EUVIMEDEUVIMED entdecken
Crossref

Exploring explainable machine learning techniques to aid dysphagia risk identification: A feasibility study

Melanie L McIntyre, Yuxi Liu, Joanne Murray, Shaowen Qin, Timothy Chimunda, Sebastian H Doeltgen

Australian Critical Care · 2025

DOI: 10.1016/j.aucc.2025.101307 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Australian Critical Care, 2025. Verfasst von Melanie L McIntyre und 5 weiteren Autor:innen. Beteiligte Einrichtung: Swallowing Neurorehabilitation Research Lab, Caring Futures Institute, College of Nursing and Health Sciences, Flinders University, GPO Box 2100, Ade…. Hauptthemen laut MEDLINE: Deglutition Disorders, Machine Learning, Intubation, Intratracheal. Die Arbeit nennt 43 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Machine learning offers opportunities to identify complex risk patterns in large data sets. We explored the methodological feasibility, and proof of concept, of applying machine learning techniques to dysphagia (swallowing difficulty) risk identification for adult patients who required endotracheal intubation within an intensive care unit (ICU). AIM: The aim of this study was to explore the methodological feasibility and proof of concept of developing machine learning models for dysphagia risk identification for adult patients who required endotracheal intubation within an ICU. METHODS: In this cohort study, two large healthcare databases were linked using deterministic logic. All participants received invasive mechanical ventilation in an ICU. Several machine learning model candidates were explored. Insights into the model decision-making have been provided using SHapley Additive exPlanation values. RESULTS: A total of 59 811 patients from 42 sites were included in the study. The top five most influential factors in determining the presence or absence of dysphagia at a cohort level were duration of mechanical ventilation, age, cardiac admission, neurological admission, and Acute Physiology and Chronic Health Evaluation III score. CONCLUSION: There is a promising prospect of machine learning in dynamic dysphagia risk screening, which we propose should be considered for clinical use in the future. The patient-specific influence of each risk factor in determining the presence or absence of dysphagia highlights the importance of determining risk based on the individual patient's unique combination of risk factors, and not on cohort means, as has been done previously.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deglutition DisordersMachine LearningIntubation, IntratrachealHumansFeasibility StudiesMaleFemaleMiddle AgedAgedRisk AssessmentIntensive Care UnitsRespiration, ArtificialRisk FactorsCohort StudiesAdult

Stichwörter der Autor:innen

Artificial intelligenceCritically ill patientDysphagiaMachine learningMechanical ventilation

Autor:innen und Institutionen

  • Swallowing Neurorehabilitation Research Lab, Caring Futures Institute, College of Nursing and Health Sciences, Flinders University, GPO Box 2100, Adelaide, SA, 5001, Australia; Bendigo Health, Department of Speech Patho…
  • Biostatistics and Health Data Science, School of Medicine, Indiana University, Indianapolis, IN, 46202 United States.
  • Swallowing Neurorehabilitation Research Lab, Caring Futures Institute, College of Nursing and Health Sciences, Flinders University, GPO Box 2100, Adelaide, SA, 5001, Australia.
  • College of Science Engineering, Flinders University, GPO Box 2100, Adelaide, SA, 5001, Australia.
  • University of Melbourne, Grattan Street, Parkville, VIC, 3010, Australia; University of Queensland, St Lucia, QLD, 4072, Australia; Department of Intensive Care Medicine, Northern Health, Melbourne, VIC, 3076, Australia.

Zitieren

APA

McIntyre, M. L., Liu, Y., Murray, J., Qin, S., Chimunda, T., & Doeltgen, S. H. (2025). Exploring explainable machine learning techniques to aid dysphagia risk identification: A feasibility study. Australian Critical Care. https://doi.org/10.1016/j.aucc.2025.101307

Vancouver

McIntyre ML, Liu Y, Murray J, Qin S, Chimunda T, Doeltgen SH. Exploring explainable machine learning techniques to aid dysphagia risk identification: A feasibility study. Australian Critical Care. 2025. doi:10.1016/j.aucc.2025.101307

BibTeX
@article{McIntyre2025,
  author = {McIntyre, Melanie L and Liu, Yuxi and Murray, Joanne and Qin, Shaowen and Chimunda, Timothy and Doeltgen, Sebastian H},
  title = {Exploring explainable machine learning techniques to aid dysphagia risk identification: A feasibility study},
  journal = {Australian Critical Care},
  year = {2025},
  doi = {10.1016/j.aucc.2025.101307}
}
Kostenlos starten →