论文标题
DeepBeat：一种评估可穿戴设备中信号质量和心律不齐检测的多任务深度学习方法
DeepBeat: A multi-task deep learning approach to assess signal quality and arrhythmia detection in wearable devices
论文作者
论文摘要
可穿戴设备可实现理论上连续的，纵向监测生理测量，例如步骤计数，能量消耗和心率。尽管可穿戴设备的心脏纤维等异常心律的分类具有巨大的潜力，但商业算法仍然专有，并且倾向于专注于腕部噪声上的绿色频谱LED传感器衍生出的心率变异性，其中噪声仍然是未解决的问题。在这里，我们开发了一种多任务深度学习方法，以评估可穿戴光摄影设备中的信号质量和心律不齐的事件检测，以实时检测房颤（AF）。我们在超过100万个模拟未标记的生理信号上训练算法，并在策划的数据集上进行微调，该数据集的500k超过500K标记的信号来自来自3个不同可穿戴设备的100多人。我们证明，与传统的基于森林的方法相比（精度：0.24，召回：0.58，f1：0.34，auprc：0.44）和单个任务CNN（精度：0.59，召回：0.69，f1：0.64，0.64，0.64，auprc：0.68），使用无需固定的自动化训练训练训练训练训练训练训练效果，以上的自动化型固定型螺纹螺丝驾驶仪的指示，并划分自动划分。休息的参与者（PR：0.94，RC：0.98，F1：0.96，AUPRC：0.96）。此外，我们使用从独立工程设备得出的数据验证了前瞻性衍生的卧床受试者的算法性能。我们表明，两阶段培训可以帮助解决稀缺大型数据集的生物医学应用程序常见的不平衡数据问题。总之，尽管模拟和转移学习的结合，并且我们开发并应用了多任构建结构，从可穿戴腕部传感器的AF检测问题上，表现出高度的准确性和解决机械噪声烦恼挑战的解决方案。
Wearable devices enable theoretically continuous, longitudinal monitoring of physiological measurements like step count, energy expenditure, and heart rate. Although the classification of abnormal cardiac rhythms such as atrial fibrillation from wearable devices has great potential, commercial algorithms remain proprietary and tend to focus on heart rate variability derived from green spectrum LED sensors placed on the wrist where noise remains an unsolved problem. Here, we develop a multi-task deep learning method to assess signal quality and arrhythmia event detection in wearable photoplethysmography devices for real-time detection of atrial fibrillation (AF). We train our algorithm on over one million simulated unlabeled physiological signals and fine-tune on a curated dataset of over 500K labeled signals from over 100 individuals from 3 different wearable devices. We demonstrate that in comparison with a traditional random forest-based approach (precision:0.24, recall:0.58, f1:0.34, auPRC:0.44) and a single task CNN (precision:0.59, recall:0.69, f1:0.64, auPRC:0.68) our architecture using unsupervised transfer learning through convolutional denoising autoencoders dramatically improves the performance of AF detection in participants at rest (pr:0.94, rc:0.98, f1:0.96, auPRC:0.96). In addition, we validate algorithm performance on a prospectively derived replication cohort of ambulatory subjects using data derived from an independently engineered device. We show that two-stage training can help address the unbalanced data problem common to biomedical applications where large well-annotated datasets are scarce. In conclusion, though a combination of simulation and transfer learning and we develop and apply a multitask architecture to the problem of AF detection from wearable wrist sensors demonstrating high levels of accuracy and a solution for the vexing challenge of mechanical noise.
