CoChat
Sign Up
Cited by 29Machine Learning in HealthcareArtificial Intelligence in Healthcare and EducationArtificial Intelligence in Healthcare

Identifying and evaluating barriers for the implementation of machine learning in the intensive care unit

Open access
D’Hondt, Ellie, Ashby, Thomas J., Chakroun, Imen, Koninckx, Thomas, Wuyts, Roel·2022·Communications Medicine
DOI 10.1038/s43856-022-00225-1PMC PMC9768782
Open this paper in CoChat — free accountOpen PDF

Abstract

BACKGROUND: Despite apparent promise and the availability of numerous examples in the literature, machine learning models are rarely used in practice in ICU units. This mismatch suggests that there are poorly understood barriers preventing uptake, which we aim to identify. METHODS: We begin with a qualitative study with 29 interviews of 40 Intensive Care Unit-, hospital- and MedTech company staff members. As a follow-up to the study, we attempt to quantify some of the technical issues raised. To perform experiments we selected two models based on criteria such as medical relevance. Using these models we measure the loss of performance in predictive models due to drift over time, change of available patient features, scarceness of data, and deploying a model in a different context to the one it was built in. RESULTS: The qualitative study confirms our assumptions on the potential of AI-driven analytics for patient care, as well as showing the prevalence and type of technical blocking factors that are responsible for its slow uptake. The experiments confirm that each of these issues can cause important loss of predictive model performance, depending on the model and the issue. CONCLUSIONS: Based on the qualitative study and quantitative experiments we conclude that more research on practical solutions to enable AI-driven innovation in Intensive Care Units is needed. Furthermore, the general poor situation with respect to public, usable implementations of predictive models would appear to limit the possibilities for both the scientific repeatability of the underlying research and the transfer of this research into practice.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s43856-022-00225-1

Cites

3 of 3 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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?

