CoChat
Sign Up
Cited by 97Machine Learning in HealthcareArtificial Intelligence in Healthcare and EducationArtificial Intelligence in Healthcare

Artificial intelligence for clinical decision support for monitoring patients in cardiovascular ICUs: A systematic review

Open access
Moazemi, Sobhan, Vahdati, Sahar, Li, Jason, Kalkhoff, Sebastian, Castano, Luis J. V., Dewitz, Bastian, Bibo, Roman, Sabouniaghdam, Parisa +5 more·2023·Frontiers in Medicine
DOI 10.3389/fmed.2023.1109411PMC PMC10102653
Open this paper in CoChat — free accountOpen PDF

Abstract

Background: Artificial intelligence (AI) and machine learning (ML) models continue to evolve the clinical decision support systems (CDSS). However, challenges arise when it comes to the integration of AI/ML into clinical scenarios. In this systematic review, we followed the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA), the population, intervention, comparator, outcome, and study design (PICOS), and the medical AI life cycle guidelines to investigate studies and tools which address AI/ML-based approaches towards clinical decision support (CDS) for monitoring cardiovascular patients in intensive care units (ICUs). We further discuss recent advances, pitfalls, and future perspectives towards effective integration of AI into routine practices as were identified and elaborated over an extensive selection process for state-of-the-art manuscripts. Methods: Studies with available English full text from PubMed and Google Scholar in the period from January 2018 to August 2022 were considered. The manuscripts were fetched through a combination of the search keywords including AI, ML, reinforcement learning (RL), deep learning, clinical decision support, and cardiovascular critical care and patients monitoring. The manuscripts were analyzed and filtered based on qualitative and quantitative criteria such as target population, proper study design, cross-validation, and risk of bias. Results: More than 100 queries over two medical search engines and subjective literature research were developed which identified 89 studies. After extensive assessments of the studies both technically and medically, 21 studies were selected for the final qualitative assessment. Discussion: Clinical time series and electronic health records (EHR) data were the most common input modalities, while methods such as gradient boosting, recurrent neural networks (RNNs) and RL were mostly used for the analysis. Seventy-five percent of the selected papers lacked validation against external datasets highlighting the generalizability issue. Also, interpretability of the AI decisions was identified as a central issue towards effective integration of AI in healthcare.

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 · 10.3389/fmed.2023.1109411

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.

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?

  • Most reviewed studies relied on retrospective datasets, including MIMIC-III, MIMIC-IV, and other ICU databases, with cohort sizes ranging from 4,500 to 14,500 patients.

    “Most studies relied on retrospective datasets, including MIMIC-III, MIMIC-IV, and other ICU databases, with cohort sizes ranging from 4,500 to 14,500 patients ([12, 13, 18, 19, 22, 23]).”

    From Explainable AI for critical care: a systematic review of interpretable models for sepsis and ICU mortality prediction (2026) · cites this paper as [23]

    Section 4.5 reports that 13 of 21 selected studies used open-access datasets and 10 used a version of MIMIC. Table 2 in Section 4.2 lists many retrospective analyses, including MIMIC-III, MIMIC-IV, and other ICU data, but it does not support the stated cohort-size range: listed cohorts include 75 and 162 patients, as well as 16,189 patients and 61,532 ICU stays. Page numbers are not available in our copy. (LLM, conf=0.90)

    Experimental — accuracy not yet measured

  • Models developed for sepsis onset, in-hospital mortality, and cardiovascular ICU monitoring exhibited high predictive accuracy, highlighting the robustness and reliability of XAI approaches in critical care settings.

    “Similarly, models developed for sepsis onset, in-hospital mortality, and cardiovascular ICU monitoring exhibited high predictive accuracy, highlighting the robustness and reliability of XAI approaches in critical care settings [19, 22, 23].”

