KD-HCM 2011 - Workshop on Knowledge Discovery in Health Care and Medicine (KD-HCM)

Throughout its modern existence, humankind has benefited from continuous advances in health care and medicine resulting in substantial improvements in the quality of life. Better disease understanding, improved medicines, and effective treatment protocols, are just some of the reasons behind the 10+ years increase in life expectancy from 1950 to 1997. However, in the last decade, despite the widely held belief that the post-genomic era will lead to substantial additional improvements, we have witnessed a considerable slow down at the rate at which new treatments are discovered and introduced into the health care system. In addition, the ever increasing costs associated with modern health care, makes it critical to reduce unnecessary treatments and procedures while still ensuring the best possible health outcomes. To this end, mining massive amounts of data being generated in health care is increasingly considered an integral part of technological breakthroughs needed to provide meaningful solutions to the above problems.

The purpose of this workshop is to report on the latest advances in data mining research for solving health care-related problems. The workshop is organized around the three themes of (i) mining of health-related data, (ii) mining in drug discovery, and (iii) mining for personalized medicine; all of which represent high-impact areas of ongoing and emerging data mining research. Health-related data (e.g., electronic health-records, health-related scientific literature, treatment and care guidelines, adverse effects reporting systems, health-related social media, etc.) provide an unprecedented opportunity for the development and application of data mining methods towards improving global health by identifying better practices and diagnosis, monitoring and predicting epidemics, and performing post-market surveillance of drugs and practices. Within the area of drug discovery, data mining is already an integral part of the drug development life cycle as it is used extensively to understand, predict and improve biological characteristics of therapeutic agents. In addition, exciting new opportunities for data mining research are emerging in drug discovery. Researchers in academia and industry have been developing data mining techniques to inform the design of novel drugs and biologics for novel and orphan molecular targets, to establish relations between the chemical and biological space in order to eliminate adverse side effects, to mine and predict absorption & distribution characteristics of drugs in humans, and to enhance the efficacy of a therapeutic agent by exploiting polypharmacology. Finally, personalized medicine is the next frontier in designing effective medical treatments. Personalized medicine is a broad term that encompasses technologies as well as practices in medicine tailored towards individual patients as opposed to standard of care principles generated from large samples of a given population. This involves identification of key bio-markers (e.g., genetic markers, proteomic profiles) and patient characteristics and associating them to certain outcomes such as efficacy and toxicity in the presence of a drug.
Suggested Topics (but not limited to the following) include:

Knowledge discovery in electronic medical records.

Text mining of unstructured and semi-structured biomedical health-related data, drug target validation, indications discovery, and adverse event mining.

Analysis of complex preclinical in-vivo outcomes.

Medical insurance fraud and abuse detection.

Patient-centered and evidence-based care.

Information retrieval for health applications.

Knowledge discovery for improving patient-provider communication.

Large-scale longitudinal mining of medical records.

Medical and wellness recommender system (e.g., medical products, fitness programs)

Personalized predictive modeling for clinical management.

Privacy preserving mining of health records.

Patient management.

Social media analytics for disease and outbreak monitoring and prediction.

Data integration for drug discovery research.

Gene expression analysis for target validation and toxicity analysis

Data-mining and machine learning in designing therapeutic agents.

Mining and prediction of characteristics such as absorption & distribution of therapeutic agents.

Patent mining and analysis for pharmaceutical research.

Computational discovery of genetic biomarkers for selecting the right patient population.

Integrating and mining diverse data (text, pathology, phenotypic data) to predict patient outcomes.

Pharmacovigilance and post-market surveillance.

Impact of social networks on personalized medicine.

Medical device fault detection and prevention.

Pattern recognition in medical images and data.

Important Dates:

Jun 7, 2011: Manuscripts Due.

Jul 1, 2011: Author Notification.

Jul 21, 2011: Camera-ready papers.

Sep 9, 2011: Workshop Day

Workshop Organizers:

Workshop Co-Chairs:

Huzefa Rangwala, George Mason University, US.

Andrea Tagarelli, University of Calabria, IT.

Nikil Wale, Pfizer, US.

George Karypis, University of Minnesota, US.

Program Committee

Shivani Agarwal, Indian Institute of Science, India

Sophia Ananiadou, National Centre for Text Mining, University of Manchester

Karsten Borgwardt, Max Planck Institute, Germany

Eric Gifford, CS CoE, Pfizer Inc, Groton, USA

Max Kuhn, Bio-statistics, Pfizer Inc, Groton, USA

Jessica Lin, George Mason University

Huan Luke, University of Kansas

Zoran Obradovic, Information Science and Technology Center, Temple University

Ketan Patel, CS CoE, Pfizer Inc, Sandwich UK

Jan Ramon, Katholieke Universiteit Leuven

I. V. Tetko, Helmholtz Zentrum, München, Germany

Alfonso Valencia, Spanish National Cancer Research Center

Ian A Watson, Eli lilly and Company, Indianapolis, USA

Ying Zhao, Tshingua University, China

Submission Instructions:

Submission Link: https://cmt.research.microsoft.com/KDHCM2011

Format : Papers submitted to this workshop should have a maximum length of 12 pages and formatted according to the Springer-Verlag Lecture Notes in Artificial Intelligence guidelines. Authors instructions and style files can be downloaded at http://www.springer.de/comp/lncs/authors.html.

Special Journal Issues : Authors of selected papers from the workshop will be invited to submit an extended version of their paper to a special issue of BMC Bioinformatics and/or International Journal