IEEE J Biomed Health Inform. 2019 Jan;23(1):47-58. doi: 10.1109/JBHI.2018.2820054. Epub 2018 Jun 5.
The role of sensing technologies, such as wearables, in delivering precision care is becoming widely acceptable. Given the very large quantities of sensor data that rapidly accumulate, there is a need to employ automated algorithms to label biosignal sensor data. In many real-life clinical applications, no such expert labels are available, and algorithms for processing sensor data must be relied upon, without access to the "ground truth." It is therefore extremely difficult to choose which algorithms to trust or discard at any point in time, where different algorithms may be optimal for different patients, or even for different points in time for the same patient. We propose two fully Bayesian approaches for fusing labels from independent and potentially correlated annotators (i.e., algorithms or, where available, experts). These are generative models to aggregate labels (i.e., the outputs of the algorithms, such as identified ECG morphology) in an unsupervised manner, to estimate jointly the assumed bias and precision of each algorithm without access to the ground truth. The latter fused estimate may then be used to infer the underlying ground truth. For the first time in the biomedical context, we show that modeling correlations between annotators, and fusing information concerning task difficulty (such as the estimated quality of the sensor data), improve these estimates with respect to commonly employed strategies in the literature. Also, we adopt a strongly Bayesian approach to inference using Gibbs sampling to improve estimates over the existing state of the art. We present results from applying the proposed pair of models to simulated and two publicly available biomedical datasets, to demonstrate proof-of-principle. We show that our proposed models outperform all existing approaches recreated from the literature. We also show that the proposed methods are robust when dealing with missing values (as often occurs in real-life biomedical applications), and that they are suitably efficient for use in real-time applications, thereby providing the basis for the reliable use of sensors for personalizing the care of the individual.
可穿戴等传感技术在提供精准医疗中的作用正被广泛接受。鉴于传感器数据的数量非常庞大且快速积累，需要采用自动化算法来标注生物信号传感器数据。在许多实际的临床应用中，没有此类专家标签，必须依赖于处理传感器数据的算法，而无法获取“真实情况”。因此，在任何时候，选择信任或丢弃哪些算法都极其困难，因为不同的算法可能对不同的患者，甚至是同一患者的不同时间点都是最优的。我们提出了两种完全贝叶斯方法来融合来自独立且可能相关的标注者（即算法，或者在可用的情况下是专家）的标签。这些是生成模型，可以以无监督的方式聚合标签（即算法的输出，例如识别出的 ECG 形态），在没有真实情况的情况下，联合估计每个算法的假设偏差和精度。然后，可以使用融合后的估计值来推断潜在的真实情况。这是在生物医学背景下首次表明，对标注者之间的相关性进行建模，并融合有关任务难度的信息（例如传感器数据的估计质量），可以提高与文献中常用策略相比的这些估计值。此外，我们采用了一种强贝叶斯方法进行推断，使用 Gibbs 抽样来改进现有的推断方法。我们通过将所提出的模型应用于模拟和两个公开的生物医学数据集来展示原理验证。我们表明，我们提出的模型优于从文献中重新创建的所有现有方法。我们还表明，所提出的方法在处理缺失值时具有鲁棒性（这在实际的生物医学应用中经常发生），并且对于实时应用非常高效，从而为可靠地使用传感器为个人提供个性化护理奠定了基础。