    From Explainable AI for critical care: a systematic review of interpretable models for sepsis and ICU mortality prediction (2026) · cites this paper as [23]

    The Results (§4.2; page unavailable) report high predictive performance for several cardiovascular ICU models, including a SHAP-assisted model with an AUROC up to 0.94. But the Conclusion (§6; page unavailable) calls for better interpretability and prospective testing; these results do not establish the general robustness and reliability of XAI approaches in critical care. (LLM, conf=0.85)

    Experimental — accuracy not yet measured

  • AI has the potential to perform in emergency circumstances, assisting in monitoring cardiovascular patients in ICUs.

    “Interestingly, a study has reported that AI has also the potential to perform in emergency circumstances, assisting in monitoring cardiovascular patients in ICUs. 40”

    From Artificial Intelligence and Decision-Making in Healthcare: A Thematic Analysis of a Systematic Review of Reviews (2024) · cites this paper as [40]

  • Moazemi et al. found generally strong predictive performance (AUROC approximately 0.79-0.96).

    “Results showed generally strong predictive performance (AUROC ~0.79–0.96), but highlighted major limitations including lack of external validation (≈75% of studies), poor generalizability, and limited interpretability [32].”

    From Artificial Intelligence to Facilitate SEP-1 Measure Compliance and Fluid Management in Sepsis (2026) · cites this paper as [32]

  • Moazemi et al. highlighted major limitations including lack of external validation in approximately 75% of studies, poor generalizability, and limited interpretability.

    “Results showed generally strong predictive performance (AUROC ~0.79–0.96), but highlighted major limitations including lack of external validation (≈75% of studies), poor generalizability, and limited interpretability [32].”

    From Artificial Intelligence to Facilitate SEP-1 Measure Compliance and Fluid Management in Sepsis (2026) · cites this paper as [32]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

