In today's environment, health care industry must balance between the often contradictory goals of cost reduction and improving quality of care. With growing costs and rising populations comes an inevitable paradigm shift towards accountable care where organizations are focusing on cost reduction, standardized care and quality improvement like never before. In addition, with the information overload in clinical literature coupled with the difficulty in extrapolating evidence from clinical trials to real world settings, providers find it difficult to select appropriate therapy for each patient. Thus far, health care has lagged behind other industries in improving operational performance and adopting technology-enabled process improvements.
It is possible to address many of these challenges by emulating and implementing best practices in health care by analyzing large amount of available information (extensive electronic health records recording patient conditions, diagnostic tests, labs, imaging exams, genomics, proteomics, treatments, outcomes, claims, financial records, clinical guidelines and best practices etc.). This data contains tremendously valuable hidden information relevant both for clinical and non-clinical decision support. At the heart of healthcare analytics is the ability to recognize (identify, classify and discover) patterns from the plethora of information available. As such, pattern recognition plays a pivotal role in the future of healthcare, specifically in healthcare analytics.
However, with the opportunities come challenges unique to the healthcare market. The healthcare sector creates large amounts of data, from various sources in diverse formats, often incomplete and contradictory. Data is highly fragmented, extremely noisy, sparse and often not randomly missing. Even when clinical data are in digital form, they are usually held by an individual provider and rarely shared due to privacy concerns. Yet another grand challenge is the regulatory approval for any patient care related discovery or innovation. More recently, all of this has gained significant traction and researchers have been trying to address these problems. However, the problems are not yet fully understood and the technology is far from mature.
The purpose of this workshop is to bring together pattern recognition and healthcare researchers interested in healthcare analytics and applications of pattern recognition in this field. The goal of the workshop will be to bridge the gap between the theory of pattern recognition and the applications and needs of the healthcare community. There will be exchange of ideas, identification of important and challenging applications and discovery of possible synergies. The emphasis will be on the mathematical and engineering aspects of pattern recognition and how it relates to practical medical problems.
The workshop program will consist of presentations by invited speakers from both pattern recognition and healthcare and by authors of papers submitted to the workshop. In addition, there will be a panel discussion to identify important problems, applications and synergies between pattern recognition and healthcare analytics disciplines. The intended audience of the workshop includes pattern recognition researchers interested in solving healthcare analytics problems, as well as the healthcare community in general including payers, providers and researchers.