Nabavi Ali, Safari Farimah, Faramarzi Ali, Kashkooli Mohammad, Kebede Meskerem Aleka, Aklilu Tesfamariam, Celi Leo Anthony
Otolaryngology Research Center, Department of Otolaryngology, Shiraz University of Medical Sciences, Shiraz, Iran.
Student Research Committee, School of Medicine, Shiraz University of Medical Sciences, Shiraz, Iran.
Sci Rep. 2025 Mar 22;15(1):9944. doi: 10.1038/s41598-025-94253-1.
Hearing loss poses immense burden worldwide and early detection is crucial. The accurate models identify high-risk groups, enabling timely intervention to improve quality of life. The subtle changes in hearing often go unnoticed, presenting a challenge for early hearing loss detection. While machine learning shows promise, prior studies have not leveraged cardiovascular risk factors known to impact hearing. As hearing outcomes remain challenging to characterize associations, we evaluated a new approach to predict current hearing outcomes through machine learning models using cardiovascular risk factors. The National Health and Nutrition Examination Survey (NHANES) 2012-2018 data comprising audiometric tests and cardiovascular risk factors was utilized. Machine learning algorithms were trained to classify hearing impairment thresholds and predict pure tone average values. Key results showed light gradient boosted machine performing best in classifying mild or greater impairment (> 25 dB HL) with 80.1% accuracy. It also classified > 16 dB HL and > 40 dB HL thresholds, with accuracies exceeding 77% and 86% respectively. The study also found that CatBoost and Gradient Boosting performed well in classifying hearing loss thresholds, with test set accuracies around 0.79 and F1-scores around 0.79-0.80. A multi-layer neural network emerged as the top predictor of pure tone averages, achieving a mean absolute error of just 3.05 dB. Feature analysis identified age, gender, blood pressure and waist circumference as key associated factors. Findings offer a promising direction for a clinically applicable tool, personalized prevention strategies, and calls for prospective validation.
听力损失在全球范围内造成了巨大负担，早期检测至关重要。准确的模型可识别高危人群，从而实现及时干预以提高生活质量。听力的细微变化往往未被察觉，这给早期听力损失检测带来了挑战。虽然机器学习显示出前景，但先前的研究尚未利用已知会影响听力的心血管危险因素。由于听力结果的关联特征仍具有挑战性，我们评估了一种通过使用心血管危险因素的机器学习模型来预测当前听力结果的新方法。我们使用了2012 - 2018年美国国家健康与营养检查调查（NHANES）的数据，其中包括听力测试和心血管危险因素。机器学习算法经过训练，用于对听力障碍阈值进行分类并预测纯音平均值。关键结果表明，轻梯度提升机器在对轻度或更严重障碍（> 25 dB HL）进行分类时表现最佳，准确率为80.1%。它还对> 16 dB HL和> 40 dB HL阈值进行了分类，准确率分别超过77%和86%。该研究还发现，CatBoost和梯度提升在对听力损失阈值进行分类时表现良好，测试集准确率约为0.79，F1分数约为0.79 - 0.80。多层神经网络成为纯音平均值的最佳预测器，平均绝对误差仅为3.05 dB。特征分析确定年龄、性别、血压和腰围为关键相关因素。研究结果为临床适用工具、个性化预防策略提供了一个有前景的方向，并呼吁进行前瞻性验证。
