Moving from bytes to bedside: a systematic review on the use of artificial intelligence in the intensive care unit
Open accessThe DOI matches its Crossref record; 62 of the 63 references it cites were found in a registry or an index, and 1 are not checked yet; 3 of the 68 sources its claims cite were checked for support.
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.
Verified 2026-11-20 · 1 reference not checked yet
Overview
CoChat Summary
TL;DR
This systematic review of 494 studies found that most artificial intelligence models for the intensive care unit remain in retrospective testing and prototyping, with few clinically evaluated and none evaluated after integration into routine clinical practice. The authors conclude that a uniform, structured approach is needed to move ICU-AI safely from development to bedside benefit.
Key findings
- Of 494 included studies, 476 (96.4%) were retrospective, 8 (1.6%) were prospective observational, and 10 (2%) were clinical studies; the clinical studies comprised 5 non-randomized trials and 5 randomized clinical trials.
- Risk of bias was high in 378 of 467 (80.9%) retrospective development studies assessed with PROBAST, most often in the “participants” and “analysis” domains.
- On the readiness scale, 441 studies (89.3%) scored level 4 or below, 35 (7.1%) reached external validation (level 5), 8 (1.6%) integrated an AI model clinically without exposing staff to results (level 6), and 10 (2%) clinically evaluated model performance (level 8); no studies reported outcome evaluation of an AI model integrated in routine clinical practice (level 9).
- Among 10 clinical studies, 8 provided complete information on study characteristics and patient outcomes, and 7 showed significant improvement in patient outcomes.
Methods
- Systematic review prepared according to PRISMA and registered in PROSPERO, with searches in Embase, MEDLINE ALL, Web of Science Core Collection, Cochrane Central Register of Controlled Trials, and Google Scholar from March to July 28, 2020.
- Eligible studies included adults (≥17 years), assessed AI or ML algorithms for clinical impact, used data gathered during ICU stay, were original research, and were available in English full text.
- Data extracted included study design, aim, dataset size, level of validation, AI readiness level adapted from NASA technology readiness levels, and clinical trial outcomes; PROBAST was used to assess risk of bias in retrospective development studies, and no quantitative synthesis was conducted.
Limitations
- The authors state that the review focused specifically on AI models developed in the ICU, so models translatable from other specialties may have been missed; PROBAST was designed for conventional prediction models rather than AI-based models; the literature search may have missed eligible studies; and PROBAST did not assess discrimination, calibration, algorithmic bias, or racial and minority bias.
- The text also makes evident an inconsistency in the reported number of studies identified through the electronic search: the abstract states 6455, while the Results section states 8645.
- The review did not assess applicability because no specific therapeutic question was defined, and it conducted no quantitative synthesis.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures
![Fig. 1 PRISMA 2009 flow diagram of the study review process and the exclusion of studies; from [19]](https://figures.cochat.ai/paper-figures/1e2aaf4a728b47b1b036f5890b8f3dec/moving-from-bytes-to-bedside-a-systematic-review-on-the-use-of-artificial-figure-1.jpg)


![Fig. 4 Percentage risk of bias according to the domain of assessment for all studies with a retrospective study design; assessed using PROBAST [23]](https://figures.cochat.ai/paper-figures/ae559657e7f648e0a8fbd2c14748f57d/moving-from-bytes-to-bedside-a-systematic-review-on-the-use-of-artificial-figure-4.jpg)
Verification
Claims the paper makes
3 Valid · 1 Not valid · 48 Not checked · 57 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Sepsis-related in hospital mortality rate decreased by 60.24% (p < 0.001)”
§ Moving from bytes to bedside: a systematic review on the use of artificial intelligence in the intensive care unit > Discussion
What the sources say
- Partly supportedcites [28] 27. McCoy A, Das R (2017) Reducing patient mortality, length of stay and readmissions through machine learning-based sepsis prediction in the emergency department, intensive care unit and hospital floor units. BMJ Open Qual 6:e000158 sourceExperimental — accuracy not yet measured
The Results section (Figure 1 passage) confirms the magnitude: 'Average mortality over the entire post-implementation period was 2.93%, for a 60.24% (p<0.01) average reduction,' echoed in the Abstract (Results). However, the source reports the significance as p<0.01, not p<0.001 as the citing sentence states, so the statistical claim overstates the source. Note also that the 60.24% figure is a relative pre- vs post-implementation reduction in a single-hospital SIRS-criteria population (n=1328, Cape Regional Medical Center), which the citing sentence does not carry. (LLM, conf=0.80)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Significantly reduced average LOS (2.7 days on average; p = 0.042)”
§ Moving from bytes to bedside: a systematic review on the use of artificial intelligence in the intensive care unit > Discussion
What the sources say
- Partly supportedcites [33] 32. Shimabukuro DW, Barton CW, Feldman MD, Mataraso SJ, Das R (2017) Effect of a machine learning-based severe sepsis prediction algorithm on patient survival and hospital length of stay: a randomised clinical trial. BMJ Open Respir Res 4:e000234 sourceExperimental — accuracy not yet measured
The source confirms the direction, significance and p-value: Table 2 (Results > Outcomes) reports hospital LOS of 13.0 (SE 1.23) days in controls vs 10.3 (SE 0.912) in the experimental arm with p=0.042, and the Discussion restates a 20.6% decrease (p=0.042). However, the magnitude the citing sentence attributes is 2.7 days, whereas the paper's own stated 'amount of reduction' is 2.30 days (Table 2); no passage in our copy reports a 2.7-day LOS reduction (the only 2.7-figure is 2.76 hours earlier antibiotics / 2.79 hours earlier blood cultures, Results > Outcomes). So the significance and p-value are supported but the quoted effect size is not the source's number. (LLM, conf=0.78)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Sepsis onset was predicted in advance in realtime”
