Key result
Machine learning model using CV risk factors detects hearing impairment with ~80% accuracy.
Why the study?
Prior machine learning studies for early hearing loss detection had not leveraged cardiovascular risk factors known to impact hearing.
Can machine learning models using cardiovascular risk factors accurately predict hearing loss thresholds and pure tone averages?
Population
Participants in NHANES 2012-2018 with audiometric tests and cardiovascular risk factors
Comparison
Cardiovascular risk factors used to predict hearing outcomes via machine learning models
Authors
Loading...
Hypothesis-generating for CV risk factor-based hearing loss screening; prospective validation needed before clinical adoption.
Cross-Sectional (n=7,996)
Can machine learning models using cardiovascular risk factors accurately predict hearing loss thresholds and pure tone averages?
Machine learning models utilizing cardiovascular risk factors such as age, gender, blood pressure, and waist circumference can accurately predict hearing loss thresholds.
Nabavi et al. (2025) conducted a cross-sectional in Hearing loss (n=7,996). Machine learning models (LightGBM, MLNN) using cardiovascular risk factors was evaluated on Classification of mild or greater hearing impairment (> 25 dB HL). A light gradient boosted machine model utilizing cardiovascular risk factors classified mild or greater hearing impairment (> 25 dB HL) with 80.1% accuracy.
Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context: