Literature DB >> 34772497

Artificial intelligence for mechanical ventilation: systematic review of design, reporting standards, and bias.

Jack Gallifant1, Joe Zhang2, Maria Del Pilar Arias Lopez3, Tingting Zhu4, Luigi Camporota5, Leo A Celi6, Federico Formenti7.   

Abstract

BACKGROUND: Artificial intelligence (AI) has the potential to personalise mechanical ventilation strategies for patients with respiratory failure. However, current methodological deficiencies could limit clinical impact. We identified common limitations and propose potential solutions to facilitate translation of AI to mechanical ventilation of patients.
METHODS: A systematic review was conducted in MEDLINE, Embase, and PubMed Central to February 2021. Studies investigating the application of AI to patients undergoing mechanical ventilation were included. Algorithm design and adherence to reporting standards were assessed with a rubric combining published guidelines, satisfying the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis [TRIPOD] statement. Risk of bias was assessed by using the Prediction model Risk Of Bias ASsessment Tool (PROBAST), and correspondence with authors to assess data and code availability.
RESULTS: Our search identified 1,342 studies, of which 95 were included: 84 had single-centre, retrospective study design, with only one randomised controlled trial. Access to data sets and code was severely limited (unavailable in 85% and 87% of studies, respectively). On request, data and code were made available from 12 and 10 authors, respectively, from a list of 54 studies published in the last 5 yr. Ethnicity was frequently under-reported 18/95 (19%), as was model calibration 17/95 (18%). The risk of bias was high in 89% (85/95) of the studies, especially because of analysis bias.
CONCLUSIONS: Development of algorithms should involve prospective and external validation, with greater code and data availability to improve confidence in and translation of this promising approach. TRIAL REGISTRATION NUMBER: PROSPERO - CRD42021225918.
Copyright © 2021 British Journal of Anaesthesia. Published by Elsevier Ltd. All rights reserved.

Entities:  

Keywords:  artificial intelligence; bias; critical care; decision support; mechanical ventilation respiratory failure

Mesh:

Year:  2021        PMID: 34772497      PMCID: PMC8792831          DOI: 10.1016/j.bja.2021.09.025

Source DB:  PubMed          Journal:  Br J Anaesth        ISSN: 0007-0912            Impact factor:   9.166


  36 in total

Review 1.  Healthcare disparities in critical illness.

Authors:  Graciela J Soto; Greg S Martin; Michelle Ng Gong
Journal:  Crit Care Med       Date:  2013-12       Impact factor: 7.598

2.  Artificial intelligence in intensive care: are we there yet?

Authors:  Matthieu Komorowski
Journal:  Intensive Care Med       Date:  2019-06-24       Impact factor: 17.440

3.  Race representation matters in cancer care.

Authors: 
Journal:  Lancet Digit Health       Date:  2021-07

4.  Ventilation with lower tidal volumes as compared with traditional tidal volumes for acute lung injury and the acute respiratory distress syndrome.

Authors:  Roy G Brower; Michael A Matthay; Alan Morris; David Schoenfeld; B Taylor Thompson; Arthur Wheeler
Journal:  N Engl J Med       Date:  2000-05-04       Impact factor: 91.245

5.  PROBAST: A Tool to Assess the Risk of Bias and Applicability of Prediction Model Studies.

Authors:  Robert F Wolff; Karel G M Moons; Richard D Riley; Penny F Whiting; Marie Westwood; Gary S Collins; Johannes B Reitsma; Jos Kleijnen; Sue Mallett
Journal:  Ann Intern Med       Date:  2019-01-01       Impact factor: 25.391

6.  DECIDE-AI: new reporting guidelines to bridge the development-to-implementation gap in clinical artificial intelligence.

Authors: 
Journal:  Nat Med       Date:  2021-02       Impact factor: 53.440

7.  Moving from bytes to bedside: a systematic review on the use of artificial intelligence in the intensive care unit.

Authors:  Davy van de Sande; Michel E van Genderen; Joost Huiskens; Diederik Gommers; Jasper van Bommel
Journal:  Intensive Care Med       Date:  2021-06-05       Impact factor: 17.440

Review 8.  The reproducibility crisis in the age of digital medicine.

Authors:  Aaron Stupple; David Singerman; Leo Anthony Celi
Journal:  NPJ Digit Med       Date:  2019-01-29

9.  Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement.

Authors:  David Moher; Alessandro Liberati; Jennifer Tetzlaff; Douglas G Altman
Journal:  PLoS Med       Date:  2009-07-21       Impact factor: 11.069

10.  Physiological and quantitative CT-scan characterization of COVID-19 and typical ARDS: a matched cohort study.

Authors:  Davide Chiumello; Mattia Busana; Silvia Coppola; Federica Romitti; Paolo Formenti; Matteo Bonifazi; Tommaso Pozzi; Maria Michela Palumbo; Massimo Cressoni; Peter Herrmann; Konrad Meissner; Michael Quintel; Luigi Camporota; John J Marini; Luciano Gattinoni
Journal:  Intensive Care Med       Date:  2020-10-21       Impact factor: 17.440

View more
  1 in total

Review 1.  Moving towards vertically integrated artificial intelligence development.

Authors:  Joe Zhang; Sanjay Budhdeo; Wasswa William; Paul Cerrato; Haris Shuaib; Harpreet Sood; Hutan Ashrafian; John Halamka; James T Teo
Journal:  NPJ Digit Med       Date:  2022-09-15
  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.