Abstract
The hectic domain of critical care is, arguably, one of the most demanding instances of multidisciplinary medical decision-making. It is also a domain infused with monitoring and life-sustaining technologies that leave behind the type of digital data trail that is ideal for the deployment of artificial intelligence and, particularly, machine learning methods and analytical pipelines. These data analysis methods should provide medical decision support to intensivists, but there is yet no clear framework or standard set of guidelines on how to do so. In this chapter, we aim to provide readers with information on the current landscape of applications of machine learning in critical care and also with a clear outline of some of the many challenges yet to overcome to guarantee the success of such applications, including the problem of model interpretability and explainability, the technology compliance with current legislation, or the education of medical practitioners in the area of data analytics using open-source software.
References
Cosgriff CV, Celi LA, Stone DJ. Critical care, critical data. Biomed Eng Comput Biol. 2019;10:1179597219856564.
Ravì D, Wong C, Deligianni F, Berthelot M, Andreu-Pérez J, Lo B, Yang GZ. Deep learning for health informatics. IEEE J Biomed Health. 2017;21(1):4–21.
Cabitza F, Rasoini R, Gensini GF. Unintended consequences of machine learning in medicine. JAMA. 2017;318(6):517–8.
Tu JV. Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. J Clin Epidemiol. 1996;49(11):1225–31.
Doshi-Velez F, Kim B. Towards a rigorous science of interpretable machine learning. 2017. arXiv preprint. arXiv:1702.08608.
Bacciu D, Lisboa PJ, Martín JD, Stoean R, Vellido A. Bioinformatics and medicine in the era of deep learning. In: Proceedings of the 26th European symposium on artificial neural networks, computational intelligence and machine learning (ESANN 2018), Bruges, 2018. p. 345–54.
Vellido A, Martín JD, Rossi F, Lisboa PJG. Seeing is believing: the importance of visualization in real-world machine learning applications. In: Proceedings of the 19th European symposium on artificial neural networks (ESANN), 2011. p. 219–26.
Bhanot G, Biehl M, Villmann T, Zühlke D. Biomedical data analysis in translational research: integration of expert knowledge and interpretable models. In: Proceedings of the 25th European symposium on artificial neural networks, computational intelligence and machine learning (ESANN), 2017. p. 177–86.
Vellido A. The importance of interpretability and visualization in Machine Learning for applications in medicine and health care. Neural Comput Appl. ePub ahead of press. https://doi.org/10.1007/s00521-019-04051-w.
Waring J, Lindvall C, Umeton R. Automated machine learning: review of the state-of-the-art and opportunities for healthcare. Artif Intell Med. 2020;104:101822.
Safdar S, Zafar S, Zafar N, Khan NF. Machine learning based decision support systems (DSS) for heart disease diagnosis: a review. Artif Intell Rev. 2017;50(4):597–623.
Vellido A, Ribas V, Morales C, Ruiz-Sanmartín A, Ruiz-Rodríguez JC. Machine learning for critical care: state-of-the-art and a sepsis case study. Biomed Eng Online. 2018;17(S1):135.
Dreiseitl S, Binder M. Do physicians value decision support? A look at the effect of decision support systems on physician opinion. Artif Intell Med. 2005;33(1):25–30.
Rhee C, Jones TM, Hamad Y, Pande A, Varon J, O’Brien C, Anderson DJ, Warren DK, Dantes RB, Epstein L, Klompas M. Prevalence, underlying causes, and preventability of sepsis-associated mortality in US acute care hospitals. JAMA Netw Open. 2019;2(2):e187571.
Marshall JC. Why have clinical trials in sepsis failed? Trends Mol Med. 2014;20(4):195–203.
Nguyen D, Ngo B, van Sonnenberg E. AI in the intensive care unit: up-to-date review. J Intensive Care Med. 2020. ePub ahead of publication. https://doi.org/10.1177/0885066620956620.
