Department of Otolaryngology-Head and Neck Surgery, Massachusetts Eye and Ear, Boston, Massachusetts, USA.
Department of Otolaryngology-Head and Neck Surgery, Harvard Medical School, Boston, Massachusetts, USA.
Ear Hear. 2021 July/Aug;42(4):982-989. doi: 10.1097/AUD.0000000000000993.
Hearing loss is the most common sensory loss in humans and carries an enhanced risk of depression. No prior studies have attempted a contemporary machine learning approach to predict depression using subjective and objective hearing loss predictors. The objective was to deploy supervised machine learning to predict scores on a validated depression scale using subjective and objective audiometric variables and other health determinant predictors.
A large predictor set of health determinants from the National Health and Nutrition Examination Survey 2015-2016 database was used to predict adults' scores on a validated instrument to screen for the presence and severity of depression (Patient Health Questionnaire-9 [PHQ-9]). After model training, the relative influence of individual predictors on depression scores was stratified and analyzed. Model prediction performance was determined by prediction error metrics.
The test set mean absolute error was 3.03 (95% confidence interval: 2.91 to 3.14) and 2.55 (95% confidence interval: 2.48 to 2.62) on datasets with audiology-only predictors and all predictors, respectively, on the PHQ-9's 27-point scale. Participants' self-reported frustration when talking to members of family or friends due to hearing loss was the fifth-most influential of all predictors. Of the top 10 most influential audiometric predictors, five were related to social contexts, two for significant noise exposure, two objective audiometric parameters, and one presence of bothersome tinnitus.
Machine learning algorithms can accurately predict PHQ-9 depression scale scores from National Health and Nutrition Examination Survey data. The most influential audiometric predictors of higher scores on a validated depression scale were social dynamics of hearing loss and not objective audiometric testing. Such models could be useful in predicting depression scale scores at the point-of-care in conjunction with a standard audiologic assessment.
听力损失是人类最常见的感觉损失，会增加患抑郁症的风险。以前没有研究尝试使用主观和客观听力损失预测因子来进行基于机器学习的抑郁预测。本研究旨在使用监督机器学习，通过主观和客观听力测试变量以及其他健康决定因素预测因子，来预测经过验证的抑郁量表的评分。
使用来自 2015-2016 年国家健康和营养检查调查数据库的大量健康决定因素预测因子集，来预测成年人在经过验证的用于筛查抑郁（患者健康问卷-9[PHQ-9]）的工具上的评分。在模型训练后，对个体预测因子对抑郁评分的相对影响进行分层和分析。通过预测误差指标来确定模型的预测性能。
测试集的平均绝对误差分别为 3.03（95%置信区间：2.91 至 3.14）和 2.55（95%置信区间：2.48 至 2.62），分别为仅包含听力测试预测因子和所有预测因子的 PHQ-9 27 分制量表的数据集。由于听力损失，参与者在与家人或朋友交谈时感到沮丧的报告，是所有预测因子中第五个最具影响力的因素。在十大最具影响力的听力测试预测因子中，有五个与社会环境有关，两个与噪声暴露显著有关，两个是客观听力测试参数，一个是恼人的耳鸣存在。
机器学习算法可以从国家健康和营养检查调查数据中准确预测 PHQ-9 抑郁量表评分。对验证后抑郁量表高分最具影响力的听力测试预测因子是听力损失的社会动态，而不是客观听力测试。这种模型可能有助于在标准听力评估的同时，在护理点预测抑郁量表评分。
