Artificial intelligence for mechanical ventilation: systematic review of design, reporting standards, and bias
Open accessAbstract
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.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In Gallifant et al., most studies were single-center retrospective analyses (88%) with high risk of bias (89%) and limited data/code availability.
“Most studies were single-center retrospective analyses (88%) with high risk of bias (89%) and limited data/code availability.”
From Artificial Intelligence to Facilitate SEP-1 Measure Compliance and Fluid Management in Sepsis (2026) · cites this paper as [36]
The Study characteristics section reports that 88% of studies were retrospective, but only 56% were single-centre; it does not report that 88% were both. The Risk of bias section reports high risk in 85/95 studies (89%), and the reporting-standards table and ‘Moving beyond the black box’ section document limited data and code availability. (LLM, conf=0.92)
Experimental — accuracy not yet measuredGallifant et al. performed a systematic review evaluating design, reporting quality, and risk of bias of AI applications in mechanical ventilation by analyzing ninety-five studies across MEDLINE, Embase, and PubMed.
“Gallifant et al. performed a systematic review evaluating the design, reporting quality, and risk of bias of AI applications in mechanical ventilation by analyzing ninety-five studies across MEDLINE, Embase, and PubMed.”
From Artificial Intelligence to Facilitate SEP-1 Measure Compliance and Fluid Management in Sepsis (2026) · cites this paper as [36]
Gallifant et al. observed reporting and reproducibility challenges including incomplete transparency in model development, inadequate handling of missing data, and insufficient attention to calibration and post-deployment performance monitoring.
“Reporting and reproducibility challenges were also observed, including incomplete transparency in model development, inadequate handling of missing data, and insufficient attention to calibration and post-deployment performance monitoring [36].”
From Artificial Intelligence to Facilitate SEP-1 Measure Compliance and Fluid Management in Sepsis (2026) · cites this paper as [36]
Very few studies discuss the impact of bias and its computation.
“Very few studies discuss about the impact of bias and its computation [45,142].”
From Artificial intelligence bias in medical system designs: a systematic review (2023) · cites this paper as [45]
Specific medical domain applications include mechanical ventilation, COVID CT-scans, ECG, and COVID X-rays; generic applications assess bias at different stages of AI model in medical domain.
“Applications to specific medical domains include mechanical ventilation [45], COVID CT-Scans [104], ECG [97] and COVID X-rays [144], whereas generic refers to assessing bias at different stages of AImodel in medical domain [19,52,107].”
From Artificial intelligence bias in medical system designs: a systematic review (2023) · cites this paper as [45]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Preferred Reporting Items for Systematic Reviews and Meta-Analyses: the PRISMA statement
Moher, D., Liberati, A., Tetzlaff, J., Altman, D. G., & for the PRISMA Group (2009) · BMJ · doi:10.1136/bmj.b2535 · Cited by 83,823 · see citing works
Preferred Reporting Items for Systematic Reviews and Meta-Analyses: The PRISMA Statement
Moher, D., Liberati, A., Tetzlaff, J., Altman, D. G., & The PRISMA Group (2009) · PLoS Medicine · doi:10.1371/journal.pmed.1000097 · Cited by 64,042 · see citing works
Preferred reporting items for systematic reviews and meta-analyses: the PRISMA Statement.