Seymour CW, Liu VX, Iwashyna TJ, Brunkhorst FM, Rea TD, Scherag A, Rubenfeld G, Kahn JM, Shankar-Hari M, Singer M, Deutschman CS. Assessment of clinical criteria for sepsis: for the third international consensus definitions for sepsis and septic shock (sepsis-3). JAMA. 2016;315(8):762–74.
Seymour CW, Kennedy JN, Wang S, Chang CC, Elliott CF, Xu Z, Berry S, Clermont G, Cooper G, Gomez H, Huang DT. Derivation, validation, and potential treatment implications of novel clinical phenotypes for sepsis. JAMA. 2019;321(20):2003–17.
Ribas VJ, Vellido A, Ruiz-Rodríguez JC, Rello J. Severe sepsis mortality prediction with logistic regression over latent factors. Expert Syst Appl. 2012;39(2):1937–43.
Raghu A, Komorowski M, Celi LA, Szolovits P, Ghassemi M. Continuous state-space models for optimal sepsis treatment-a deep reinforcement learning approach. arXiv preprint arXiv:1705.08422. 2017 May 23.
Aushev A, Ribas Ripoll V, Vellido A, Aletti F, Bollen Pinto B, Bendjelid K, Herpain A, Hendrik Post E, Romay Medina E, Ferrer R, Baselli G. Feature selection for the accurate prediction of septic and cardiogenic shock ICU mortality in the acute phase. PLoS One. 2018;13(11):e0199089.
Ripoll VJ, Vellido A, Romero E, Ruiz-Rodríguez JC. Sepsis mortality prediction with the quotient basis kernel. Artif Intell Med. 2014;61(1):45–52.
Goodman B, Flaxman S. European Union regulations on algorithmic decision making and a “right to explanation”. AI Mag. 2017;38(3):50–57.
Reiz AN, de la Hoz MA, García MS. Big data analysis and machine learning in intensive care units. Med Intensiva (English Edition). 2019;43(7):416–26.
Yoon J, Drumright LN, Van Der Schaar M. Anonymization through data synthesis using generative adversarial networks (ADS-GAN). IEEE J Biomed Health Inform. 2020;24(8):2378–88.
McLennan S, Shaw D, Celi LA. The challenge of local consent requirements for global critical care databases. Intensive Care Med. 2019;45(2):246–8.
Tanner A. Our bodies, our data: how companies make billions selling our medical records. Beacon Press; 2017.
Hueso M, de Haro L, Calabia J, Dal-Ré R, Tebé C, Gibert K, Cruzado JM, Vellido A. Leveraging data science for a personalized haemodialysis. Kidney Dis. 2020. ePub ahead of print. https://doi.org/10.1159/000507291.
Caban JJ, Joshi A, Nagy P. Rapid development of medical imaging tools with open-source libraries. J Digit Imaging. 2007;20(Suppl 1):83–93.
Karopka T, Schmuhl H, Demski H. Free/libre open source software in health care: a review. Healthc Inform Res. 2014;20(1):11–22.
Aminpour F, Sadoughi F, Ahamdi M. Utilization of open source electronic health record around the world: a systematic review. J Res Med Sci. 2014;19(1):57–64.
Alaa AM, van der Schaar M. Autoprognosis: automated clinical prognostic modeling via Bayesian optimization with structured kernel learning. arXiv preprint arXiv:1802.07207. 2018.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic Supplementary Materials
(MP4 56481 kb)
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this entry
Cite this entry
Vellido, A., Ribas, V. (2021). Artificial Intelligence in Critical Care. In: Lidströmer, N., Ashrafian, H. (eds) Artificial Intelligence in Medicine. Springer, Cham. https://doi.org/10.1007/978-3-030-58080-3_174-1
Download citation
DOI: https://doi.org/10.1007/978-3-030-58080-3_174-1
Received:
Accepted:
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58080-3
Online ISBN: 978-3-030-58080-3
eBook Packages: Springer Reference MedicineReference Module Medicine