Choi Jae Won, Koo Dae Lim, Kim Dong Hyun, Nam Hyunwoo, Lee Ji Hyun, Hong Seung-No, Kim Baekhyun
Department of Radiology, Seoul National University Hospital and Seoul National University College of Medicine, Seoul, South Korea.
Department of Neurology, Seoul Metropolitan Government Seoul National University Boramae Medical Center and Seoul National University College of Medicine, Seoul, South Korea.
Sleep. 2024 Dec 11;47(12). doi: 10.1093/sleep/zsae184.
The demand for cost-effective and accessible alternatives to polysomnography (PSG), the conventional diagnostic method for obstructive sleep apnea (OSA), has surged. In this study, we have developed and validated a deep learning model for detecting apnea-hypopnea events using radar data.
We conducted a single-center prospective cohort study, dividing participants with suspected sleep-disordered breathing into development and temporally independent test sets. Utilizing a hybrid CNN-Transformer architecture, we performed fivefold cross-validation on the development set to develop and subsequently validate the model. Evaluation metrics included sensitivity for event detection, mean absolute error (MAE), intraclass correlation coefficient (ICC), and Pearson correlation coefficient (r) for apnea-hypopnea index (AHI) estimation. Linearly weighted kappa statistics (κ) assessed OSA severity.
The development set comprised 54 participants (July 2021-May 2022), while the test set included 35 participants (June 2022-June 2023). In the test set, our model achieved an event detection sensitivity of 67.2% (95% CI = 65.8% to 68.5%) and demonstrated a MAE of 7.54 (95% CI = 5.36 to 9.72), indicating good agreement (ICC = 0.889 [95% CI = 0.792 to 0.942]) and a strong correlation (r = 0.892 [95% CI = 0.795 to 0.945]) with the ground truth for AHI estimation. Furthermore, OSA severity estimation showed substantial agreement (κ = 0.780 [95% CI = 0.658 to 0.903]).
Our study highlights radar sensors and advanced AI models' potential to improve OSA diagnosis, paving the path for future radar-based diagnostic models in sleep medicine research.
对多导睡眠图（PSG）这一阻塞性睡眠呼吸暂停（OSA）的传统诊断方法而言，对具有成本效益且可及的替代方法的需求激增。在本研究中，我们开发并验证了一种使用雷达数据检测呼吸暂停 - 低通气事件的深度学习模型。
我们进行了一项单中心前瞻性队列研究，将疑似睡眠呼吸障碍的参与者分为开发集和时间上独立的测试集。利用混合卷积神经网络 - 变换器（CNN - Transformer）架构，我们在开发集上进行了五折交叉验证以开发并随后验证模型。评估指标包括事件检测的敏感性、平均绝对误差（MAE）、组内相关系数（ICC）以及用于呼吸暂停 - 低通气指数（AHI）估计的皮尔逊相关系数（r）。线性加权kappa统计量（κ）评估OSA严重程度。
开发集包括54名参与者（2021年7月 - 2022年5月），而测试集包括35名参与者（2022年6月 - 2023年6月）。在测试集中，我们的模型实现了67.2%的事件检测敏感性（95%置信区间 = 65.8%至68.5%），并且平均绝对误差为7.54（95%置信区间 = 5.36至9.72），表明在AHI估计方面与真实情况具有良好的一致性（ICC = 0.889 [95%置信区间 = 0.792至0.942]）和强相关性（r = 0.892 [95%置信区间 = 0.795至0.945]）。此外，OSA严重程度估计显示出高度一致性（κ = 0.780 [95%置信区间 = 0.658至0.903]）。
我们的研究突出了雷达传感器和先进人工智能模型在改善OSA诊断方面的潜力，为睡眠医学研究中未来基于雷达的诊断模型铺平了道路。
