Expert-in-Loop Digital Twin-based Decision Support System for Early Detection of Ventilator-Induced Lung Injury

Abstract

Mechanical ventilation has been a critical life support mechanism for patients with severe traumatic brain injuries (TBI) for decades. While lifesaving, mechanical ventilation has drawbacks, including the risk of complications such as Ventilator-Induced Lung Injury (VILI). This paper focuses on Ventilator-Associated Pneumonia (VAP), a significant complication that can adversely affect patient health and extend the duration of ventilation, thereby increasing the cost of critical care. To address this issue, we propose a novel Decision Support System (DSS) framework for the early detection of VAP, utilizing Digital Twin technology and the expertise of healthcare professionals. The framework is aligned with ISO-23247, with the addition of two new functional entities: a Learning Module and a Rule-Based System. Early detection of VILI through this DSS framework can significantly reduce weaning time, enhancing the affordability and accessibility of critical care. The framework offers real-time tracking and detection of patient conditions, enabling timely interventions and personalized treatment, which ultimately improves patient outcomes and optimizes resource utilization in critical care. This integration of Digital Twin technology and clinical expertise introduces a crucial advancement in critical care facilities in the context of today's AI-driven healthcare landscape. © 2024 The Authors.