Causability and explainability of artificial intelligence in medicine

By Andreas Holzinger, Georg Langs, H. Denk, Kurt Zatloukal, Heimo Müller. 2019

1,566 citations recorded by the source corpus.

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

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI (2019, background): “Many more works have thus been dedicated to exploring explainability in the medical fields [11], [20], [43].”
Unbox the black-box for the medical explainable AI via multi-modal and multi-centre data fusion: A mini-review, two showcases and beyond (2021, background): “As a result, several recent studies [81, 84, 85] have been devoted to the exploration of explainability in medical AI.”
On Explaining Decision Trees (2020, neutral): “[2,68,25,32,1,7,57,24,26,70,67,58,44,30,17,5,73,35,4,78,69,10,34,72,71,36,46,11,45].”
A historical perspective of explainable Artificial Intelligence (2020, background): “Additional metrics targetting the notion of causability of explanations have recently been introduced by (Holzinger, Langs, et al., 2019; Holzinger, Carrington, & Müller, 2020).”
Toward Interpretable Machine Learning: Transparent Deep Neural Networks and Beyond (2020, background): “Various other works apply interpretable machine learning to image-based analyses in the sciences, especially in medical applications [57].”
Redefining Radiology: A Review of Artificial Intelligence Integration in Medical Imaging (2023, background): “saliency maps, feature importance, and surrogate models, aid in visualising and explaining the rationale behind AI models’ decisions, making them accessible to both experts and lay audiences [99,100].”
Supporting Skin Lesion Diagnosis with Content-Based Image Retrieval (2021, background): “worthy, transparent, interpretable and explainable for a human expert [31].”
A Novel Transfer Learning Based Approach for Pneumonia Detection in Chest X-ray Images (2020, methodology): “In this framework, we adopted the transfer learning approach and used the pretrained architectures, AlexNet, DenseNet121, Inception V3, GoogLeNet and ResNet18 trained on the ImageNet dataset, to extract features.”
Evaluating the Quality of Machine Learning Explanations: A Survey on Methods and Metrics (2021, background): “While causability refers to the measurable extent to which an explanation to a human achieves a specified level of causal understanding [25], and it does refer to a human model.”
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications (2021, background): “An important application area is in medicine [74].”
Current Challenges and Future Opportunities for XAI in Machine Learning-Based Clinical Decision Support Systems: A Systematic Review (2021, methodology): “In constructing CDSS, developers are confronted with “unknown, incomplete, imbalanced, heterogeneous, noisy, dirty, erroneous, inaccurate, and missing datasets in arbitrarily high-dimensional spaces” [3].”