Faithful and Plausible Explanations of Medical Code Predictions

• URL: http://arxiv.org/abs/2104.07894v1
• Date: Fri, 16 Apr 2021 05:13:36 GMT
• Title: Faithful and Plausible Explanations of Medical Code Predictions
• Authors: Zach Wood-Doughty, Isabel Cachola, and Mark Dredze
• Abstract summary: Explanations must balance faithfulness to the model's decision-making with their plausibility to a domain expert. We train a proxy model that mimics the behavior of the trained model and provides fine-grained control over these trade-offs. We evaluate our approach on the task of assigning ICD codes to clinical notes to demonstrate that explanations from the proxy model are faithful and replicate the trained model behavior.
• Score: 12.156363504753244
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine learning models that offer excellent predictive performance often lack the interpretability necessary to support integrated human machine decision-making. In clinical medicine and other high-risk settings, domain experts may be unwilling to trust model predictions without explanations. Work in explainable AI must balance competing objectives along two different axes: 1) Explanations must balance faithfulness to the model's decision-making with their plausibility to a domain expert. 2) Domain experts desire local explanations of individual predictions and global explanations of behavior in aggregate. We propose to train a proxy model that mimics the behavior of the trained model and provides fine-grained control over these trade-offs. We evaluate our approach on the task of assigning ICD codes to clinical notes to demonstrate that explanations from the proxy model are faithful and replicate the trained model behavior.

Related papers

• Human Trajectory Forecasting with Explainable Behavioral Uncertainty [63.62824628085961]
  Human trajectory forecasting helps to understand and predict human behaviors, enabling applications from social robots to self-driving cars. Model-free methods offer superior prediction accuracy but lack explainability, while model-based methods provide explainability but cannot predict well. We show that BNSP-SFM achieves up to a 50% improvement in prediction accuracy, compared with 11 state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-07-04T16:45:21Z)
• Clinical outcome prediction under hypothetical interventions -- a representation learning framework for counterfactual reasoning [31.97813934144506]
  We introduce a new representation learning framework, which considers the provision of counterfactual explanations as an embedded property of the risk model. Our results suggest that our proposed framework has the potential to help researchers and clinicians improve personalised care.
  arXiv  Detail & Related papers  (2022-05-15T09:41:16Z)
• Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations [97.91630330328815]
  We conduct a crowdsourcing study, where participants interact with deception detection models that have been trained to distinguish between genuine and fake hotel reviews. We observe that for a linear bag-of-words model, participants with access to the feature coefficients during training are able to cause a larger reduction in model confidence in the testing phase when compared to the no-explanation control.
  arXiv  Detail & Related papers  (2021-12-17T18:29:56Z)
• Test-time Collective Prediction [73.74982509510961]
  Multiple parties in machine learning want to jointly make predictions on future test points. Agents wish to benefit from the collective expertise of the full set of agents, but may not be willing to release their data or model parameters. We explore a decentralized mechanism to make collective predictions at test time, leveraging each agent's pre-trained model.
  arXiv  Detail & Related papers  (2021-06-22T18:29:58Z)
• Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations [64.85696493596821]
  In computer vision applications, generative counterfactual methods indicate how to perturb a model's input to change its prediction. We propose a counterfactual method that learns a perturbation in a disentangled latent space that is constrained using a diversity-enforcing loss. Our model improves the success rate of producing high-quality valuable explanations when compared to previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-03-18T12:57:34Z)
• Learning to Predict with Supporting Evidence: Applications to Clinical Risk Prediction [9.199022926064009]
  The impact of machine learning models on healthcare will depend on the degree of trust that healthcare professionals place in the predictions made by these models. We present a method to provide people with clinical expertise with domain-relevant evidence about why a prediction should be trusted.
  arXiv  Detail & Related papers  (2021-03-04T00:26:32Z)
• (Un)fairness in Post-operative Complication Prediction Models [20.16366948502659]
  We consider a real-life example of risk estimation before surgery and investigate the potential for bias or unfairness of a variety of algorithms. Our approach creates transparent documentation of potential bias so that the users can apply the model carefully.
  arXiv  Detail & Related papers  (2020-11-03T22:11:19Z)
• Double Robust Representation Learning for Counterfactual Prediction [68.78210173955001]
  We propose a novel scalable method to learn double-robust representations for counterfactual predictions. We make robust and efficient counterfactual predictions for both individual and average treatment effects. The algorithm shows competitive performance with the state-of-the-art on real world and synthetic data.
  arXiv  Detail & Related papers  (2020-10-15T16:39:26Z)
• Are Visual Explanations Useful? A Case Study in Model-in-the-Loop Prediction [49.254162397086006]
  We study explanations based on visual saliency in an image-based age prediction task. We find that presenting model predictions improves human accuracy. However, explanations of various kinds fail to significantly alter human accuracy or trust in the model.
  arXiv  Detail & Related papers  (2020-07-23T20:39:40Z)
• Calibrating Healthcare AI: Towards Reliable and Interpretable Deep Predictive Models [41.58945927669956]
  We argue that these two objectives are not necessarily disparate and propose to utilize prediction calibration to meet both objectives. Our approach is comprised of a calibration-driven learning method, which is also used to design an interpretability technique based on counterfactual reasoning.
  arXiv  Detail & Related papers  (2020-04-27T22:15:17Z)
• Interpretability of machine learning based prediction models in healthcare [8.799886951659627]
  We give an overview of interpretability approaches and provide examples of practical interpretability of machine learning in different areas of healthcare. We highlight the importance of developing algorithmic solutions that can enable machine-learning driven decision making in high-stakes healthcare problems.
  arXiv  Detail & Related papers  (2020-02-20T07:23:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.