The healthcare domain is one of the most exciting application areas for machine learning, but a lack of model transparency contributes to a lag in adoption within the industry. In this work, we explore the current art of explainability and interpretability within a case study in clinical text classification, using a task of mortality prediction within MIMIC-III clinical notes. We demonstrate various visualization techniques for fully interpretable methods as well as model-agnostic post hoc attributions, and we provide a generalized method for evaluating the quality of explanations using infidelity and local Lipschitz across model types from logistic regression to BERT variants. With these metrics, we introduce a framework through which practitioners and researchers can assess the frontier between a model's predictive performance and the quality of its available explanations. We make our code available to encourage continued refinement of these methods.
翻译:保健领域是机器学习最令人兴奋的应用领域之一,但缺乏模型透明度导致该行业内部的采用滞后。在这项工作中,我们利用MIMIC-III临床说明中的死亡率预测任务,在临床文本分类案例研究中探讨目前解释性和可解释性艺术,我们展示了各种可充分解释的方法的可视化技术,以及模型-不可知后特有属性,我们提供了一种通用方法,用于评估解释质量,从后勤回归到BERT变异模型类型中采用不忠和当地Lipschitz等解释的质量。我们采用这些衡量标准,我们引入了一个框架,使从业人员和研究人员能够评估模型的预测性能与其现有解释的质量之间的界限。我们提供了我们的守则,鼓励继续改进这些方法。