EUVIMEDEUVIMED entdecken
Multizentrische StudieValidierungsstudie

Development and Validation of Machine Learning Models to Optimize Imaging and Referrals for Dizziness in the Emergency Department

Danielle Carole Roy, David Savage iD, Saswata Deb, Salimur Choudhury, Robert Ohle iD

Academic Emergency Medicine · 2026-07 · 33 (7)

DOI: 10.1111/acem.70369 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Academic Emergency Medicine, online erschienen am 01.07.2026. Verfasst von Danielle Carole Roy und 4 weiteren Autor:innen. Beteiligte Einrichtung: Health Sciences North Research Institute, Sudbury, Ontario, Canada. Hauptthemen laut MEDLINE: Emergency Service, Hospital, Dizziness, Referral and Consultation, Machine Learning. Die Arbeit nennt 40 Literaturangaben. Gefördert von: Northern Ontario Academic Medicine Association (NOAMA).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Dizziness and vertigo are common emergency department (ED) presentations, but only 2%–5% receive a serious diagnosis, such as stroke or transient ischemic attack (TIA). Due to the lack of reliable validated prediction tools, many undergo unnecessary imaging and consultations, highlighting the need for improved risk stratification.

Objective

To develop machine learning (ML) models that predict serious diagnoses in ED patients presenting with dizziness or vertigo.

Methods

This multicenter cohort study included 6637 ED patients with dizziness, vertigo, or imbalance from September 2014–December 2022. The primary outcome was a serious diagnosis—stroke, TIA, vertebral artery dissection, or brain tumor—within 30 days, adjudicated by a blinded committee. Data were split 80/20 into training and test sets. Four ML models (decision tree, LASSO logistic regression, random forest, XGBoost) were trained on 17 variables using 5‐fold cross‐validation and evaluated alongside the Sudbury Vertigo Risk score. Performance was assessed using area under the curve (AUC) and diagnostic accuracy measures. Computed tomography (CT) and referral rates were hypothetically compared pre‐ and post‐model application.

Results

Among 6637 patients (mean age 78.1; 57.8% female), 3.3% had a serious diagnosis. All ML models demonstrated strong discrimination, with AUCs ranging from 0.92 to 0.97. At a 5% predicted probability threshold, sensitivities ranged from 53%–97% and specificities from 84% to 96%. Logistic regression with LASSO demonstrated a favorable balance between discrimination (AUC: 0.97, sensitivity: 97% and specificity: 91%), although confidence intervals overlapped substantially across models. In a hypothetical model‐based analysis, ML‐guided classification corresponded to projected reductions in CT utilization and referrals ranging from 53%–85% and 11%–73%, respectively.

Conclusions

Select ML models demonstrated discrimination comparable to the Sudbury Vertigo Risk Score while potentially improving specificity and reducing projected resource utilization. These tools show promise, but external validation is needed.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Emergency Service, HospitalDizzinessReferral and ConsultationMachine LearningHumansFemaleMalePredictive Learning ModelsMiddle AgedStrokeAgedIschemic Attack, TransientVertigoBoosting Machine Learning AlgorithmsTomography, X-Ray ComputedRisk AssessmentVertebral Artery DissectionRandom ForestCohort StudiesClassification AlgorithmsLogistic ModelsEmergency Room Visits

Stichwörter der Autor:innen

dizzinessemergency departmentmachine learningpredictionstrokevertigo

Autor:innen und Institutionen

  • Health Sciences North Research Institute, Sudbury, Ontario, Canada.
  • Northern Ontario School of Medicine, Thunder Bay, Ontario, Canada.
  • Department of Emergency Medicine & Sunnybrook Research Institute, Sunnybrook Health Sciences Centre, Temerty Faculty of Medicine, University of Toronto, Toronto, Ontario, Canada.
  • Queens School of Computing, Queens University, Kingston, Ontario, Canada.

ORCID-Profile: David Savage, Robert Ohle

Förderung

  • Northern Ontario Academic Medicine Association (NOAMA)

Zitieren

APA

Roy, D. C., Savage, D., Deb, S., Choudhury, S., & Ohle, R. (2026). Development and Validation of Machine Learning Models to Optimize Imaging and Referrals for Dizziness in the Emergency Department. Academic Emergency Medicine, 33(7). https://doi.org/10.1111/acem.70369

Vancouver

Roy DC, Savage D, Deb S, Choudhury S, Ohle R. Development and Validation of Machine Learning Models to Optimize Imaging and Referrals for Dizziness in the Emergency Department. Academic Emergency Medicine. 2026;33(7). doi:10.1111/acem.70369

BibTeX
@article{Roy2026,
  author = {Roy, Danielle Carole and Savage, David and Deb, Saswata and Choudhury, Salimur and Ohle, Robert},
  title = {Development and Validation of Machine Learning Models to Optimize Imaging and Referrals for Dizziness in the Emergency Department},
  journal = {Academic Emergency Medicine},
  year = {2026},
  volume = {33},
  number = {7},
  doi = {10.1111/acem.70369}
}
Kostenlos starten →