Rationale: The incidence of clinically undiagnosed obstructive sleep apnea (OSA) is high among the general population because of limited access to polysomnography. Computed tomography (CT) of craniofacial regions obtained for other purposes can be beneficial in predicting OSA and its severity. Objectives: To predict OSA and its severity based on paranasal CT using a three-dimensional deep learning algorithm. Methods: One internal dataset (N = 798) and two external datasets (N = 135 and N = 85) were used in this study. In the internal dataset, 92 normal participants and 159 with mild, 201 with moderate, and 346 with severe OSA were enrolled to derive the deep learning model. A multimodal deep learning model was elicited from the connection between a three-dimensional convolutional neural network-based part treating unstructured data (CT images) and a multilayer perceptron-based part treating structured data (age, sex, and body mass index) to predict OSA and its severity. Measurements and Main Results: In a four-class classification for predicting the severity of OSA, the AirwayNet-MM-H model (multimodal model with airway-highlighting preprocessing algorithm) showed an average accuracy of 87.6% (95% confidence interval [CI], 86.8-88.6%) in the internal dataset and 84.0% (95% CI, 83.0-85.1%) and 86.3% (95% CI, 85.3-87.3%) in the two external datasets, respectively. In the two-class classification for predicting significant OSA (moderate to severe OSA), the area under the receiver operating characteristic curve, accuracy, sensitivity, specificity, and F1 score were 0.910 (95% CI, 0.899-0.922), 91.0% (95% CI, 90.1-91.9%), 89.9% (95% CI, 88.8-90.9%), 93.5% (95% CI, 92.7-94.3%), and 93.2% (95% CI, 92.5-93.9%), respectively, in the internal dataset. Furthermore, the diagnostic performance of the Airway Net-MM-H model outperformed that of the other six state-of-the-art deep learning models in terms of accuracy for both four- and two-class classifications and area under the receiver operating characteristic curve for two-class classification (P < 0.001). Conclusions: A novel deep learning model, including a multimodal deep learning model and an airway-highlighting preprocessing algorithm from CT images obtained for other purposes, can provide significantly precise outcomes for OSA diagnosis.

中文翻译：

---

使用深度学习模型根据计算机断层扫描预测阻塞性睡眠呼吸暂停。


理由：由于多导睡眠监测的机会有限，普通人群中临床未确诊的阻塞性睡眠呼吸暂停 (OSA) 的发病率很高。出于其他目的而获得的颅面部区域计算机断层扫描 (CT) 有助于预测 OSA 及其严重程度。目标：使用三维深度学习算法根据鼻旁 CT 预测 OSA 及其严重程度。方法：本研究使用一个内部数据集（N = 798）和两个外部数据集（N = 135 和 N = 85）。在内部数据集中，招募了 92 名正常参与者、159 名轻度 OSA、201 名中度 OSA 和 346 名重度 OSA 参与者来推导深度学习模型。基于处理非结构化数据（CT 图像）的基于三维卷积神经网络的部分和处理结构化数据（年龄、性别和体重指数）的基于多层感知器的部分之间的连接得出了多模态深度学习模型，以进行预测OSA 及其严重程度。测量和主要结果：在预测 OSA 严重程度的四级分类中，AirwayNet-MM-H 模型（具有气道突出显示预处理算法的多模态模型）的平均准确度为 87.6%（95% 置信区间 [CI]） ，86.8-88.6%）在内部数据集中，在两个外部数据集中分别为 84.0%（95% CI，83.0-85.1%）和 86.3%（95% CI，85.3-87.3%）。在预测显着 OSA（中度至重度 OSA）的两级分类中，受试者工作特征曲线下面积、准确度、敏感性、特异性和 F1 评分分别为 0.910（95% CI，0.899-0.922）、91.0%（ 95% CI, 90.1-91.9%)、89.9% (95% CI, 88.8-90.9%)、93.5% (95% CI, 92.7-94.3%) 和 93.2% (95% CI, 92.5-93.9%)，分别在内部数据集中。 此外，Airway Net-MM-H 模型的诊断性能在四类和两类分类的准确性以及接收者操作特征下的面积方面优于其他六种最先进的深度学习模型两类分类曲线（P < 0.001）。结论：一种新颖的深度学习模型，包括多模态深度学习模型和针对其他目的获得的 CT 图像的气道突出预处理算法，可以为 OSA 诊断提供非常精确的结果。