Calibrating Healthcare AI: Towards Reliable and Interpretable Deep Predictive Models

• URL: http://arxiv.org/abs/2004.14480v1
• Date: Mon, 27 Apr 2020 22:15:17 GMT
• Title: Calibrating Healthcare AI: Towards Reliable and Interpretable Deep Predictive Models
• Authors: Jayaraman J. Thiagarajan, Prasanna Sattigeri, Deepta Rajan and Bindya Venkatesh
• Abstract summary: 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.
• Score: 41.58945927669956
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The wide-spread adoption of representation learning technologies in clinical decision making strongly emphasizes the need for characterizing model reliability and enabling rigorous introspection of model behavior. While the former need is often addressed by incorporating uncertainty quantification strategies, the latter challenge is addressed using a broad class of interpretability techniques. In this paper, we argue that these two objectives are not necessarily disparate and propose to utilize prediction calibration to meet both objectives. More specifically, our approach is comprised of a calibration-driven learning method, which is also used to design an interpretability technique based on counterfactual reasoning. Furthermore, we introduce \textit{reliability plots}, a holistic evaluation mechanism for model reliability. Using a lesion classification problem with dermoscopy images, we demonstrate the effectiveness of our approach and infer interesting insights about the model behavior.

Related papers

• Towards Unifying Interpretability and Control: Evaluation via Intervention [25.4582941170387]
  We propose intervention as a fundamental goal of interpretability and introduce success criteria to evaluate how well methods are able to control model behavior through interventions. We extend four popular interpretability methods--sparse autoencoders, logit lens, tuned lens, and probing--into an abstract encoder-decoder framework. We introduce two new evaluation metrics: intervention success rate and the coherence-intervention tradeoff, designed to measure the accuracy of explanations and their utility in controlling model behavior.
  arXiv  Detail & Related papers  (2024-11-07T04:52:18Z)
• Unsupervised Model Diagnosis [49.36194740479798]
  This paper proposes Unsupervised Model Diagnosis (UMO) to produce semantic counterfactual explanations without any user guidance. Our approach identifies and visualizes changes in semantics, and then matches these changes to attributes from wide-ranging text sources.
  arXiv  Detail & Related papers  (2024-10-08T17:59:03Z)
• Decoding Decision Reasoning: A Counterfactual-Powered Model for Knowledge Discovery [6.1521675665532545]
  In medical imaging, discerning the rationale behind an AI model's predictions is crucial for evaluating its reliability. We propose an explainable model that is equipped with both decision reasoning and feature identification capabilities. By implementing our method, we can efficiently identify and visualise class-specific features leveraged by the data-driven model.
  arXiv  Detail & Related papers  (2024-05-23T19:00:38Z)
• Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models [49.95603725998561]
  We propose a new paradigm to build robust and interpretable medical image classifiers with natural language concepts. Specifically, we first query clinical concepts from GPT-4, then transform latent image features into explicit concepts with a vision-language model.
  arXiv  Detail & Related papers  (2023-10-04T21:57:09Z)
• Deep Generative Models for Decision-Making and Control [4.238809918521607]
  The dual purpose of this thesis is to study the reasons for these shortcomings and to propose solutions for the uncovered problems. We highlight how inference techniques from the contemporary generative modeling toolbox, including beam search, can be reinterpreted as viable planning strategies for reinforcement learning problems.
  arXiv  Detail & Related papers  (2023-06-15T01:54:30Z)
• Two-step interpretable modeling of Intensive Care Acquired Infections [0.0]
  We present a novel methodology for integrating high resolution longitudinal data with the dynamic prediction capabilities of survival models. The aim is two-fold: to improve the predictive power while maintaining interpretability of the models.
  arXiv  Detail & Related papers  (2023-01-26T14:54:17Z)
• Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability [82.29775890542967]
  Estimating personalized effects of treatments is a complex, yet pervasive problem. Recent developments in the machine learning literature on heterogeneous treatment effect estimation gave rise to many sophisticated, but opaque, tools. We use post-hoc feature importance methods to identify features that influence the model's predictions.
  arXiv  Detail & Related papers  (2022-06-16T17:59:05Z)
• Exploring the Trade-off between Plausibility, Change Intensity and Adversarial Power in Counterfactual Explanations using Multi-objective Optimization [73.89239820192894]
  We argue that automated counterfactual generation should regard several aspects of the produced adversarial instances. We present a novel framework for the generation of counterfactual examples.
  arXiv  Detail & Related papers  (2022-05-20T15:02:53Z)
• (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)
• Accurate and Robust Feature Importance Estimation under Distribution Shifts [49.58991359544005]
  PRoFILE is a novel feature importance estimation method. We show significant improvements over state-of-the-art approaches, both in terms of fidelity and robustness.
  arXiv  Detail & Related papers  (2020-09-30T05:29:01Z)

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.