Clinical decision support for vestibular diagnosis: large-scale machine learning with lived experience coaching

Abstract Diagnosing vestibular disorders remains challenging due to complex symptoms and extensive history-taking required. While machine learning approaches have shown promise in medical diagnostics, their application to vestibular disorder classification has been limited. We developed a CatBoost m...

Full description

Saved in:
Bibliographic Details
Main Authors: Cecilia A. Callejas Pastor, Hyun Tae Ryu, Jung Sook Joo, Yunseo Ku, Myung-Whan Suh
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:npj Digital Medicine
Online Access:https://doi.org/10.1038/s41746-025-01880-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849342006245982208
author Cecilia A. Callejas Pastor
Hyun Tae Ryu
Jung Sook Joo
Yunseo Ku
Myung-Whan Suh
author_facet Cecilia A. Callejas Pastor
Hyun Tae Ryu
Jung Sook Joo
Yunseo Ku
Myung-Whan Suh
author_sort Cecilia A. Callejas Pastor
collection DOAJ
description Abstract Diagnosing vestibular disorders remains challenging due to complex symptoms and extensive history-taking required. While machine learning approaches have shown promise in medical diagnostics, their application to vestibular disorder classification has been limited. We developed a CatBoost machine learning model to classify six common vestibular disorders using a retrospective dataset of patients. The model incorporates 50 clinical features, selected through a hybrid approach combining algorithmic methods (RFE-SVM and SKB score) and expert clinical knowledge. We designed the system to achieve high sensitivity for common vestibular disorders (BPPV and VM) and high specificity for conditions requiring intensive interventions (MD and HOD) or careful differential diagnosis (PPPD and VEST) to minimize unnecessary invasive treatments. When applied to test data, reaches 88.4% accuracy, with 60.9% correct classifications, 27.5% partially correct, and 11.6% incorrect classifications. Results suggest that machine learning can support clinical decision-making in vestibular disorder diagnosis when combining algorithmic capabilities with clinical expertise.
format Article
id doaj-art-c466bfd117bc43e0a32ee986fe683aa9
institution Kabale University
issn 2398-6352
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series npj Digital Medicine
spelling doaj-art-c466bfd117bc43e0a32ee986fe683aa92025-08-20T03:43:30ZengNature Portfolionpj Digital Medicine2398-63522025-07-018111010.1038/s41746-025-01880-zClinical decision support for vestibular diagnosis: large-scale machine learning with lived experience coachingCecilia A. Callejas Pastor0Hyun Tae Ryu1Jung Sook Joo2Yunseo Ku3Myung-Whan Suh4Department of Otorhinolaryngology-Head and Neck Surgery, Seoul National University HospitalDepartment of Otorhinolaryngology-Head and Neck Surgery, Seoul National University HospitalDepartment of Otorhinolaryngology-Head and Neck Surgery, Seoul National University HospitalDepartment of Biomedical Engineering, College of Medicine, Chungnam National UniversityDepartment of Otorhinolaryngology-Head and Neck Surgery, Seoul National University HospitalAbstract Diagnosing vestibular disorders remains challenging due to complex symptoms and extensive history-taking required. While machine learning approaches have shown promise in medical diagnostics, their application to vestibular disorder classification has been limited. We developed a CatBoost machine learning model to classify six common vestibular disorders using a retrospective dataset of patients. The model incorporates 50 clinical features, selected through a hybrid approach combining algorithmic methods (RFE-SVM and SKB score) and expert clinical knowledge. We designed the system to achieve high sensitivity for common vestibular disorders (BPPV and VM) and high specificity for conditions requiring intensive interventions (MD and HOD) or careful differential diagnosis (PPPD and VEST) to minimize unnecessary invasive treatments. When applied to test data, reaches 88.4% accuracy, with 60.9% correct classifications, 27.5% partially correct, and 11.6% incorrect classifications. Results suggest that machine learning can support clinical decision-making in vestibular disorder diagnosis when combining algorithmic capabilities with clinical expertise.https://doi.org/10.1038/s41746-025-01880-z
spellingShingle Cecilia A. Callejas Pastor
Hyun Tae Ryu
Jung Sook Joo
Yunseo Ku
Myung-Whan Suh
Clinical decision support for vestibular diagnosis: large-scale machine learning with lived experience coaching
npj Digital Medicine
title Clinical decision support for vestibular diagnosis: large-scale machine learning with lived experience coaching
title_full Clinical decision support for vestibular diagnosis: large-scale machine learning with lived experience coaching
title_fullStr Clinical decision support for vestibular diagnosis: large-scale machine learning with lived experience coaching
title_full_unstemmed Clinical decision support for vestibular diagnosis: large-scale machine learning with lived experience coaching
title_short Clinical decision support for vestibular diagnosis: large-scale machine learning with lived experience coaching
title_sort clinical decision support for vestibular diagnosis large scale machine learning with lived experience coaching
url https://doi.org/10.1038/s41746-025-01880-z
work_keys_str_mv AT ceciliaacallejaspastor clinicaldecisionsupportforvestibulardiagnosislargescalemachinelearningwithlivedexperiencecoaching
AT hyuntaeryu clinicaldecisionsupportforvestibulardiagnosislargescalemachinelearningwithlivedexperiencecoaching
AT jungsookjoo clinicaldecisionsupportforvestibulardiagnosislargescalemachinelearningwithlivedexperiencecoaching
AT yunseoku clinicaldecisionsupportforvestibulardiagnosislargescalemachinelearningwithlivedexperiencecoaching
AT myungwhansuh clinicaldecisionsupportforvestibulardiagnosislargescalemachinelearningwithlivedexperiencecoaching