EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Two-Step Approach for Occupancy Estimation in Intensive Care Units Based on Bayesian Optimization Techniques

José A González-Nóvoa iD, Laura Busto iD, Silvia Campanioni iD, José Fariña iD, Juan J Rodríguez-Andina iD, Dolores Vila, César Veiga iD

Sensors · 2023

DOI: 10.3390/s23031162 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von José A González-Nóvoa und 6 weiteren Autor:innen. Beteiligte Einrichtung: Galicia Sur Health Research Institute (IIS Galicia Sur), Álvaro Cunqueiro Hospital, 36310 Vigo, Spain. Hauptthemen laut MEDLINE: Artificial Intelligence, Intensive Care Units. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Axencia Galega de Innovacion, Agencia Gallega de Innovación (GAIN).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Due to the high occupational pressure suffered by intensive care units (ICUs), a correct estimation of the patients’ length of stay (LoS) in the ICU is of great interest to predict possible situations of collapse, to help healthcare personnel to select appropriate treatment options and to predict patients’ conditions. There has been a high amount of data collected by biomedical sensors during the continuous monitoring process of patients in the ICU, so the use of artificial intelligence techniques in automatic LoS estimation would improve patients’ care and facilitate the work of healthcare personnel. In this work, a novel methodology to estimate the LoS using data of the first 24 h in the ICU is presented. To achieve this, XGBoost, one of the most popular and efficient state-of-the-art algorithms, is used as an estimator model, and its performance is optimized both from computational and precision viewpoints using Bayesian techniques. For this optimization, a novel two-step approach is presented. The methodology was carefully designed to execute codes on a high-performance computing system based on graphics processing units, which considerably reduces the execution time. The algorithm scalability is analyzed. With the proposed methodology, the best set of XGBoost hyperparameters are identified, estimating LoS with a MAE of 2.529 days, improving the results reported in the current state of the art and probing the validity and utility of the proposed approach.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceIntensive Care UnitsHumansBayes TheoremAlgorithmsComputing Methodologies

Stichwörter der Autor:innen

Bayesian optimizationICU occupancyMIMICXGBoostartificial intelligenceautomated machine learningintensive care unitlength of staymachine learning

Autor:innen und Institutionen

  • Galicia Sur Health Research Institute (IIS Galicia Sur), Álvaro Cunqueiro Hospital, 36310 Vigo, Spain.
  • Department of Electronic Technology, University of Vigo, 36310 Vigo, Spain.
  • Intensive Care Unit Department, Complexo Hospitalario Universitario de Vigo (SERGAS), Álvaro Cunqueiro Hospital, 36213 Vigo, Spain.

ORCID-Profile: José A González-Nóvoa, Laura Busto, Silvia Campanioni, José Fariña, Juan J Rodríguez-Andina, César Veiga

Förderung

  • Axencia Galega de Innovacion
  • Agencia Gallega de Innovación (GAIN)

Zitieren

APA

González-Nóvoa, J. A., Busto, L., Campanioni, S., Fariña, J., Rodríguez-Andina, J. J., Vila, D., & Veiga, C. (2023). Two-Step Approach for Occupancy Estimation in Intensive Care Units Based on Bayesian Optimization Techniques. Sensors. https://doi.org/10.3390/s23031162

Vancouver

González-Nóvoa JA, Busto L, Campanioni S, Fariña J, Rodríguez-Andina JJ, Vila D, et al. Two-Step Approach for Occupancy Estimation in Intensive Care Units Based on Bayesian Optimization Techniques. Sensors. 2023. doi:10.3390/s23031162

BibTeX
@article{GonzlezNvoa2023,
  author = {González-Nóvoa, José A and Busto, Laura and Campanioni, Silvia and Fariña, José and Rodríguez-Andina, Juan J and Vila, Dolores and Veiga, César},
  title = {Two-Step Approach for Occupancy Estimation in Intensive Care Units Based on Bayesian Optimization Techniques},
  journal = {Sensors},
  year = {2023},
  doi = {10.3390/s23031162}
}
Kostenlos starten →