(2009) · PubMed Central · Cited by 44,859 · see citing works
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707 · see citing works
Advances in neural information processing systems 7
Cios, K. J., & Shields, M. E. (1997) · Neurocomputing · doi:10.1016/s0925-2312(97)90018-7 · Cited by 22,089 · see citing works
(2000) · New England Journal of Medicine · doi:10.1056/nejm200005043421801 · Cited by 12,941 · see citing works
MIMIC-III, a freely accessible critical care database
Johnson, A. E. W., Pollard, T. J., Shen, L., Lehman, L.-W. H., Feng, M., Ghassemi, M., Moody, B., Szolovits, P., Anthony Celi, L., & Mark, R. G. (2016) · Scientific Data · doi:10.1038/sdata.2016.35 · Cited by 8,141 · see citing works
Moons, K. G. M., Altman, D. G., Reitsma, J. B., Ioannidis, J. P. A., Macaskill, P., Steyerberg, E. W., Vickers, A. J., Ransohoff, D. F., & Collins, G. S. (2015) · Annals of Internal Medicine · doi:10.7326/m14-0698 · Cited by 5,147 · see citing works
Collins, G. S., Reitsma, J. B., Altman, D. G., & Moons, K. G. M. (2015) · BMJ · doi:10.1136/bmj.g7594 · Cited by 4,388 · see citing works
Collins, P. G. S., Reitsma, J. B., Altman, D. G., & Moons, K. G. M. (2015) · British Journal of Cancer · doi:10.1038/bjc.2014.639 · Cited by 3,312 · see citing works
The future of digital health with federated learning
Rieke, N., Hancox, J., Li, W., Milletarì, F., Roth, H. R., Albarqouni, S., Bakas, S., Galtier, M. N., Landman, B. A., Maier-Hein, K., et al. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-00323-1 · Cited by 3,119 · see citing works
PROBAST: A Tool to Assess the Risk of Bias and Applicability of Prediction Model Studies
Wolff, R. F., Moons, K. G. M., Riley, R. D., Whiting, P. F., Westwood, M., Collins, G. S., Reitsma, J. B., Kleijnen, J., Mallett, S., & for the PROBAST Group† (2019) · Annals of Internal Medicine · doi:10.7326/m18-1376 · Cited by 2,984 · see citing works
(2004) · New England Journal of Medicine · doi:10.1056/nejmoa032193 · Cited by 2,565 · see citing works
Ventilator-Induced Lung Injury
Slutsky, A. S., & Ranieri, V. M. (2013) · New England Journal of Medicine · doi:10.1056/nejmra1208707 · Cited by 2,276 · see citing works
Acute Respiratory Distress Syndrome
Fan, E., Brodie, D., & Slutsky, A. S. (2018) · JAMA · doi:10.1001/jama.2017.21907 · Cited by 1,482 · see citing works
Komorowski, M., Celi, L. A., Badawi, O., Gordon, A. C., & Faisal, A. A. (2018) · Nature Medicine · doi:10.1038/s41591-018-0213-5 · Cited by 1,290 · see citing works
Self-citationBenjamens, S., Dhunnoo, P., & Meskó, B. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-00324-0 · Cited by 1,215 · see citing works
Nagendran, M., Chen, Y., Lovejoy, C. A., Gordon, A. C., Komorowski, M., Harvey, H., Topol, E. J., Ioannidis, J. P. A., Collins, G. S., & Maruthappu, M. (2020) · BMJ · doi:10.1136/bmj.m689 · Cited by 1,152 · see citing works
Roberts, M., Driggs, D., Thorpe, M., Gilbey, J., Yeung, M., Ursprung, S., Aviles-Rivero, A. I., Etmann, C., McCague, C., Beer, L., et al. (2021) · Nature Machine Intelligence · doi:10.1038/s42256-021-00307-0 · Cited by 1,044 · see citing works
Writing Group for the Alveolar Recruitment for Acute Respiratory Distress Syndrome Trial (ART) Investigators, Cavalcanti, A. B., Suzumura, É. A., Laranjeira, L. N., Paisani, D. D. M., Damiani, L. P., Guimarães, H. P., Romano, E. R., Regenga, M. D. M., Taniguchi, L. N. T., et al. (2017) · JAMA · doi:10.1001/jama.2017.14171 · Cited by 1,018 · see citing works
Roberts, M. T., Driggs, D., Thorpe, M., Gilbey, J., Yeung, M., Ursprung, S., Avilés-Rivero, A. I., Etmann, C., McCague, C., Beer, L., et al. (2020) · Apollo (University of Cambridge) · doi:10.17863/cam.64000 · Cited by 902 · see citing works
Sex and gender differences and biases in artificial intelligence for biomedicine and healthcare
Cirillo, D., Catuara-Solarz, S., Morey, C., Guney, E., Subirats, L., Mellino, S., Gigante, A., Valencia, A., Rementeria, M. J., Chadha, A. S., et al. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-0288-5 · Cited by 553 · see citing works
Why digital medicine depends on interoperability
