Risk Management In Intensive Care Units With Artificial Intelligence Technologies: Systematic Review of Prediction Models Using Electronic Health Records

Abstract

Background and aim: Clinical risk assessments should be made to protect patients from negative outcomes, and the definition, frequency and severity of the risk should be determined. The information contained in the electronic health records (EHRs) can use in different areas such as risk prediction, estimation of treatment effect ect. Many prediction models using artificial intelligence (AI) technologies that can be used in risk assessment have been developed. The aim of this study is to bring together the researches on prediction models developed with AI technologies using the EHRs of patients hospitalized in the intensive care unit (ICU) and to evaluate them in terms of risk management in healthcare. Methods: The study restricted the search to the Web of Science, Pubmed, Science Direct, and Medline databases to retrieve research articles published in English in 2010 and after. Studies with a prediction model using data obtained from EHRs in the ICU are included. The study focused solely on research conducted in ICU to predict a health condition that poses a significant risk to patient safety using artificial intellegence (AI) technologies. Results: Recognized prediction subcategories were mortality (n=6), sepsis (n=4), pressure ulcer (n=4), acute kidney injury (n=3), and other areas (n=10). It has been found that EHR-based prediction models are good risk management and decision support tools and adoption of such models in ICUs may reduce the prevalence of adverse conditions. Conclusions: The article results remarks that developed models was found to have higher performance and better selectivity than previously developed risk models, so they are better at predicting risks and serious adverse events in ICU. It is recommended to use AI based prediction models developed using EHRs in risk management studies. Future work is still needed to researches to predict different health conditions risks.

Keywords

• Risk Management
• Artificial Intelligence
• Electronic Health Record
• Intensive Care Unit

References

1. 1. European Union, European Comission, Costs of unsafe care and costeffectiveness of patient safety programmes, 2016, https://ec.europa.eu/health/sites/health/files/systems_performance_assessment/docs/2016_costs_psp_en.pdf, Access date:9.12.2020
2. 2. OECD, The Economics of Patient Safety, Strengthening a value-based approach to reducing patient harm at national level, 2017, https://www.oecd.org/els/health-systems/The-economics-of-patient-safety-March-2017.pdf, Access date:09.12.2020
3. 3. Solomon PR, Quattrone MS, Information technologies and risk management, (Ed) Roberta L. Carroll, Risk Management Handbook for Health Care Organizations, A San Francisco, USA, Wiley Imprint, 2009
4. 4. Biancone PP, Martra A, Secinaro S, Iannaci D, The Data Quality for Healthcare: The Risk Management Tools, (Ed) Paola De Vincentiis · Francesca Culasso, Stefano A. Cerrato, The Future of Risk Management, Volume I, Perspectives on Law, Healthcare, and the Environment, ISBN 978-3-030-14548-4 (eBook), Springer Nature Switzerland AG, https://doi.org/10.1007/978-3-030-14548-4, 2019
5. 5. Carroll R L, Risk Management Handbook for Health Care Organizations, American Society for Healthcare Risk Management, Wiley Imprint, San Francisco, ISBN 978-0-470-30017-6, 2011
6. 6. Joint Commission on Accreditation of Healthcare Organizations (JCAHO) “Accreditation Issues for Risk Managers”, Joint Commission Resources, Illinois, ISBN-10 : 0866888160, 2004
7. 7. International Standardization of Organization , ISO 31000, Risk Management, 2009 https://www.iso.org/obp/ui/#iso:std:iso:31000:ed-1:v1:en, Access date:01.01.2021
8. 8. MoH, SAS Standards of Accreditation in Health Hospital Kit, Pozitif Printing Press Ltd. Co, Ankara, ISBN: 978-975-590-544-0, 2018

