  • 创伤患者(traumatically injured patients)的结局预测场景。

研究设计与关键结果

  • 研究类型:系统评价;检索截至2021年5月,来源包括Embase、MEDLINE(通过Ovid)、Web of Science、Google Scholar及相关灰色文献,由2名独立评审员筛选和数据提取。
  • 共筛查14,694篇文章,纳入67篇进行数据提取。
  • 人工神经网络是最常用的模型,死亡率是最常见的关注结局。
  • 模型开发方面,缺乏采用外部验证、特征选择方法和进行正式校准测试的研究。
  • 不同机器学习模型、患者人群、性能指标和所用特征之间报告异质性显著。

证据类型、等级与局限

  • 证据类型:系统评价。
  • 作者结论:这些模型作为临床决策辅助存在机会,建议未来模型开发需更多标准化和严谨指南。
  • 局限:原文报告机器学习模型开发与报告存在异质性,缺乏外部验证、特征选择方法和正式校准测试,不同模型、患者人群、性能指标和特征之间报告异质性显著。

对床旁实践的改变

  • 作者认为创伤结局的机器学习模型作为临床决策辅助存在机会,建议未来模型开发需更多标准化和严谨指南。

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

STUDY OBJECTIVE: Machine learning models carry unique potential as decision-making aids and prediction tools for improving patient care. Traumatically injured patients provide a uniquely heterogeneous population with severe injuries that can be difficult to predict. Given the relative infancy of machine learning applications in medicine, this systematic review aimed to better understand the current state of machine learning development and implementation to help create a basis for future research.

METHODS: We conducted a systematic review from inception to May 2021, using Embase, MEDLINE through Ovid, Web of Science, Google Scholar, and relevant gray literature, for uses of machine learning in predicting the outcomes of trauma patients. The screening and data extraction were performed by 2 independent reviewers.

RESULTS: Of the 14,694 identified articles screened, 67 were included for data extraction. Artificial neural networks comprised the most commonly used model, and mortality was the most prevalent outcome of interest. In terms of machine learning model development, there was a lack of studies that employed external validation, feature selection methods, and performed formal calibration testing. Significant heterogeneity in reporting was also observed between the machine learning models employed, patient populations, performance metrics, and features employed.

CONCLUSION: This review highlights the heterogeneity in the development and reporting of machine learning models for the prediction of trauma outcomes. While these models present an area of opportunity as an ancillary to clinical decision-making, we recommend more standardization and rigorous guidelines for the development of future models.

来源:Ann Emerg Med,查看原文。版权归原作者所有。

参考来源

  1. Zhang T, Nikouline A, Lightfoot D, et al. Machine Learning in the Prediction of Trauma Outcomes: A Systematic Review. Ann Emerg Med. 2022. PMID: 35842343. doi:10.1016/j.annemergmed.2022.05.011

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。