公众号 / 文章重症综合管理与镇静镇痛

重症监护大数据的现代学习:首先不伤害

Modern Learning from Big Data in Critical Care: Primum Non Nocere.
PubMed 文献 · Neurocrit Care · 2022-05-05
一句话结论聚类与预测研究中使用机器学习需谨慎评估可推广性,作者主张工程师、流行病学家与统计学家协作以避免伤害。

本文为观点文章,讨论重症监护研究中日益普及的大数据集与统计学习/机器学习(ML)技术。作者指出ML在诊断领域(如识别影像学异常)已获成功,但在聚类和预测研究中其获益与效率仍有争议;聚类研究的关键挑战是确保和评估可推广性,这限制了将研究结果用于个体患者;预测问题中算法选择取决于数据量、模型维度和缺失数据程度。作者主张在ML方法中纳入统计框架(如处理缺失数据和测量误差),并呼吁ML专家、流行病学家和统计学家加强互动,在提取信息的同时避免伤害。

要点

  • 聚类研究的关键挑战是确保和评估可推广性,这限制了将聚类研究结果应用于个体患者。
  • 预测问题中,决定ML相对统计技术是否有用的因素包括数据量、首选模型的维度和缺失数据的程度。
  • 存在现代ML方法可能更优的领域,但应努力在ML方法中纳入统计框架(如处理缺失数据和测量误差)。
  • 作者主张对新数据驱动的发现进行谨慎评估,并呼吁ML专家、流行病学家和统计学家加强互动以避免伤害。

研究设计与关键结果

  • 本文为观点文章,阐述重症监护中常用的统计学习与ML技术,并为聚类和预测问题中的负责任使用提供指导。
  • ML在诊断领域(如识别影像学异常)已获成功;在聚类和预测研究中,ML相对统计学习的获益与效率仍有更多讨论。
  • 聚类研究的关键挑战是确保和评估可推广性,这限制了将研究结果应用于个体患者。
  • 预测问题中算法选择受数据量、首选模型维度和缺失数据程度影响;存在现代ML方法可能更优的领域。
  • 作者主张在ML方法中纳入统计框架(如处理缺失数据或测量误差),并呼吁ML专家、流行病学家和统计学家加强互动。

证据类型、等级与局限

  • 证据类型:观点文章。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者主张对新的数据驱动发现进行谨慎评估。
  • 作者认为需要ML方法专家的工程思维、流行病学家对偏倚的洞察和统计学家的概率思维之间更多互动,以尽可能从数据中提取信息和知识,同时避免伤害。

提炼说明

  • 本条依据论文摘要整理;摘要未涉及「适用人群与场景」「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

Large and complex data sets are increasingly available for research in critical care. To analyze these data, researchers use techniques commonly referred to as statistical learning or machine learning (ML). The latter is known for large successes in the field of diagnostics, for example, by identification of radiological anomalies. In other research areas, such as clustering and prediction studies, there is more discussion regarding the benefit and efficiency of ML techniques compared with statistical learning. In this viewpoint, we aim to explain commonly used statistical learning and ML techniques and provide guidance for responsible use in the case of clustering and prediction questions in critical care. Clustering studies have been increasingly popular in critical care research, aiming to inform how patients can be characterized, classified, or treated differently. An important challenge for clustering studies is to ensure and assess generalizability. This limits the application of findings in these studies toward individual patients. In the case of predictive questions, there is much discussion as to what algorithm should be used to most accurately predict outcome. Aspects that determine usefulness of ML, compared with statistical techniques, include the volume of the data, the dimensionality of the preferred model, and the extent of missing data. There are areas in which modern ML methods may be preferred. However, efforts should be made to implement statistical frameworks (e.g., for dealing with missing data or measurement error, both omnipresent in clinical data) in ML methods. To conclude, there are important opportunities but also pitfalls to consider when performing clustering or predictive studies with ML techniques. We advocate careful valuation of new data-driven findings. More interaction is needed between the engineer mindset of experts in ML methods, the insight in bias of epidemiologists, and the probabilistic thinking of statisticians to extract as much information and knowledge from data as possible, while avoiding harm.

来源:Neurocrit Care,查看原文。版权归原作者所有。

参考来源

  1. Gravesteijn BY, Steyerberg EW, Lingsma HF, et al. Modern Learning from Big Data in Critical Care: Primum Non Nocere. Neurocrit Care. 2022. PMID: 35513752. doi:10.1007/s12028-022-01510-6

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。