Simulation systems

In-development

This documentation is currently in-development. Please visit again soon, this section is actively updated.

Modern approaches with computational statistics are promising powerful methods to define and create probabilistic systems, particularly systems that can represent statistical models of states under a variety of conditions and constraints, and are capable of sampling new data from these states by the generative nature of these models. For the HeartAI deployments within SAVCS, the primary approach to these simulation models considers inference from a Bayesian perspective, such as by generating samples from a prior or posterior predictive distribution, where there may also be a conditioning or marginalisation of such a distribution. In addition to the creating of a representative simulation construct, these models may be used for the generation of new data under a variety of assumptions and hypothetical situations, and also for the prediction and forecasting of future events and potential outcomes.

Platform: Analytical capabilities

Further information about HeartAI analytical capabilities may be found with the following documentation:

Simulation benefits

Simulation systems provide supporting services to SAVCS through several key benefits:

  • Creating a reproducible and safe framework for the development of software and supporting systems.
  • Allowing the generation of data and information of a direct or similar nature, and providing approaches to generation with a variety of conditions or constraints.
  • Providing systems and tools for the investigation of SAVCS information and operations under specifiable hypothetical assumptions.
  • Supporting statistical modelling and predictive forecasting.

SAVCS simulation contexts

Within the context of SAVCS, simulation capabilities are useful for many clinical and operational purposes:

  • Generative modelling and forecasting of SAVCS service metrics such as:
    • Admissions to the service, including seasonal and potentially autoregressive factors.
    • The cohort of patients of the service, including:
      • Patient age.
      • Patient gender.
      • Primary complaint.
      • Admission acuity.
    • The primary outcome of service admissions.
    • The length of time of service admissions.
    • Any other informative considerations.
  • Service-level predictive capabilities:
    • The ability to predict future admissions.
    • The ability to predict patient length-of-stay.
    • The ability to predict patient primary outcome.