# Scalable, Axiomatic Explanations of Deep Alzheimer's Diagnosis from Heterogeneous Data

arXiv: https://arxiv.org/abs/2107.05997 · HTML: https://mlsanity.com/paper/2107.05997/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 34 references that are in the map.
- First posted on arXiv 13 Jul 2021.

## Builds on (most cited first, 16 of 16)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximation](https://mlsanity.com/paper/1903.10992/) (2019)
- [Lightweight Probabilistic Deep Networks](https://mlsanity.com/paper/1805.11327/) (2018)
- [Semi-Structured Deep Piecewise Exponential Models](https://mlsanity.com/paper/2011.05824/) (2020)
- [A Wide and Deep Neural Network for Survival Analysis from Anatomical Shape and Tabular Clinical Data](https://mlsanity.com/paper/1909.03890/) (2019)
- [Respond-CAM: Analyzing Deep Models for 3D Imaging Data by Visualizations](https://mlsanity.com/paper/1806.00102/) (2018)
- [Brain Biomarker Interpretation in ASD Using Deep Learning and fMRI](https://mlsanity.com/paper/1808.08296/) (2018)
- [Deep Multi-Structural Shape Analysis: Application to Neuroanatomy](https://mlsanity.com/paper/1806.01069/) (2018)
- [Invertible Network for Classification and Biomarker Selection for ASD](https://mlsanity.com/paper/1907.09729/) (2019)

## Built on by (most cited first, 1 of 1)

- [Multi-Modal Hypergraph Diffusion Network with Dual Prior for Alzheimer Classification](https://mlsanity.com/paper/2204.02399/) (2022)

## Abstract (arXiv)

Deep Neural Networks (DNNs) have an enormous potential to learn from complex biomedical data. In particular, DNNs have been used to seamlessly fuse heterogeneous information from neuroanatomy, genetics, biomarkers, and neuropsychological tests for highly accurate Alzheimer's disease diagnosis. On the other hand, their black-box nature is still a barrier for the adoption of such a system in the clinic, where interpretability is absolutely essential. We propose Shapley Value Explanation of Heterogeneous Neural Networks (SVEHNN) for explaining the Alzheimer's diagnosis made by a DNN from the 3D point cloud of the neuroanatomy and tabular biomarkers. Our explanations are based on the Shapley value, which is the unique method that satisfies all fundamental axioms for local explanations previously established in the literature. Thus, SVEHNN has many desirable characteristics that previous work on interpretability for medical decision making is lacking. To avoid the exponential time complexity of the Shapley value, we propose to transform a given DNN into a Lightweight Probabilistic Deep Network without re-training, thus achieving a complexity only quadratic in the number of features. In our experiments on synthetic and real data, we show that we can closely approximate the exact Shapley value with a dramatically reduced runtime and can reveal the hidden knowledge the network has learned from the data.