Skip to main content

Machine Learning Model Can Diagnose Meniere Disease

Medically reviewed by Carmen Pope, BPharm. Last updated on Oct 4, 2024.

By Elana Gotkine HealthDay Reporter

FRIDAY, Oct. 4, 2024 -- A machine learning model based on pure-tone audiometry features can diagnose Meniere disease (MD) and predict endolymphatic hydrops (EH), according to a study published online Aug. 28 in Otolaryngology-Head and Neck Surgery.

Xu Liu, M.D., from Fudan University in Shanghai, and colleagues collected gadolinium-enhanced magnetic resonance imaging sequences and pure-tone audiometry data in a retrospective study. Based on the air conduction thresholds of pure-tone audiometry, basic and multiple analytical features were engineered. The engineered features were used to train five classical machine learning models to diagnose MD. The models with excellent performance were selected to predict EH.

The researchers found that the winning light gradient boosting (LGB) machine learning model demonstrated remarkable performance for diagnosis of MD, achieving accuracy of 87 percent, sensitivity and specificity of 83 and 90 percent, and an area under the receiver operating characteristic curve of 0.95, comparing favorably with experienced clinicians. The LGB model had 78 percent accuracy for EH prediction and outperformed the other three models. Specific pure-tone audiometry features that are essential for both MD diagnosis and EH prediction include standard deviation and mean of the whole-frequency hearing, audiogram peak, and hearing at low frequencies (notably at 250 Hz).

"The study showed promising diagnostic capabilities, indicating the potential of machine learning based on pureā€tone audiometry results as an MD screening method," the authors write.

Abstract/Full Text

Disclaimer: Statistical data in medical articles provide general trends and do not pertain to individuals. Individual factors can vary greatly. Always seek personalized medical advice for individual healthcare decisions.

© 2024 HealthDay. All rights reserved.

Read this next

cfDNA Fragmentome, Protein Analyses Detect Ovarian Cancer

FRIDAY, Oct. 4, 2024 -- Integrated cell-free DNA (cfDNA) fragmentome and protein analyses detect ovarian cancers with high performance, according to a study published online Sept...

Subclinical Atherosclerosis Burden Linked to All-Cause Mortality

FRIDAY, Oct. 4, 2024 -- For asymptomatic individuals, subclinical atherosclerosis burden is associated with all-cause mortality, according to a study published in the Oct. 8 issue...

Long-Term Efficacy for Lebrikizumab Seen in Moderate, Severe Eczema

FRIDAY, Oct. 4, 2024 -- For patients with moderate-to-severe atopic dermatitis (AD), lebrikizumab has long-term efficacy, according to a study presented at the annual meeting of...

More news resources

Subscribe to our newsletter

Whatever your topic of interest, subscribe to our newsletters to get the best of Drugs.com in your inbox.