Search

The current move towards digital pathology enables pathologists to use artificial intelligence (AI)-based computer programmes for the advanced analysis of whole slide images. However, currently, the best-performing AI algorithms for image analysis are deemed black boxes since it remains - even to their developers - often unclear why the algorithm delivered a particular result. Especially in medicine, a better understanding of algorithmic decisions is essential to avoid mistakes and adverse effects on patients. This review article aims to provide medical experts with insights on the issue of explainability in digital pathology. A short introduction to the relevant underlying core concepts of machine learning shall nurture the reader's understanding of why explainability is a specific issue in this field. Addressing this issue of explainability, the rapidly evolving research field of explainable AI (XAI) has developed many techniques and methods to make black-box machine-learning systems more transparent. These XAI methods are a first step towards making black-box AI systems understandable by humans. However, we argue that an explanation interface must complement these explainable models to make their results useful to human stakeholders and achieve a high level of causability, i.e. a high level of causal understanding by the user. This is especially relevant in the medical field since explainability and causability play a crucial role also for compliance with regulatory requirements. We conclude by promoting the need for novel user interfaces for AI applications in pathology, which enable contextual understanding and allow the medical expert to ask interactive 'what-if'-questions. In pathology, such user interfaces will not only be important to achieve a high level of causability. They will also be crucial for keeping the human-in-the-loop and bringing medical experts' experience and conceptual knowledge to AI processes., (© 2023 The Authors. The Journal of Pathology: Clinical Research published by The Pathological Society of Great Britain and Ireland and John Wiley & Sons Ltd.)

The explosion of interest in exploiting machine learning techniques in healthcare has brought the issue of inferring causation from observational data to centre stage. In our work in supporting the health decisions of the individual person/patient-as-person at the point of care, we cannot avoid making decisions about which options are to be included or excluded in a decision support tool. Should the researcher's routine injunction to use their findings 'with caution', because of methodological limitations, lead to inclusion or exclusion? The task is one of deciding, first on causal plausibility, and then on causality. Like all decisions these are both sensitive to error preferences (trade-offs). We engage selectively with the Artificial Intelligence (AI) literature on the causality challenge and on the closely associated issue of the 'explainability' now demanded of 'black box' AI. Our commitment to embracing 'lifestyle' as well as 'medical' options for the individual person, leads us to highlight the key issue as that of who is to make the preference- sensitive decisions on causal plausibility and causality.

Artificial Intelligence (AI) for the biomedical domain is gaining significant interest and holds considerable potential for the future of healthcare, particularly also in the context of in vitro diagnostics. The European In Vitro Diagnostic Medical Device Regulation (IVDR) explicitly includes software in its requirements. This poses major challenges for In Vitro Diagnostic devices (IVDs) that involve Machine Learning (ML) algorithms for data analysis and decision support. This can increase the difficulty of applying some of the most successful ML and Deep Learning (DL) methods to the biomedical domain, just by missing the required explanatory components from the manufacturers. In this context, trustworthy AI has to empower biomedical professionals to take responsibility for their decision-making, which clearly raises the need for explainable AI methods. Explainable AI, such as layer-wise relevance propagation, can help in highlighting the relevant parts of inputs to, and representations in, a neural network that caused a result and visualize these relevant parts. In the same way that usability encompasses measurements for the quality of use, the concept of causability encompasses measurements for the quality of explanations produced by explainable AI methods. This paper describes both concepts and gives examples of how explainability and causability are essential in order to demonstrate scientific validity as well as analytical and clinical performance for future AI-based IVDs., (Copyright © 2022. Published by Elsevier B.V.)

