You are required to read and agree to the below before accessing a full-text version of an article in the IDE article repository.

The full-text document you are about to access is subject to national and international copyright laws. In most cases (but not necessarily all) the consequence is that personal use is allowed given that the copyright owner is duly acknowledged and respected. All other use (typically) require an explicit permission (often in writing) by the copyright owner.

For the reports in this repository we specifically note that

  • the use of articles under IEEE copyright is governed by the IEEE copyright policy (available at http://www.ieee.org/web/publications/rights/copyrightpolicy.html)
  • the use of articles under ACM copyright is governed by the ACM copyright policy (available at http://www.acm.org/pubs/copyright_policy/)
  • technical reports and other articles issued by M‰lardalen University is free for personal use. For other use, the explicit consent of the authors is required
  • in other cases, please contact the copyright owner for detailed information

By accepting I agree to acknowledge and respect the rights of the copyright owner of the document I am about to access.

If you are in doubt, feel free to contact webmaster@ide.mdh.se

Causality in Explainable AI for Medical Applications

Publication Type:

Conference/Workshop Paper

Venue:

SciLifeLab Science Summit 2019


Abstract

AI-based medical applications, often casualty is lacking in explainable decision making. However, as human beings, we have the basic rights to ask the explanation with possible cause and effect of a machine generated decision. The challenge for AI model is to provide a better understanding of “why” different decisions have been made and “what can be the effect”. Conse-quently, reasoning on these “cause and effect” provides expla-nations for a better prediction. Introducing this casual aspect of the predicted decision and reasoning on them will be a step forward in the intelligent health monitoring systems. Today, of-ten huge amount of data from different sources are available for efficient decision making. casualty -based AI can enhance ef-ficiency in many levels such as monitoring patent’s state, better decision-making support for the Physicians, optimization of treatment support etc. Hence, a novel casual knowledge-based inference process in AI can create values for different actors. Such casual knowledge will define casual relations and argu-ments and indicates related events. Despite the inner complex structure of AI models the challenge here is to make the end-to-end learning paradigm explainable for human understand-ing. Integrating this casual knowledge in AI will support the total decision making from possibility to probability and could certainly be helpful for areas where meaningful communica-tions and trustworthy relations between a human and artificial intelligence system is necessary such as in health domain.

Bibtex

@inproceedings{Begum5640,
author = {Shahina Begum and Shaibal Barua and Mobyen Uddin Ahmed},
title = {Causality in Explainable AI for Medical Applications },
month = {May},
year = {2019},
booktitle = {SciLifeLab Science Summit 2019},
url = {http://www.es.mdu.se/publications/5640-}
}