Computer Safety, Reliability, and Security - 42nd International Conference, SAFECOMP 2023, Toulouse, France, September 20-22, 2023, Proceedings
Computer Safety, Reliability, and Security - 42nd International Conference, SAFECOMP 2023, Toulouse, France, September 20-22, 2023, Proceedings
复制标题
计算机安全、可靠性和安保 - 第 42 届国际会议，SAFECOMP 2023，法国图卢兹，2023 年 9 月 20-22 日，会议记录
DOI：
10.1007/978-3-031-40923-3_16
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Ryan Conmy P
中科院分区：
文献类型：
--
作者：
Ryan Conmy P
具有人工智能（AI）和机器学习（ML）组件的决策支持系统在确保对运营性能的信任方面存在许多挑战，特别是在医疗保健等安全关键领域。在操作过程中，Human in/on the Loop （html）可能需要帮助来确定何时信任ML输出以及何时覆盖它，特别是为了防止危险情况。在本文中，我们考虑了训练数据不足的问题如何导致机器学习的不同安全性能。我们提出了一个案例研究，使用基于机器学习的临床决策支持系统来预测2型糖尿病相关的共发病（DCP）。DCP ML组件使用真实的患者数据进行训练，但是这些数据来自多年来收集的非常大的实时数据库，并且记录的分布和完整性各不相同。开发类似临床预测系统的研究描述了不同的方法来弥补训练数据的不足，但只专注于固定数据以最大化机器学习性能，而没有考虑系统安全的角度。这意味着机器学习不同性能的影响在系统层面上并没有被完全理解。此外，诸如数据输入之类的方法可能会引入进一步的偏差风险，而这一风险尚未得到解决。本文将机器学习数据不足补偿措施的使用与探索性安全分析相结合，以确保考虑到所有降低风险的手段。我们证明，这些共同提供了一个更丰富的画面，允许更有效地识别和减轻培训数据不足的风险。
Decision support systems with Artificial intelligence (AI) and specifically Machine Learning (ML) components present many challenges when assuring trust in operational performance, particularly in a safety-critical domain such as healthcare. During operation the Human in/on The Loop (HTL) may need assistance in determining when to trust the ML output and when to override it, particularly to prevent hazardous situations. In this paper, we consider how issues with training data shortfalls can cause varying safety performance in ML. We present a case study using an ML-based clinical decision support system for Type-2 diabetes related co-morbidity prediction (DCP). The DCP ML component is trained using real patient data, but the data was taken from a very large live database gathered over many years, and the records vary in distribution and completeness. Research developing similar clinical predictor systems describe different methods to compensate for training data shortfalls, but concentrate only on fixing the data to maximise the ML performance without considering a system safety perspective. This means the impact of the ML’s varying performance is not fully understood at the system level. Further, methods such as data imputation can introduce a further risk of bias which is not addressed. This paper combines the use of ML data shortfall compensation measures with exploratory safety analysis to ensure all means of reducing risk are considered. We demonstrate that together these provide a richer picture allowing more effective identification and mitigation of risks from training data shortfalls.