Lehne, M., Sass, J., Essenwanger, A., Schepers, J., & Thun, S. (2019) · npj Digital Medicine · doi:10.1038/s41746-019-0158-1 · Cited by 501 · see citing works
Wu, E., Wu, K., Daneshjou, R., Ouyang, D., Ho, D. E., & Zou, J. (2021) · Nature Medicine · doi:10.1038/s41591-021-01312-x · Cited by 494 · see citing works
Early prediction of circulatory failure in the intensive care unit using machine learning
Hyland, S. L., Faltys, M., Hüser, M., Lyu, X., Gumbsch, T., Esteban, C., Bock, C., Horn, M., Moor, M., Rieck, B., et al. (2020) · Nature Medicine · doi:10.1038/s41591-020-0789-4 · Cited by 477 · see citing works
The myth of generalisability in clinical research and machine learning in health care
Futoma, J., Simons, M., Panch, T., Doshi-Velez, F., & Celi, L. A. (2020) · The Lancet Digital Health · doi:10.1016/s2589-7500(20)30186-2 · Cited by 467 · see citing works
Self-citationConstantin, J., Jabaudon, M., Lefrant, J., Jaber, S., Quenot, J., Langeron, O., Ferrandière, M., Grelon, F., Séguin, P., Ichaï, C., et al. (2019) · The Lancet Respiratory Medicine · doi:10.1016/s2213-2600(19)30138-9 · Cited by 381 · see citing works
Pirracchio, R., Petersen, M. L., Carone, M., Rigon, M. R., Chevret, S., & van der Laan, M. J. (2015) · The Lancet Respiratory Medicine · doi:10.1016/s2213-2600(14)70239-5 · Cited by 374 · see citing works
Chiumello, D., Busana, M., Coppola, S., et al. (2020) · Intensive Care Medicine · doi:10.1007/s00134-020-06281-2 · Cited by 294 · see citing works
van de Sande, D., van Genderen, M. E., Huiskens, J., Gommers, D., & van Bommel, J. (2021) · Intensive Care Medicine · doi:10.1007/s00134-021-06446-7 · Cited by 279 · see citing works
Goligher, E. C., Costa, E. L. V., Yarnell, C. J., Brochard, L. J., Stewart, T. E., TOMLINSON, G. A., Brower, R. G., Slutsky, A. S., & Amato, M. B. P. (2021) · American Journal of Respiratory and Critical Care Medicine · doi:10.1164/rccm.202009-3536oc · Cited by 275 · see citing works
“Big Data” in the Intensive Care Unit. Closing the Data Loop
Celi, L. A., Mark, R. G., Stone, D. J., & Montgomery, R. A. (2013) · American Journal of Respiratory and Critical Care Medicine · doi:10.1164/rccm.201212-2311ed · Cited by 209 · see citing works
Self-citationARDS Subphenotypes: Understanding a Heterogeneous Syndrome
Wilson, J. G., & Calfee, C. S. (2020) · Critical Care · doi:10.1186/s13054-020-2778-x · Cited by 204 · see citing works
The DECIDE-AI Steering Group (2021) · Nature Medicine · doi:10.1038/s41591-021-01229-5 · Cited by 184 · see citing works
Healthcare Disparities in Critical Illness
Soto, G. J., Martin, G. S., & Gong, M. N. (2013) · Critical Care Medicine · doi:10.1097/ccm.0b013e3182a84a43 · Cited by 166 · see citing works
The reproducibility crisis in the age of digital medicine
Stupple, A., Singerman, D., & Celi, L. A. (2019) · npj Digital Medicine · doi:10.1038/s41746-019-0079-z · Cited by 137 · see citing works
Self-citationClinical Predictors of Hospital Mortality Differ Between Direct and Indirect ARDS
Luo, L., Shaver, C. M., Zhao, Z., Koyama, T., Calfee, C. S., Bastarache, J. A., & Ware, L. B. (2016) · CHEST Journal · doi:10.1016/j.chest.2016.09.004 · Cited by 132 · see citing works
Mitigating Inequities and Saving Lives with ICU Triage during the COVID-19 Pandemic
White, D. B., & Lo, B. (2020) · American Journal of Respiratory and Critical Care Medicine · doi:10.1164/rccm.202010-3809cp · Cited by 129 · see citing works
Warren, L. R., Clarke, J., Arora, S., & Darzi, A. W. (2019) · BMJ Open · doi:10.1136/bmjopen-2019-031637 · Cited by 66 · see citing works
Artificial intelligence in intensive care: are we there yet?
Komorowski, M. (2019) · Intensive Care Medicine · doi:10.1007/s00134-019-05662-6 · Cited by 56 · see citing works
Clinical Verification of A Clinical Decision Support System for Ventilator Weaning
Hsu, J. C., Chen, Y. F., Chung, W. S., Tan, T. H., Chen, T., & Chiang, J. Y. (2013) · BioMedical Engineering OnLine · doi:10.1186/1475-925x-12-s1-s4 · Cited by 43 · see citing works
Race representation matters in cancer care
Health, T. L. D. (2021) · The Lancet Digital Health · doi:10.1016/s2589-7500(21)00113-8 · Cited by 5 · see citing works
Who does the model learn from?
