Explainable Artificial Intelligence for Human Decision Support System in the Medical Domain

• Published in: Machine learning and knowledge extraction 2021-09, Vol.3 (3), p.740-770
• Main Authors: Knapič, Samanta, Malhi, Avleen, Saluja, Rohit, Främling, Kary
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial intelligence; Artificial neural networks; Automation; computer and systems sciences; data- och systemvetenskap; Datasets; Decision analysis; Decision making; Decision support systems; Deep learning; Explainable artificial intelligence; human decision support; Image analysis; image recognition; In vivo methods and tests; Lime; Machine learning; medical image analyses; Medical imaging; Neural networks; Trust; User groups; Vision systems
• ISSN: 2504-4990; 2504-4990
• DOI: 10.3390/make3030037

In this paper, we present the potential of Explainable Artificial Intelligence methods for decision support in medical image analysis scenarios. Using three types of explainable methods applied to the same medical image data set, we aimed to improve the comprehensibility of the decisions provided by the Convolutional Neural Network (CNN). In vivo gastral images obtained by a video capsule endoscopy (VCE) were the subject of visual explanations, with the goal of increasing health professionals’ trust in black-box predictions. We implemented two post hoc interpretable machine learning methods, called Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP), and an alternative explanation approach, the Contextual Importance and Utility (CIU) method. The produced explanations were assessed by human evaluation. We conducted three user studies based on explanations provided by LIME, SHAP and CIU. Users from different non-medical backgrounds carried out a series of tests in a web-based survey setting and stated their experience and understanding of the given explanations. Three user groups (n = 20, 20, 20) with three distinct forms of explanations were quantitatively analyzed. We found that, as hypothesized, the CIU-explainable method performed better than both LIME and SHAP methods in terms of improving support for human decision-making and being more transparent and thus understandable to users. Additionally, CIU outperformed LIME and SHAP by generating explanations more rapidly. Our findings suggest that there are notable differences in human decision-making between various explanation support settings. In line with that, we present three potential explainable methods that, with future improvements in implementation, can be generalized to different medical data sets and can provide effective decision support to medical experts.