Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: Journal of Medical Internet Research

Date Submitted: Oct 12, 2021
Date Accepted: Jun 13, 2022

The final, peer-reviewed published version of this preprint can be found here:

A Questionnaire-Based Ensemble Learning Model to Predict the Diagnosis of Vertigo: Model Development and Validation Study

Yu F, Wu P, Deng H, Wu J, Sun S, Yu H, Yang J, Luo X, He J, Ma X, Wen J, Qiu D, Nie G, Liu R, Hu G, Chen T, Zhang C, Li H

A Questionnaire-Based Ensemble Learning Model to Predict the Diagnosis of Vertigo: Model Development and Validation Study

J Med Internet Res 2022;24(8):e34126

DOI: 10.2196/34126

PMID: 35921135

PMCID: 9386585

A questionnaire-based ensemble learning model to predict the diagnosis of vertigo: model development and validation study

  • Fangzhou Yu; 
  • Peixia Wu; 
  • Haowen Deng; 
  • Jingfang Wu; 
  • Shan Sun; 
  • Huiqian Yu; 
  • Jianming Yang; 
  • Xianyang Luo; 
  • Jing He; 
  • Xiulan Ma; 
  • Junxiong Wen; 
  • Danhong Qiu; 
  • Guohui Nie; 
  • Rizhao Liu; 
  • Guohua Hu; 
  • Tao Chen; 
  • Cheng Zhang; 
  • Huawei Li

ABSTRACT

Background:

Questionnaires have been used to predict the diagnosis of vertigo and assist clinical decision making. A questionnaire-based machine learning model is expected to improve the diagnostic efficiency of vestibular disorders.

Objective:

To develop and validate a questionnaire-based machine learning model that predicts the diagnosis of vertigo.

Methods:

In this multicenter prospective study, patients presented with vertigo entered a consecutive cohort at their first visit to the ENT and vertigo clinics of 7 tertiary referral centers from August 2019 to March 2021, with a follow-up period of 2 months. All participants completed a diagnostic questionnaire after eligibility screening. Participants who received only one final diagnosis by their treating specialists for their primary complaint were included in model development and validation. Data of patients enrolled before Feburary 1, 2021 were used for modeling and cross validation, while patients enrolled afterwards entered external validation.

Results:

A total of 1693 patients were enrolled, with a response rate of 96%. The median age was 51 years (interquartile range, 38 to 61) with 991 (58.5%) female. 1041 (61.5%) patients were included in model development and validation, and classified into 5 diagnostic categories. We compared 9 candidate machine learning methods, and the recalibrated model of light gradient boosting machine achieved the best performance, with an area under the curve of 0.937 (95% confidence interval, 0.917-0.962) in cross validation and 0.954 (95% confidence interval, 0.944-0.967) in external validation.

Conclusions:

The questionnaire-based light gradient boosting machine was able to predict common vestibular disorders and assist decision making in ENT and vertigo clinics. Further study with lager sample size and the participation of neurology specialists will help assess its generalization and robustness. Clinical Trial: Name: Design and application of Otogenic Vertigo AI Recognition (OVerAIR) registration number: No. ChiCTR2000032904 URL: https://www.chictr.org.cn/showproj.aspx?proj=53595


 Citation

Please cite as:

Yu F, Wu P, Deng H, Wu J, Sun S, Yu H, Yang J, Luo X, He J, Ma X, Wen J, Qiu D, Nie G, Liu R, Hu G, Chen T, Zhang C, Li H

A Questionnaire-Based Ensemble Learning Model to Predict the Diagnosis of Vertigo: Model Development and Validation Study

J Med Internet Res 2022;24(8):e34126

DOI: 10.2196/34126

PMID: 35921135

PMCID: 9386585

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.