The citation lists haven’t been fetched yet

References 90 · Cited by 97

Research works printed but not linked: 72

  1. [1]Oyebode F. Clinical errors and medical negligence. Med Princ Pract. (2013) 22: 323– 33. doi: 10.1159/000346296, PMID: 23343656 PMC5586760 · DOI
  2. [2]Reason J. Understanding adverse events: human factors. BMJ Qual Saf. (1995) 4: 80– 9. doi: 10.1136/qshc.4.2.80, PMID: 10151618 PMC1055294 · DOI
  3. [3]Lin YW Zhou Y Faghri F Shaw MJ Campbell RH. Analysis and prediction of unplanned intensive care unit readmission using recurrent neural networks with long short-term memory. PLoS One. (2019) 14: e0218942. doi: 10.1371/journal.pone.0218942, PMID: 31283759 PMC6613707 · DOI
  4. [4]Almashrafi A Elmontsri M Aylin P. Systematic review of factors influencing length of stay in ICU after adult cardiac surgery. BMC Health Serv Res. (2016) 16: 318. doi: 10.1186/s12913-016-1591-3, PMID: 27473872 PMC4966741 · DOI
  5. [6]Michel JJ Flores EJ Dutcher L Mull NK Tsou AY. Translating an evidence-based clinical pathway into shareable CDS: developing a systematic process using publicly available tools. J Am Med Inform Assoc. (2020) 28: 52– 61. doi: 10.1093/jamia/ocaa257, PMID: 33120411 PMC7810443 · DOI
  6. [7]Gorgi Zadeh S MWM W Wiens V Thiele S Holz FG Finger RP. CNNs enable accurate and Fast segmentation of Drusen in optical coherence tomography In: Cardoso MJ Arbel T Carneiro G Syeda-Mahmood T JMRS T Moradi M, editors. Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Cham: Springer International Publishing (2017). 65– 73.
  7. [8]Andrearczyk V Fontaine P Oreiller V Castelli J Jreige M Prior JO. Multi-task deep segmentation and Radiomics for automatic prognosis in head and neck cancer In: Rekik I Adeli E Park SH Schnabel J, editors. Predictive Intelligence in Medicine. Cham: Springer International Publishing (2021). 147– 56.
  8. [9]Moazemi S Khurshid Z Erle A Lütje S Essler M Schultz T. Machine learning facilitates hotspot classification in PSMA-PET/CT with nuclear medicine specialist accuracy. Diagnostics. (2020) 10: 622. doi: 10.3390/diagnostics10090622, PMID: 32842599 PMC7555620 · DOI
  9. [10]Moazemi S Essler M Schultz T Bundschuh R. Predicting Treatment Response in Prostate Cancer Patients Based on Multimodal PET/CT for Clinical Decision Support. In: Multimodal Learning for Clinical Decision Support. eds. Syeda-Mahmood T Li X Madabhushi A Greenspan H Li Q Leahy R. (Cham: Springer International Publishing) (2021). 22– 35.
  10. [11]Lao J Chen Y Li ZC Li Q Zhang J Liu J. A deep learning-based Radiomics model for prediction of survival in glioblastoma Multiforme. Sci Rep. (2017) 7: 10353. doi: 10.1038/s41598-017-10649-8, PMID: 28871110 PMC5583361 · DOI · Paper page
  11. [13]Moazemi S Erle A Lütje S Gaertner F Essler M Bundschuh R. Estimating the potential of radiomics features and radiomics signature from pretherapeutic PSMA-PET-CT scans and clinical data for prediction of overall survival when treated with 177Lu-PSMA. Diagnostics (Basel). (2021) 11: 186. doi: 10.3390/diagnostics11020186 33525456 PMC7912143 · DOI
  12. [14]Lin WT Chen WL Chao CM Lai CC. The outcomes and prognostic factors of the patients with unplanned intensive care unit readmissions. Medicine (Baltimore). (2018) 97: e11124. doi: 10.1097/MD.0000000000011124, PMID: 29952954 PMC6039646 · DOI
  13. [15]Huang K Altosaar J Ranganath R. ClinicalBERT: modeling clinical notes and predicting hospital readmission. arXiv. (2019) doi: 10.48550/arXiv.1904.05342 · DOI · Paper page
  14. [16]Kessler S Schroeder D Korlakov S Hettlich V Kalkhoff S Moazemi S. Predicting readmission to the cardiovascular intensive care unit using recurrent neural networks. Digit Health. (2023) 9: 205520762211495. doi: 10.1177/20552076221149529 PMC9834934 36644663 · DOI
  15. [17]Wang D Li J Sun Y Ding X Zhang X Liu S. A machine learning model for accurate prediction of sepsis in ICU patients. Front Public Health. (2021) 9: 754348. doi: 10.3389/fpubh.2021.754348, PMID: 34722452 PMC8553999 · DOI
  16. [18]Ghalati PF Samal SS Bhat JS Deisz R Marx G Schuppert A. Critical transitions in intensive care units: a sepsis case study. Sci Rep. (2019) 9: 12888. doi: 10.1038/s41598-019-49006-2, PMID: 31501451 PMC6733794 · DOI
  17. [19]Scherpf M Gräßer F Malberg H Zaunseder S. Predicting sepsis with a recurrent neural network using the MIMIC III database. Comput Biol Med. (2019) 113: 103395. doi: 10.1016/j.compbiomed.2019.103395, PMID: 31480008 · DOI · Paper page
