论文标题
MCU-NET：针对决策支持系统的不确定性表示框架，医疗保健环境中的患者转诊
MCU-Net: A framework towards uncertainty representations for decision support system patient referrals in healthcare contexts
论文作者
论文摘要
在部署自动决策支持时，在医疗保健环境中至关重要的是建立信任，并在患者到患者的基础上提供可靠的绩效。高性能的深度学习方法，由于缺乏不确定性表示，因此不允许这种以患者为中心的方法。因此，我们使用MCU-NET将U-NET与Monte Carlo辍学的MCU-NET评估了不确定性表示的框架，并与四个不同的不确定性指标进行了评估。该框架通过基于自动转诊不确定案件的不确定性阈值来增加对医学专家的不确定性阈值，从而增加了这一框架。我们证明，MCU-NET结合了认知不确定性和为此应用调整的不确定性阈值，可在单个患者水平上最大化自动表现，但确实是指真正不确定的病例。当在医疗保健设置中部署基于机器学习的决策支持时，这是迈向不确定性表示的一步。
Incorporating a human-in-the-loop system when deploying automated decision support is critical in healthcare contexts to create trust, as well as provide reliable performance on a patient-to-patient basis. Deep learning methods while having high performance, do not allow for this patient-centered approach due to the lack of uncertainty representation. Thus, we present a framework of uncertainty representation evaluated for medical image segmentation, using MCU-Net which combines a U-Net with Monte Carlo Dropout, evaluated with four different uncertainty metrics. The framework augments this by adding a human-in-the-loop aspect based on an uncertainty threshold for automated referral of uncertain cases to a medical professional. We demonstrate that MCU-Net combined with epistemic uncertainty and an uncertainty threshold tuned for this application maximizes automated performance on an individual patient level, yet refers truly uncertain cases. This is a step towards uncertainty representations when deploying machine learning based decision support in healthcare settings.