9. 9. WHO, (2021), Topic 6: Understanding and managing clinical risk, [online].Website https://www.who.int/patientsafety/education/curriculum/who_mc_topic-6.pdf, Access date:14.01.2021
10. 10. Bose SN, Verigan A, Hanson J, et al., Early identification of impending cardiac arrest in neonates and infants in the cardiovascular ICU: a statistical modelling approach using physiologic monitoring data. Cardiol Young, 2019; 29: 1340–1348. doi: 10.1017/ S1047951119002002
11. 11. Campbell V, Conway R, Carey K, et al., Predicting clinical deterioration with Q-ADDS compared to NEWS, Between the Flags, and eCART track and trigger tools, Resuscitation, 2020;1 5 3:28-34, https://doi.org/10.1016/j.resuscitation.2020.05.027.
12. 12. Agor J, Ozaltın OY, Ivy JS, Capan M, Arnold R, Romero S, The value of missing information in severity of illness score development, J Biomed Inform, 2019;97, https://doi.org/10.1016/j.jbi.2019.103255.
13. 13. Karabıyık L, (2010), Yoğun Bakımda Skorlama Sistemleri,[ Intensive Care Scoring Systems], Yoğun Bakım Dergisi, 2010;9(3):129-143 http://www.yogunbakimdergisi.org/managete/fu_folder/2010-03/html/2010-9-3-129-143.htm
14. 14. Büyükgöze S, Dereli E, Dijital Sağlık Uygulamalarında Yapay Zeka, [Artificial Intelligence In Digital Health Application], VI. Uluslararası Bilimsel ve Mesleki Çalışmalar Kongresi-Fen ve Sağlık, 07-10 Kasım 2019, Ankara
15. 15. Kavakiotis, I. Tsave O, Salifoglou A, Maglaveras N, Vlahavas I, Chouvarda I, Machine Learning and Data Mining Methods in Diabetes Research. Comput Struct Biotechnol J. 2017;15:104–116, http://dx.doi.org/10.1016/j.csbj.2016.12.005
16. 16. Verenyurt U, Deveci AF., Esen MF., Veranyurt O., Disease classification by machine learning techniques: random forest, k-nearest neighbor and adaboost algorithms applications, Uluslararası Sağlık Yönetimi ve Stratejileri Araştırma Dergisi 2020; 6(2):275-286
17. 17. Hauskrecht M, Batal I, Hong C, et al., Outlier-based detection of unusual patient-management actions: An ICU study, J Biomed Inform, 2016;64:211–221, http://dx.doi.org/10.1016/j.jbi.2016.10.002
18. 18. Schneeweiss S., Learning from Big Health Care Data, N Engl J Med., 2014;370:2161–2163. pmid:24897079
19. 19. Hripcsak G, Albers DJ., Next-generation phenotyping of electronic health records, J Am Med Inform Assoc. 2013;20(1):117–121, doi:10.1136/amiajnl-2012-001145
20. 20. Low S, Vathsala A, Muralı TM, et al., Electronic health records accurately predict renal replacement therapy in acute kidney injury, BMC Nephrol, 2019;20:32, https://doi.org/10.1186/s12882-019-1206-4
21. 21. Moher D, Liberati A, Tetzlaff J, Altman DG, The PRISMA Group. Preferred Reporting Items for Systematic Reviews and Meta-Analyses: The PRISMA Statement. PLoS Med., 2015, www.prisma-statement.org, Access date: 01.01.2020
22. 22. Kmet, Lee R, Cook L, Standard Quality Assessment Criteria for Evaluating Primary Research Papers from a Variety of Fields, Alberta Heritage Foundation for Medical Research, Alberta, Canada, ISBN online:1-896956-79-3, 2004
23. 23. Marafıno BJ, Park M, Davies JM, et al., Validation of Prediction Models for Critical Care Outcomes Using Natural Language Processing of Electronic Health Record Data, JAMA Netw Open, 2018;1(8):e185097. doi:10.1001/jamanetworkopen.2018.5097
