Explainable Artificial Intelligence for Trustworthy Machine Learning and Deep Learning Models in Healthcare

Dear Colleagues,

With the advent of machine learning (ML)- and deep learning (DL)-empowered applications in critical domains such as healthcare, explainability has become one of the most heavily debated topics. The black-box nature of various DL and ML models is a roadblock to clinical utilization. Therefore, to gain the trust of clinicians and patients, we need to provide explanations about the decisions of DL and ML models. In this upcoming Special Issue, we welcome various research articles or reviews on explainable and interpretable ML techniques for various healthcare applications. The objective of this Special Issue is to explore the recent advances and techniques in the XAI (explainable artificial intelligence) area. Research topics of interest include (but are not limited to) the following:

• Transparent-by-design machine learning models;
• Transparent machine learning pipeline, from data collection to training, testing, and production;
• Ante-hoc and post-hoc XAI approaches in the medical domain;
• Context-sensitive, human-in-the-loop, and human-centric XAI algorithms;
• Explainable and interpretable state-of-the-art neural network architectures and algorithms (e.g., transformers) and non-neural network models (e.g., trees, kernel methods; clustering algorithms) for healthcare applications; 
• Interactive XAI using chatbots;
• Human–computer interaction for designing user interfaces for explainability;
• Black-box model auditing using XAI;
• Knowledge representation for human-centric explanations;
• Knowledge-enhanced semantic explanations;
• Role of fuzzy knowledge representation in XAI;
• Detecting data bias and algorithmic bias using XAI methods;
• Visualizing causal relationships;
• Integrating social and ethical aspects of explainability;
• Designing new explanation modalities;
• Multimodal XAI;
• Design, development, and evaluation of responsible XAI;
• Role of natural language generation in XAI;
• Novel criteria to evaluate explanation and interpretability;
• Applications of ontologies for explainability and trustworthiness in specific domains;
• Factual and counterfactual explanations;
• Causal thinking, reasoning, and modeling;
• Uncertainty quantification in XAI algorithms;
• Exploring existing and proposing new theoretical aspects of explainability and interpretability;
• Fairness, accountability, and transparency in healthcare XAI;
• Explainable AI, big data, electronic health record, and clinical decision support systems;
• Role of ontologies and knowledge in XAI;
• Empirical studies of (human-centric) XAI applications in healthcare, bioinformatics, and medical informatics.

Dr. Shaker El-Sappagh
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Diagnostics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.