A Multi-Component Framework for the Analysis and Design of Explainable Artificial Intelligence

Kim, Miyoung; Atakishiyev, Shahin; Babiker, Housam Khalifa Bashier; Farruque, Nawshad; Goebel, Randy; Zaı̈ane, Osmar R.; Motallebi, Mohammad-Hossein; Rabelo, Juliano; Syed, Talat Iqbal; Yao, Hengshuai; Chun, Peter

doi:10.3390/make3040045

Cited by 28 publications

(23 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a consequence, we conclude that heatmaps are a good start but remain one of the weaker XAI methods, as they are not semantically driven and can only provide low-level, post-hoc explanations 37 . Other methods such as gradient-based saliency maps, Class Activation Mapping, and Excitation Backpropagation can all be considered in future work 38,39 .…”

Section: Discussionmentioning

confidence: 92%

Artificial intelligence enabled automated diagnosis and grading of ulcerative colitis endoscopy images

Sutton

Ane

Goebel

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Endoscopic evaluation to reliably grade disease activity, detect complications including cancer and verification of mucosal healing are paramount in the care of patients with ulcerative colitis (UC); but this evaluation is hampered by substantial intra- and interobserver variability. Recently, artificial intelligence methodologies have been proposed to facilitate more objective, reproducible endoscopic assessment. In a first step, we compared how well several deep learning convolutional neural network architectures (CNNs) applied to a diverse subset of 8000 labeled endoscopic still images derived from HyperKvasir, the largest multi-class image and video dataset from the gastrointestinal tract available today. The HyperKvasir dataset includes 110,079 images and 374 videos and could (1) accurately distinguish UC from non-UC pathologies, and (2) inform the Mayo score of endoscopic disease severity. We grouped 851 UC images labeled with a Mayo score of 0–3, into an inactive/mild (236) and moderate/severe (604) dichotomy. Weights were initialized with ImageNet, and Grid Search was used to identify the best hyperparameters using fivefold cross-validation. The best accuracy (87.50%) and Area Under the Curve (AUC) (0.90) was achieved using the DenseNet121 architecture, compared to 72.02% and 0.50 by predicting the majority class (‘no skill’ model). Finally, we used Gradient-weighted Class Activation Maps (Grad-CAM) to improve visual interpretation of the model and take an explainable artificial intelligence approach (XAI).

show abstract

Section: Discussionmentioning

confidence: 92%

Artificial intelligence enabled automated diagnosis and grading of ulcerative colitis endoscopy images

Sutton

Ane

Goebel

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Although deep learning models currently have the ability to conduct language processing tasks such as tagging, text classification, machine translation, and question answering, existing state-of-the-art models are criticized for lacking explainability —more specifically, being able to describe how the algorithm came to a particular result or action, which is considered a key pillar in discourse around ethical AI development [ 103 - 105 ]. This and future studies must seek to improve the methods of explainable NLP.…”

Section: Discussionmentioning

confidence: 99%

Developing, Implementing, and Evaluating an Artificial Intelligence–Guided Mental Health Resource Navigation Chatbot for Health Care Workers and Their Families During and Following the COVID-19 Pandemic: Protocol for a Cross-sectional Study