24. 24. Calvert J, Mao Q, Hoffman JL, et al., Using electronic health record collected clinical variables to predict medical intensive care unit mortality, Ann Med Surg, 2016a;11:52-57, http://dx.doi.org/10.1016/j.amsu.2016.09.002
25. 25. Calvert J, Mao Q, Rogers AJ, Barton C, Jay M, A computational approach to mortality prediction of alcohol use disorder inpatients, Comput Biol Med, 2016b;75: 74–79, PMID: 27253619
26. 26. Che Z, Purushotham S, Khemani R, Liu Y, Interpretable Deep Models for ICU Outcome Prediction, AMIA Annu Symp Proc. 2017 Feb 10;2016:371-380. PMID: 28269832; PMCID: PMC5333206.
27. 27. Davoodi R, Moradi MH, Mortality prediction in intensive care units (ICUs) using a deep rule-based fuzzy classifier, J Biomed Inform, 2018;79:48–59, https://doi.org/10.1016/j.jbi.2018.02.008
28. 28. Lee J, Maslove DM, Dubin JA, Personalized Mortality Prediction Driven by Electronic Medical Data and a Patient Similarity Metric, PLoS ONE, 2015;10(5): e0127428. doi:10.1371/journal. pone.0127428.
29. 29. Rafiei A., Rezaee A., Hajati F., Gheisari S., Golzan M., Early Prediction of Sepsis using Fully Connected LSTM-CNN Model, Comput Biol Med., 2020, https:// doi.org/10.1016/j.compbiomed.2020.104110.
30. 30. Desautels T, Calvert J, Hoffman J, et al., Prediction of Sepsis in the Intensive Care Unit With Minimal Electronic Health Record Data: A Machine Learning Approach, JMIR Med Inform, 2016;4(3):e28 doi:10.2196/medinform.5909 PMID: 27694098
31. 31. Harrison AM, Thongprayoon C, Kashyap R, et al., Developing the Surveillance Algorithm for Detection of Failure to Recognize and Treat Severe Sepsis, Mayo Clin Proc., 2015;90(2):166–175. doi:10.1016/j.mayocp.2014.11.014.
32. 32. Nemati S, Holder A, Razmi F, et al., An Interpretable Machine Learning Model for Accurate Prediction of Sepsis in the ICU, Crit Care Med., 2018;46(4): 547–553. doi:10.1097/CCM.0000000000002936
33. 33. Cho I, Park I, Kime E, Lee E, Bates DW, Using EHR data to predict hospital-acquired pressure ulcers: A prospective study of a Bayesian Network model, Int J Med Inform 2013;82(11):1059-1067, https://doi.org/10.1016/j.ijmedinf.2013.06.012
34. 34. Cramer EM, Seneviratne MG, Sharifi H, Ozturk A, Hernandez-Boussard, T., Predicting the Incidence of Pressure Ulcers in the Intensive Care Unit Using Machine Learning, EGEMS (Wash DC), 2019;7(1):49: 1–11. https://doi.org/10.5334/egems.307
35. 35. Kaewprag P, Newton C, Vermillion B, et al., Predictive models for pressure ulcers from intensive care unit electronic health records using Bayesian networks, BMC Med Inform Decis Mak, 2017;17(2):65 Doi:10.1186/s12911-017-0471-z.
36. 36. Hyun S, Moffatt-Bruce S, Cooper C, Hixon B, Kaewprag P, Prediction Model for Hospital-Acquired Pressure Ulcer Development: Retrospective Cohort Study, JMIR Med Inform, 2019;7(3):e13785 doi: 10.2196/13785 PMID: 31322127
37. 37. Koyner JL, Carey KA, Edelson DP, Churpek MM, The Development of a Machine Learning Inpatient Acute Kidney Injury Prediction Model, Crit Care Med, 2018, doi: 10.1097/CCM.0000000000003123.
