Call for Chapters

Explainable Artificial Intelligence (XAI) in Healthcare

Edited by Utku Kose, Nilgun Sengoz, Xi Chen, Jose Antonio Marmolejo Saucedo 

to be published by CRC Press

Machine learning, the development of systems that learn from data to recognize patterns and make accurate predictions about future events, has great potential to transform healthcare. Machine learning-based tools can support complex clinical decision-making and automate many routine tasks that can waste healthcare professionals' time and cause job dissatisfaction. Issues with data security and privacy, poor performance of mathematical models or high accuracy models acting as black-boxes, difficulty integrating tools into the workflow, low acceptability of machine learning-based solutions among healthcare professionals, and uncertainty about how to evaluate these solutions There may be barriers to its adoption.

The word black-box mentioned here can be semantically defined as a lack of observability. Since algorithms with a large number of hidden layers such as deep learning networks have black-box models, they create a lack of explanation and trust to the end user.

Developing machine learning-based solutions for clinical purposes requires a solid understanding of clinical care, image processing, data science and application science. A solution design phase for the development of machine learning-based models and user-friendly tools to define the development and adoption of machine learning-based solutions, and an implementation and evaluation phase for the deployment of the solution, an evaluation of the solution and its impact are required. In artificial intelligence (AI), many "data-driven" approaches, and deep learning in particular, suffer from a lack of explainability. They make good predictions in terms of performance accuracy but cannot explain them. In this context, physicians need to understand the recommendations of decision support systems in order to adhere to them. For this reason, Explainable Artificial Intelligence (XAI) is emerging as a new trend in the field of artificial intelligence to overcome such problems. Especially in the health sector, which is one of the critical decision-making areas, the adaptation of artificial intelligence has always been one step behind due to the lack of trust.

This book will introduce use of Explainable Artificial Intelligence (XAI) systems for healthcare field just not for engineers also for clinicians who want to use artificial intelligence for detecting and diagnose the disease effectively. So, this book will appeal to everyone in a broad sense.

Submission Guidelines

All full chapter submissions should be done by e-mail to: utkukose@gmail.com and / or nilgunsengoz@gmail.com

All papers must be original and not simultaneously submitted to another book project, journal or conference.

Interested authors should use the template file and prepare other associated documents inside the authors-file here: https://utkukose.com/Author_Files_CRC.zip

Before submitting your work(s), you may also contact utkukose@gmail.com and / or nilgunsengoz@gmail.com for any queries regarding chapter preparment.

Submissions can be done till the following date (before preparing full chapter, it may appropriate to send brief proposal / abstract for pre-acceptance by the editors): 

• Chapter Proposal Submission: 2 April 2023
• Full Chapter Submission: 28 May 2023
• Notification of Accept. / Reject.: 7 June 2023
• Final Chapter Submission: 9 July 2023

Important: Similarity Rate for the full chapter should be max. 15%. The authors able to get similarity report are suggested to send the similarity reports with other files.

List of Topics (as not limited to)

• Fundamental concepts of Explainable AI
• Transparency interventions in black-box/opaque systems in biomedical problems
• Simulatability, Decomposability, and Algorithmic transparency for biomedical
• XAI Techniques/Frameworks/Tools
• Interpretable Machine Learning in biomedical applications
• XAI for Deep Learning in biomedical applications
• Evaluation Methods and Metrics for XAI
• XAI for disease diagnosis
• XAI for medical treatment processes
• XAI for drug discovery
• IoHT / medical environments with XAI support
• XAI for medical robotics
• XAI for massive data control (i.e. pandemics),
• Usability evaluation of XAI in biomedical applications,
• Human-compatibility with XAI in biomedical problems,
• Anxieties in XAI for biomedical,
• Open problems in XAI for biomedical applications,
• Ethical, Legal and Social Issues of XAI in Healthcare
• Future perspectives in XAI for biomedical applications.
• ...etc.

Editors

• Utku Kose, PhD. (Suleyman Demirel University, Turkey)
• Nilgun Sengoz, PhD. (Burdur Mehmet Akif Ersoy University, Turkey)
• Xi Chen, PhD. (Meta, USA)
• Jose Antonio Marmolejo Saucedo (National Autonomous University of Mexico, Mexico)

Publication

'Explainable Artificial Intelligence in Healthcare' will be published by CRC Press, a member of Taylor & Francis Group, UK.

Contact

All questions about submissions should be emailed to: utkukose@gmail.com and / or nilgunsengoz@gmail.com