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

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.

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

Fig 1

PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) flow chart of study records. The full list of screened papers is available in Supplementary file 5. AI, artificial intelligence; MV, mechanical ventilation; NIV, noninvasive ventilation; OSA, obstructive sleep apnoea.

Fig 2

Temporal distribution illustrating the number and maturity of studies included in this review. The average number of publications per year is presented for two decades (1990–9∗ and 2000–9∗) because of the limited number of relevant publications in that period; the highest number of publications in any 1 yr during that period was three (2002 and 2009). There has been a significant rise in the number of artificial intelligence algorithms being used to develop models applied to mechanical ventilation in the last 5 yr; 55 since January 2016. However, there has been no consistent shift towards device creation and subsequent deployment and evaluation in clinical practice.

Fig 3

Risk of bias assessed using Prediction model Risk Of Bias ASsessment Tool (PROBAST) reporting standards for all included studies. Low indicates the percentage of studies that did not receive any high-risk rating for a particular category. High denotes those that achieved a high-risk rating in at least one criterion for a particular category.