§ Moving from bytes to bedside: a systematic review on the use of artificial intelligence in the intensive care unit > Discussion
What the sources say
- Supportedcites [33] 32. Shimabukuro DW, Barton CW, Feldman MD, Mataraso SJ, Das R (2017) Effect of a machine learning-based severe sepsis prediction algorithm on patient survival and hospital length of stay: a randomised clinical trial. BMJ Open Respir Res 4:e000234 source
The Results ('Patient inclusion and baseline characteristics') state that 142 patients were randomised (75 control, 67 experimental) in this trial of a machine learning-based severe sepsis prediction algorithm. The Introduction describes a prospective randomised study in which the algorithm was applied to EHR data and 'generated real-time telephonic notifications', and its 'ability to identify patients with severe sepsis before onset'; the Discussion adds that it was designed 'to predict severe sepsis up to 4 hours in advance' and contrasts it with systems that 'detect, not predict'. Together these support that sepsis onset was predicted in advance in real time in this n=142 RCT. (LLM, conf=0.90)
plainn = 142- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Of all studies which reported on external validation, most of them analyzed data on 1000-10,000 patients [13 of 35 studies (37.1%)] (Fig. 2).”
§ Moving from bytes to bedside: a systematic review on the use of artificial intelligence in the intensive care unit > Study design and purpose of AI
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“441 studies (89.3%) scored level 4 or below on the 'level of readiness' scale, 35 (7.1%) studies performed external validation (level 5), 8 studies (1.6%) integrated an AI model in the clinical setting without exposing the clinical staff to the results (level 6) and ten studies (2%) clinically evaluated model performance (level 8).”
§ Moving from bytes to bedside: a systematic review on the use of artificial intelligence in the intensive care unit > Level of readiness
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
61 more claims
Create a free account to see all 109 claims and to verify the 63 references still open.
- It may state two separate claims as one. 18
- The quote only partly states this claim. 1
- Probably not a substantial claim. 31
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“A recent meta-analysis analyzed publications concerning the use of AI in the ICU: out of the 494 articles studied, the majority were retrospective studies 476 articles (96.4%). In total, 10 articles (10/494, 2%) were clinical studies, of which only 5 (5/494, 1%) were randomized trials with a control arm.”
From Expectations of Intensive Care Physicians Regarding an AI-Based Decision Support System for Weaning From Continuous Renal Replacement Therapy: Predevelopment Survey Study (2025) · cites this paper as [3]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Systematic reviews show that most ICU AI studies remain retrospective, with limited external validation and scarce evidence on patient-centered outcomes after real-world deployment [35].”
From Artificial Intelligence to Facilitate SEP-1 Measure Compliance and Fluid Management in Sepsis (2026) · cites this paper as [35]
The cited source says what the claim attributes to it.
In the citing paper
“These AI-based CDSS have demonstrated potential across several domains in ICU, including sepsis prediction, early detection of patient deterioration, and management of mechanical ventilation [2-4].”
The cited source says what the claim attributes to it.
In the citing paper
“In addition, the majority of retrospective studies presented a high risk of bias [3].”
In the citing paper
“This manuscript has been prepared according to the Preferred Reporting Items for Systematic reviews and Metaanalysis (PRISMA) guideline and was registered in the online PROSPERO database (Record ID: 199,683; reference number: CRD42020199863) before initiation of the literature search [19,20].”
From Moving from bytes to bedside: a systematic review on the use of artificial intelligence in the intensive care unit (2021) · cites this paper as [20]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Moving from bytes to bedside: a systematic review on the use of artificial intelligence in the intensive care unit > Abstract
“Out of 6455 studies identified through literature search, 494 were included.”
§ Moving from bytes to bedside: a systematic review on the use of artificial intelligence in the intensive care unit > Identification of studies
“A total of 8645 studies were identified through our electronic search”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
“intervention group 38.41 days ± 3.35 vs. control group 43.69 days ± 14.89, with a difference on average of 5.2 days [p < 0.01]”
§ Moving from bytes to bedside: a systematic review on the use of artificial intelligence in the intensive care unit > Discussion
Reported 5.2 · recomputed 5.28
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Moving from bytes to bedside: a systematic review on the use of artificial intelligence in the intensive care unit > Study design and purpose of AI
“classifying sub-populations [57 studies (11.7%)]”
§ Moving from bytes to bedside: a systematic review on the use of artificial intelligence in the intensive care unit > Conclusion
“Classifying sub-populations | 58 (11.7%)”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Moving from bytes to bedside: a systematic review on the use of artificial intelligence in the intensive care unit > Study design and purpose of AI
“improving prognostic models/risk scoring systems [86 studies (17.4%)]”
§ Moving from bytes to bedside: a systematic review on the use of artificial intelligence in the intensive care unit > Conclusion
“Improving prognostic models/risk scoring | 91 (18.4%)”
Citations
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
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
Preferred reporting items for systematic reviews and meta-analyses: the PRISMA Statement.
