文献速递耳科与耳神经小儿耳鼻咽喉

一种混合深度学习方法用于识别可预防的儿童听力损失

A Hybrid Deep Learning Approach to Identify Preventable Childhood Hearing Loss.
PubMed 文献 · Ear Hear · 2023-06-15

本研究评估混合深度学习模型对窄带鼓室压图进行分类的诊断性能,模型在4810对由听力学家和普通人采集的鼓室压图上进行10折交叉验证训练与评估,以听力学家判读为参考标准。对普通人采集的数据,模型敏感度为95.2%(93.3, 97.1),特异度为92.3%(91.5, 93.1),AUC为0.968(0.955, 0.978)。结论认为机器学习检测中耳疾病的性能与听力学家相当,可支持在资源匮乏社区由普通人引导的鼓室压测量用于听力筛查。

要点

  • 混合深度学习模型分类鼓室压图(A正常、B积液或穿孔、C内陷)以听力学家判读为参考标准。
  • 普通人采集数据中模型敏感度95.2%,高于鼓室压计内置分类器的79.2%和基于临床推荐规范值的决策树的56.9%。
  • 听力学家采集数据中模型AUC为0.987,敏感度95.2%,特异度97.7%。

核心结论

  • 机器学习使用听力学家或普通人采集的鼓室压图检测中耳疾病,性能与听力学家相当。
  • 自动分类使普通人引导的鼓室压测量可用于农村和服务不足社区的听力筛查项目。
  • 在儿童中早期发现可治疗病变对预防儿童听力损失的终生不良影响至关重要。

研究设计与样本

  • 诊断性能研究,评估混合深度学习模型对窄带鼓室压图进行分类。
  • 使用10折交叉验证,在4810对由听力学家和普通人采集的鼓室压图上训练和评估模型。
  • 模型训练将鼓室压图分为A型(正常)、B型(积液或穿孔)和C型(内陷),以听力学家判读为参考标准。
  • 鼓室压数据来自1635名儿童,采集时间为2017年10月10日至2019年3月28日,来自两项既往整群随机听力筛查试验(NCT03309553、NCT03662256)。
  • 参与者为阿拉斯加农村服务不足人群的学龄儿童,该人群感染相关听力损失患病率高。

主要发现

  • 对普通人采集的数据,机器学习模型敏感度为95.2%(93.3, 97.1),特异度为92.3%(91.5, 93.1),AUC为0.968(0.955, 0.978)。
  • 模型敏感度高于鼓室压计内置分类器的79.2%(75.5, 82.8)和基于临床推荐规范值的决策树的56.9%(52.4, 61.3)。
  • 对听力学家采集的数据,模型AUC为0.987(0.980, 0.993),敏感度为95.2(93.3, 97.1),特异度为97.7(97.3, 98.2)。

临床怎么用

  • 自动分类使普通人引导的鼓室压测量可用于农村和服务不足社区的听力筛查项目。
  • 在儿童中早期发现可治疗病变对预防儿童听力损失的终生不良影响至关重要。

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: Childhood hearing loss has well-known, lifelong consequences. Infection-related hearing loss disproportionately affects underserved communities yet can be prevented with early identification and treatment. This study evaluates the utility of machine learning in automating tympanogram classifications of the middle ear to facilitate layperson-guided tympanometry in resource-constrained communities. DESIGN: Diagnostic performance of a hybrid deep learning model for classifying narrow-band tympanometry tracings was evaluated. Using 10-fold cross-validation, a machine learning model was trained and evaluated on 4810 pairs of tympanometry tracings acquired by an audiologist and layperson. The model was trained to classify tracings into types A (normal), B (effusion or perforation), and C (retraction), with the audiologist interpretation serving as reference standard. Tympanometry data were collected from 1635 children from October 10, 2017, to March 28, 2019, from two previous cluster-randomized hearing screening trials (NCT03309553, NCT03662256). Participants were school-aged children from an underserved population in rural Alaska with a high prevalence of infection-related hearing loss. Two-level classification performance statistics were calculated by treating type A as pass and types B and C as refer. RESULTS: For layperson-acquired data, the machine-learning model achieved a sensitivity of 95.2% (93.3, 97.1), specificity of 92.3% (91.5, 93.1), and area under curve of 0.968 (0.955, 0.978). The model's sensitivity was greater than that of the tympanometer's built-in classifier [79.2% (75.5, 82.8)] and a decision tree based on clinically recommended normative values [56.9% (52.4, 61.3)]. For audiologist-acquired data, the model achieved a higher AUC of 0.987 (0.980, 0.993), had an equivalent sensitivity of 95.2 (93.3, 97.1), and a higher specificity of 97.7 (97.3, 98.2). CONCLUSIONS: Machine learning can detect middle ear disease with comparable performance to an audiologist using tympanograms acquired either by an audiologist or a layperson. Automated classification enables the use of layperson-guided tympanometry in hearing screening programs in rural and underserved communities, where early detection of treatable pathology in children is crucial to prevent the lifelong adverse effects of childhood hearing loss.

来源:Ear Hear,查看原文。版权归原作者所有。

引用

  1. Jin FQ, Huang O, Kleindienst Robler S, et al. A Hybrid Deep Learning Approach to Identify Preventable Childhood Hearing Loss. Ear Hear. 2023. PMID: 37318215. doi:10.1097/AUD.0000000000001380

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。