Data-driven Prediction and Decision-making on Health Care

Introduction

   In theory, data-driven prediction and decision making should enable us to combine big data sets and machine learning methods to establish prediction models and decision support systems. In healthcare, ‘big data environments’ like patient history data exist, which could be utilised to predict health events that have the potential to improve patient care. However, these real-world ‘dirty’ data sets are far from perfect, and present many real-world challenges to extract meaningful insights and predictions.

    Cross-functional research has the potential to enhance the productivity and accuracy of real-world big data applications, and improve the quality of organisational data-based decisions. Successful developments have emerged for data mining techniques for prediction, data inference methods for decision support and fuzzy machine learning for classification. These have been applied to a diverse range of fields, including organisational decision-making, product and service evaluation, social crisis prediction, resource planning, logistics optimisation, customer relationship management, knowledge management, and importantly in public health and medical fields. Leveraging the lessons learned across other fields, MedicalDirector® and the Center for Artificial Intelligence at the University of Technology Sydney (CAI.UTS) have partnered to improve real-world data prediction modelling in the healthcare space.

   MedicalDirector® is a leading provider of quality health information and software in Australia. Its software powers Australia’s healthcare industry and provides electronic health records, patient management, billing, scheduling, care coordination and population health management services to general practice, specialists and hospitals. The CAI.UTS is a world-leading research center in data science in Australia. They have been working together to develop data-driven prediction and decision support systems, as well as related applications in healthcare using advanced machine learning technologies.

   MD and UTS will co-chair this special session, drawing on the insights and experience of their research partnership to promote similar collaboration between experts, scholars, researchers and academics across different fields to work together. This special session will offer a systematic overview of this new field and will provide innovative approaches to handling various data-driven decision-making issues in primary healthcare, by applying advanced machine learning and other computational intelligent techniques.

Scope and Topics

The main topics of this special session include, but are not limited to, the following:
  • Data-driven prediction and decision making framework
  • Data-driven prediction and decision making methodology
  • Recommender systems for medicine and healthcare services
  • Tools and techniques for healthcare big data analytics
  • Artificial intelligence methods for big data analytics in healthcare area
  • Techniques to address data driven decision support systems in healthcare big data
  • Feature selection and extraction techniques for healthcare big data processing
  • Clustering, modelling and neural networks in healthcare big data
  • Uncertain data presentation and modelling in cloud computing for healthcare

Special Session Organisers

  • Hua Lin, Catherine Panwar, MedicalDirector, Australia, Email: hua.lin@medicaldirector.com
  • Jie Lu, Guangquan Zhang, Center for Artificial Intelligence, University of Technology Sydney, Australia, Email: Jie.Lu@uts.edu.au

Important Dates


1 Paper Submission Deadline: Aug 1, 2017
2 Notification Acceptance: Sep 1, 2017
3 Camera-ready Paper and Registration: Sep 25, 2017