organised by

Invited Talk 2019

Machine Learning using Medical Data: Revolution or Evolution?

Prof. Dr. Mehmed Kantardzic, Professor

  • Associate Chair of CECS Department & Director of CECS Graduate Programs
  • Director of Data Mining Lab
  • Computer Engineering and Computer Science Department
  • J. B. Speed School of Engineering
  • University of Louisville
  • Louisville, KY, USA
  • Web: http://cecs.louisville.edu/datamining/
  • ...

    Abstract

    Machine learning has initiated tremendous innovations in many sectors, from speech recognition and sentiment analysis to spam filters, chat-bots and autonomous car driving. While the adoption of machine learning in these sectors is becoming almost ubiquitous, its introduction into the medical field has been much slower with relatively small number of real world clinical applications. This landscape in a medical domain, however, is rapidly changing. Gaining knowledge and actionable insights from complex, high-dimensional and heterogeneous biomedical data remains a key challenge in transforming modern health care. While the potential for machine learning to fundamentally change the way we practice medicine is now well-appreciated, we have to note some limitations of the current approaches for their expanded use in healthcare. After years of hype mixed with overblown fears about machine learning trends, which is both dangerous and biased, the research and clinical application of machine learning are reaching a more serious and smoother phase, where interdisciplinary approach is helping in overcoming some of current very serious challenges.

  • presentation © Shutterstock presentation © Petra Perner presentation © Shutterstock