Department of Otolaryngology, MacKay Memorial Hospital, Taipei, Taiwan; Department of Audiology and Speech-Language Pathology, Mackay Medical College, New Taipei City, Taiwan; Department of Otolaryngology, National Taiwan University Hospital, Taipei, Taiwan.
Graduate Institute of Networking and Multimedia, National Taiwan University, Taipei, Taiwan.
Comput Biol Med. 2024 Jun;176:108597. doi: 10.1016/j.compbiomed.2024.108597. Epub 2024 May 15.
Recessive GJB2 variants, the most common genetic cause of hearing loss, may contribute to progressive sensorineural hearing loss (SNHL). The aim of this study is to build a realistic predictive model for GJB2-related SNHL using machine learning to enable personalized medical planning for timely intervention.
Patients with SNHL with confirmed biallelic GJB2 variants in a nationwide cohort between 2005 and 2022 were included. Different data preprocessing protocols and computational algorithms were combined to construct a prediction model. We randomly divided the dataset into training, validation, and test sets at a ratio of 72:8:20, and repeated this process ten times to obtain an average result. The performance of the models was evaluated using the mean absolute error (MAE), which refers to the discrepancy between the predicted and actual hearing thresholds.
We enrolled 449 patients with 2184 audiograms available for deep learning analysis. SNHL progression was identified in all models and was independent of age, sex, and genotype. The average hearing progression rate was 0.61 dB HL per year. The best MAE for linear regression, multilayer perceptron, long short-term memory, and attention model were 4.42, 4.38, 4.34, and 4.76 dB HL, respectively. The long short-term memory model performed best with an average MAE of 4.34 dB HL and acceptable accuracy for up to 4 years.
We have developed a prognostic model that uses machine learning to approximate realistic hearing progression in GJB2-related SNHL, allowing for the design of individualized medical plans, such as recommending the optimal follow-up interval for this population.
隐性 GJB2 变异是导致听力损失的最常见遗传原因，可能导致进行性感音神经性听力损失 (SNHL)。本研究旨在使用机器学习构建 GJB2 相关 SNHL 的现实预测模型，以实现及时干预的个性化医疗计划。
纳入 2005 年至 2022 年间全国性队列中具有双等位基因 GJB2 变异的 SNHL 患者。结合不同的数据预处理协议和计算算法构建预测模型。我们将数据集随机分为训练集、验证集和测试集，比例为 72:8:20，并重复此过程十次以获得平均结果。使用平均绝对误差 (MAE) 评估模型的性能，MAE 是指预测和实际听力阈值之间的差异。
我们纳入了 449 名患者，其中有 2184 份听力图可用于深度学习分析。所有模型均识别出 SNHL 进展，且与年龄、性别和基因型无关。平均听力进展率为每年 0.61dBHL。线性回归、多层感知机、长短期记忆和注意力模型的最佳 MAE 分别为 4.42、4.38、4.34 和 4.76dBHL。长短期记忆模型表现最好，平均 MAE 为 4.34dBHL，在 4 年内具有可接受的准确性。
我们开发了一种预后模型，该模型使用机器学习来近似 GJB2 相关 SNHL 中的真实听力进展，从而可以为该人群设计个性化医疗计划，例如推荐最佳随访间隔。
