Department of Otolaryngology-Head and Neck Surgery, Mayo Clinic, Rochester, MN, United States of America; Department of Neurologic Surgery, Mayo Clinic, Rochester, MN, United States of America.
Department of Otolaryngology-Head and Neck Surgery, Mayo Clinic, Rochester, MN, United States of America.
Am J Otolaryngol. 2024 Jul-Aug;45(4):104337. doi: 10.1016/j.amjoto.2024.104337. Epub 2024 Apr 23.
To describe an AI model to facilitate adult cochlear implant candidacy prediction based on basic demographical data and standard behavioral audiometry.
A machine-learning approach using retrospective demographic and audiometric data to predict candidacy CNC word scores and AzBio sentence in quiet scores was performed at a tertiary academic center. Data for the model were derived from adults completing cochlear implant candidacy testing between January 2011 and March 2023. Comparison of the prediction model to other published prediction tools and benchmarks was performed.
The final dataset included 770 adults, encompassing 1045 AzBio entries, and 1373 CNC entries. Isophoneme scores and word recognition scores exhibited strongest importance to both the CNC and AzBio prediction models, followed by standard pure tone average and low-frequency pure tone average. The mean absolute difference between the predicted and actual score was 15 percentage points for AzBio sentences in quiet and 13 percentage points for CNC word scores, approximating anticipated test-retest constraints inherent to the variables incorporated into the model. Our final combined model achieved an accuracy of 87 % (sensitivity: 90 %; precision: 80 %).
We present an adaptive AI model that predicts adult cochlear implant candidacy based on routine behavioral audiometric and basic demographical data. Implementation efforts include a public-facing online prediction tool and accompanying smartphone program, an embedded notification flag in the electronic medical record to alert providers of potential candidates, and a program to retrospectively engage past patients who may be eligible for cochlear implantation based on audiogram results.
描述一种人工智能模型，该模型基于基本人口统计学数据和标准行为测听来辅助成人人工耳蜗植入候选者预测。
在一家三级学术中心，采用机器学习方法，使用回顾性人口统计学和测听数据来预测候选者 CNC 单词得分和 AzBio 安静句子得分。该模型的数据来自于 2011 年 1 月至 2023 年 3 月期间完成人工耳蜗植入候选者测试的成年人。对预测模型与其他已发表的预测工具和基准进行了比较。
最终数据集包括 770 名成年人，包含 1045 个 AzBio 条目和 1373 个 CNC 条目。音位得分和单词识别得分对 CNC 和 AzBio 预测模型都具有最强的重要性，其次是标准纯音平均听阈和低频纯音平均听阈。AzBio 安静句子的预测得分与实际得分之间的平均绝对差异为 15 个百分点，CNC 单词得分的平均绝对差异为 13 个百分点，接近模型中纳入的变量固有的预期测试-重测限制。我们的最终综合模型的准确率为 87%（灵敏度：90%；精确度：80%）。
我们提出了一种自适应人工智能模型，该模型基于常规行为测听和基本人口统计学数据来预测成人人工耳蜗植入候选者。实施工作包括一个面向公众的在线预测工具和配套的智能手机程序，一个电子病历中的嵌入式通知标志，以提醒提供者潜在的候选者，以及一个根据听力图结果回顾性接触可能有资格接受耳蜗植入的过去患者的计划。
