基于观察性ICU数据的因果推断:范围综述与未来实践建议
本范围综述检索Embase、MEDLINE ALL、Web of Science核心合集、Google Scholar、medRxiv、bioRxiv、arXiv和ACM数字图书馆,纳入79项在成人ICU中处理时变治疗的因果推断模型研究,评估其目标试验要素(纳入标准、治疗策略、随访期、结局、分析计划)和主要因果假设(条件可交换性、阳性性、一致性)的报告质量。方法学上G方法占61%、强化学习方法占39%;静态治疗策略占51%、动态治疗策略占49%。仅30项(38%)报告全部5个目标试验要素,仅7项(9%)提及全部3个因果假设。作者倡导:为实现ICU中可操作的AI,应仔细考虑感兴趣的因果问题、将该研究问题描述为目标试验模拟、使用合适的因果推断方法,并认识(并检验潜在违反)因果假设。
要点
- 本综述纳入79项成人ICU中处理时变治疗的因果推断模型研究,方法学上G方法占61%、强化学习方法占39%。
- 治疗策略方面,静态方案占51%、动态方案占49%。
- 仅30项(38%)研究报告全部5个目标试验要素(纳入标准、治疗策略、随访期、结局、分析计划)。
- 仅7项(9%)研究提及全部3个因果假设(条件可交换性、阳性性、一致性)。
- 作者倡导将因果问题描述为目标试验模拟、选用合适因果推断方法,并认识(并检验潜在违反)因果假设,以实现ICU中可操作的AI。
适用人群与场景
- 成人ICU中涉及处理时变治疗的因果推断模型研究。
研究设计与关键结果
- 研究类型:范围综述;检索Embase、MEDLINE ALL、Web of Science核心合集、Google Scholar、medRxiv、bioRxiv、arXiv和ACM数字图书馆,筛查2184条题录,最终纳入79项研究。
- 方法学:G方法占61%,强化学习方法占39%;静态治疗策略占51%,动态治疗策略占49%。
- 报告质量:仅30项(38%)研究报告全部5个目标试验要素(纳入标准、治疗策略、随访期、结局、分析计划);仅7项(9%)研究提及全部3个因果假设(条件可交换性、阳性性、一致性)。
证据类型、等级与局限
- 证据类型:范围综述。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者倡导:为实现ICU中可操作的AI,应仔细考虑感兴趣的因果问题,并将该研究问题描述为目标试验模拟。
- 作者倡导:使用合适的因果推断方法,并认识(并检验潜在违反)因果假设。
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
This scoping review focuses on the essential role of models for causal inference in shaping actionable artificial intelligence (AI) designed to aid clinicians in decision-making. The objective was to identify and evaluate the reporting quality of studies introducing models for causal inference in intensive care units (ICUs), and to provide recommendations to improve the future landscape of research practices in this domain. To achieve this, we searched various databases including Embase, MEDLINE ALL, Web of Science Core Collection, Google Scholar, medRxiv, bioRxiv, arXiv, and the ACM Digital Library. Studies involving models for causal inference addressing time-varying treatments in the adult ICU were reviewed. Data extraction encompassed the study settings and methodologies applied. Furthermore, we assessed reporting quality of target trial components (i.e., eligibility criteria, treatment strategies, follow-up period, outcome, and analysis plan) and main causal assumptions (i.e., conditional exchangeability, positivity, and consistency). Among the 2184 titles screened, 79 studies met the inclusion criteria. The methodologies used were G methods (61%) and reinforcement learning methods (39%). Studies considered both static (51%) and dynamic treatment regimes (49%). Only 30 (38%) of the studies reported all five target trial components, and only seven (9%) studies mentioned all three causal assumptions. To achieve actionable AI in the ICU, we advocate careful consideration of the causal question of interest, describing this research question as a target trial emulation, usage of appropriate causal inference methods, and acknowledgement (and examination of potential violations of) the causal assumptions.
参考来源
- Smit JM, Krijthe JH, Kant WMR, et al. Causal inference using observational intensive care unit data: a scoping review and recommendations for future practice. NPJ Digit Med. 2023. PMID: 38012221. doi:10.1038/s41746-023-00961-1
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。