[Paper Review] A Dynamic System Model for Personalized Healthcare Delivery and Managed Individual Health Outcomes

Inas S. Khayal, Amro M. Farid|arXiv (Cornell University)|Oct 17, 2019

Healthcare Operations and Scheduling OptimizationHealth Professions70 references22 citations

TL;DR

This paper proposes a dynamic system model that synchronizes a healthcare delivery system with individual health state evolution using two coupled Petri nets—one for clinical processes and one for health outcomes. It enables personalized care by linking treatment costs and timing to measurable health outcomes in both acute and chronic conditions, demonstrating transparent cost-outcome trade-offs through discrete-event simulation.

ABSTRACT

The current healthcare system is facing an unprecedented chronic disease burden. This paper develops a healthcare dynamic model for personalized healthcare delivery and managed individual health outcomes. It utilizes a hetero-functional graph theory rooted in Axiomatic Design for Large Flexible Engineering Systems and Petri nets. The dynamics of the model builds upon a recently developed systems architecture for healthcare delivery which bears several analogies to the architecture of mass-customized production systems. At its essence, the model consists of two synchronized Petri nets; one for the healthcare delivery system and another for individuals' health state evolution. The model is demonstrated on two clinical case studies; one acute and another chronic. Together, the case studies show that the model applies equally to the care of both acute and chronic conditions, transparently describes health outcomes and links them to the evolution of the healthcare delivery system and its associated costs.

Motivation & Objective

• To develop a dynamic system model that integrates personalized healthcare delivery with individual health outcome management.
• To address the gap in existing models that treat healthcare systems and patient health as separate, static processes.
• To enable real-time coordination between clinical system operations and patient health state evolution for improved care outcomes.
• To quantify the relationship between healthcare delivery costs and individual health outcomes over time.

Proposed method

• The model uses a hetero-functional graph theory rooted in Axiomatic Design and Petri nets to represent system form and function.
• It defines two synchronized Petri nets: one for the healthcare delivery system (with transformation, decision, measurement, and transportation processes) and one for individual health state evolution.
• System resources (e.g., clinicians, imaging, surgery) and processes are formally classified into functional categories (F, D, M, N) with unique assignments.
• The model employs discrete-event simulation to track the firing of transitions in both nets, representing clinical actions and spontaneous health state changes.
• Stochastic processes in the health net simulate spontaneous health changes (e.g., symptom progression), while deterministic transitions represent planned care steps.
• Costs are accumulated per system resource utilization, and outcomes are tracked as health state trajectories, including % healthy over time.

Experimental results

Research questions

• RQ1 How can a dynamic system model effectively link healthcare delivery system operations with individual health state evolution in a synchronized manner?
• RQ2 To what extent can this model support personalized care for both acute and chronic conditions?
• RQ3 What is the quantitative relationship between healthcare delivery system costs and individual health outcomes over time?
• RQ4 How do coordination and timing of clinical processes affect long-term health outcomes in chronic disease management?

Key findings

• The model successfully demonstrates applicability to both acute and chronic care, with the chronic care case showing a 218-day care trajectory involving 49 transitions and $4,500 in cumulative costs.
• In the chronic care case, the individual’s health state remained at 90% healthy for 100 days before declining, with a final outcome of 70% healthy after 219 days.
• The model transparently reveals a cumulative healthcare delivery system operating cost of $4,500 over 219 days in the chronic care example.
• The acute care case shows a rapid cycle of 100 days with 26 transitions and a cost of $2,000, with health state returning to 100% healthy after treatment.
• The model’s dual Petri net structure enables real-time tracking of cost accumulation and health outcome evolution, with time-series data showing cost and outcome trends.
• The model identifies clear trade-offs between system utilization patterns and health outcomes, supporting decision-making for better care coordination.