# The Explanation Necessity for Healthcare AI

arXiv: https://arxiv.org/abs/2406.00216 · HTML: https://mlsanity.com/paper/2406.00216/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 36 references that are in the map.
- First posted on arXiv 31 May 2024.

## Builds on (most cited first, 11 of 11)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI](https://mlsanity.com/paper/1907.07374/) (2019)
- [Segment Anything in Medical Images](https://mlsanity.com/paper/2304.12306/) (2023)
- [Explainable artificial intelligence (XAI) in deep learning-based medical image analysis](https://mlsanity.com/paper/2107.10912/) (2021)
- [Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions](https://mlsanity.com/paper/2310.19775/) (2023)
- [Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review](https://mlsanity.com/paper/2402.10086/) (2024)
- [Neural Network Attribution Methods for Problems in Geoscience: A Novel Synthetic Benchmark Dataset](https://mlsanity.com/paper/2103.10005/) (2021)
- [ExplAIn: Explanatory Artificial Intelligence for Diabetic Retinopathy Diagnosis](https://mlsanity.com/paper/2008.05731/) (2020)
- [Ten years of image analysis and machine learning competitions in dementia](https://mlsanity.com/paper/2112.07922/) (2021)
- [The Robust Semantic Segmentation UNCV2023 Challenge Results](https://mlsanity.com/paper/2309.15478/) (2023)
- [A novel framework employing deep multi-attention channels network for the autonomous detection of metastasizing cells through fluorescence microscopy](https://mlsanity.com/paper/2309.00911/) (2023)

## Abstract (arXiv)

Explainability is a critical factor in enhancing the trustworthiness and acceptance of artificial intelligence (AI) in healthcare, where decisions directly impact patient outcomes. Despite advancements in AI interpretability, clear guidelines on when and to what extent explanations are required in medical applications remain lacking. We propose a novel categorization system comprising four classes of explanation necessity (self-explainable, semi-explainable, non-explainable, and new-patterns discovery), guiding the required level of explanation; whether local (patient or sample level), global (cohort or dataset level), or both. To support this system, we introduce a mathematical formulation that incorporates three key factors: (i) robustness of the evaluation protocol, (ii) variability of expert observations, and (iii) representation dimensionality of the application. This framework provides a practical tool for researchers to determine the appropriate depth of explainability needed, addressing the critical question: When does an AI medical application need to be explained, and at what level of detail?