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: Aug 1, 2023
Date Accepted: Jan 16, 2024

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

Machine Learning–Based Prediction of Suicidality in Adolescents With Allergic Rhinitis: Derivation and Validation in 2 Independent Nationwide Cohorts

Lee H, Cho JK, Park J, Yang H, Fond G, Boyer L, Kim HJ, Park S, Lee J, Cho W, Lee H, Yon DK

Machine Learning–Based Prediction of Suicidality in Adolescents With Allergic Rhinitis: Derivation and Validation in 2 Independent Nationwide Cohorts

J Med Internet Res 2024;26:e51473

DOI: 10.2196/51473

PMID: 38354043

PMCID: 10902766

Machine learning-based prediction of suicidality in adolescents with allergic rhinitis: Derivation and validation in two independent nationwide cohorts in South Korea

  • Hojae Lee; 
  • Joong Ki Cho; 
  • Jaeyu Park; 
  • Hwi Yang; 
  • Guillaume Fond; 
  • Laurent Boyer; 
  • Hyeon Jin Kim; 
  • Seoyoung Park; 
  • Jinseok Lee; 
  • Wonyoung Cho; 
  • Hayeon Lee; 
  • Dong Keon Yon

ABSTRACT

Background:

Given the additional risk of suicide-related behaviors that adolescents with allergic rhinitis (AR) have, it would be relevant to utilize the growing field of machine learning to better evaluate this risk.

Objective:

This study aimed to evaluate the validity and usefulness of a machine-learning (ML) model for predicting the suicide risks of patients with AR.

Methods:

We used data from two independent survey studies, Korea Youth Risk Behavior Web-based Survey (KYRBS; n=299,468) for the original dataset and the external validation Korea National Health and Nutrition Examination Survey (KNHANES; n=833), to predict suicide risks of AR in adolescent (age range 13 to 18) patients, noting 10,341 (3.45%) and 12 (1.44%) of patients with suicidal attempts in KYRBS and KNHANES respectively. The outcome of interest was suicide attempt risks. We selected various ML-based models with hyperparameter tuning in the discovery and performed an area under the receiver operating characteristic curve (AUROC) analysis in the train, test, and external-validation data.

Results:

The study dataset included 299,468 (KYRBS; original dataset) and 833 (KNHANES; external validation dataset) patients with AR recruited between 2005–2022. The best performing ML model was the random forest with a mean AUROC of 84.12% (95% CI, 83.98–84.27) in the original dataset. Applying this result to the external validation dataset revealed the best performance among the models, with an AUROC of 89.87% (sensitivity of 83.33%, specificity of 82.58%, accuracy of 82.59%, balanced accuracy of 82.96 %). While looking at feature importance, the five most important features in predicting suicide attempts in adolescent patients with AR are depression, stress status, academic achievement, age, and alcohol consumption.

Conclusions:

The study emphasizes the potential of ML models in predicting suicide risks in patients with AR, encouraging further application in other conditions to enhance adolescent health and decrease suicide rates.


 Citation

Please cite as:

Lee H, Cho JK, Park J, Yang H, Fond G, Boyer L, Kim HJ, Park S, Lee J, Cho W, Lee H, Yon DK

Machine Learning–Based Prediction of Suicidality in Adolescents With Allergic Rhinitis: Derivation and Validation in 2 Independent Nationwide Cohorts

J Med Internet Res 2024;26:e51473

DOI: 10.2196/51473

PMID: 38354043

PMCID: 10902766

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.