(2009) · PubMed Central · Cited by 44,859
The Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970
Dermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362
CONSORT 2010 Statement: updated guidelines for reporting parallel group randomised trials
the CONSORT Group, Schulz, K. F., Altman, D. G., & Moher, D. (2010) · BMC Medicine · doi:10.1186/1741-7015-8-18 · Cited by 13,371
The Elements of Statistical Learning: Data Mining, Inference, and Prediction
John Lu, Z. Q. (2010) · Journal of the Royal Statistical Society Series A: Statistics in Society · doi:10.1111/j.1467-985x.2010.00646_6.x · Cited by 12,390
CONSORT 2010 Statement: updated guidelines for reporting parallel group randomised trials
Schulz, K. F., Altman, D. G., Moher, D., & for the CONSORT Group (2010) · BMJ · doi:10.1136/bmj.c332 · Cited by 9,329
Gulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., Venugopalan, S., Widner, K., Madams, T., Cuadros, J., et al. (2016) · JAMA · doi:10.1001/jama.2016.17216 · Cited by 7,697
SPIRIT 2013 Statement: Defining Standard Protocol Items for Clinical Trials
Chan, A.-W., Tetzlaff, J. M., Altman, D. G., Laupacis, A., Gøtzsche, P. C., Krleža-Jerić, K., Hróbjartsson, A., Mann, H., Dickersin, K., Berlin, J. A., et al. (2013) · Annals of Internal Medicine · doi:10.7326/0003-4819-158-3-201302050-00583 · Cited by 7,363
Cited by
Items 101–200 of 278
McNamara, R., Meka, S. A., Anstey, J. R., Fatovich, D. M., Haseler, L. J., Fitzgerald, M., & Udy, A. A. (2022) · Critical Care and Resuscitation · doi:10.51893/2022.1.oa5 · Cited by 9
“14 To apply data science for the benefit of m-sTBI patients, several points need to be understood.”
MethodNonlinear Machine Learning in Warfarin Dose Prediction: Insights from Contemporary Modelling Studies
Zhang, F., Liu, Y., Ma, W., Zhao, S., Chen, J., & Gu, Z. (2022) · Journal of Personalized Medicine · doi:10.3390/jpm12050717 · Cited by 12
Artificial intelligence for the prediction of postoperative complications in the critically ill
Moll, V., Khanna, A. K., & Mathur, P. (2025) · Critical Care Science · doi:10.62675/2965-2774.20250025 · Cited by 11
From promise to practice: A roadmap for artificial intelligence in critical care
Agard, G., Hraiech, S., & Gauss, T. (2025) · Journal of Critical Care · doi:10.1016/j.jcrc.2025.155263 · Cited by 9
Diversity and inclusion: A hidden additional benefit of Open Data
Charpignon, M., Celi, L. A., Cobanaj, M., Eber, R., Fiske, A., Gallifant, J., Li, C., Lingamallu, G., Petushkov, A., & Pierce, R. L. (2024) · PLOS Digital Health · doi:10.1371/journal.pdig.0000486 · Cited by 13
The value of machine and deep learning in management of critically ill patients: An umbrella review
Tungushpayev, M., Suleimenova, D., Sarria-Santamerra, A., Aimyshev, T., Gaipov, A., & Viderman, D. (2025) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2025.106081 · Cited by 11
Wesdorp, N. J., Zeeuw, M. J., van der Meulen, D., Erve, I. V. ’., Bodalal, Z., Roor, J., van Waesberghe, J. H., Moos, S. I., van den Bergh, J., Nota, I., et al. (2023) · Cancers · doi:10.3390/cancers15235648 · Cited by 11
Self-citationCurrent perspectives on the use of artificial intelligence in critical patient safety
Barea‐Mendoza, J. A., Fernández, M. V., Pardo, À., & Álvarez, J. G. (2024) · Medicina Intensiva (English Edition) · doi:10.1016/j.medine.2024.04.002 · Cited by 10
Artificial Intelligence Is the Future of Surgical Departments … Are We Ready?
Valente, M., Bellini, V., RIO, P. D., Freyrie, A., & Bignami, E. G. (2022) · Angiology · doi:10.1177/00033197221121192 · Cited by 8
Kloka, J., Holtmann, S. C., Nürenberg-Goloub, E., Piekarski, F., Zacharowski, K., & Friedrichson, B. (2022) · JMIR Formative Research · doi:10.2196/43896 · Cited by 6
“In line with challenges highlighted in previous research [4,5,14,15,26,27], our survey shows that intensivists and anesthesiologists anticipate a high potential for technical problems and legal issues related to defining liability and ensuring data protection.”
ResultPorter, L. L., Hazeleger, L., Bos, K., Simons, K. S., van der Hoeven, J. G., Yeghaian, M., van der Woude, M. C. E., van Santen, S., Rettig, T. C. D., de Vries, M., et al. (2025) · Intensive Care Medicine · doi:10.1007/s00134-025-08052-3 · Cited by 10
“This supports the use of a multidimensional approach to define subgroups of ICU patients.”