Deep learning models have achieved high performance across different domains, such as medical decision-making, autonomous vehicles, decision support systems, among many others. However, despite this success, the inner mechanisms of these models are opaque because their internal representations are too complex for a human to understand. This opacity makes it hard to understand the how or the why of the predictions of deep learning models. There has been a growing interest in model-agnostic methods that make deep learning models more transparent and explainable to humans. Some researchers recently argued that for a machine to achieve human-level explainability, this machine needs to provide human causally understandable explanations, also known as causability. A specific class of algorithms that have the potential to provide causability are counterfactuals. This paper presents an in-depth systematic review of the diverse existing literature on counterfactuals and causability for explainable artificial intelligence (AI). We performed a Latent Dirichlet topic modelling analysis (LDA) under a Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework to find the most relevant literature articles. This analysis yielded a novel taxonomy that considers the grounding theories of the surveyed algorithms, together with their underlying properties and applications to real-world data. Our research suggests that current model-agnostic counterfactual algorithms for explainable AI are not grounded on a causal theoretical formalism and, consequently, cannot promote causability to a human decision-maker. Furthermore, our findings suggest that the explanations derived from popular algorithms in the literature provide spurious correlations rather than cause/effects relationships, leading to sub-optimal, erroneous, or even biased explanations. Thus, this paper also advances the literature with new directions and challenges on promoting causability in model-agnostic approaches for explainable AI. • A survey on model-agnostic counterfactual approaches for XAI. • A novel taxonomy for model-agnostic counterfactual approaches for XAI. • A set of properties for causability systems for XAI. • Opportunities and challenges for causability systems based on modelagnostic counterfactual approaches. [ABSTRACT FROM AUTHOR]

• Human-centered XAI design is required to create human-understandable explanations. • We present a human-centered design approach to develop explanations for AI systems. • User requirements for explanations from clinical support systems are derived. • A set of re-usable explanation design patterns for decision-support systems is created. [Display omitted] Much of the research on eXplainable Artificial Intelligence (XAI) has centered on providing transparency of machine learning models. More recently, the focus on human-centered approaches to XAI has increased. Yet, there is a lack of practical methods and examples on the integration of human factors into the development processes of AI-generated explanations that humans prove to uptake for better performance. This paper presents a case study of an application of a human-centered design approach for AI-generated explanations. The approach consists of three components: Do main analysis to define the concept & context of explanations, Re quirements elicitation & assessment to derive the use cases & explanation requirements, and the consequential M ulti-modal i nteraction design & evaluation to create a library of design patterns for explanations. In a case study, we adopt the DoReMi-approach to design explanations for a Clinical Decision Support System (CDSS) for child health. In the requirements elicitation & assessment, a user study with experienced paediatricians uncovered what explanations the CDSS should provide. In the interaction design & evaluation, a second user study tested the consequential interaction design patterns. This case study provided a first set of user requirements and design patterns for an explainable decision support system in medical diagnosis, showing how to involve expert end users in the development process and how to develop, more or less, generic solutions for general design problems in XAI. [ABSTRACT FROM AUTHOR]

• This study examines the effect of explainability in AI on user trust and attitudes toward AI. • Conceptualizes causability as an antecedent of explainability and as a key cue of an algorithm and examines them in relation to trust. • The dual roles of causability and explainability in terms of its underlying links to trust. • Causability lends the justification for what and how should be explained. • Causable explainable AI will help people understand the decision-making process of AI algorithms. Artificial intelligence and algorithmic decision-making processes are increasingly criticized for their black-box nature. Explainable AI approaches to trace human-interpretable decision processes from algorithms have been explored. Yet, little is known about algorithmic explainability from a human factors' perspective. From the perspective of user interpretability and understandability, this study examines the effect of explainability in AI on user trust and attitudes toward AI. It conceptualizes causability as an antecedent of explainability and as a key cue of an algorithm and examines them in relation to trust by testing how they affect user perceived performance of AI-driven services. The results show the dual roles of causability and explainability in terms of its underlying links to trust and subsequent user behaviors. Explanations of why certain news articles are recommended generate users trust whereas causability of to what extent they can understand the explanations affords users emotional confidence. Causability lends the justification for what and how should be explained as it determines the relative importance of the properties of explainability. The results have implications for the inclusion of causability and explanatory cues in AI systems, which help to increase trust and help users to assess the quality of explanations. Causable explainable AI will help people understand the decision-making process of AI algorithms by bringing transparency and accountability into AI systems. [ABSTRACT FROM AUTHOR]

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 [ABSTRACT FROM AUTHOR]