38. 38. Sanchez-Pinto NL, Khemani RG, Development of a Prediction Model of Early Acute Kidney Injury in Critically Ill Children Using Electronic Health Record Data, Pediatr Crit Care Med., 2016, Jun;17(6):508-15. doi:10.1097/PCC.0000000000000750. PMID: 27124567.
39. 39. Xu Z, Choua J, Zhanga XS, et al., Identifying sub-phenotypes of acute kidney injury using structured and unstructured electronic health record data with memory networks, J Biomed Inform., 2020;102, https://doi.org/10.1016/j.jbi.2019.103361
40. 40. Eickelberg G., Sanchez-Pinto N., Luo Y., Predictive modeling of bacterial infections and antibiotic therapy needs in critically ill adults, J Biomed Inform, 2020;109, https://doi.org/10.1016/j.jbi.2020.103540
41. 41. Li BY, Oh J, Young VB, Rao K, Wiens J, Using Machine Learning and the Electronic Health Record to Predict Complicated Clostridium difficile Infection, Open Forum Infect Dis. 2019;20;6(5):ofz186. doi: 10.1093/ofid/ofz186. PMID: 31139672; PMCID: PMC6527086.
42. 42. Liu R, Greenstein JL, Granite SJ, Fackler JC, Bembea MM, et al., Data-driven discovery of a novel sepsis pre-shock state predicts impending septic shock in the ICU, Sci Rep, 2019:9:6145,https://doi.org/10.1038/s41598-019-42637-5
43. 43. Mollura M, Romano S, Mantoan G, Lehman L, Barbieri R, Prediction of Septic Shock Onset in ICU by Instantaneous Monitoring of Vital Signs, Annu Int Conf IEEE Eng Med Biol Soc. 2020:2768-2771. doi: 10.1109/EMBC44109.2020.9176276. PMID: 33018580.
44. 44. Alvarez AC, Clark CA, Zhang S, et al., Predicting out of intensive care unit cardiopulmonary arrest or death using electronic medical record data, BMC Med Inform Decis Mak, 2013;13(28), http://www.biomedcentral.com/1472-6947/13/28
45. 45. Moon KJ, Jin Y, Jin T, Lee SM., Development and validation of an automated delirium risk assessment system (Auto-DelRAS) implemented in the electronic health record system. Int J Nurs Stud., 2018;77:46-53. doi:10.1016/j.ijnurstu.2017.09.014. Epub 2017 Sep 23. PMID: 29035732.
46. 46. Lee JY, Park HA, Chung E, Use of electronic critical care flow sheet data to predict unplanned extubation in ICUs, Int J Med Inform 2018;117: 6–12, https://doi.org/10.1016/j.ijmedinf.2018.05.011
47. 47. Jeong DH, Hong SB., Lim CM, et al., Comparison of Accuracy of NUTRIC and Modified NUTRIC Scores in Predicting 28-Day Mortality in Patients with Sepsis: A Single Center Retrospective Study. Nutrients, 2018;17;10(7):911. doi: 10.3390/nu10070911. PMID: 30018224; PMCID: PMC6073879.
48. 48. Meyfroidt G, Guiza F, Cottem D, et al., Computerized prediction of intensive care unit discharge after cardiac surgery: development and validation of a Gaussian processes model. BMC Med Inform Decis Mak., 2011;11:64. doi: 10.1186/1472-6947-11-64. PMID: 22027016; PMCID: PMC3228706.
49. 49. Holmes J, Roberts G, Geen J, et al., Utility of electronic AKI alerts in intensive care: A national multicentre cohort study, J Crit Care, 2018;44:185–190, https://doi.org/10.1016/j.jcrc.2017.10.024
50. 50. Çelik, R., Özel, F., Türkiye’de Yoğunbakım Ünitelerinde Oluşan Hastane Enfeksiyonları Gelişme Oranlarının Karşılaştırılması, [A Comparison of the Development of Nozocomial Infections Occurring in Intensive Care Units in Turkey], Sağlık Akademisi Kastamonu (SAK), 2020;5(2):158-169, doi: 10.25279/sak. 335045