超越不确定性量化：学习不确定性以实现信任感知的神经网络决策——COVID-19分类案例研究
Beyond Uncertainty Quantification: Learning Uncertainty for Trust-Informed Neural Network Decisions - A Case Study in COVID-19 Classification
AI总结：
本文提出不确定性感知堆叠神经网络，由基础模型与元模型学习预测信任标志，并在 COVIDx CXR-4 上验证其可显著减少高置信错误预测。
摘要：
可靠的不确定性量化在医疗诊断等高风险应用中至关重要，因为在这些场景中，自信但错误的预测会削弱人们对自动化决策系统的信任。传统不确定性量化方法依赖预定义的置信度阈值，将预测分类为可信或不确定。然而，该方法假设超过阈值的预测值得信任，而低于阈值的预测不确定，却没有显式评估高置信度预测的正确性。因此，自信但错误的预测仍可能出现，从而导致误导性的不确定性评估。为解决这一局限，本研究提出了一种不确定性感知的堆叠神经网络，通过学习预测何时应被信任来扩展传统不确定性量化。该框架由两层模型组成：基础模型生成带有不确定性估计的预测，而元模型学习分配信任标志，以区分自信且正确的病例与需要专家审查的病例。研究使用 COVIDx CXR-4 数据集，在多个置信度阈值和预训练架构上，将所提方法与传统的基于阈值的方法进行评估。结果表明，所提框架显著减少了自信但错误的预测，为高风险领域提供了更值得信任且更高效的决策支持系统。
英文摘要：
Reliable uncertainty quantification is critical in high-stakes applications, such as medical diagnosis, where confidently incorrect predictions can erode trust in automated decision-making systems. Traditional uncertainty quantification methods rely on a predefined confidence threshold to classify predictions as confident or uncertain. However, this approach assumes that predictions exceeding the threshold are trustworthy, while those below it are uncertain, without explicitly assessing the correctness of high-confidence predictions. As a result, confidently incorrect predictions may still occur, leading to misleading uncertainty assessments. To address this limitation, this study proposed an uncertainty-aware stacked neural network, which extends conventional uncertainty quantification by learning when predictions should be trusted. The framework consists of a two-tier model: the base model generates predictions with uncertainty estimates, while the meta-model learns to assign a trust flag, distinguishing confidently correct cases from those requiring expert review. The proposed approach is evaluated against the traditional threshold-based method across multiple confidence thresholds and pre-trained architectures using the COVIDx CXR-4 dataset. Results demonstrate that the proposed framework significantly reduces confidently incorrect predictions, offering a more trustworthy and efficient decision-support system for high-stakes domains.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