Noble¹,

Zamani²,

Gharaat³

et al. 2022

JMIR Res Protoc

Self Cite

View full text Add to dashboard Cite

Background Approximately 1 in 3 Canadians will experience an addiction or mental health challenge at some point in their lifetime. Unfortunately, there are multiple barriers to accessing mental health care, including system fragmentation, episodic care, long wait times, and insufficient support for health system navigation. In addition, stigma may further reduce an individual’s likelihood of seeking support. Digital technologies present new and exciting opportunities to bridge significant gaps in mental health care service provision, reduce barriers pertaining to stigma, and improve health outcomes for patients and mental health system integration and efficiency. Chatbots (ie, software systems that use artificial intelligence to carry out conversations with people) may be explored to support those in need of information or access to services and present the opportunity to address gaps in traditional, fragmented, or episodic mental health system structures on demand with personalized attention. The recent COVID-19 pandemic has exacerbated even further the need for mental health support among Canadians and called attention to the inefficiencies of our system. As health care workers and their families are at an even greater risk of mental illness and psychological distress during the COVID-19 pandemic, this technology will be first piloted with the goal of supporting this vulnerable group. Objective This pilot study seeks to evaluate the effectiveness of the Mental Health Intelligent Information Resource Assistant in supporting health care workers and their families in the Canadian provinces of Alberta and Nova Scotia with the provision of appropriate information on mental health issues, services, and programs based on personalized needs. Methods The effectiveness of the technology will be assessed via voluntary follow-up surveys and an analysis of client interactions and engagement with the chatbot. Client satisfaction with the chatbot will also be assessed. Results This project was initiated on April 1, 2021. Ethics approval was granted on August 12, 2021, by the University of Alberta Health Research Board (PRO00109148) and on April 21, 2022, by the Nova Scotia Health Authority Research Ethics Board (1027474). Data collection is anticipated to take place from May 2, 2022, to May 2, 2023. Publication of preliminary results will be sought in spring or summer 2022, with a more comprehensive evaluation completed by spring 2023 following the collection of a larger data set. Conclusions Our findings can be incorporated into public policy and planning around mental health system navigation by Canadian mental health care providers—from large public health authorities to small community-based, not-for-profit organizations. This may serve to support the development of an additional touch point, or point of entry, for individuals to access the appropriate services or care when they need them, wherever they are. International Registered Report Identifier (IRRID) PRR1-10.2196/33717

show abstract

“…It enhances the social acceptance of the decisions made by the system, with a proper explanation of the decision being made. Implementing such a multicomponent framework for XAI system analysis imparts deeper trust in the system [61]. • Visual analytics: With interaction representations of the decisions made by the XAI systems, the incorporation of visual analytics makes humans understand the decisionmaking process of AI systems with much ease.…”

Section: A Explainable Aimentioning

confidence: 99%

Explainable AI Over the Internet of Things (IoT): Overview, State-of-the-Art and Future Directions

Jagatheesaperumal¹,

Pham

Ruby

et al. 2022

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

Explainable Artificial Intelligence (XAI) is transforming the field of Artificial Intelligence (AI) by enhancing the trust of end-users in machines. As the number of connected devices keeps on growing, the Internet of Things (IoT) market needs to be trustworthy for the end-users. However, existing literature still lacks a systematic and comprehensive survey work on the use of XAI for IoT. To bridge this lacking, in this paper, we address the XAI frameworks with a focus on their characteristics and support for IoT. We illustrate the widely-used XAI services for IoT applications, such as security enhancement, Internet of Medical Things (IoMT), Industrial IoT (IIoT), and Internet of City Things (IoCT). We also suggest the implementation choice of XAI models over IoT systems in these applications with appropriate examples and summarize the key inferences for future works. Moreover, we present the cutting-edge development in edge XAI structures and the support of sixth-generation (6G) communication services for IoT applications, along with key inferences. In a nutshell, this paper constitutes the first holistic compilation on the development of XAI-based frameworks tailored for the demands of future IoT use cases.

show abstract

A Multi-Component Framework for the Analysis and Design of Explainable Artificial Intelligence

Cited by 28 publications

References 34 publications

Artificial intelligence enabled automated diagnosis and grading of ulcerative colitis endoscopy images

Artificial intelligence enabled automated diagnosis and grading of ulcerative colitis endoscopy images

Developing, Implementing, and Evaluating an Artificial Intelligence–Guided Mental Health Resource Navigation Chatbot for Health Care Workers and Their Families During and Following the COVID-19 Pandemic: Protocol for a Cross-sectional Study

Explainable AI Over the Internet of Things (IoT): Overview, State-of-the-Art and Future Directions

Contact Info

Product

Resources

About