  18. [20]Harerimana G Kim JW Jang B. A deep attention model to forecast the length of stay and the in-hospital mortality right on admission from ICD codes and demographic data. J Biomed Inform. (2021) 118: 103778. doi: 10.1016/j.jbi.2021.103778, PMID: 33872817 · DOI
  19. [21]Ye J Yao L Shen J Janarthanam R Luo Y. Predicting mortality in critically ill patients with diabetes using machine learning and clinical notes. BMC Med Inform Decis Mak. (2020) 20: 295. doi: 10.1186/s12911-020-01318-4, PMID: 33380338 PMC7772896 · DOI
  20. [22]Parikh RB Teeple S Navathe AS. Addressing bias in artificial intelligence in health care. JAMA. (2019) 322: 2377– 8. doi: 10.1001/jama.2019.18058, PMID: 31755905 · DOI · Paper page
  21. [23]Larrazabal AJ Nieto N Peterson V Milone DH Ferrante E. Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis. Proc Natl Acad Sci. (2020) 117: 12592– 4. doi: 10.1073/pnas.1919012117, PMID: 32457147 PMC7293650 · DOI · Paper page
  22. [25]Moazemi S Kalkhoff S Kessler S Boztoprak Z Hettlich V Liebrecht A. Evaluating a recurrent neural network model for predicting readmission to cardiovascular ICUs based on clinical time series data. Eng Proc. (2022) 18: 1. doi: 10.3390/engproc2022018001 · DOI
  23. [27]Giordano C Brennan M Mohamed B Rashidi P Modave F Tighe P. Accessing artificial intelligence for clinical decision-making. Front Digit Health. (2021) 3: 645232. 34713115 PMC8521931
  24. [28]Syed M Syed S Sexton K Syeda HB Garza M Zozus M. Application of machine learning in intensive care unit (ICU) settings using MIMIC dataset: systematic review. Inform MDPI. (2021) 8: 16. doi: 10.3390/informatics8010016 PMC8112729 33981592 · DOI
  25. [29]Greco M Caruso PF Cecconi M. Artificial intelligence in the intensive care unit. Semin Respir Crit Care Med. (2021) 42: 2– 9. doi: 10.1055/s-0040-1719037, PMID: 33152770 · DOI · Paper page
  26. [30]Yang G Ye Q Xia J. Unbox the black-box for the medical explainable AI via multi-modal and multi-Centre data fusion: A mini-review, two showcases and beyond. Inf Fusion. (2022) 77: 29– 52. doi: 10.1016/j.inffus.2021.07.016, PMID: 34980946 PMC8459787 · DOI · Paper page
  27. [31]Abdellatif AA Mhaisen N Chkirbene Z Mohamed A Erbad A Guizani M. Reinforcement learning for intelligent healthcare systems: A comprehensive survey. arXiv. (2021) doi: 10.48550/arXiv.2108.04087 · DOI
  28. [35]Sutton RS. Introduction: The challenge of reinforcement learning In: Sutton RS, editor. Reinforcement Learning. The Springer International Series in Engineering and Computer Science, vol. 173. Boston, MA: Springer
  29. [36]Lippman SA. Dynamic programming and Markov decision processes In:. The New Palgrave Dictionary of Economics. London: Palgrave Macmillan UK (2016). 1– 7. doi: 10.1057/978-1-349-95121-5_80-1 · DOI
  30. [37]Riedmiller M. Neural fitted Q iteration – first experiences with a data efficient neural reinforcement learning method In: Gama J Camacho R Brazdil PB Jorge AM Torgo L, editors. Machine Learning: ECML 2005. Berlin, Heidelberg: Springer Berlin Heidelberg (2005). 317– 28.
  31. [39]Parsi A Glavin M Jones E Byrne D. Prediction of paroxysmal atrial fibrillation using new heart rate variability features. Comput Biol Med. (2021) 133: 104367. doi: 10.1016/j.compbiomed.2021.104367, PMID: 33866252 · DOI
  32. [40]Yu Y Peng C Zhang Z Shen K Zhang Y Xiao J. Machine learning methods for predicting long-term mortality in patients after cardiac surgery. Front Cardiovasc Med. (2022) 9: 831390. doi: 10.3389/fcvm.2022.831390, PMID: 35592400 PMC9110683 · DOI
  33. [41]Chen WT Huang HL Ko PS Su W Kao CC Su SL. A simple algorithm using ventilator parameters to predict successfully rapid weaning program in cardiac intensive care unit patients. J Pers Med. (2022) 12: 501. doi: 10.3390/jpm12030501, PMID: 35330500 PMC8950402 · DOI
  34. [42]Bodenes L N’Guyen QT Le Mao R Ferrière N Pateau V Lellouche F. Early heart rate variability evaluation enables to predict ICU patients’ outcome. Sci Rep. (2022) 12: 2498. doi: 10.1038/s41598-022-06301-9, PMID: 35169170 PMC8847560 · DOI
  35. [43]Qin F Madan V Ratan U Karnin Z Kapoor V Bhatia P. Improving early sepsis prediction with multi modal learning. arXiv. (2021)
