Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

BedreFlyt: Improving Patient Flows through Hospital Wards with Digital Twins

Riccardo Sieve, Paul Kobialka, Laura Slaughter, Rudolf Schlatte, Einar Broch Johnsen, Silvia Lizeth Tapia Tarifa

TL;DR

The paper addresses efficient hospital ward bed allocation under dynamic patient inflow by proposing BedreFlyt, a digital twin that combines an ontology-driven knowledge base, an executable ABS model for scenario exploration, and an SMT solver (via Z3) orchestrated by SMOL. This architecture enables what-if scenario analysis for both short-term decisions and long-term planning, mapping streams of arriving patients to optimization problems and producing day-by-day bed allocation schedules that respect constraints such as bed-bay categories, contagion status, and gender. The authors implement a prototype and validate it with realistic data and synthetic scalability experiments, demonstrating feasibility for day-by-day planning up to thousands of patients while maintaining modularity and extensibility for future enhancements like online learning and multi-ward integration. The work provides a concrete, configurable framework that bridges knowledge representation, executable modeling, and constraint solving to improve hospital resource management and workflow efficiency. Practical impact includes reduced manual workload, improved bed utilization, and support for adaptive planning in dynamic hospital environments.

Abstract

Digital twins are emerging as a valuable tool for short-term decision-making as well as for long-term strategic planning across numerous domains, including process industry, energy, space, transport, and healthcare. This paper reports on our ongoing work on designing a digital twin to enhance resource planning, e.g., for the in-patient ward needs in hospitals. By leveraging executable formal models for system exploration, ontologies for knowledge representation and an SMT solver for constraint satisfiability, our approach aims to explore hypothetical "what-if" scenarios to improve strategic planning processes, as well as to solve concrete, short-term decision-making tasks. Our proposed solution uses the executable formal model to turn a stream of arriving patients, that need to be hospitalized, into a stream of optimization problems, e.g., capturing daily inpatient ward needs, that can be solved by SMT techniques. The knowledge base, which formalizes domain knowledge, is used to model the needed configuration in the digital twin, allowing the twin to support both short-term decision-making and long-term strategic planning by generating scenarios spanning average-case as well as worst-case resource needs, depending on the expected treatment of patients, as well as ranging over variations in available resources, e.g., bed distribution in different rooms. We illustrate our digital twin architecture by considering the problem of bed bay allocation in a hospital ward.

BedreFlyt: Improving Patient Flows through Hospital Wards with Digital Twins

TL;DR

The paper addresses efficient hospital ward bed allocation under dynamic patient inflow by proposing BedreFlyt, a digital twin that combines an ontology-driven knowledge base, an executable ABS model for scenario exploration, and an SMT solver (via Z3) orchestrated by SMOL. This architecture enables what-if scenario analysis for both short-term decisions and long-term planning, mapping streams of arriving patients to optimization problems and producing day-by-day bed allocation schedules that respect constraints such as bed-bay categories, contagion status, and gender. The authors implement a prototype and validate it with realistic data and synthetic scalability experiments, demonstrating feasibility for day-by-day planning up to thousands of patients while maintaining modularity and extensibility for future enhancements like online learning and multi-ward integration. The work provides a concrete, configurable framework that bridges knowledge representation, executable modeling, and constraint solving to improve hospital resource management and workflow efficiency. Practical impact includes reduced manual workload, improved bed utilization, and support for adaptive planning in dynamic hospital environments.

Abstract

Digital twins are emerging as a valuable tool for short-term decision-making as well as for long-term strategic planning across numerous domains, including process industry, energy, space, transport, and healthcare. This paper reports on our ongoing work on designing a digital twin to enhance resource planning, e.g., for the in-patient ward needs in hospitals. By leveraging executable formal models for system exploration, ontologies for knowledge representation and an SMT solver for constraint satisfiability, our approach aims to explore hypothetical "what-if" scenarios to improve strategic planning processes, as well as to solve concrete, short-term decision-making tasks. Our proposed solution uses the executable formal model to turn a stream of arriving patients, that need to be hospitalized, into a stream of optimization problems, e.g., capturing daily inpatient ward needs, that can be solved by SMT techniques. The knowledge base, which formalizes domain knowledge, is used to model the needed configuration in the digital twin, allowing the twin to support both short-term decision-making and long-term strategic planning by generating scenarios spanning average-case as well as worst-case resource needs, depending on the expected treatment of patients, as well as ranging over variations in available resources, e.g., bed distribution in different rooms. We illustrate our digital twin architecture by considering the problem of bed bay allocation in a hospital ward.
Paper Structure (16 sections, 2 equations, 4 figures)

This paper contains 16 sections, 2 equations, 4 figures.

Table of Contents

  1. Introduction
  2. Motivating Scenario
  3. Background and Related Work
  4. Approach
  5. Knowledge Modeling with Ontologies
  6. Scenario Simulation with ABS
  7. SMT Solver
  8. Implementation
  9. Data processing phase.
  10. Resource requirement phase.
  11. Constraint solver phase.
  12. Output.
  13. Evaluation
  14. A Realistic Hospital Scenario
  15. Synthetic Scalability of the Hospital Scenario
  16. ...and 1 more sections

Figures (4)

  • Figure 1: Example of a hospital ward.
  • Figure 2: Architecture of the DT, where the arrows indicate the flow of data.
  • Figure 3: Sequence diagram of the bed allocation process in the digital twin.
  • Figure 4: Left: Room allocation in the ward, illustrating a solution from the DT for a given day (males blue, females red). Right: execution times for varying scenarios ($z$-axis, in minutes), ranging over patients ($x$-axis, from $100$ to $2000$ patients) and days ($y$-axis, from $30$ to $365$ days).