[论文解读] Developing Personalized Models of Blood Pressure Estimation from Wearable Sensors Data Using Minimally-trained Domain Adversarial Neural Networks
该论文提出了一种基于领域对抗性神经网络(DANN)的多任务学习模型,通过极少的训练数据,实现可个性化、无袖带的可穿戴生物阻抗信号血压估计。通过对抗性训练学习与受试者无关的特征,该模型仅需四分钟个体特定数据即可达到ISO标准的精度,与基线方法相比,收缩压的RMSE降低最多0.67 mmHg,舒张压降低最多0.26 mmHg。
Blood pressure monitoring is an essential component of hypertension management and in the prediction of associated comorbidities. Blood pressure is a dynamic vital sign with frequent changes throughout a given day. Capturing blood pressure remotely and frequently (also known as ambulatory blood pressure monitoring) has traditionally been achieved by measuring blood pressure at discrete intervals using an inflatable cuff. However, there is growing interest in developing a cuffless ambulatory blood pressure monitoring system to measure blood pressure continuously. One such approach is by utilizing bioimpedance sensors to build regression models. A practical problem with this approach is that the amount of data required to confidently train such a regression model can be prohibitive. In this paper, we propose the application of the domain-adversarial training neural network (DANN) method on our multitask learning (MTL) blood pressure estimation model, allowing for knowledge transfer between subjects. Our proposed model obtains average root mean square error (RMSE) of 4.80 ± 0.74 mmHg for diastolic blood pressure and 7.34 ± 1.88 mmHg for systolic blood pressure when using three minutes of training data, 4.64 ± 0.60 mmHg and 7.10 ± 1.79 respectively when using four minutes of training data, and 4.48±0.57 mmHg and 6.79±1.70 respectively when using five minutes of training data. DANN improves training with minimal data in comparison to both directly training and to training with a pretrained model from another subject, decreasing RMSE by 0.19 to 0.26 mmHg (diastolic) and by 0.46 to 0.67 mmHg (systolic) in comparison to the best baseline models. We observe that four minutes of training data is the minimum requirement for our framework to exceed ISO standards within this cohort of patients.
研究动机与目标
- 解决从可穿戴传感器训练个性化血压估计模型所需数据量过高的挑战。
- 通过最小化训练数据量来减少无袖带血压监测的校准时间,同时保持精度。
- 通过领域对抗性训练实现知识迁移,提升模型在不同受试者间的泛化能力。
- 评估四分钟训练数据是否足以满足ISO标准对血压测量精度的要求。
- 开发一种框架,实现在仅有少量个体特定数据的情况下,高效适应新个体的模型。
提出的方法
- 在每个心动周期的生物阻抗信号上训练一个多任务学习(MTL)回归模型,以估计收缩压和舒张压。
- 应用领域对抗性训练(DANN),通过训练一个领域判别器来区分源域(已有受试者)与目标域(新受试者)的领域,从而学习与受试者无关的特征。
- 优化特征提取器,使其最小化领域分类准确率,从而迫使模型学习解耦的、与受试者无关的表征。
- 在3、4或5分钟的个体特定数据上进行微调,实现在极低数据量下的快速个性化。
- 通过在训练过程中利用其他受试者的数据实现知识迁移,提升低数据场景下的性能。
- 采用包含三分之一受试者的平衡领域划分,防止因领域预测中类别不平衡导致的模型崩溃。
实验结果
研究问题
- RQ1深度学习模型是否能在少于五分钟的个体特定训练数据下,实现符合ISO标准的血压估计精度?
- RQ2领域对抗性训练在个性化血压估计中如何提升受试者之间的知识迁移能力?
- RQ3使用生物阻抗信号进行无袖带血压监测时,满足ISO标准所需的最短训练时长是多少?
- RQ4与标准MTL或从预训练模型微调的方法相比,DANN是否能减少对个体受试者特征的过拟合?
- RQ5该模型在训练期间未见过的插值血压范围上的表现如何?
主要发现
- 在五分钟后训练数据下,DANN增强模型的平均舒张压RMSE为4.48 ± 0.57 mmHg,收缩压RMSE为6.79 ± 1.70 mmHg。
- 在四分钟训练数据下,模型的RMSE为4.64 ± 0.60 mmHg(舒张压)和7.10 ± 1.79 mmHg(收缩压),达到ISO标准。
- 与最佳基线模型(来自另一名受试者的预训练模型)相比,该模型使收缩压的RMSE降低0.46至0.67 mmHg,舒张压降低0.19至0.26 mmHg。
- 在本研究队列中,四分钟是达到ISO标准的最短训练时长,因为使用三分钟数据时性能低于标准。
- 该模型对缺失的血压范围具有良好的泛化能力,其在范围内与范围外值的RMSE相近,表明具备稳健的回归能力。
- DANN减少了对受试者特异性特征的记忆,相比独立的MTL或微调模型,显著提升了泛化性能。
更好的研究,从现在开始
从阅读论文到最终审阅,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。