Charpignon, M.-L., Celi, L. A., & Samuel, M. C. (2021) · The Lancet Digital Health · doi:10.1016/s2589-7500(21)00057-1 · Cited by 4 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
How to optimize the systematic review process using AI tools
Fabiano, N., Gupta, A., Bhambra, N., Luu, B., Wong, S., Maaz, M., Fiedorowicz, J. G., Smith, A. L., & Solmi, M. (2024) · JCPP Advances · doi:10.1002/jcv2.12234 · Cited by 130 · see citing works
Cai, Y., Cai, Y.-Q., Tang, L.-Y., Wang, Y.-H., Gong, M., Jing, T.-C., Li, H.-J., Li-Ling, J., Hu, W., Yin, Z., et al. (2024) · BMC Medicine · doi:10.1186/s12916-024-03273-7 · Cited by 122 · see citing works
Artificial intelligence bias in medical system designs: a systematic review
Kumar, A., Aelgani, V., Vohra, R., Gupta, S. K., Bhagawati, M., Paul, S., Saba, L., Suri, N., Khanna, N. N., Laird, J. R., et al. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16029-x · Cited by 65 · see citing works
O'Reilly, D., McGrath, J., & Martin-Loeches, I. (2024) · Journal of Intensive Medicine · doi:10.1016/j.jointm.2023.10.001 · Cited by 55 · see citing works
Mlodzinski, E., Wardi, G., Viglione, C., Nemati, S., Crotty Alexander, L., & Malhotra, A. (2023) · JMIR Perioperative Medicine · doi:10.2196/41056 · Cited by 28 · see citing works
Harnessing AI in critical care: opportunities, challenges and key steps for success
Kalimouttou, A., Stevens, R. D., & Pirracchio, R. (2026) · Thorax · doi:10.1136/thorax-2024-222125 · Cited by 12 · see citing works
Artificial Intelligence to Facilitate SEP-1 Measure Compliance and Fluid Management in Sepsis
Nguyen, H. B., Krishtopaytis, E., Lopez, E., Farnoudi, N., Van, T., Kharalampova, V., & Coz Yataco, A. (2026) · Journal of Clinical Medicine · doi:10.3390/jcm15093477
“Reporting and reproducibility challenges were also observed, including incomplete transparency in model development, inadequate handling of missing data, and insufficient attention to calibration and post-deployment performance monitoring [36].”
- Authors
- Gallifant, J., Zhang, J., del Pilar Arias Lopez, M., Zhu, T., Camporota, L., Celi, L. A., & Formenti, F.
- Affiliations
- King's College London (GB)
- Guy's and St Thomas' NHS Foundation Trust (GB)
- University of Oxford (GB)
- Beth Israel Deaconess Medical Center (US)
- University of Nebraska at Omaha (US)
- Corresponding author
- Gallifant, Jack
- Celi, Leo A.
- Venue
- British Journal of Anaesthesia
- Publisher
- Elsevier BV
- Published
- 2022-02
- Volume
- 128
- Issue
- 2
- Pages
- 343-351
- ISSN
- 0007-0912 (ISSN-L)
- PMC
- PMC8792831
- OpenAlex
- W3213508730
- Cited by
- 72
- References
- 43
- Citations by year
- 2026: 13 · 2025: 15 · 2024: 23 · 2023: 11 · 2022: 7 · 2021: 3
- FWCI
- 1.77
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- Locations
- British Journal of Anaesthesia (publishedVersion)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Institute of Biomedical Imaging and Bioengineering (R01 EB017205)
- Wellcome Trust
- National Institute of Academic Anaesthesia (NIAA19R108)
- Royal Academy of Engineering
- National Institutes of Health
- Topics
- Health Sciences › Medicine › Pulmonary and Respiratory Medicine › Respiratory Support and Mechanisms
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Keywords
- artificial intelligence, mechanical ventilation, respiratory failure, algorithm design, reporting guidelines, tripod, PROBAST, risk of bias, model calibration, external validation, analysis bias
- MeSH terms
- Algorithms, Artificial Intelligence, Humans, Models, Theoretical, Research Design, Respiration, Artificial, Respiratory Insufficiency, Bias, Randomized Controlled Trials as Topic, Research Report
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
