Abstract

Clinical information systems record large amounts of data from multiple sources. This data could be used to model the process and learn how a decision-making algorithm (CDSS) was actually executed.

We have developed an open source interface that uses data from different patient repositories for the integration of large data mining in a Fast Healthcare Interoperability Resources (FHIR) format. An interoperable solution that has emerged as a multi-layer architecture to manage critical medicine data. The layered architecture focuses on sharing processed information and making it easily available in a control panel for users of the Intensive Care Unit, improving the security and quality of medical care, meeting cybersecurity requirements and under standards. very strict ethics. The introduction of these techniques will allow health care in a more predictive way, through new algorithms.

The results demonstrate that the data mining obtained is a constant flow of highly dynamic and unstructured information; The above goes against the dogma that only EHRs are useful when making decisions. Only 4% of the data is used for this purpose and between 0.002% comes from the EHR, while even new algorithm designs will require structured data to exceed a greater percentage of all data.

We conclude that any clinical process requires a volume of structured data, robust on the basis of data mining and is not feasible with the use of background information only from the EHR, in a highly demanding unit.

Keywords: Data sources; Intensive Care Units; data mining; Artificial Intelligence; Interoperability; Electronic Health Records

References

1. Tambone V., et al. “Ethical Criteria for the Admission and Management of Patients in the ICU Under Conditions of Limited Medical Resources: A Shared International Proposal in View of the COVID-19 Pandemic”. Frontiers in Public Health 8 (2020): 284.
2. Curtis JR and Vincent J-L. “Ethics and end-of-life care for adults in the intensive care unit”. The Lancet 376.9749 (2010): 1347-53.
3. Piers RD., et al. “Perceptions of Appropriateness of Care Among European and Israeli Intensive Care Unit Nurses and Physicians”. JAMA 306.24 (2011): 2694-703.
4. Lapsley I and Melia K. “Clinical actions and financial constraints: the limits to rationing intensive care”. Sociology of Health & Illness 23.5 (2001): 729-46.
5. Trentini F., et al. “The pressure on healthcare system and intensive care utilization during the COVID-19 outbreak in the Lombardy region: a retrospective observational study on 43,538 hospitalized patients”. Am J Epidemiol 191.1 (2022): 137-146.
6. Thoral PJ., et al. “Explainable Machine Learning on AmsterdamUMCdb for ICU Discharge Decision Support: Uniting Intensivists and Data Scientists”. Critical Care Explorations 3.9 (2021): e0529.
7. Cosgriff CV, Celi LA and Sauer CM. “Boosting Clinical Decision-making: Machine Learning for Intensive Care Unit Discharge”. Annals ATS 15.7 (2018): 804-5.
8. Sauer Christopher M., et al. “Leveraging electronic health records for data science: common pitfalls and how to avoid them”. The Lancet Digital Health 4.12 (2022): e893-e898.
9. Chávez Plaza B., et al. “HL7 FHIR Platform, Scalable, Reliable and Comprehensive of Clinical Databases Analyzed with Machine Learning for ICU Public Healthcare Center”. Springer Nature Switzerland AG 2024. E. Pino et al. (Eds.): ICBHI 2022, IFMBE Proceedings 108 (2024) 1-6.
10. Tobias Gentner., et al. “Data Lakes in Healthcare: Applications and Benefits from the Perspective of Data Sources and Players”. Procedia Computer Science 225 (2023): 1302-1311.
11. Sutton RT., et al. “An overview of clinical decision support systems: benefits, risks, and strategies for success”. npj Digit. Med 3 (2020): 17.
12. Hripcsak G. “Arden Syntax for Medical Logic Modules”. MD Comput 8.2 (1991): 76-8.
13. HL7 International. Arden Syntax v 2.10 (Health Level Seven Arden Syntax for Medical Logic Systems, Version 2.10).
14. Johnson PD., et al. “A virtual medical record for guideline-based decision support”. Proc AMIA Symp (2001): 294-8.
15. Topol EJ. “High-performance medicine: the convergence of human and artificial intelligence”. Nat Med 25 (2019): 44-56.
16. Bailly S, Meyfroidt G, Timsit JF. “News at UCI in 2050: big data and machine learning”. Intensive Care Med 44 (2018): 1524-1527.
17. Ghassemi M, Celi LA and Stone DJ. “State of the art review: the data revolution in critical care”. Critical Care 19 (2015): 118.
18. Beam AL and Kohane IS. “Translate artificial intelligence into clinical care”. JAMA 316 (2016): 2368-2369.
19. Ince C. “Intensive care medicine in 2050: the ICU in vivo”. Intensive Care Med 43 (2017): 1700-1702.
20. Nemati S., et al. “An interpretable machine learning model for accurate prediction of sepsis in the ICU”. Crit Care Med 46 (2018): 547-553.
21. Pirracchio R., et al. “Predicting mortality in intensive care units with the Super ICU Learning Algorithm (SICULA): a population-based study”. Lancet Respir Med 3 (2015): 42-52.
22. Gårdlund B., et al. “Six subphenotypes in septic shock: latent class analysis of the PROWESS Shock study”. J Crit Care 47 (2018): 70-79.
23. Antcliffe DB., et al. “Transcriptomic signatures in sepsis and a differential response to steroids: from the randomized VANISH trial”. Am J Respir Crit Care Med 199 (2018): 980-986.
24. Seymour CW., et al. “Derivation, validation, and potential treatment implications of novel clinical phenotypes for sepsis”. JAMA 321.20 (2019): 2003-2017.
25. Sutton RS and Barto AG. “Reinforcement Learning: An Introduction”. 2nd ed. MIT Press, Cambridge (2018).
26. Guiza F, Van Eyck J and Meyfroidt G. “Predictive data mining on intensive care unit monitoring data”. J Clin Monitor Computer 27 (2013): 449-453.
27. Gottesman O., et al. “Guidelines for reinforcement learning in healthcare”. Nat Med 25 (2019): 16-18.
28. Komorowski M., et al. “AI doctor learns optimal treatment strategies for sepsis in intensive care”. Nat Med 24 (2018): 1716-1720.
29. HL7 International. DSTU updates.
30. HL7 International. Welcome to FHIR.
31. 21st Century Cures Act: Interoperability, information blocking, and the ONC Health IT Certification Program. Fed Regist 85 (2020): 25642-961.
32. Jung CY, Sward KA and Haug PJ. “Executing medical logic modules expressed in ArdenML using Drools”. J Am Med Inform Assoc 19.4 (2012): 533-6.
33. Q Mao., et al. “Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU”. BMJ Open 8.1 (2018): e017833.
34. Bernardo Chávez P., et al. SUB-PROJECT: “Monitoring with command and control panels for the centralized management of data in critical patients, which guarantees the safety and quality of services, with a robust, interoperable and resilient platform of Artificial Intelligence and Machine Learning, at the Hospital El Salvador, Santiago de Chile”. International Conference on Biomedical and Health Informatics 2022. IFMBE Proceedings. (2022).

Citation

Bernardo Chávez P., et al. “Data Sources for use in a Healthcare Interoperability Resources (HL7-FHIR) Platform. A Decision Guide for Clinicians and Data Scientists in Public ICUs". Clareus Scientific Medical Sciences 1.1 (2024): 35-42.

Copyright

2024 Bernardo Chávez P., et al. Licensee Clareus Scientific Publications. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.