Middle-ear conditions are common causes of primary care visits, hearing impairment, and inappropriate antibiotic use. Deep learning (DL) may assist clinicians in interpreting otoscopic images. This study included patients over 5 years old from an ambulatory ENT practice in Strasbourg, France, between 2013 and 2020. Digital otoscopic images were obtained using a smartphone-attached otoscope (Smart Scope, Karl Storz, Germany) and labeled by a senior ENT specialist across 11 diagnostic classes (reference standard). An Inception-v2 DL model was trained using 41,664 otoscopic images, and its diagnostic accuracy was evaluated by calculating class-specific estimates of sensitivity and specificity. The model was then incorporated into a smartphone app called i-Nside. The DL model was evaluated on a validation set of 3,962 images and a held-out test set comprising 326 images. On the validation set, all class-specific estimates of sensitivity and specificity exceeded 98%. On the test set, the DL model achieved a sensitivity of 99.0% (95% confidence interval: 94.5–100) and a specificity of 95.2% (91.5–97.6) for the binary classification of normal vs. abnormal images; wax plugs were detected with a sensitivity of 100% (94.6–100) and specificity of 97.7% (95.0–99.1); other class-specific estimates of sensitivity and specificity ranged from 33.3% to 92.3% and 96.0% to 100%, respectively. We present an end-to-end DL-enabled system able to achieve expert-level diagnostic accuracy for identifying normal tympanic aspects and wax plugs within digital otoscopic images. However, the system’s performance varied for other middle-ear conditions. Further prospective validation is necessary before wider clinical deployment.

中耳疾病是初级保健就诊、听力障碍和抗生素使用不当的常见原因。深度学习（DL）可以帮助临床医生解释耳镜图像。这项研究包括 2013 年至 2020 年间在法国斯特拉斯堡门诊耳鼻喉诊所就诊的 5 岁以上患者。数字耳镜图像是使用智能手机连接的耳镜（Smart Scope，Karl Storz，德国）获得的，并由高级耳鼻喉专家标记跨越 11 个诊断类别（参考标准）。使用 41,664 个耳镜图像训练 Inception-v2 DL 模型，并通过计算特定类别的敏感性和特异性估计来评估其诊断准确性。该模型随后被整合到名为 i-Nside 的智能手机应用程序中。 DL 模型在包含 3,962 个图像的验证集和包含 326 个图像的保留测试集上进行评估。在验证集上，所有特定类别的敏感性和特异性估计值均超过 98%。在测试集上，DL 模型对正常与异常图像的二元分类实现了 99.0% 的敏感性（95% 置信区间：94.5–100）和 95.2%（91.5–97.6）的特异性；检测蜡塞的灵敏度为 100% (94.6–100)，特异性为 97.7% (95.0–99.1)；其他特定类别的敏感性和特异性估计值分别为 33.3% 至 92.3% 和 96.0% 至 100%。我们提出了一种支持深度学习的端到端系统，能够实现专家级的诊断准确性，用于识别数字耳镜图像中的正常鼓室方面和蜡塞。然而，该系统的性能因其他中耳状况而异。在更广泛的临床部署之前，需要进一步的前瞻性验证。