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

Flagged first, then by citations

Research works printed but not linked: 34

  1. [1]Fogel AL Kvedar JC Artificial intelligence powers digital medicine NPJ Digit. Med. 2018 1 1 4 10.1038/s41746-017-0012-2 31304291 PMC6548340 · DOI
  2. [2]Keane, P. A. & Topol, E. J. With an eye to AI and autonomous diagnosis. NPJ Digit. Med.1, 40 (2018). PMC6550235 31304321
  3. [5]Scheetz, J. et al. A survey of clinicians on the use of artificial intelligence in ophthalmology, dermatology, radiology and radiation oncology. Sci. Rep. 1110.1038/s41598-021-84698-5 (2021). PMC7933437 33664367 · DOI
  4. [6]Buck C Doctor E Hennrich J Jöhnk J Eymann T General practitioners’ attitudes toward artificial intelligence–enabled systems: interview study J. Med. Internet Res. 2022 24 e28916 10.2196/28916 35084342 PMC8832268 · DOI · Paper page
  5. [7]Panch, T., Mattie, H. & Celi, L. The “inconvenient truth” about AI in healthcare. NPJ Digit. Med. 2, 77 (2019). PMC6697674 31453372
  6. [8]Johnson, A. E. W., Pollard, T. J. & Naumann, T. Generalizability of predictive models for intensive care unit patients. https://arxiv.org/abs/1812.02275 (2018). · arXiv
  7. [9]Wiens J Guttag JV Horvitz E A study in transfer learning: leveraging data from multiple hospitals to enhance hospital-specific predictions J. Am. Med. Inform. Assoc. 2014 21 699 706 10.1136/amiajnl-2013-002162 24481703 PMC4078276 · DOI · Paper page
  8. [10]Lee, G., Rubinfeld, I. & Syed, Z. Adapting surgical models to individual hospitals using transfer learning. InL 2012 IEEE 12th International Conference on Data Mining Workshops, 57–63 (IEEE, 2012).
  9. [11]Nestor, B. et al. Feature robustness in non-stationary health records: Caveats to deployable model performance in common clinical machine learning tasks. In Doshi-Velez, F. et al. (eds.) Proceedings of the 4th Machine Learning for Healthcare Conference, Vol. 106, 381–405 (PMLR, 2019). http://proceedings.mlr.press/v106/nestor19a.html.
  10. [12]Subbaswamy, A., Adams, R. & Saria, S. Evaluating model robustness and stability to dataset shift. In Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, Vol. 130, 2611–2619 (PMLR, 2021).
  11. [13]Harutyunyan H Khachatrian H Kale DC Ver Steeg G Galstyan A Multitask learning and benchmarking with clinical time series data Sci. Data 2019 6 96 10.1038/s41597-019-0103-9 31209213 PMC6572845 · DOI · Paper page
  12. [14]McWilliams, C. J. et al. Towards a decision support tool for intensive care discharge: machine learning algorithm development using electronic healthcare data from MIMIC-III and Bristol, UK. BMJ Open9 https://bmjopen.bmj.com/content/9/3/e025925. https://bmjopen.bmj.com/content/9/3/e025925.full.pdf (2019). PMC6429919 30850412
  13. [15]Roimi, M. et al. Early diagnosis of bloodstream infections in the intensive care unit using machine-learning algorithms. Intensive Care Med.46, 454–462 (2020). 31912208
  14. [16]Gourova, E. & Toteva, K. Enhancing knowledge creation and innovation in smes. In 2012 Mediterranean Conference on Embedded Computing (MECO), 292–297 (IEEE, 2012).
  15. [17]Sanders, E. B.-N., Singh, S. & Braun, E. Co-designing with communities. Engaged Scholars. Vol. 6, (Ohio State University, Office of Outreach and Engagement, 2018).
  16. [18]Coorevits L Schuurman D Oelbrandt K Logghe S Bringing personas to life: user experience design through interactive coupled open innovation Pers. Stud. 2016 2 97 114 10.21153/ps2016vol2no1art534 · DOI
  17. [19]Brown T Design thinking Harv. Bus. Rev. 2008 86 84 92 18605031
  18. [20]Johnson AE MIMIC-III, a freely accessible critical care database Sci. Data 2016 3 160035 10.1038/sdata.2016.35 27219127 PMC4878278 · DOI · Paper page
  19. [21]Johnson, A. E., Pollard, T. J. & Mark, R. G. MIMIC-III Clinical Database(version 1.4). 10.13026/C2XW26 (2016). · DOI · Paper page
  20. [22]Pollard TJ The eICU collaborative research database, a freely available multi-center database for critical care research Sci. Data 2018 5 1 13 10.1038/sdata.2018.178 30204154 PMC6132188 · DOI · Paper page
  21. [23]Pollard, T. J. et al. eICU Collaborative Research Database (version 2.0). 10.13026/C2WM1R (2019). · DOI
  22. [24]Pakbin, A. et al. Prediction of icu readmissions using data at patient discharge. In 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 4932–4935 (IEEE, 2018). 30441449
  23. [25]Hobson, C. et al. Cost and mortality associated with postoperative acute kidney injury. Ann. Surg. 261, 1207–1214 (2015). PMC4247993 24887982
  24. [27]Li Y Early prediction of acute kidney injury in critical care setting using clinical notes Proceedings (IEEE Int. Conf. Bioinformatics Biomed.) 2018 2018 683 686 33376624 PMC7768909
  25. [28]Zimmerman, L. P. et al. Early prediction of acute kidney injury following ICU admission using a multivariate panel of physiological measurements. BMC Med. Inform. Decis. Mak. 19, 16 (2019). PMC6354330 30700291
  26. [29]Du H Self-correcting recurrent neural network for acute kidney injury prediction in critical care Health Data Sci. 2021 2021 1 10 10.34133/2021/9808426 PMC10904062 38487505 · DOI
  27. [30]Mohamadlou H Prediction of acute kidney injury with a machine learning algorithm using electronic health record data Can. J. Kidney Health Dis. 2018 5 2054358118776326 10.1177/2054358118776326 30094049 PMC6080076 · DOI
  28. [31]Van Biesen W Vanmassenhove J Decruyenaere J Prediction of acute kidney injury using artificial intelligence: are we there yet? Nephrol. Dial. Transplant. 2019 35 204 205 10.1093/ndt/gfz226 31782793 · DOI
  29. [33]Desautels, T. et al. Prediction of early unplanned intensive care unit readmission in a UK tertiary care hospital: a cross-sectional machine learning approach. BMJ Open7, 9. e017199 (2017). PMC5640090 28918412
  30. [34]Wallis L Alarm fatigue linked to patient’s death Am. J. Nurs. 2010 110 16 20574186
  31. [36]Sadilek, A. et al. Privacy-first health research with federated learning. NPJ Digit. Med. 410.1038/s41746-021-00489-2 (2021). PMC8423792 34493770 · DOI · Paper page
  32. [37]Ding X-F Predictive model for acute respiratory distress syndrome events in icu patients in china using machine learning algorithms: a secondary analysis of a cohort study J. Transl. Med. 2019 17 1 10 10.1186/s12967-019-2075-0 31570096 PMC6771100 · DOI
  33. [38]Vasilevskis EE The cost of ICU delirium and coma in the intensive care unit patient Med. Care 2018 56 890 897 10.1097/MLR.0000000000000975 30179988 PMC6200340 · DOI
  34. [39]Kaji DA An attention based deep learning model of clinical events in the intensive care unit PLoS ONE 2019 14 e0211057 10.1371/journal.pone.0211057 30759094 PMC6373907 · DOI

Cited by

Sorted by citations

Authors
D’Hondt, E., Ashby, T. J., Chakroun, I., Koninckx, T., & Wuyts, R.
Affiliations
IMEC (BE)
Corresponding author
  • D’Hondt, Ellie
  • Ashby, Thomas J.
  • Chakroun, Imen
  • Wuyts, Roel
ORCID
Venue
Communications Medicine
Publisher
Springer Science and Business Media LLC
Published
2022-12-21
Volume
2
Issue
1
Pages
162-162
ISSN
2730-664X (ISSN-L)
DOI
10.1038/s43856-022-00225-1
PMC
PMC9768782
OpenAlex
W4312113333
Cited by
29
References
3
Citations by year
2026: 5 · 2025: 7 · 2024: 10 · 2023: 7
FWCI
1.97
Type
journal article
Language
en
Open access
Licence
Locations
  • Communications Medicine (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Lirias (KU Leuven) (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
Keywords
intensive care unit, clinical implementation of AI, model degradation, data scarcity, clinical implementation, AI-driven analytics, medical technology

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