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.
@article{arxiv.2107.05693,
title = {Quantifying Explainability in NLP and Analyzing Algorithms for Performance-Explainability Tradeoff},
author = {Mitchell Naylor and Christi French and Samantha Terker and Uday Kamath},
journal= {arXiv preprint arXiv:2107.05693},
year = {2021}
}
Comments
To appear at Interpretable ML in Healthcare workshop at ICML 2021. 9 pages (excluding references), 6 figures