Davy van de Sande1, Michel E van Genderen2, Joost Huiskens3, Diederik Gommers1, Jasper van Bommel1. 1. Department of Adult Intensive Care, Erasmus MC University Medical Center, Room Ne-413, Doctor Molewaterplein 40, 3015 GD, Rotterdam, The Netherlands. 2. Department of Adult Intensive Care, Erasmus MC University Medical Center, Room Ne-413, Doctor Molewaterplein 40, 3015 GD, Rotterdam, The Netherlands. m.vangenderen@erasmusmc.nl. 3. SAS Institute, Health Care Analytics, Huizen, The Netherlands.
Abstract
PURPOSE: Due to the increasing demand for intensive care unit (ICU) treatment, and to improve quality and efficiency of care, there is a need for adequate and efficient clinical decision-making. The advancement of artificial intelligence (AI) technologies has resulted in the development of prediction models, which might aid clinical decision-making. This systematic review seeks to give a contemporary overview of the current maturity of AI in the ICU, the research methods behind these studies, and the risk of bias in these studies. METHODS: A systematic search was conducted in Embase, Medline, Web of Science Core Collection and Cochrane Central Register of Controlled Trials databases to identify eligible studies. Studies using AI to analyze ICU data were considered eligible. Specifically, the study design, study aim, dataset size, level of validation, level of readiness, and the outcomes of clinical trials were extracted. Risk of bias in individual studies was evaluated by the Prediction model Risk Of Bias ASsessment Tool (PROBAST). RESULTS: Out of 6455 studies identified through literature search, 494 were included. The most common study design was retrospective [476 studies (96.4% of all studies)] followed by prospective observational [8 (1.6%)] and clinical [10 (2%)] trials. 378 (80.9%) retrospective studies were classified as high risk of bias. No studies were identified that reported on the outcome evaluation of an AI model integrated in routine clinical practice. CONCLUSION: The vast majority of developed ICU-AI models remain within the testing and prototyping environment; only a handful were actually evaluated in clinical practice. A uniform and structured approach can support the development, safe delivery, and implementation of AI to determine clinical benefit in the ICU.
PURPOSE: Due to the increasing demand for intensive care unit (ICU) treatment, and to improve quality and efficiency of care, there is a need for adequate and efficient clinical decision-making. The advancement of artificial intelligence (AI) technologies has resulted in the development of prediction models, which might aid clinical decision-making. This systematic review seeks to give a contemporary overview of the current maturity of AI in the ICU, the research methods behind these studies, and the risk of bias in these studies. METHODS: A systematic search was conducted in Embase, Medline, Web of Science Core Collection and Cochrane Central Register of Controlled Trials databases to identify eligible studies. Studies using AI to analyze ICU data were considered eligible. Specifically, the study design, study aim, dataset size, level of validation, level of readiness, and the outcomes of clinical trials were extracted. Risk of bias in individual studies was evaluated by the Prediction model Risk Of Bias ASsessment Tool (PROBAST). RESULTS: Out of 6455 studies identified through literature search, 494 were included. The most common study design was retrospective [476 studies (96.4% of all studies)] followed by prospective observational [8 (1.6%)] and clinical [10 (2%)] trials. 378 (80.9%) retrospective studies were classified as high risk of bias. No studies were identified that reported on the outcome evaluation of an AI model integrated in routine clinical practice. CONCLUSION: The vast majority of developed ICU-AI models remain within the testing and prototyping environment; only a handful were actually evaluated in clinical practice. A uniform and structured approach can support the development, safe delivery, and implementation of AI to determine clinical benefit in the ICU.
Entities:
Keywords:
Artificial intelligence; Clinical trials; Intensive care unit; Machine learning
Authors: Giuseppe Citerio; Soojin Park; J Michael Schmidt; Richard Moberg; Jose I Suarez; Peter D Le Roux Journal: Neurocrit Care Date: 2015-06 Impact factor: 3.210
Authors: Andre Esteva; Brett Kuprel; Roberto A Novoa; Justin Ko; Susan M Swetter; Helen M Blau; Sebastian Thrun Journal: Nature Date: 2017-01-25 Impact factor: 49.962
Authors: Robert Lindsey; Aaron Daluiski; Sumit Chopra; Alexander Lachapelle; Michael Mozer; Serge Sicular; Douglas Hanel; Michael Gardner; Anurag Gupta; Robert Hotchkiss; Hollis Potter Journal: Proc Natl Acad Sci U S A Date: 2018-10-22 Impact factor: 11.205
Authors: Jack Gallifant; Joe Zhang; Maria Del Pilar Arias Lopez; Tingting Zhu; Luigi Camporota; Leo A Celi; Federico Formenti Journal: Br J Anaesth Date: 2021-11-09 Impact factor: 9.166
Authors: Swantje Voller; H Rob Taal; Serife Kurul; Kinga Fiebig; Robert B Flint; Irwin K M Reiss; Helmut Küster; Sinno H P Simons Journal: Pediatr Res Date: 2021-09-08 Impact factor: 3.756
Authors: Franck Verdonk; Dorien Feyaerts; Rafael Badenes; Julie A Bastarache; Adrien Bouglé; Wesley Ely; Brice Gaudilliere; Christopher Howard; Katarzyna Kotfis; Alexandre Lautrette; Matthieu Le Dorze; Babith Joseph Mankidy; Michael A Matthay; Christopher K Morgan; Aurélien Mazeraud; Brijesh V Patel; Rajyabardhan Pattnaik; Jean Reuter; Marcus J Schultz; Tarek Sharshar; Gentle S Shrestha; Charles Verdonk; Lorraine B Ware; Romain Pirracchio; Matthieu Jabaudon Journal: Anaesth Crit Care Pain Med Date: 2022-06-30 Impact factor: 7.025
Authors: Aileen Kharat; Carla Ribeiro; Berrin Er; Christoph Fisser; Daniel López-Padilla; Foteini Chatzivasiloglou; Leo M A Heunks; Maxime Patout; Rebecca F D'Cruz Journal: ERJ Open Res Date: 2022-05-23
Authors: Davy van de Sande; Michel E Van Genderen; Jim M Smit; Joost Huiskens; Jacob J Visser; Robert E R Veen; Edwin van Unen; Oliver Hilgers Ba; Diederik Gommers; Jasper van Bommel Journal: BMJ Health Care Inform Date: 2022-02