Zhang, Z., & Ye, J. (2025) · Frontiers in Cardiovascular Medicine · doi:10.3389/fcvm.2025.1568907 · Cited by 9
On relevant features for the recurrence prediction of urothelial carcinoma of the bladder
Schwarz, L., Sobania, D., & Rothlauf, F. (2024) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2024.105414 · Cited by 12
Glucocorticoid therapy for sepsis in the AI era: a survey on current and future approaches
Liang, C., Pan, S., Wu, W., Chen, F., Zhang, C., Zhou, C., Gao, Y., Ruan, X., Quan, S., Zhao, Q., et al. (2024) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2024.04.020 · Cited by 7
Federated learning: a step in the right direction to improve data equity
van Genderen, M. E., van de Sande, D., Cecconi, M., & Jung, C. (2024) · Intensive Care Medicine · doi:10.1007/s00134-024-07525-1 · Cited by 7
Natural language processing in the intensive care unit: A scoping review
Pilowsky, J. K., Choi, J.-W., Saavedra, A. F., Daher, M., Nguyen, N., Williams, L., & Jones, S. L. (2024) · Critical Care and Resuscitation · doi:10.1016/j.ccrj.2024.06.008 · Cited by 8
“2,27 While a variety of studies in this review have demonstrated that it is feasible to use NLP on clinical data, there is a clear need for more studies that are able to demonstrate both the safety and ef fi cacy of NLP, and other AI-based algorithms, when implemented in clinical settings.”
BackgroundAugmented intelligence facilitates concept mapping across different electronic health records
Dam, T. A., Fleuren, L. M., Roggeveen, L. F., Otten, M., Biesheuvel, L. A., Jagesar, A. R., Lalisang, R. C. A., Kullberg, R. F. J., Hendriks, T., Girbes, A. R. J., et al. (2023) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2023.105233 · Cited by 7
Spencer, E.-J., Economou-Zavlanos, N., & van Genderen, M. E. (2024) · Intensive Care Medicine · doi:10.1007/s00134-024-07747-3 · Cited by 7
“Still, the majority of AI models do not reach beyond the prototyping phase, particularly in the ICU [4, 7].”
AI in neurocritical care: what to expect
Hemphill, J. C., & Meyfroidt, G. (2025) · Intensive Care Medicine · doi:10.1007/s00134-025-07803-6 · Cited by 7
“Specific AI models for the neurointensive care unit setting are being increasingly developed, but their exter-nal validity is often questionable, and implementation research is lagging [14].”
Popoff, B., Cabon, S., Cuggia, M., Bouzillé, G., & Clavier, T. (2025) · JMIR Medical Informatics · doi:10.2196/63709 · Cited by 6
Patient safety in the Intensive Care Department
Delgado, M. C. M., & Bodí, M. A. (2024) · Medicina Intensiva · doi:10.1016/j.medin.2024.07.010 · Cited by 8
Barea‐Mendoza, J. A., Fernández, M. V., Pardo, À., & Álvarez, J. G. (2024) · Medicina Intensiva · doi:10.1016/j.medin.2024.03.007 · Cited by 8
The Role of Artificial Intelligence in Pediatric Intensive Care: A Systematic Review
Abdallah, A. B. A. A., Sadaka, S. I. H., Ali, E. I., Bilal, S. A. M., Abdelrahman, M. O., Mohammed, F. B. F., Ahmed, S. D. N., & Saeed, N. E. A. (2025) · Cureus · doi:10.7759/cureus.80142 · Cited by 8
“While AI has made significant strides in adult medicine, particularly in intensive care and inpatient settings, its integration into pediatric care remains in its early stages [43].”
Mapping Artificial Intelligence Research Trends in Critical Care Nursing: A Bibliometric Analysis
Zhou, L., Geng, K., & Yu, C. (2025) · Journal of Multidisciplinary Healthcare · doi:10.2147/jmdh.s522731 · Cited by 10
Old, O., Friedrichson, B., Zacharowski, K. D., & Kloka, J. A. (2022) · European Journal of Anaesthesiology Intensive Care · doi:10.1097/ea9.0000000000000014 · Cited by 6
González‐Nóvoa, J. A., Busto, L., Campanioni, S., Fariña, J., Rodriguez-Andina, J. J., Vila, D., & Veiga, C. (2023) · Sensors · doi:10.3390/s23031162 · Cited by 9
“It is very difficult to analyze all of this volume of information manually, so it is of great interest to use artificial intelligence (AI) tools that automate and help in these tasks [2], especially in extraordinary situations such as the one experienced due to the COVID-19 pandemic, where ICUs were overwhelmed.”
Trash in/trash out? Using routinely collected clinical data for data science in the ICU: Con
Pörteners, B., Jung, C., & Meyfroidt, G. (2024) · Intensive Care Medicine · doi:10.1007/s00134-024-07739-3 · Cited by 6
Zeeuw, M. J., Bereska, J. I., Strampel, M., Wagenaar, L., Janssen, B. V., Marquering, H. A., Kemna, R., van Waesberghe, J. H., van den Bergh, J., Nota, I., et al. (2025) · Insights into Imaging · doi:10.1186/s13244-025-01984-w · Cited by 6
“This emphasizes the critical need for external validation and clinical evaluation to ultimately facilitate clinical implementation [20, 21].”
Self-citationKhodaveisi, T., Aslani, N., Amiri, P., Kamrani, F., & Saeedi, S. (2025) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-025-03243-w · Cited by 6
“Our review revealed that 89.06% of studies employed a retrospective design, consistent with the 96.4% reported in intensive care unit studies [97].”
InfluentialNabi, J., Staynings, R., Sofi, J. I., & Willis, H. H. (2025) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph22111734 · Cited by 6
Atkova, I., Jansson, M., Ahokangas, P., Härkönen, H., Rana, T., & Vesty, G. M. (2026) · Technological Forecasting and Social Change · doi:10.1016/j.techfore.2026.124711 · Cited by 7
Machine Learning: A Potential Therapeutic Tool to Facilitate Neonatal Therapeutic Decision Making
Tang, B., Li, Q., Liu, H., Zheng, Y., Wu, Y., van den Anker, J. N., Hao, G., & Zhao, W. (2024) · Pediatric Drugs · doi:10.1007/s40272-024-00638-6 · Cited by 7
Subphenotypes in Acute Respiratory Distress Syndrome: Universal Steps Toward Treatable Traits
Filippini, D. F. L., Smit, M. R., & Bos, L. D. J. (2024) · Anesthesia & Analgesia · doi:10.1213/ane.0000000000006727 · Cited by 5
Bai, Y., Huang, X., Xia, J., & Zhan, Q. (2022) · Annals of Translational Medicine · doi:10.21037/atm-22-3153 · Cited by 5
Gastrointestinal failure, big data and intensive care
Singer, P., Robinson, E., & Raphaeli, O. (2023) · Current Opinion in Clinical Nutrition & Metabolic Care · doi:10.1097/mco.0000000000000961 · Cited by 9
Zhang, J., Whebell, S. F., Gallifant, J., Budhdeo, S., Mattie, H., Lertvittayakumjorn, P., Lopez, M. P. A., Tiangco, B., Gichoya, J. W., Ashrafian, H., et al. (2021) · medRxiv · doi:10.1101/2021.11.23.21266758 · Cited by 5
Hinrichs, N., Roeschl, T., Lanmüeller, P., Balzer, F., Eickhoff, C., O’Brien, B., Falk, V., & Meyer, A. (2024) · PLOS Digital Health · doi:10.1371/journal.pdig.0000598 · Cited by 7
Jiang, J., Jiang, Y., Xu, Y. X., & Zhang, S. (2026) · Frontiers in Medicine · doi:10.3389/fmed.2025.1748154 · Cited by 5
Muñoz, J., Fernández-Araujo, N. J., Ruíz-Cacho, R., & Muñoz-Visedo, J. (2026) · Journal of Critical Care · doi:10.1016/j.jcrc.2026.155600 · Cited by 5
Abdullah, H. R., Brenda, T. P. Y., Loh, C. J. L., Ong, M. E. H., Lamoureux, E. L., Lim, G. H., & Lum, E. (2024) · BMJ Open · doi:10.1136/bmjopen-2024-086769 · Cited by 8
de Hond, A., Vosslamber, S. M., Lange, S., Engel, F., Lindhout, M., Noorlag, P., Steyerberg, E. W., Cinà, G., & Arbous, M. S. (2025) · Human Factors in Healthcare · doi:10.1016/j.hfh.2025.100095 · Cited by 5
Kramer, A. A., LaFonte, M., Husseini, I. E., Cary, R., DIDCOTE, S., Maurer, G., HASTRUP, F. C., & Krinsley, J. S. (2023) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2023.101433 · Cited by 6
van de Sande, D., van Genderen, M. E., Huiskens, J., Veen, R. E. R., Meijerink, Y., Gommers, D. A. M. P. J., & van Bommel, J. (2021) · BMJ Health & Care Informatics · doi:10.1136/bmjhci-2021-100447 · Cited by 4
Self-citationBaidillah, M. R., Busono, P., & Riyanto, R. (2023) · Measurement Science and Technology · doi:10.1088/1361-6501/acc11e · Cited by 6
Experimental asynchrony to study self-inflicted lung injury
Cronin, J. N., & Formenti, F. (2021) · British Journal of Anaesthesia · doi:10.1016/j.bja.2021.11.020 · Cited by 5
Navigating the Ocean of Big Data in Neurocritical Care
Dhar, R., & Meyfroidt, G. (2022) · Neurocritical Care · doi:10.1007/s12028-022-01558-4 · Cited by 4
“There are a growing number of publications expounding the predictive value of machine learning models, but there are only a precious few demonstrating that the implementation of such algorithms actually improves anything; few are even validated beyond a single population, ignoring diversity and potential biases [19].”
BackgroundMarshall, C. E., Narendrula, S., Wang, J., Vale, J. G. D. S., Jeong, H., Krishnan, P., Yang, P., Esper, A. M., & Kamaleswaran, R. (2022) · medRxiv · doi:10.1101/2022.11.14.22282274 · Cited by 4
“However, the EMR does have limitations due to its’ sparse nature as well as its’ indicator and behavioral biases that are involved in the ordering of labs and other clinical measures [8].”
BackgroundFestor, P., Nagendran, M., Gordon, A. C., Faisal, A. A., & Komorowski, M. (2023) · medRxiv · doi:10.1101/2023.10.03.23296437 · Cited by 6
Goulenok, C., Kentish‐Barnes, N., & Bougouin, W. (2025) · Intensive Care Medicine · doi:10.1007/s00134-025-07923-z · Cited by 4
Catling, F. J., Nagendran, M., Festor, P., Bien, Z., Harris, S., Faisal, A. A., Gordon, A. C., & Komorowski, M. (2023) · doi:10.1101/2023.08.26.23294666 · Cited by 3
de Carvalho, D., Hoffmann, K., Filho, J. R. N., & Baptistella, A. R. (2025) · Journal of Critical Care · doi:10.1016/j.jcrc.2025.155238 · Cited by 3
Pereira, R. M., Luís, F., Abecasis, M., Nobre, Â. L., Moita, L. F., & Velho, T. R. (2025) · Journal of Thoracic and Cardiovascular Surgery · doi:10.1016/j.jtcvs.2025.11.020 · Cited by 5
Spoon, D., de Vroed, A., Greup, S., van Dijk, M., & Ista, E. (2026) · Journal of Clinical Nursing · doi:10.1111/jocn.70212 · Cited by 7
Mechanical ventilation in ARDS: navigating the fine line with real-time monitoring
Ball, L., Benzi, G., Battaglini, D., Robba, C., Patroniti, N. A., Silva, P. L., Marini, J. J., & Rocco, P. R. M. (2026) · Critical Care · doi:10.1186/s13054-026-05895-0 · Cited by 4
Data science in the intensive care unit
Luo, M.-H., Huang, D.-L., Luo, J., Su, Y., Li, J.-K., Tu, G.-W., & Luo, Z. (2022) · World Journal of Critical Care Medicine · doi:10.5492/wjccm.v11.i5.311 · Cited by 6
Artificial intelligence in pediatric medicine: a call for rigorous reporting standards
Barry, J. S., Beam, K., & McAdams, R. M. (2025) · Journal of Perinatology · doi:10.1038/s41372-025-02284-3 · Cited by 4
Tack, J., Bruyneel, A., Maes, J., Mercier, G., Taccone, F. S., & Pirson, M. (2025) · Journal of Advanced Nursing · doi:10.1111/jan.16984 · Cited by 4
Transforming AI Solutions in Healthcare—The Medical Information Tokens
Hafez, W., Elshamy, S., Farid, A., & Camara, R. (2023) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai54212.2023.00134 · Cited by 4
Early prediction of sepsis using a high-order Markov dynamic Bayesian network (HMDBN) classifier
Zhang, S., Duan, Y., Hou, F., Yan, G., Li, S., Wang, H., & Zhou, L. (2023) · Applied Intelligence · doi:10.1007/s10489-023-04920-x · Cited by 3
Quality, safety and artificial intelligence
Soukup, T., & Franklin, B. D. (2024) · BMJ Quality & Safety · doi:10.1136/bmjqs-2024-017382 · Cited by 5
“Furthermore, such efforts must prioritise the development of AI applications that enhance diagnostic accuracy and treatment efficacy and actively contribute to advancing the overall quality and safety of healthcare, ensuring that every technological advancement directly benefits patients.”
Doctors as Device Manufacturers? Regulation of Clinician-Generated Innovation in the ICU
Simon, D. A., & Young, M. J. (2024) · Critical Care Medicine · doi:10.1097/ccm.0000000000006296 · Cited by 3
“Clinician innovations like those in Box 1 may be developed but not disseminated even when there is evidence for doing so, restricting their potential use and benefit to patients (6–8).”
Beyond perfection: why imperfect routinely collected intensive care data still hold value
Rodemund, N., Wernly, B., Stundner, O., Rockenschaub, P., & Koköfer, A. (2025) · Intensive Care Medicine · doi:10.1007/s00134-025-07844-x · Cited by 2
Gao, J., Yao, Y., Xue, J., Chen, R., Yang, X., Xu, J., & Cheng, W. (2025) · BMC Pregnancy and Childbirth · doi:10.1186/s12884-025-07727-5 · Cited by 5
“Van De Sande et al. [10] reviewed 494 studies referring to ML models in the intensive care unit, and 80.9% of the retrospective studies were classified as having a high risk of bias.”
InfluentialMatheny, M. E., Ohno-Machado, L., Davis, S. E., & Nemati, S. (2023) · Elsevier eBooks · doi:10.1016/b978-0-323-91200-6.00031-0 · Cited by 3
Artificial Intelligence in medicine: Potential applications and barriers to deployment
Sonawane, U., & Komorowski, M. (2023) · AI critique · doi:10.1515/9783839467664-009 · Cited by 5
Machine-assisted nutritional and metabolic support
Reignier, J., Arabi, Y. M., & Preiser, J. (2022) · Intensive Care Medicine · doi:10.1007/s00134-022-06753-7 · Cited by 4
The future of AI in health-care quality: defining the challenges and opportunities moving forward
Phan, P., & Abad, C. L. R. (2022) · International Journal for Quality in Health Care · doi:10.1093/intqhc/mzac080 · Cited by 3
Smit, J. M., Krijthe, J. H., van Bommel, J., Labrecque, J. A., Komorowski, M., Gommers, D. A. M. P. J., Reinders, M. J. T., & van Genderen, M. E. (2022) · medRxiv · doi:10.1101/2022.10.29.22281684 · Cited by 3
Self-citationKeats, K. R., Deng, S., Chen, X., Zhang, T., Devlin, J. W., Murphy, D. J., Smith, S. E., Murray, B., Kamaleswaran, R., & Sikora, A. N. (2024) · medRxiv · doi:10.1101/2024.03.21.24304663 · Cited by 3
Popoff, B., Delange, B., Nicolas, J., Le Gall, A., Dahamna, B., Cuggia, M., Clavier, T., & Bouzillé, G. (2025) · Scientific Reports · doi:10.1038/s41598-025-26774-8 · Cited by 2
Emotional Intelligence: A Human-Centred AI Perspective
Gámez, M. E. (2026) · Springer eBooks · doi:10.1007/978-981-97-8440-0_109-1 · Cited by 5
Nkhono, W., van Lieshout, E., Calis, J. C. J., Yebei, V. N., Hoogendoorn, M., Phiri, K. S., & Villalobos-Quesada, M. J. (2026) · EClinicalMedicine · doi:10.1016/j.eclinm.2025.103743 · Cited by 3
“12 Potential challenges observed in HICs, such as data scarcity, data quality, and concerns about transparency, explainability, bias, and negative effects on the work floor, 5 may overlap with those in LMICs.”