  36. [44]Baral S Alsadoon A Prasad PWC Al Aloussi S Alsadoon OH. A novel solution of using deep learning for early prediction cardiac arrest in sepsis patient: enhanced bidirectional long short-term memory (LSTM). Multimed Tools Appl. (2021) 80: 32639– 64. doi: 10.1007/s11042-021-11176-5 · DOI
  37. [45]Cox DR. The regression analysis of binary sequences. J R Stat Soc Ser B Methodol. (1958) 20: 215– 32. doi: 10.1111/j.2517-6161.1958.tb00292.x · DOI
  38. [46]Cortes C Vapnik V. Support-vector networks. Mach Learn. (1995) 20: 273– 97. doi: 10.1007/BF00994018 · DOI · Paper page
  39. [47]Quinlan JR. Induction of decision trees. Mach Learn. (1986) 1: 81– 106. doi: 10.1007/BF00116251 · DOI · Paper page
  40. [48]Breiman L. Random forests. Mach Learn. (2001) 45: 5– 32. doi: 10.1023/A:1010933404324 · DOI · Paper page
  41. [49]Friedman JH. Greedy function approximation: A gradient boosting machine. Ann Stat. (2001) 29: 1189– 232. doi: 10.1214/aos/1013203451 · DOI · Paper page
  42. [50]Dorogush AV Ershov V Gulin A. CatBoost: Gradient boosting with categorical features support. arXiv. (2018)
  43. [52]Hochreiter S Schmidhuber J. Long short-term memory. Neural Comput. (1997) 9: 1735– 80. doi: 10.1162/neco.1997.9.8.1735 9377276 · DOI · Paper page
  44. [53]Johnson AEW Pollard TJ Shen L Lehman L Wei H Feng M. MIMIC-III, a freely accessible critical care database. Sci Data. (2016) 3: 160035. doi: 10.1038/sdata.2016.35, PMID: 27219127 PMC4878278 · DOI · Paper page
  45. [55]Ho KM Dobb GJ Knuiman M Finn J Lee KY Webb SA. A comparison of admission and worst 24-hour acute physiology and chronic health evaluation II scores in predicting hospital mortality: a retrospective cohort study. Crit Care. (2005) 10: R4. PMC1550848 16356207
  46. [56]Higgins TL Teres D Copes WS Nathanson BH Stark M Kramer AA. Assessing contemporary intensive care unit outcome: an updated mortality probability admission model (MPM0-III). Crit Care Med. (2007) 35: 827– 35. doi: 10.1097/01.CCM.0000257337.63529.9F, PMID: 17255863 · DOI
  47. [57]Vincent JL de Mendonca A Cantraine F Moreno R Takala J Suter PM. Use of the SOFA score to assess the incidence of organ dysfunction/failure in intensive care units: results of a multicenter, prospective study. Crit Care Med. (1998) 26: 1793– 800. doi: 10.1097/00003246-199811000-00016 9824069 · DOI · Paper page
  48. [58]Jabali AK Waris A Khan DI Ahmed S Hourani RJ. Electronic health records: three decades of bibliometric research productivity analysis and some insights. Inform Med Unlocked. (2022) 29: 100872. doi: 10.1016/j.imu.2022.100872 · DOI
  49. [61]Yèche H Kuznetsova R Zimmermann M Hüser M Lyu X Faltys M. HiRID-ICU-benchmark - A comprehensive machine learning benchmark on high-resolution ICU data. arXiv. (2022) doi: 10.48550/arXiv.2111.08536 · DOI · Paper page
  50. [62]Saeed M Villarroel M Reisner AT Clifford G Lehman LW Moody G. Multiparameter intelligent monitoring in intensive care II: A public-access intensive care unit database*. Crit Care Med. (2011) 39: 952– 60. doi: 10.1097/CCM.0b013e31820a92c6, PMID: 21283005 PMC3124312 · DOI · Paper page
  51. [63]Pollard TJ Johnson AEW Raffa JD Celi LA Mark RG Badawi O. The eICU collaborative research database, a freely available multi-center database for critical care research. Sci Data. (2018) 5: 180178. doi: 10.1038/sdata.2018.178, PMID: 30204154 PMC6132188 · DOI · Paper page
  52. [64]Shaban-Nejad A Michalowski M Buckeridge DL. Explainability and interpretability: AAAI international workshop on health intelligence, W3PHIAI 2020 In: Shaban-Nejad A Michalowski M Buckeridge DL, editors. Explainable AI In Healthcare and Medicine - Building A Culture of Transparency and Accountability: Springer Science and Business Media Deutschland GmbH (2020). 1– 10.
  53. [65]Zhao QY Wang H Luo JC Luo MH Liu LP Yu SJ. Development and validation of a machine-learning model for prediction of extubation failure in intensive care units. Front Med. (2021) 8: 676343. doi: 10.3389/fmed.2021.676343 PMC8165178 34079812 · DOI
  54. [66]Jentzer JC Kashou AH Lopez-Jimenez F Attia ZI Kapa S Friedman PA. Mortality risk stratification using artificial intelligence-augmented electrocardiogram in cardiac intensive care unit patients. Eur Heart J Acute Cardiovasc Care. (2021) 10: 532– 41. doi: 10.1093/ehjacc/zuaa021, PMID: 33620440 PMC8245143 · DOI
  55. [67]Andersson P Johnsson J Björnsson O Cronberg T Hassager C Zetterberg H. Predicting neurological outcome after out-of-hospital cardiac arrest with cumulative information; development and internal validation of an artificial neural network algorithm. Crit Care Lond Engl. (2021) 25: 83. doi: 10.1186/s13054-021-03505-9, PMID: 33632280 PMC7905905 · DOI
  56. [69]Srinivasu PN Sandhya N Jhaveri RH Raut R. From Blackbox to explainable AI in healthcare: existing tools and case studies. Mob Inf Syst. (2022) 2022: 1– 20. doi: 10.1155/2022/8167821 · DOI
  57. [70]Guyon I Weston J Barnhill S Vapnik V. Gene selection for cancer classification using support vector machines. Mach Learn. (2002) 46: 389– 422. doi: 10.1023/A:1012487302797 · DOI · Paper page
  58. [74]Gandin I Scagnetto A Romani S Barbati G. Interpretability of time-series deep learning models: A study in cardiovascular patients admitted to intensive care unit. J Biomed Inform. (2021) 121: 103876. doi: 10.1016/j.jbi.2021.103876, PMID: 34325021 · DOI
  59. [76]Dutra GP Gomes Bf De O Do CJP JLF P Nascimento EM Pereira De B. Mortality from heart failure with mid-range ejection fraction. Arq Bras Cardiol. (2022) 118: 694– 700. doi: 10.36660/abc.20210050, PMID: 35508046 PMC9007002 · DOI
  60. [77]Nanayakkara T Clermont G Langmead CJ Swigon D. Unifying cardiovascular modelling with deep reinforcement learning for uncertainty aware control of sepsis treatment. PLOS Digit Health. (2022) 1: e0000012. doi: 10.1371/journal.pdig.0000012, PMID: 36812511 PMC9931225 · DOI
  61. [78]Zheng H Zhu J Xie W Zhong J. Reinforcement learning assisted oxygen therapy for COVID-19 patients under intensive care. BMC Med Inform Decis Mak. (2021) 21: 350. doi: 10.1186/s12911-021-01712-6, PMID: 34920724 PMC8678583 · DOI
  62. [79]Peine A Hallawa A Bickenbach J Dartmann G Fazlic LB Schmeink A. Development and validation of a reinforcement learning algorithm to dynamically optimize mechanical ventilation in critical care. Npj Digit Med. (2021) 4: 1– 12. doi: 10.1038/s41746-021-00388-6 33608661 PMC7895944 · DOI
  63. [81]Aushev A Ripoll VR Vellido A Aletti F Pinto BB Herpain A. Feature selection for the accurate prediction of septic and cardiogenic shock ICU mortality in the acute phase. PLoS One. (2018) 13: e0199089. doi: 10.1371/journal.pone.0199089, PMID: 30457997 PMC6245679 · DOI
  64. [82]Kim J Chae M Chang HJ Kim YA Park E. Predicting cardiac arrest and respiratory failure using feasible artificial intelligence with simple trajectories of patient data. J Clin Med. (2019) 8: 1336. doi: 10.3390/jcm8091336, PMID: 31470543 PMC6780058 · DOI
  65. [84]Yoon JH Mu L Chen L Dubrawski A Hravnak M Pinsky MR. Predicting tachycardia as a surrogate for instability in the intensive care unit. J Clin Monit Comput. (2019) 33: 973– 85. doi: 10.1007/s10877-019-00277-0, PMID: 30767136 PMC6823304 · DOI
  66. [85]Zou H Hastie T. Regularization and variable selection via the elastic net. J R Stat Soc Ser B Stat Methodol (Statistical Methodology). (2005) 67: 301– 20. doi: 10.1111/j.1467-9868.2005.00503.x · DOI · Paper page
  67. [87]Yang M Wang X Gao H Li Y Liu X Li J. “ Early Prediction of Sepsis Using Multi-Feature Fusion Based XGBoost Learning and Bayesian Optimization,” in The IEEE Conference on Computing in Cardiology (CinC) (2019) 46: 1– 4. Available at: http://www.cinc.org/archives/2019/pdf/CinC2019-020.pdf (Accessed October 31, 2022)
  68. [88]Gottesman O Johansson F Komorowski M Faisal A Sontag D Doshi-Velez F. Guidelines for reinforcement learning in healthcare. Nat Med. (2019) 25: 16– 8. doi: 10.1038/s41591-018-0310-5 30617332 · DOI · Paper page
  69. [91]Asan O Bayrak AE Choudhury A. Artificial intelligence and human Trust in Healthcare: focus on clinicians. J Med Internet Res. (2020) 22: e15154. doi: 10.2196/15154, PMID: 32558657 PMC7334754 · DOI · Paper page
  70. [92]Muehlematter UJ Daniore P Vokinger KN. Approval of artificial intelligence and machine learning-based medical devices in the USA and Europe (2015–20): a comparative analysis. Lancet Digit Health. (2021) 3: e195– 203. doi: 10.1016/S2589-7500(20)30292-2, PMID: 33478929 · DOI · Paper page
  71. [93]Zanca F Brusasco C Pesapane F Kwade Z Beckers R Avanzo M. Regulatory aspects of the use of artificial intelligence medical software. Semin Radiat Oncol. (2022) 32: 432– 41. doi: 10.1016/j.semradonc.2022.06.012, PMID: 36202445 · DOI
  72. [94]Roller R Budde K Burchardt A Dabrock P Möller S Osmanodja B. When performance is not enough - A multidisciplinary view on clinical decision support. arXiv. (2022) PMC10124862 37093808

