用脑部MRI和深度迁移学习预测人工耳蜗儿童语言发展，准确率达92%。
Forecasting Spoken Language Development in Children with Cochlear Implants Using Preimplantation MRI
- 采用深度迁移学习融合双线性注意力，从脑结构影像中提取语言发展特征
- 模型准确率92.39%，敏感性91.22%，特异性93.56%，AUC达0.977
- 可为全球人工耳蜗儿童提供个体化语言预后评估，适合临床决策支持
人工耳蜗（CI）显著改善重度至极重度感音神经性听力损失（SNHL）儿童的口语能力，但结果差异仍大于听力正常儿童。当前无法可靠预测个体儿童的听力恢复效果，仅靠植入年龄或残余听力难以实现。本研究比较传统机器学习（ML）与深度迁移学习（DTL）算法在预测双侧SNHL儿童植入后口语发展方面的表现，采用二分类模型区分高改善者与低改善者。共纳入来自三个中心的278名植入儿童。基于脑部神经解剖特征的预测模型在准确性、敏感性和特异性方面进行评估。使用双线性注意力融合策略的DTL模型达到：准确率92.39%（95%置信区间，90.70%–94.07%），敏感性91.22%（95%置信区间，89.98%–92.47%），特异性93.56%（95%置信区间，90.91%–96.21%），曲线下面积（AUC）为0.977（95%置信区间，0.969–0.986）。所有指标均优于传统机器学习模型。DTL通过直接捕捉判别性与任务特定信息，展现出表征学习的优势。结果支持建立一个适用于全球人工耳蜗项目儿童的语言预测单一深度迁移学习模型。
原文摘要 · Abstract (English)
Cochlear implants (CI) significantly improve spoken language in children with severe-to-profound sensorineural hearing loss (SNHL), yet outcomes remain more variable than in children with normal hearing. This variability cannot be reliably predicted for individual children using age at implantation or residual hearing. This study aims to compare the accuracy of traditional machine learning (ML) to deep transfer learning (DTL) algorithms to predict post-CI spoken language development of children with bilateral SNHL using a binary classification model of high versus low language improvers. A total of 278 implanted children enrolled from three centers. The accuracy, sensitivity and specificity of prediction models based upon brain neuroanatomic features using traditional ML and DTL learning. DTL prediction models using bilinear attention-based fusion strategy achieved: accuracy of 92.39% (95% CI, 90.70%-94.07%), sensitivity of 91.22% (95% CI, 89.98%-92.47%), specificity of 93.56% (95% CI, 90.91%-96.21%), and area under the curve (AUC) of 0.977 (95% CI, 0.969-0.986). DTL outperformed traditional ML models in all outcome measures. DTL was significantly improved by direct capture of discriminative and task-specific information that are advantages of representation learning enabled by this approach over ML. The results support the feasibility of a single DTL prediction model for language prediction of children served by CI programs worldwide.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。