Causal inference using observational intensive care unit data: a scoping review and recommendations for future practice.

Autor: Smit JM; Department of Intensive Care, Erasmus University Medical Center, Rotterdam, The Netherlands. j.smit@erasmusmc.nl.; Pattern Recognition & Bioinformatics group, EEMCS, Delft University of Technology, Delft, The Netherlands. j.smit@erasmusmc.nl., Krijthe JH; Pattern Recognition & Bioinformatics group, EEMCS, Delft University of Technology, Delft, The Netherlands., Kant WMR; Data Science group, Institute for Computing and Information Sciences, Radboud University, Nijmegen, The Netherlands., Labrecque JA; Department of Epidemiology, Erasmus Medical Center, Rotterdam, The Netherlands., Komorowski M; Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, UK.; Intensive Care Unit, Charing Cross Hospital, Imperial College Healthcare NHS Trust, London, UK., Gommers DAMPJ; Department of Intensive Care, Erasmus University Medical Center, Rotterdam, The Netherlands., van Bommel J; Department of Intensive Care, Erasmus University Medical Center, Rotterdam, The Netherlands., Reinders MJT; Pattern Recognition & Bioinformatics group, EEMCS, Delft University of Technology, Delft, The Netherlands., van Genderen ME; Department of Intensive Care, Erasmus University Medical Center, Rotterdam, The Netherlands.
Jazyk: angličtina
Zdroj: NPJ digital medicine [NPJ Digit Med] 2023 Nov 27; Vol. 6 (1), pp. 221. Date of Electronic Publication: 2023 Nov 27.
DOI: 10.1038/s41746-023-00961-1
Abstrakt: 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.
(© 2023. The Author(s).)
Databáze: MEDLINE
Externí odkaz: