Causal inference using observational intensive care unit data: a scoping review and recommendations for future practice
Abstract 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 infere...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-11-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-023-00961-1 |
| _version_ | 1827602796913885184 |
|---|---|
| author | J. M. Smit J. H. Krijthe W. M. R. Kant J. A. Labrecque M. Komorowski D. A. M. P. J. Gommers J. van Bommel M. J. T. Reinders M. E. van Genderen |
| author_facet | J. M. Smit J. H. Krijthe W. M. R. Kant J. A. Labrecque M. Komorowski D. A. M. P. J. Gommers J. van Bommel M. J. T. Reinders M. E. van Genderen |
| author_sort | J. M. Smit |
| collection | DOAJ |
| description | Abstract 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. |
| first_indexed | 2024-03-09T05:25:35Z |
| format | Article |
| id | doaj.art-be441d244a7a4a9d8cfcfa801fb9c74f |
| institution | Directory Open Access Journal |
| issn | 2398-6352 |
| language | English |
| last_indexed | 2024-03-09T05:25:35Z |
| publishDate | 2023-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj.art-be441d244a7a4a9d8cfcfa801fb9c74f2023-12-03T12:37:17ZengNature Portfolionpj Digital Medicine2398-63522023-11-016111110.1038/s41746-023-00961-1Causal inference using observational intensive care unit data: a scoping review and recommendations for future practiceJ. M. Smit0J. H. Krijthe1W. M. R. Kant2J. A. Labrecque3M. Komorowski4D. A. M. P. J. Gommers5J. van Bommel6M. J. T. Reinders7M. E. van Genderen8Department of Intensive Care, Erasmus University Medical CenterPattern Recognition & Bioinformatics group, EEMCS, Delft University of TechnologyData Science group, Institute for Computing and Information Sciences, Radboud UniversityDepartment of Epidemiology, Erasmus Medical CenterDepartment of Surgery and Cancer, Faculty of Medicine, Imperial College LondonDepartment of Intensive Care, Erasmus University Medical CenterDepartment of Intensive Care, Erasmus University Medical CenterPattern Recognition & Bioinformatics group, EEMCS, Delft University of TechnologyDepartment of Intensive Care, Erasmus University Medical CenterAbstract 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.https://doi.org/10.1038/s41746-023-00961-1 |
| spellingShingle | J. M. Smit J. H. Krijthe W. M. R. Kant J. A. Labrecque M. Komorowski D. A. M. P. J. Gommers J. van Bommel M. J. T. Reinders M. E. van Genderen Causal inference using observational intensive care unit data: a scoping review and recommendations for future practice npj Digital Medicine |
| title | Causal inference using observational intensive care unit data: a scoping review and recommendations for future practice |
| title_full | Causal inference using observational intensive care unit data: a scoping review and recommendations for future practice |
| title_fullStr | Causal inference using observational intensive care unit data: a scoping review and recommendations for future practice |
| title_full_unstemmed | Causal inference using observational intensive care unit data: a scoping review and recommendations for future practice |
| title_short | Causal inference using observational intensive care unit data: a scoping review and recommendations for future practice |
| title_sort | causal inference using observational intensive care unit data a scoping review and recommendations for future practice |
| url | https://doi.org/10.1038/s41746-023-00961-1 |
| work_keys_str_mv | AT jmsmit causalinferenceusingobservationalintensivecareunitdataascopingreviewandrecommendationsforfuturepractice AT jhkrijthe causalinferenceusingobservationalintensivecareunitdataascopingreviewandrecommendationsforfuturepractice AT wmrkant causalinferenceusingobservationalintensivecareunitdataascopingreviewandrecommendationsforfuturepractice AT jalabrecque causalinferenceusingobservationalintensivecareunitdataascopingreviewandrecommendationsforfuturepractice AT mkomorowski causalinferenceusingobservationalintensivecareunitdataascopingreviewandrecommendationsforfuturepractice AT dampjgommers causalinferenceusingobservationalintensivecareunitdataascopingreviewandrecommendationsforfuturepractice AT jvanbommel causalinferenceusingobservationalintensivecareunitdataascopingreviewandrecommendationsforfuturepractice AT mjtreinders causalinferenceusingobservationalintensivecareunitdataascopingreviewandrecommendationsforfuturepractice AT mevangenderen causalinferenceusingobservationalintensivecareunitdataascopingreviewandrecommendationsforfuturepractice |