AI in Healthcare: Methods and Applications

Dear Colleagues,

The development of Artificial Intelligence (AI), along with its subcategories, such as deep learning and reinforcement learning, has led to significant success in various domains, including advanced image processing and pattern detection, and signal processing/recognition and its applications. However, this success comes with a clear gap which, without serious consideration, will hinder the further advancement of AI. Indeed, a great many AI and machine learning (ML) algorithms are viewed as “Black Boxes” when it comes to their applications, their parameters, and model characteristics, which cannot be fully interpreted most of the time, even by domain experts.

Cooperation between algorithms and humans depends on trust. This issue of lacking enough interpretation further increases the gap between decisions made via AI-supported diagnosis and trust from clinical/medical experts. Incompleteness in the formalization of trust criteria is a barrier to straightforward optimization approaches. As their nature dictates (life or death), decisions made in the clinical practice require an utmost understanding of their mechanisms. This absolute necessity can only be satisfied by leveraging the explainable AI (XAI), hence bridging the interpretation of advanced algorithms/solutions and the clinician’s trust. XAI algorithms are considered to follow three principles: transparency, interpretability, and explainability. In this context, if algorithms meet these requirements, they can provide a basis for justifying decisions, tracking and verifying them, further improving algorithms and, more importantly, exploring new clinical facts.

The purpose of this Special Issue is to reflect the state-of-the-art development of deep understanding/interpretation for AI/ML algorithms/applications in the medical/clinical domains and define future research directions/trends toward a better interpretation of AI in the healthcare field. Topics of interest include but are not limited to:

• Explainable AI in medical/clinical practice;
• XAI in healthcare;
• Medical learning theory and applications;
• Deep learning applications in healthcare;
• Expert system;
• Knowledge-based systems.

Dr. Su Yang
Dr. Erick Perwanto
Guest Editors

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. AI is an international peer-reviewed open access quarterly 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 1600 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.