PointExplainer: Towards Transparent Parkinson's Disease Diagnosis

TL;DR

PointExplainer is a novel explainable AI method that interprets neural network diagnoses of Parkinson's disease from hand-drawn signals by identifying key regions, enhancing clinical trust without sacrificing accuracy.

Contribution

It introduces a new interpretability framework that assigns importance to hand-drawn segments in Parkinson's diagnosis, combining point cloud encoding and surrogate modeling.

Findings

Provides intuitive explanations without reducing diagnostic accuracy.

Demonstrates effectiveness on multiple benchmark datasets.

Addresses faithfulness in model explanations.

Abstract

Deep neural networks have shown potential in analyzing digitized hand-drawn signals for early diagnosis of Parkinson's disease. However, the lack of clear interpretability in existing diagnostic methods presents a challenge to clinical trust. In this paper, we propose PointExplainer, an explainable diagnostic strategy to identify hand-drawn regions that drive model diagnosis. Specifically, PointExplainer assigns discrete attribution values to hand-drawn segments, explicitly quantifying their relative contributions to the model's decision. Its key components include: (i) a diagnosis module, which encodes hand-drawn signals into 3D point clouds to represent hand-drawn trajectories, and (ii) an explanation module, which trains an interpretable surrogate model to approximate the local behavior of the black-box diagnostic model. We also introduce consistency measures to further address the issue of faithfulness in explanations. Extensive experiments on two benchmark datasets and a newly constructed dataset show that PointExplainer can provide intuitive explanations with no diagnostic performance degradation. The source code is available at https://github.com/chaoxuewang/PointExplainer.