基于纯音测听数据应用机器学习进行梅尼埃病评估
本研究为回顾性研究,在三级医疗中心收集钆增强磁共振成像序列与纯音测听数据,基于气导阈值构建特征并训练5种经典机器学习模型诊断梅尼埃病(MD)及预测内淋巴积水(EH)。表现最优的LGB模型诊断MD准确率87%、敏感度83%、特异度90%、AUC为0.95,与经验丰富的耳鼻咽喉科医师比较具有优势;LGB模型预测EH准确率78%,优于其他3种机器学习模型。
要点
- 基于纯音测听特征的LGB模型诊断MD准确率87%、敏感度83%、特异度90%、AUC为0.95。
- LGB模型预测EH准确率78%,优于另外3种机器学习模型。
- 全频听力标准差与均值、听力图峰值及低频(尤其250 Hz)听力为关键特征。
核心结论
- 基于纯音测听特征构建的高效机器学习模型可用于诊断MD,并显示出预测EH亚型的潜力。
研究设计与样本
- 回顾性研究,在三级医疗中心收集钆增强磁共振成像序列与纯音测听数据。
- 基于纯音测听气导阈值构建基础与多重分析特征,训练5种经典机器学习模型诊断MD。
- 选择表现优异的模型预测EH,并将模型诊断MD的效果与经验丰富的耳鼻咽喉科医师比较。
主要发现
- 由多重特征训练胜出的轻量梯度提升(LGB)机器学习模型诊断MD准确率87%、敏感度83%、特异度90%、受试者工作特征曲线下面积(AUC)为0.95。
- LGB模型诊断MD的表现与经验丰富的临床医师比较具有优势。
- LGB模型预测EH准确率78%,优于其他3种机器学习模型。
- 特征重要性分析显示,全频听力标准差与均值、听力图峰值及低频(尤其250 Hz)听力是MD诊断与EH预测的关键纯音测听特征。
临床怎么用
- 原文结论仅指出该模型可用于MD诊断并显示出预测EH亚型的潜力,未据此给出具体临床推荐。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
OBJECTIVE: To apply machine learning models based on air conduction thresholds of pure-tone audiometry for automatic diagnosis of Meniere's disease (MD) and prediction of endolymphatic hydrops (EH). STUDY DESIGN: Retrospective study. SETTING: Tertiary medical center. METHODS: Gadolinium-enhanced magnetic resonance imaging sequences and pure-tone audiometry data were collected. Subsequently, basic and multiple analytical features were engineered based on the air conduction thresholds of pure-tone audiometry. Later, 5 classical machine learning models were trained to diagnose MD using the engineered features. The models demonstrating excellent performance were also selected to predict EH. The model's effectiveness in MD diagnosis was compared with experienced otolaryngologists. RESULTS: First, the winning light gradient boosting (LGB) machine learning model trained by multiple features demonstrates a remarkable performance on the diagnosis of MD, achieving an accuracy rate of 87%, sensitivity of 83%, specificity of 90%, and a robust area under the receiver operating characteristic curve of 0.95, which compares favorably with experienced clinicians. Second, the LGB model, with an accuracy of 78% on EH prediction, outperformed the other 3 machine learning models. Finally, a feature importance analysis reveals a pivotal role of the specific pure-tone audiometry features that are essential for both MD diagnosis and EH prediction. Highlighted features include standard deviation and mean of the whole-frequency hearing, the peak of the audiogram, and hearing at low frequencies, notably at 250 Hz. CONCLUSION: An efficient machine learning model based on pure-tone audiometry features was produced to diagnose MD, which also showed the potential to predict the subtypes of EH. The innovative approach demonstrated a game-changing strategy for MD screening and promising cost-effective benefits for the health care enterprise.
引用
- Liu X, Guo P, Wang D, et al. Applications of Machine Learning in Meniere's Disease Assessment Based on Pure-Tone Audiometry. Otolaryngol Head Neck Surg. 2024. PMID: 39194410. doi:10.1002/ohn.956
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。