The Intensive Care Unit (ICU) is a hospital department where machine learning has the potential to provide valuable assistance in clinical decision making. Classical machine learning models usually only provide point-estimates and no uncertainty of predictions. In practice, uncertain predictions should be presented to doctors with extra care in order to prevent potentially catastrophic treatment decisions. In this work we show how Bayesian modelling and the predictive uncertainty that it provides can be used to mitigate risk of misguided prediction and to detect out-of-domain examples in a medical setting. We derive analytically a bound on the prediction loss with respect to predictive uncertainty. The bound shows that uncertainty can mitigate loss. Furthermore, we apply a Bayesian Neural Network to the MIMIC-III dataset, predicting risk of mortality of ICU patients. Our empirical results show that uncertainty can indeed prevent potential errors and reliably identifies out-of-domain patients. These results suggest that Bayesian predictive uncertainty can greatly improve trustworthiness of machine learning models in high-risk settings such as the ICU.

翻译：重症监护室（ICU）是机器学习在临床决策中具有重要辅助潜力的医院科室。经典的机器学习模型通常仅提供点估计，而无法给出预测的不确定性。在实践中，不确定的预测需要格外谨慎地呈现给医生，以避免可能引发灾难性后果的治疗决策。本研究展示了贝叶斯建模及其提供的预测不确定性如何用于降低误导性预测的风险，并在医疗场景中检测域外样本。我们通过解析方法推导了预测损失相对于预测不确定性的一个上界，该上界表明不确定性能够减轻损失。此外，我们将贝叶斯神经网络应用于MIMIC-III数据集，预测ICU患者的死亡风险。实证结果表明，不确定性确实能够预防潜在错误，并可靠地识别域外患者。这些发现表明，贝叶斯预测不确定性能够显著提升机器学习模型在高风险环境（如ICU）中的可信度。