ORAHS2024
Abstract Submission

225. Using Data-Driven Models for Critical Care Decision Support

Contributed abstract in session TA-3: Healthcare Logistics /1, stream Regular talks.

Tuesday, 9:00-10:30
Room: Room S2

Authors (first author is the speaker)

1. Daniel García-Vicuña
Department of Statistic, IT and Mathematics, Public University of Navarre
2. Ana María Anaya-Arenas
Université du Québec à Montréal
3. Janosch Ortmann
GERAD, CRM and UQAM
4. Angel Ruiz
Opérations et systèmes de décision, Université Laval
5. Fermin Mallor
Institute of Smart Cities, Public University of Navarre

Abstract

The dilemma of the last available bed highlights the lack of ICU beds and the difficult decisions hospitals must make when resources are limited. With a surge in demand, hospitals are often compelled to prioritize patients, leading to the postponement of surgeries or premature discharges. Such actions, while necessary, pose significant logistical challenges in ensuring that all patients receive the necessary level of care. Effective management of hospital beds becomes paramount in optimizing patient treatment, particularly during times of healthcare crises.
To address this challenge, this study endeavors to develop innovative methodologies utilizing real patient data. These methodologies aim to provide healthcare professionals with valuable insights for making informed decisions regarding resource allocation and capacity planning. By leveraging a comprehensive set of patient characteristics and medical history, we seek to predict the length of stay for patients in the ICU. This predictive modeling approach enables us to anticipate patient needs more accurately and allocate resources more effectively.
By illustrating our findings with real-world data and simulations, we aim to demonstrate the practical utility of these methodologies. Our goal is to empower healthcare professionals with tools that can enhance decision-making processes, ultimately improving patient outcomes and optimizing resource utilization in healthcare services.

Keywords

Status: accepted

Back to the list of papers