A bayesian approach for the continuous monitoring of the prediction of the physiological evolution of a crisis victim: A decision support system

Abstract

Catastrophic events like earthquakes demand innovative tools for crisis management. Mathematical modeling and decision support systems (DSSs) have proved crucial for understanding, predicting and mitigating disaster impact. The quantification of complex phenomena through probabilistic models, to estimate the likelihood of events, provides actionable insights that are essential for disaster risk reduction (DRR).

The present work stems from research conducted within the framework of the Search & Rescue (S&R) project (H2020-SU-SEC-2019), in particular from the development of the PHYSIO DSS module, the medical component of the S&R Decision Support System (DSS). The PHYSIO DSS focuses on predicting the physiological evolution of crisis victims: using a Bayesian approach, it incorporates real-time field observations to forecast patient conditions. This enables the prediction of the evolution of physiological compensation, allowing efficient resource allocation and timely interventions. By providing real-time insights into victim severity, PHYSIO DSS empowers medical personnel to prioritize treatment, potentially saving lives. Its adaptability allows integration into different platforms, from crisis management systems to apps to personal health devices.

This tool has the potential to substantially enhance emergency response capability and overall disaster resilience by offering real-time, data-driven decision support.