Decision-making process analysis in intensive care units under high occupancy conditions
Decision-making in Intensive Care Units (ICUs) is a complex and dynamic process that directly influences patient outcomes and resource allocation. While existing studies focus on individual admission decisions based on clinical or ethical criteria, they often overlook the collective impact of these...
| Autores: | , , |
|---|---|
| Tipo de recurso: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2026 |
| País: | España |
| Institución: | Universidad Pública de Navarra |
| Repositorio: | Academica-e. Repositorio Institucional de la Universidad Pública de Navarra |
| OAI Identifier: | oai:academica-e.unavarra.es:2454/56234 |
| Acceso en línea: | https://hdl.handle.net/2454/56234 |
| Access Level: | acceso abierto |
| Palabra clave: | ICU Decision-making Data-driven Decision analysis Patient flow Bed allocation |
| Sumario: | Decision-making in Intensive Care Units (ICUs) is a complex and dynamic process that directly influences patient outcomes and resource allocation. While existing studies focus on individual admission decisions based on clinical or ethical criteria, they often overlook the collective impact of these choices in high-occupancy scenarios, where bed allocation must balance individual needs with system-wide constraints. This study introduces a novel methodology for analysing ICU decision-making process, characterizing different management styles through control mechanisms such as patient transfers, surgery cancellations, and length-of-stay adjustments. A multi-perspective analysis examines ICU decision-making, from the global use of control mechanisms to their application under different occupancy levels and the types of patients affected. Specific metrics quantify differences between ICU managers¿ decisions over time; among these, we introduce a novel metric based on the Hamming distance to measure differences between binary matrices. This methodology is illustrated through an empirical study of admission and discharge decisions made by healthcare professionals from different categories (e.g., physicians, nurses) over three weeks. Data was collected using an interactive ICU simulator, developed with an ICU medical team, capturing real-time decision dynamics under varying operational conditions. Our findings highlight a lack of standardization in ICU management decisions, raising the question of whether collective-level admission and discharge protocols should complement existing individual-based guidelines. This study provides a dynamic and data-driven perspective on ICU operations, offering insights that can inform both policy design and clinical decision support systems to enhance efficiency, consistency, and patient care. |
|---|