Display options
Cite
Kaufmann T, Castela Forte J, Hiemstra B, et al. A Bayesian Network Analysis of the Diagnostic Process and Its Accuracy to Determine How Clinicians Estimate Cardiac Function in Critically Ill Patients: Prospective Observational Cohort Study. JMIR Med Inform. 2019;7(4):e15358doi: 10.2196/15358.
Kaufmann, T., Castela Forte, J., Hiemstra, B., Wiering, M. A., Grzegorczyk, M., Epema, A. H., van der Horst, I. C. C. (2019). A Bayesian Network Analysis of the Diagnostic Process and Its Accuracy to Determine How Clinicians Estimate Cardiac Function in Critically Ill Patients: Prospective Observational Cohort Study. JMIR medical informatics, 7(4), e15358. https://doi.org/10.2196/15358
Kaufmann, Thomas, et al. "A Bayesian Network Analysis of the Diagnostic Process and Its Accuracy to Determine How Clinicians Estimate Cardiac Function in Critically Ill Patients: Prospective Observational Cohort Study." JMIR medical informatics vol. 7,4 (2019): e15358. doi: https://doi.org/10.2196/15358
Kaufmann T, Castela Forte J, Hiemstra B, Wiering MA, Grzegorczyk M, Epema AH, van der Horst ICC. A Bayesian Network Analysis of the Diagnostic Process and Its Accuracy to Determine How Clinicians Estimate Cardiac Function in Critically Ill Patients: Prospective Observational Cohort Study. JMIR Med Inform. 2019 Oct 30;7(4):e15358. doi: 10.2196/15358. PMID: 31670697; PMCID: PMC6913745.
Copy Download .nbib Format: NLM
Share it on

JMIR Med Inform. 2019 Oct 30;7(4):e15358. doi: 10.2196/15358.

A Bayesian Network Analysis of the Diagnostic Process and Its Accuracy to Determine How Clinicians Estimate Cardiac Function in Critically Ill Patients: Prospective Observational Cohort Study.

JMIR medical informatics

Thomas Kaufmann, José Castela Forte, Bart Hiemstra, Marco A Wiering, Marco Grzegorczyk, Anne H Epema, Iwan C C van der Horst,

Affiliations

  1. Department of Anesthesiology, University Medical Center Groningen, University of Groningen, Groningen, Netherlands.
  2. Department of Critical Care, University Medical Center Groningen, University of Groningen, Groningen, Netherlands.
  3. Department of Clinical Pharmacology, University Medical Center Groningen, University of Groningen, Groningen, Netherlands.
  4. Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, Groningen, Netherlands.
  5. Department of Intensive Care, Maastricht University Medical Center+, Maastricht University, Maastricht, Netherlands.

PMID: 31670697 PMCID: PMC6913745 DOI: 10.2196/15358

Abstract

BACKGROUND: Hemodynamic assessment of critically ill patients is a challenging endeavor, and advanced monitoring techniques are often required to guide treatment choices. Given the technical complexity and occasional unavailability of these techniques, estimation of cardiac function based on clinical examination is valuable for critical care physicians to diagnose circulatory shock. Yet, the lack of knowledge on how to best conduct and teach the clinical examination to estimate cardiac function has reduced its accuracy to almost that of "flipping a coin."

OBJECTIVE: The aim of this study was to investigate the decision-making process underlying estimates of cardiac function of patients acutely admitted to the intensive care unit (ICU) based on current standardized clinical examination using Bayesian methods.

METHODS: Patient data were collected as part of the Simple Intensive Care Studies-I (SICS-I) prospective cohort study. All adult patients consecutively admitted to the ICU with an expected stay longer than 24 hours were included, for whom clinical examination was conducted and cardiac function was estimated. Using these data, first, the probabilistic dependencies between the examiners' estimates and the set of clinically measured variables upon which these rely were analyzed using a Bayesian network. Second, the accuracy of cardiac function estimates was assessed by comparison to the cardiac index values measured by critical care ultrasonography.

RESULTS: A total of 1075 patients were included, of which 783 patients had validated cardiac index measurements. A Bayesian network analysis identified two clinical variables upon which cardiac function estimate is conditionally dependent, namely, noradrenaline administration and presence of delayed capillary refill time or mottling. When the patient received noradrenaline, the probability of cardiac function being estimated as reasonable or good P(E

CONCLUSIONS: The conditional dependencies between clinical variables and the cardiac function estimates resulted in a network consistent with known physiological relations. Conditional probability queries allow for multiple clinical scenarios to be recreated, which provide insight into the possible thought process underlying the examiners' cardiac function estimates. This information can help develop interactive digital training tools for students and physicians and contribute toward the goal of further improving the diagnostic accuracy of clinical examination in ICU patients.

TRIAL REGISTRATION: ClinicalTrials.gov NCT02912624; https://clinicaltrials.gov/ct2/show/NCT02912624.

©Thomas Kaufmann, José Castela Forte, Bart Hiemstra, Marco A Wiering, Marco Grzegorczyk, Anne H Epema, Iwan C C van der Horst, SICS Study Group. Originally published in JMIR Medical Informatics (http://medinform.jmir.org), 30.10.2019.

Keywords: Bayesian network; ICU; cardiac function; cardiology; clinical decision-support; cognition; critical care; educated guess; medical education; physical examination

References

  1. Am J Cardiol. 1977 Feb;39(2):137-45 - PubMed
  2. J Clin Monit Comput. 2016 Oct;30(5):511-8 - PubMed
  3. Br J Radiol. 2010 Nov;83(995):904-14 - PubMed
  4. JAMA Netw Open. 2019 Mar 1;2(3):e190096 - PubMed
  5. Crit Care Med. 2006 Mar;34(3):589-97 - PubMed
  6. BMC Bioinformatics. 2011 Mar 17;12:77 - PubMed
  7. Curr Opin Crit Care. 2017 Aug;23(4):326-333 - PubMed
  8. Curr Opin Crit Care. 2017 Aug;23(4):293-301 - PubMed
  9. BMJ. 2016 Jul 27;354:i3309 - PubMed
  10. Semin Respir Crit Care Med. 2015 Dec;36(6):890-8 - PubMed
  11. BMJ. 2015 Oct 28;351:h5527 - PubMed
  12. BMC Med Inform Decis Mak. 2016 Nov 3;16(1):138 - PubMed
  13. Med Educ. 2017 Nov;51(11):1127-1137 - PubMed
  14. J Biomed Inform. 2010 Apr;43(2):273-86 - PubMed
  15. Intensive Care Med. 2019 Feb;45(2):190-200 - PubMed
  16. Curr Opin Crit Care. 2009 Jun;15(3):234-8 - PubMed
  17. BMC Med Inform Decis Mak. 2017 Jun 28;17(1):93 - PubMed
  18. Intensive Care Med. 2014 Dec;40(12):1795-815 - PubMed
  19. N Engl J Med. 2013 Oct 31;369(18):1726-34 - PubMed
  20. Crit Care. 2016 Dec 20;20(1):401 - PubMed
  21. Sci Rep. 2017 Nov 10;7(1):15236 - PubMed
  22. Proc Natl Acad Sci U S A. 2008 Sep 23;105(38):14313-8 - PubMed

Publication Types