Examining the effect of explanation on satisfaction and trust in AI diagnostic systems

Expert gaze as a usability indicator of medical AI decision support systems: a preliminary study

Given the current state of medical artificial intelligence (AI) and perceptions towards it, collaborative systems are becoming the preferred choice for clinical workflows. This work aims to address expert interaction with medical AI support systems to gain insight towards how these systems can be better designed with the user in mind. As eye tracking metrics have been shown to be robust indicators of usability, we employ them for evaluating the usability and user interaction with medical AI support systems. We use expert gaze to assess experts' interaction with an AI software for caries detection in bitewing x-ray images. We compared standard viewing of bitewing images without AI support versus viewing where AI support could be freely toggled on and off. We found that experts turned the AI on for roughly 25% of the total inspection task, and generally turned it on halfway through the course of the inspection. Gaze behavior showed that when supported by AI, more attention was dedicated to user interface elements related to the AI support, with more frequent transitions from the image itself to these elements. When considering that expert visual strategy is already optimized for fast and effective image inspection, such interruptions in attention can lead to increased time needed for the overall assessment. Gaze analysis provided valuable insights into an AI's usability for medical image inspection. Further analyses of these tools and how to delineate metrical measures of usability should be developed.

Technical/Algorithm, Stakeholder, and Society (TASS) barriers to the application of artificial intelligence in medicine: A systematic review

INTRODUCTION

The use of artificial intelligence (AI), particularly machine learning and predictive analytics, has shown great promise in health care. Despite its strong potential, there has been limited use in health care settings. In this systematic review, we aim to determine the main barriers to successful implementation of AI in healthcare and discuss potential ways to overcome these challenges.

METHODS

We conducted a literature search in PubMed (1/1/2001-1/1/2023). The search was restricted to publications in the English language, and human study subjects. We excluded articles that did not discuss AI, machine learning, predictive analytics, and barriers to the use of these techniques in health care. Using grounded theory methodology, we abstracted concepts to identify major barriers to AI use in medicine.

RESULTS

We identified a total of 2,382 articles. After reviewing the 306 included papers, we developed 19 major themes, which we categorized into three levels: the Technical/Algorithm, Stakeholder, and Social levels (TASS). These themes included: Lack of Explainability, Need for Validation Protocols, Need for Standards for Interoperability, Need for Reporting Guidelines, Need for Standardization of Performance Metrics, Lack of Plan for Updating Algorithm, Job Loss, Skills Loss, Workflow Challenges, Loss of Patient Autonomy and Consent, Disturbing the Patient-Clinician Relationship, Lack of Trust in AI, Logistical Challenges, Lack of strategic plan, Lack of Cost-effectiveness Analysis and Proof of Efficacy, Privacy, Liability, Bias and Social Justice, and Education.

CONCLUSION

We identified 19 major barriers to the use of AI in healthcare and categorized them into three levels: the Technical/Algorithm, Stakeholder, and Social levels (TASS). Future studies should expand on barriers in pediatric care and focus on developing clearly defined protocols to overcome these barriers.

Concept-based reasoning in medical imaging

PURPOSE

As concept-based reasoning for improving model interpretability becomes promising, the question of how to define good concepts becomes more pertinent. In domains like medical, it is not always feasible to access instances clearly representing good concepts. In this work, we propose an approach to use organically mined concepts from unlabeled data to explain classifier predictions.

METHODS

A Concept Mapping Module (CMM) is central to this approach. Given a capsule endoscopy image predicted as abnormal, the CMM's main task is to identify which concept explains the abnormality. It consists of two parts, namely a convolutional encoder and a similarity block. The encoder maps the incoming image into the latent vector, while the similarity block retrieves the closest aligning concept as explanation.

RESULTS

Abnormal images can be explained in terms of five pathology-related concepts retrieved from the latent space given by inflammation (mild and severe), vascularity, ulcer and polyp. Other non-pathological concepts found include anatomy, debris, intestinal fluid and capsule modality.

