Between prediction, education, and quality control: simulation models in critical care

Simulation Training in Hemodynamic Monitoring and Mechanical Ventilation: An Assessment of Physician's Performance

Background

Simulation is to imitate or replicate real-life scenarios in order to improve cognitive, diagnostic and therapeutic skills. An ideal model should be good enough to output realistic clinical scenarios and respond to interventions done by trainees in real time. Use of simulation-based training has been tried in various fields of medicine. The aim of our study was to prospectively evaluate the effectiveness of simulation model “CRITICA”™ (MEDUPLAY systems) in training critical care physicians.

Materials and methods

The advanced intensive care unit (ICU) simulator “CRITICA”™ (MEDUPLAY systems) was developed as a joint collaboration between the Indian Institute of Science, Bengaluru and St John’s Medical College, Bengaluru. Two-day workshop was conducted. Intensive didactic and case-based scenarios were simulated to formally teach principles of advanced ICU scenarios. The physicians were tested on clinical scenarios in hemodynamic monitoring and mechanical ventilation displayed on the simulator. Assessment of the analytical thinking and pattern recognition ability was carried out before and after the display of the scenarios. Pre- and posttest scores were collected.

Results

The postsimulation test scores were higher than pretest scores and were statistically significant in hemodynamic monitoring and mechanical ventilation module. [Hemodynamic monitoring pre- and posttest scores 4.41 (2.06) vs 5.23 (2.22) p < 0.001] [Mechanical ventilation pre- and posttest scores 4 (2–5.5) vs 7.5 (6.5–8.5) p < 0.001]. A greater increase in posttest scores was seen in the mechanical ventilation module as compared to hemodynamic module. There was no effect of specialty or designation of a trainee on difference in pre- and posttest scores.

Conclusion

Simulator-based training in hemodynamic monitoring and mechanical ventilation was effective. Comparison of routine classroom teaching and simulator-based training needs to be evaluated prospectively.

How to cite this article

Havaldar AA, Krishna B, Sampath S, Paramasivam SK. Simulation Training in Hemodynamic Monitoring and Mechanical Ventilation: An Assessment of Physician’s Performance. Indian J Crit Care Med 2020;24(6):423–428.

Using hierarchical dynamic Bayesian networks to investigate dynamics of organ failure in patients in the Intensive Care Unit

In intensive care medicine close monitoring of organ failure status is important for the prognosis of patients and for choices regarding ICU management. Major challenges in analyzing the multitude of data pertaining to the functioning of the organ systems over time are to extract meaningful clinical patterns and to provide predictions for the future course of diseases. With their explicit states and probabilistic state transitions, Markov models seem to fit this purpose well. In complex domains such as intensive care a choice is often made between a simple model that is estimated from the data, or a more complex model in which the parameters are provided by domain experts. Our primary aim is to combine these approaches and develop a set of complex Markov models based on clinical data. In this paper we describe the design choices underlying the models, which enable them to identify temporal patterns, predict outcomes, and test clinical hypotheses. Our models are characterized by the choice of the dynamic hierarchical Bayesian network structure and the use of logistic regression equations in estimating the transition probabilities. We demonstrate the induction, inference, evaluation, and use of these models in practice in a case-study of patients with severe sepsis admitted to four Dutch ICUs.