Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2019 Jul-Aug;9(4):e1312.
doi: 10.1002/widm.1312. Epub 2019 Apr 2.

Causability and explainability of artificial intelligence in medicine

Andreas Holzinger  1 , Georg Langs  2 , Helmut Denk  3 , Kurt Zatloukal  3 , Heimo Müller  1   3
Affiliations
Review

Causability and explainability of artificial intelligence in medicine

Andreas Holzinger et al. Wiley Interdiscip Rev Data Min Knowl Discov. 2019 Jul-Aug.

Abstract

Explainable artificial intelligence (AI) is attracting much interest in medicine. Technically, the problem of explainability is as old as AI itself and classic AI represented comprehensible retraceable approaches. However, their weakness was in dealing with uncertainties of the real world. Through the introduction of probabilistic learning, applications became increasingly successful, but increasingly opaque. Explainable AI deals with the implementation of transparency and traceability of statistical black-box machine learning methods, particularly deep learning (DL). We argue that there is a need to go beyond explainable AI. To reach a level of explainable medicine we need causability. In the same way that usability encompasses measurements for the quality of use, causability encompasses measurements for the quality of explanations. In this article, we provide some necessary definitions to discriminate between explainability and causability as well as a use-case of DL interpretation and of human explanation in histopathology. The main contribution of this article is the notion of causability, which is differentiated from explainability in that causability is a property of a person, while explainability is a property of a system This article is categorized under: Fundamental Concepts of Data and Knowledge > Human Centricity and User Interaction.

Keywords: artificial intelligence; causability; explainability; explainable AI; histopathology; medicine.

PubMed Disclaimer

Conflict of interest statement

The authors have declared no conflicts of interest for this article.

Figures

Figure 1
Figure 1
The best performing statistical approaches today are black‐boxes and do not foster understanding, trust and error correction (above). This implies an urgent need not only for explainable models, but also for explanation interfaces—and as a measure for the human‐AI interaction we need the concept of causability—analogous to usability in classic human‐computer interaction
Figure 2
Figure 2
An overview of how deep learning models can be probed for information regarding uncertainty, attribution, and prototypes
Figure 3
Figure 3
Features in a histology slide annotated by a human expert pathologist
See this image and copyright information in PMC

References

    1. Abadi, M. , Agarwal, A. , Barham, P. , Brevdo, E. , Chen, Z. , Citro, C. , Corrado, G. S. , Davis, A. , Dean, J. , & Devin, M. (2016). Tensorflow: Large‐scale machine learning on heterogeneous distributed systems. arXiv:1603.04467.
    1. Araujo, T. , Aresta, G. , Castro, E. , Rouco, J. , Aguiar, P. , Eloy, C. , … Campilho, A. (2017). Classification of breast cancer histology images using convolutional neural networks. PLoS One, 12, e0177544. - PMC - PubMed
    1. Babiker, H. K. B. , & Goebel, R. (2017). An introduction to deep visual explanation. arXiv:1711.09482.
    1. Bach, S. , Binder, A. , Montavon, G. , Klauschen, F. , Müller, K.‐R. , & Samek, W. (2015). On pixel‐wise explanations for non‐linear classifier decisions by layer‐wise relevance propagation. PLoS One, 10, e0130140. - PMC - PubMed
    1. Baumgartner, C. F. , Koch, L. M. , Tezcan, K. C. , Ang, J. X. , & Konukoglu, E. (2017). Visual feature attribution using wasserstein gans. Paper presented at Proceedings of the IEEE computer society conference on computer vision and pattern recognition.

LinkOut - more resources