School of Medicine, University of Minnesota, Minnesota, Minneapolis, USA.
Department of Biomedical Engineering, University of Minnesota, Minneapolis, Minnesota, USA.
Otolaryngol Head Neck Surg. 2023 Sep;169(3):504-513. doi: 10.1002/ohn.288. Epub 2023 Feb 9.
Hearing loss (HL) is highly prevalent, yet underrecognized and underdiagnosed. Lack of standardized screening, awareness, cost, and access to hearing testing present barriers to HL identification. To facilitate prescreening and selection of patients who warrant audiometric evaluation, we developed a machine learning (ML) model to predict speech-frequency pure-tone average (PTA).
Cross-sectional study.
National Health and Nutrition Examination Survey (NHANES).
The cohort included 8918 adults (≥20 years) who completed audiometric testing with NHANES (2012-2018). The primary outcome measure was the prediction of better hearing ear speech-frequency PTA. Relevant predictors included demographics, medical conditions, and subjective assessment of hearing. Supervised ML with a tree-based architecture was used. Regression performance was determined by the mean absolute error (MAE) with binary classification assessed with area under the receiver operating characteristic curve (AUC).
Using the full set of predictors, the test set MAE between the ML-predicted and actual PTA was 5.29 dB HL (95% confidence interval [CI]: 4.97-5.61). The 5 most influential predictors of higher PTA were increased age, worse subjective hearing, male gender, increased body mass index, and history of smoking. The 5-factor abbreviated model performed comparably to the extended feature set with MAE 5.36 (95% CI: 5.03-5.69) and AUC for PTA > 25 dB HL of 0.92 (95% CI: 0.90-0.94).
The ML model was able to predict PTA with patient demographics, clinical factors, and subjective hearing status. ML-based prediction may be used to identify individuals who could benefit most from audiometric evaluation.
听力损失（HL）非常普遍，但未被充分认识和诊断。缺乏标准化的筛查、意识、成本以及听力测试的可及性是识别 HL 的障碍。为了促进预筛查并选择需要进行听力评估的患者，我们开发了一种机器学习（ML）模型来预测言语频率纯音平均（PTA）。
横断面研究。
国家健康和营养调查（NHANES）。
该队列包括 8918 名完成 NHANES 听力测试的成年人（≥20 岁）。主要结局指标是预测更好听力耳的言语频率 PTA。相关预测因素包括人口统计学、医疗状况和听力主观评估。使用基于树的架构进行监督 ML。回归性能由平均绝对误差（MAE）确定，二进制分类通过接收者操作特征曲线下的面积（AUC）进行评估。
使用完整的预测因素集，测试集中 ML 预测的 PTA 与实际 PTA 之间的 MAE 为 5.29dB HL（95%置信区间[CI]：4.97-5.61）。PTA 较高的 5 个最有影响力的预测因素是年龄增长、听力下降、男性性别、体重指数增加和吸烟史。5 因素缩写模型的性能与扩展特征集相当，MAE 为 5.36（95%CI：5.03-5.69），PTA>25dB HL 的 AUC 为 0.92（95%CI：0.90-0.94）。
该 ML 模型能够预测患者的人口统计学、临床因素和主观听力状况的 PTA。基于 ML 的预测可用于识别最有可能从听力评估中受益的个体。