Authors
Moazemi, S., Vahdati, S., Li, J., Kalkhoff, S., Castano, L. J. V., Dewitz, B., Bibo, R., Sabouniaghdam, P., Tootooni, M. S., Bundschuh, R. A., Lichtenberg, A., Aubin, H., & Schmid, F.
Affiliations
  • Düsseldorf University Hospital (DE)
  • Loyola University Chicago (US)
  • University of Augsburg (DE)
Corresponding author
Moazemi, Sobhan
ORCID
Venue
Frontiers in Medicine
Publisher
Frontiers Media SA
Published
2023-03-31
Volume
10
Pages
1109411-1109411
ISSN
2296-858X (ISSN-L)
DOI
10.3389/fmed.2023.1109411
PMC
PMC10102653
OpenAlex
W4362465788
Cited by
97
References
90
Citations by year
2026: 35 · 2025: 29 · 2024: 27 · 2023: 6
FWCI
2.03
Type
journal article
Language
en
Open access
Licence
Locations
  • Frontiers in Medicine (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • OPUS (Augsburg University) (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
Bundesministerium für Bildung und Forschung (16SV8601)
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
artificial intelligence, clinical decision support systems, cardiovascular intensive care, patient monitoring, intensive care, machine learning, reinforcement learning, deep learning, electronic health records, clinical time series, external validation, model interpretability, AI integration in healthcare

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