CONCLUSIONS

This method outlines an approach through which concept-based explanations can be generated. Exploiting the latent space of styleGAN to look for variations and using task-relevant variations for defining concepts is a powerful way through which an initial concept dictionary can be created which can subsequently be iteratively refined with much less time and resource.

Misplaced Trust and Distrust: How Not to Engage with Medical Artificial Intelligence

Artificial intelligence (AI) plays a rapidly increasing role in clinical care. Many of these systems, for instance, deep learning-based applications using multilayered Artificial Neural Nets, exhibit epistemic opacity in the sense that they preclude comprehensive human understanding. In consequence, voices from industry, policymakers, and research have suggested trust as an attitude for engaging with clinical AI systems. Yet, in the philosophical and ethical literature on medical AI, the notion of trust remains fiercely debated. Trust skeptics hold that talking about trust in nonhuman agents constitutes a category error and worry about the concept being misused for ethics washing. Proponents of trust have responded to these worries from various angles, disentangling different concepts and aspects of trust in AI, potentially organized in layers or dimensions. Given the substantial disagreements across these accounts of trust and the important worries about ethics washing, we embrace a diverging strategy here. Instead of aiming for a positive definition of the elements and nature of trust in AI, we proceed ex negativo, that is we look at cases where trust or distrust are misplaced. Comparing these instances with trust expedited in doctor-patient relationships, we systematize these instances and propose a taxonomy of both misplaced trust and distrust. By inverting the perspective and focusing on negative examples, we develop an account that provides useful ethical constraints for decisions in clinical as well as regulatory contexts and that highlights how we should not engage with medical AI.

Fairness and Explanation in AI-Informed Decision Making

AI-assisted decision-making that impacts individuals raises critical questions about transparency and fairness in artificial intelligence (AI). Much research has highlighted the reciprocal relationships between the transparency/explanation and fairness in AI-assisted decision-making. Thus, considering their impact on user trust or perceived fairness simultaneously benefits responsible use of socio-technical AI systems, but currently receives little attention. In this paper, we investigate the effects of AI explanations and fairness on human-AI trust and perceived fairness, respectively, in specific AI-based decision-making scenarios. A user study simulating AI-assisted decision-making in two health insurance and medical treatment decision-making scenarios provided important insights. Due to the global pandemic and restrictions thereof, the user studies were conducted as online surveys. From the participant’s trust perspective, fairness was found to affect user trust only under the condition of a low fairness level, with the low fairness level reducing user trust. However, adding explanations helped users increase their trust in AI-assisted decision-making. From the perspective of perceived fairness, our work found that low levels of introduced fairness decreased users’ perceptions of fairness, while high levels of introduced fairness increased users’ perceptions of fairness. The addition of explanations definitely increased the perception of fairness. Furthermore, we found that application scenarios influenced trust and perceptions of fairness. The results show that the use of AI explanations and fairness statements in AI applications is complex: we need to consider not only the type of explanations and the degree of fairness introduced, but also the scenarios in which AI-assisted decision-making is used.

Evaluating Explainable Artificial Intelligence for X-ray Image Analysis

The lack of justification of the results obtained by artificial intelligence (AI) algorithms has limited their usage in the medical context. To increase the explainability of the existing AI methods, explainable artificial intelligence (XAI) is proposed. We performed a systematic literature review, based on the guidelines proposed by Kitchenham and Charters, of studies that applied XAI methods in X-ray-image-related tasks. We identified 141 studies relevant to the objective of this research from five different databases. For each of these studies, we assessed the quality and then analyzed them according to a specific set of research questions. We determined two primary purposes for X-ray images: the detection of bone diseases and lung diseases. We found that most of the AI methods used were based on a CNN. We identified the different techniques to increase the explainability of the models and grouped them depending on the kind of explainability obtained. We found that most of the articles did not evaluate the quality of the explainability obtained, causing problems of confidence in the explanation. Finally, we identified the current challenges and future directions of this subject and provide guidelines to practitioners and researchers to improve the limitations and the weaknesses that we detected.