AI4H:B2E 2019 : IEEE Special Track on AI for Healthcare: from black box to explainable models
CALL FOR PAPERS
The special track on “Artificial Intelligence for Healthcare: from black box to explainable models” - AI4H:B2E 2019 - aims at bringing together researchers from academia, industry, government and medical centers in order to present the state of the art and discuss the latest advances in the emerging area of the use of Artificial Intelligence (AI) and Soft Computing (SC) techniques in the fields of medicine, biology, healthcare and wellbeing.
In general, in recent years, methods based on AI and SC have proved to be extremely useful in a wide variety of areas, and are becoming more and more widespread, in some cases a sort of a “de facto” standard.
Currently, many of the algorithms on offer are often black box in nature (defined as a system which can be viewed in terms of its inputs and outputs without any knowledge of its internal workings). This may not be an issue for certain practical AI solutions in healthcare, yet in other systems it may indeed be a serious limitation. This holds true when a clear explanation should be provided to a user about the reasons why a solution is proposed by an AI-based system. In fact, if the predictive models are not transparent and explainable, we lose the trust of experts such as healthcare practitioners. Moreover, without access to the knowledge of how an algorithm works we cannot truly understand the underlying meaning of the output.
Given the above general framework, AI4H:B2E is expected to cover the whole range of methodological and practical aspects related to the use of AI and SC in Healthcare:
- we request papers that explore methods to combine state-of-the-art data analytics for exploiting the huge data resources available, while ensuring that these systems are explainable to domain experts. This will result in systems that not only generate new insights but are also more fully trusted.
- we also request papers that describe more generally the successful application of AI and SC methodologies to issues as machine learning, deep learning, knowledge discovery, decision support, regression, forecasting, optimization and feature selection in the healthcare, biology, medicine and wellbeing domains.
- explainable AI models:
- Rule and Logic Based Explanation;
- Deep Learning and methods to explain Hidden Layers;
- Assistive Technology (AT);
- Recommender Systems;
- Natural Language for Explanation;
- Visualisation & Interactive Interfaces;
- the general application of AI and SC methodologies, in Health, Biology and Medicine to issues such as:
- Knowledge Management of Health Data;
- Data Mining and Knowledge Discovery in Healthcare;
- Machine and Deep learning approaches for Health Data;
- Decision Support Systems for Healthcare and Wellbeing;
- Optimization for Healthcare problems;
- Regression and Forecasting for medical and/or biomedical signals;
- Healthcare Information Systems;
- Wellness Information Systems;
- Medical Signal and Image Processing and Techniques;
- Medical Expert Systems;
- Diagnosis and Therapy Support Systems;
- Biomedical Applications;
- Applications of AI in Healthcare and Wellbeing Systems;
- Machine Learning-based Medical Systems;
- Medical Data and Knowledge Bases;
- Neural Networks in Medicine;
- Ambient Intelligence and Pervasive Computing in Medicine and Healthcare.
Best Paper Award
A "Best Paper Award" will be conferred on the author(s) of a paper presented at the Special Track, selected by the Chairs based on the best combined marks of paper reviewing, assessed by the Program Committee. This best paper award is technically sponsored by the Institute of High Performance and Computing of the National Research Council of Italy (ICAR- CNR).