Influentialvan Twist, E., van Winden, B., de Jonge, R., Taal, H. R., de Hoog, M., Schouten, A. C., Tax, D. M. J., & Kuiper, J. W. (2026) · BMJ Health & Care Informatics · doi:10.1136/bmjhci-2025-101608 · Cited by 3
Allyn, J., Oliver, M., Cerveau, R., Allou, N., Barennes, T., & Ferdynus, C. (2026) · Critical Care · doi:10.1186/s13054-026-06034-5 · Cited by 4
“Despite these resources, external validation has historically been scarce:, estimated at only 9% for mortality models as of 2021, and virtually non-existent for Remaining Length of Stay (RLoS) [14].”
Sarı, F., & Aliyeva, A. (2026) · Children · doi:10.3390/children13091166 · Cited by 2
Pucher, G., Rostalski, T., Nensa, F., Kleesiek, J., Reinhardt, H. C., & Sauer, C. M. (2024) · EBioMedicine · doi:10.1016/j.ebiom.2024.105526 · Cited by 6
AI ethics for the everyday intensivist
Tan, S. C., Modra, L. J., & Hensman, T. (2025) · Critical Care and Resuscitation · doi:10.1016/j.ccrj.2025.100115 · Cited by 5
ERS International Congress 2021: highlights from the Respiratory Intensive Care Assembly
Kharat, A., Ribeiro, C. S. M. F., Er, B., Fisser, C., Padilla, D. E. L., Chatzivasiloglou, F., Heunks, L. M. A., Patout, M., & D'Cruz, R. F. (2022) · ERJ Open Research · doi:10.1183/23120541.00016-2022 · Cited by 2
Artificial Intelligence in Infection Management in the ICU
Corte, T. D., Hoecke, S. V., & Waele, J. J. D. (2022) · Annual update in intensive care and emergency medicine · doi:10.1007/978-3-030-93433-0_28 · Cited by 4
Holder, A. L., Khanna, A. K., Scott, M. J., Rossetti, S. C., Rinehart, J. B., Linn, D. D., Weichert, J., & Dellinger, R. P. (2023) · Cureus · doi:10.7759/cureus.50169 · Cited by 1
“However, a recent systematic review of 494 AI studies using data obtained during an ICU stay found none that reported on patient outcomes following AI model integration [14].”
BackgroundResultShort-course antibiotic strategies for ventilator-associated pneumonia
Tan, W. C., Quah, J., & Li, A. (2025) · Current Opinion in Infectious Diseases · doi:10.1097/qco.0000000000001094 · Cited by 2
Bakkes, T. H. G. F., Dekker, A. J. R. D. B., van der Stam, J. A., Kaymak, U., Mischi, M., Bouwman, R. A., & Turco, S. (2025) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2025.105930 · Cited by 2
Guamán, J. A. C., Sudiaga, N. E. C., Burnhan, V. A. G., Flores, J. V. T., & Ruiz, R. A. B. (2025) · Más Vita · doi:10.47606/acven/mv0270 · Cited by 3
Advanced Hemodynamic Monitoring: Pros, Cons, and the Future
Abusannuga, M. M., Attique, Z., Abdulla, S., Zulfiqar, H., Almohannadi, M., & Shajahan, F. (2025) · IntechOpen eBooks · doi:10.5772/intechopen.1011933 · Cited by 2
CXR-TFT: Multi-modal Temporal Fusion Transformer for Predicting Chest X-Ray Trajectories
Arora, M., Ali, A., Wu, K., Davis, C., Shimazui, T., Alwakeel, M., Moas, V. M., Yang, P., Esper, A. M., & Kamaleswaran, R. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05182-0_16 · Cited by 1
Supervised Machine Learning Models Predicting Postoperative Low Cardiac Output Syndrome In Neonates
Baloğlu, O., Wang, X. F., Marino, B. S., Morca, A., Akbasli, I. T., Latifi, S. Q., Klaben, A., & Tandon, A. A. (2025) · Critical Care Explorations · doi:10.1097/cce.0000000000001327 · Cited by 6
“Accordingly, the work should be regarded as a technology readiness level 3–4 proof-of-concept that demonstrates algorithmic feasibility on retrospective data, rather than a deployment-ready solution (14).”
