Artificial Intelligence in the Intensive Care Unit

Abstract

The diffusion of electronic health records collecting large amount of clinical, monitoring, and laboratory data produced by intensive care units (ICUs) is the natural terrain for the application of artificial intelligence (AI). AI has a broad definition, encompassing computer vision, natural language processing, and machine learning, with the latter being more commonly employed in the ICUs. Machine learning may be divided in supervised learning models (i.e., support vector machine [SVM] and random forest), unsupervised models (i.e., neural networks [NN]), and reinforcement learning. Supervised models require labeled data that is data mapped by human judgment against predefined categories. Unsupervised models, on the contrary, can be used to obtain reliable predictions even without labeled data. Machine learning models have been used in ICU to predict pathologies such as acute kidney injury, detect symptoms, including delirium, and propose therapeutic actions (vasopressors and fluids in sepsis). In the future, AI will be increasingly used in ICU, due to the increasing quality and quantity of available data. Accordingly, the ICU team will benefit from models with high accuracy that will be used for both research purposes and clinical practice. These models will be also the foundation of future decision support system (DSS), which will help the ICU team to visualize and analyze huge amounts of information. We plea for the creation of a standardization of a core group of data between different electronic health record systems, using a common dictionary for data labeling, which could greatly simplify sharing and merging of data from different centers.

Keywords

ICU - critical care - machine learning - artificial intelligence - supervised learning - unsupervised learning - reinforcement learning

Publication History

Article published online:
05 November 2020

• References

• 1 Bhatt A. Evolution of clinical research: a history before and beyond James Lind. Perspect Clin Res 2010; 1 (01) 6-10
• 2 Atkins D, Best D, Briss PA. GRADE Working Group. et al. Grading quality of evidence and strength of recommendations. BMJ 2004; 328 (7454): 1490-1494
• 3 Fleming PS, Koletsi D, Ioannidis JPAA, Pandis N. High quality of the evidence for medical and other health-related interventions was uncommon in Cochrane systematic reviews. J Clin Epidemiol 2016; 78: 34-42
• 4 Vincent JL, Marini JJ, Pesenti A. Do trials that report a neutral or negative treatment effect improve the care of critically ill patients? No. Intensive Care Med 2018; 44 (11) 1989-1991
• 5 Iwashyna TJ, Burke JF, Sussman JB, Prescott HC, Hayward RA, Angus DC. Implications of heterogeneity of treatment effect for reporting and analysis of randomized trials in critical care. Am J Respir Crit Care Med 2015; 192 (09) 1045-1051
• 6 De Fauw J, Ledsam JR, Romera-Paredes B. et al. Clinically applicable deep learning for diagnosis and referral in retinal disease. Nat Med 2018; 24 (09) 1342-1350
• 7 Fu S, Chen D, He H. et al. Clinical concept extraction: a methodology review. J Biomed Inform 2020; 109: 103526
• 8 Spasic I, Nenadic G. Clinical text data in machine learning: systematic review. JMIR Med Inform 2020; 8 (03) e17984
• 9 Vincent JL, de Mendonça A, Cantraine F. et al. Use of the SOFA score to assess the incidence of organ dysfunction/failure in intensive care units: results of a multicenter, prospective study. Working group on “sepsis-related problems” of the European Society of Intensive Care Medicine. Crit Care Med 1998; 26 (11) 1793-1800
• 10 Knaus WA, Draper EA, Wagner DP, Zimmerman JE. APACHE II: a severity of disease classification system. Crit Care Med 1985; 13 (10) 818-829
• 11 Bouza C, Lopez-Cuadrado T, Amate-Blanco JM. Use of explicit ICD9-CM codes to identify adult severe sepsis: impacts on epidemiological estimates. Crit Care 2016; 20 (01) 313
• 12 Higgins TL, Deshpande A, Zilberberg MD. et al. Assessment of the accuracy of using ICD-9 diagnosis codes to identify pneumonia etiology in patients hospitalized with pneumonia. JAMA Netw Open 2020; 3 (07) e207750
• 13 Sarrazin MS, Rosenthal GE. Finding pure and simple truths with administrative data. JAMA 2012; 307 (13) 1433-1435
• 14 Johnson AEW, Pollard TJ, Shen L. et al. MIMIC-III, a freely accessible critical care database. Sci Data 2016; 3: 160035
• 15 Komorowski M, Celi LA, Badawi O, Gordon AC, Faisal AA. The artificial intelligence clinician learns optimal treatment strategies for sepsis in intensive care. Nat Med 2018; 24 (11) 1716-1720
• 16 Davoudi A, Malhotra KR, Shickel B. et al. Intelligent ICU for autonomous patient monitoring using pervasive sensing and deep learning. Sci Rep 2019; 9 (01) 8020
• 17 Amos B, Ludwiczuk B, Satyanarayanan M. OpenFace: a general-purpose face recognition library with mobile applications. Accessed August 10, 2020 at: http://elijah.cs.cmu.edu/DOCS/CMU-CS-16-118.pdf
• 18 Patel SK, George B, Rai V. Artificial intelligence to decode cancer mechanism: beyond patient stratification for precision oncology. Front Pharmacol 2020; 11: 1177
• 19 Liu S, See KC, Ngiam KY, Celi LA, Sun X, Feng M. Reinforcement learning for clinical decision support in critical care: comprehensive review. J Med Internet Res 2020; 22 (07) e18477
• 20 Aslakson RA, Wyskiel R, Thornton I. et al. Nurse-perceived barriers to effective communication regarding prognosis and optimal end-of-life care for surgical ICU patients: a qualitative exploration. J Palliat Med 2012; 15 (08) 910-915
• 21 Levin PD, Sprung CL. Cultural differences at the end of life. Crit Care Med 2003; 31 (05) S354-S357