Dakshit Sagnik, Dakshit Sristi, Khargonkar Ninad, Prabhakaran Balakrishnan
Computer Science, The University of Texas at Dallas, Dallas, USA.
J Healthc Inform Res. 2023 Jun 19;7(2):225-253. doi: 10.1007/s41666-023-00133-6. eCollection 2023 Jun.
One of the hindrances in the widespread acceptance of deep learning-based decision support systems in healthcare is bias. Bias in its many forms occurs in the datasets used to train and test deep learning models and is amplified when deployed in the real world, leading to challenges such as model drift. Recent advancements in the field of deep learning have led to the deployment of deployable automated healthcare diagnosis decision support systems at hospitals as well as tele-medicine through IoT devices. Research has been focused primarily on the development and improvement of these systems leaving a gap in the analysis of the fairness. The domain of FAccT ML (fairness, accountability, and transparency) accounts for the analysis of these deployable machine learning systems. In this work, we present a framework for bias analysis in healthcare time series (BAHT) signals such as electrocardiogram (ECG) and electroencephalogram (EEG). BAHT provides a graphical interpretive analysis of bias in the training, testing datasets in terms of protected variables, and analysis of bias amplification by the trained supervised learning model for time series healthcare decision support systems. We thoroughly investigate three prominent time series ECG and EEG healthcare datasets used for model training and research. We show the extensive presence of bias in the datasets leads to potentially biased or unfair machine-learning models. Our experiments also demonstrate the amplification of identified bias with an observed maximum of 66.66%. We investigate the effect of model drift due to unanalyzed bias in datasets and algorithms. Bias mitigation though prudent is a nascent area of research. We present experiments and analyze the most prevalently accepted bias mitigation strategies of under-sampling, oversampling, and the use of synthetic data for balancing the dataset through augmentation. It is important that healthcare models, datasets, and bias mitigation strategies should be properly analyzed for a fair unbiased delivery of service.
深度学习在医疗保健领域的决策支持系统广泛应用中面临的障碍之一是偏差。偏差以多种形式出现在用于训练和测试深度学习模型的数据集中，并且在实际应用中会被放大，从而导致模型漂移等问题。深度学习领域的最新进展促使可部署的自动化医疗诊断决策支持系统通过物联网设备在医院以及远程医疗中得到应用。研究主要集中在这些系统的开发和改进上，而在公平性分析方面存在空白。FAccT ML（公平性、问责制和透明度）领域负责对这些可部署的机器学习系统进行分析。在这项工作中，我们提出了一个针对医疗时间序列（BAHT）信号（如心电图（ECG）和脑电图（EEG））的偏差分析框架。BAHT从受保护变量的角度对训练和测试数据集中的偏差进行图形化解释分析，并对用于时间序列医疗决策支持系统的训练有监督学习模型的偏差放大情况进行分析。我们深入研究了用于模型训练和研究的三个著名的时间序列ECG和EEG医疗数据集。我们发现数据集中广泛存在的偏差会导致潜在的有偏差或不公平的机器学习模型。我们的实验还证明了所识别偏差的放大，观察到的最大放大率为66.66%。我们研究了由于数据集中未分析的偏差和算法导致的模型漂移的影响。尽管谨慎地减轻偏差是一个新兴的研究领域。我们展示了实验，并分析了最普遍接受的偏差减轻策略，即欠采样、过采样以及使用合成数据通过扩充来平衡数据集。重要的是，应该对医疗模型、数据集和偏差减轻策略进行适当分析，以实现公平无偏差的服务提供。