Artificial Intelligence in UK Hospital Medicine: From Innovation to Implementation
Carroll, D., Boodhoo, V., Lowe, D. J., & Carlin, C. M. (2025) · British Journal of Hospital Medicine · doi:10.12968/hmed.2025.0468 · Cited by 1
Intérêt de l’intelligence artificielle en anesthésie-réanimation
Ariès, P., Belot, F., Py, N., Humbert, P., & Dubost, C. (2025) · EMC-Anesthésie réanimation/Encyclopédie médico-chirurgicale. Anesthésie, réanimation · doi:10.1016/s0246-0289(25)48411-4 · Cited by 1
Moffett, A. T., & Weissman, G. E. (2026) · Critical Care Medicine · doi:10.1097/ccm.0000000000007024 · Cited by 3
Chen, Z., Li, W., & Lin, Z. (2026) · PLOS Digital Health · doi:10.1371/journal.pdig.0001283 · Cited by 7
“Subsequent evaluation using community-based benchmarks and the BERT maturity classifier identified 510 studies that met “device-into-practice” criteria, all of which featured validation in real-world clinical settings [21–23].”
KI-Algorithmen – intraoperatives hämodynamisches Monitoring von morgen?
Dehbozorgi, M., Zental, N., Larmann, J., & Grüßer, L. (2026) · AINS - Anästhesiologie · Intensivmedizin · Notfallmedizin · Schmerztherapie · doi:10.1055/a-2617-6321 · Cited by 2
Healthcare professionals show high AI enthusiasm but limited knowledge: A cross-sectional study
Abedin, N., Hahn, P., Zeuzem, S., & Dultz, G. (2026) · PLOS Digital Health · doi:10.1371/journal.pdig.0001433 · Cited by 4
“Earlier studies have shown similar results emphasizing that even when clinicians are eager to explore AI, uptake is often limited by data governance and integration pathways [23].”
Vetrugno, L., & Vetrugno, V. (2026) · Journal of Clinical Anesthesia · doi:10.1016/j.jclinane.2026.112279 · Cited by 1
Taccone, F. S., Arabi, Y., Baggiani, M., Brasil, S., Figaji, A., Bogossian, E. G., Hawryluk, G. W. J., McCREDIE, V. A., Møller, K., Puppo, C., et al. (2026) · Intensive Care Medicine · doi:10.1007/s00134-026-08558-4 · Cited by 1
“Despite these encouraging results, translating AI-based models into routine clinical practice requires progression to higher levels of technological readiness through rigorous prospective validation [101].”
Greup, S., Spoon, D., de Vroed, A., van Werkhoven, B., Timmerman, E., Ista, E., & van Dijk, M. (2026) · Journal of Clinical Nursing · doi:10.1111/jocn.70574 · Cited by 3
Mariani, S., Piero, M. E. D., & Haverich, A. (2023) · Elsevier eBooks · doi:10.1016/b978-0-443-18918-0.00005-x · Cited by 1
Beyond Quantity: Research with Subsymbolic AI
Sudmann, A., Echterhölter, A., Ramsauer, M., Retkowski, F., Schröter, J., & Waibel, A. (2023) · AI critique · doi:10.1515/9783839467664 · Cited by 14
Bennis, F. C., Aussems, C., Korevaar, J. C., & Hoogendoorn, M. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108097 · Cited by 1
Design Research on Information System of Intelligent Escort Based on Deep Learning
Ji, Z. (2023) · International Conference on Computer Simulation and Modeling, Information Security (CSMIS) · doi:10.1109/csmis60634.2023.00109 · Cited by 1
“…control commands can be remotely sent through the mobile client; After receiving instructions, the robot will parse them and send them to the underlying control platform, so that they can move according to the user's wishes, allowing infants and young children to return to the robot's view [5].”
BackgroundMoss, L., Shaw, M., Piper, I., & Hawthorne, C. (2024) · Brain and Spine · doi:10.1016/j.bas.2024.102858 · Cited by 1
Metadata
- Authors
- van de Sande, D., van Genderen, M. E., Huiskens, J., Gommers, D., & van Bommel, J.
- Affiliations
- Erasmus MC (NL)
- Corresponding author
- van Genderen, Michel E.
- Venue
- Intensive Care Medicine
- Published
- 2021-06-05
- Volume
- 47
- Issue
- 7
- Pages
- 750-760
- ISSN
- 0342-4642 (ISSN-L)
- 1432-1238
- PMC
- PMC8178026
- OpenAlex
- W3164057767
- Semantic Scholar
- e7ea75d3a5ce6931a02ccc916b79234fa90168c1
- Cited by
- 279
- References
- 59
- Citations by year
- 2026: 54 · 2025: 68 · 2024: 62 · 2023: 47 · 2022: 38 · 2021: 9
- FWCI
- 3.25
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by-nc
- creativecommons.org/licenses/by-nc/4.0 (tdm)
- creativecommons.org/licenses/by-nc/4.0 (vor)
- Locations
- Intensive Care Medicine (publishedVersion, cc-by-nc)
- PubMed Central (publishedVersion, cc-by-nc)
- PubMed (publishedVersion)
- EUR Research Repository (Erasmus University Rotterdam) (publishedVersion, other-oa)
- RePub (Erasmus University Rotterdam) (submittedVersion, other-oa)
- EUR Research Repository (Erasmus University Rotterdam) (submittedVersion, other-oa)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- artificial intelligence, intensive care unit, clinical decision support, prediction model, risk of bias, PROBAST, retrospective analysis, clinical implementation of AI, AI model validation
- MeSH terms
- Artificial Intelligence, Humans, Intensive Care Units, Retrospective Studies, Observational Studies as Topic
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-11-17, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-11-17 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash).
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.