Workshop on Knowledge Discovery in Health Care and Medicine
 Athens, Greece part of ECML PKDD 2011

Sep 9, 2011



Update: Program Schedule here .

Update: Workshop Proceedings here .

Update: Papers in PDF here .

Workshop Description:

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:

  1. Bullet    Knowledge discovery in electronic medical records.

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

  3. Bullet     Analysis of complex preclinical in-vivo outcomes.

  4. Bullet     Medical insurance fraud and abuse detection.

  5. Bullet     Patient-centered and evidence-based care.

  6. Bullet    Information retrieval for health applications.

  7. Bullet    Knowledge discovery for improving patient-provider communication.

  8. Bullet    Large-scale longitudinal mining of medical records.

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

  10. Bullet    Personalized predictive modeling for clinical management.

  11. Bullet    Privacy preserving mining of health records.

  12. Bullet    Patient management.

  13. Bullet    Social media analytics for disease and outbreak monitoring and prediction.

  14. Bullet    Data integration for drug discovery research.

  15. Bullet    Gene expression analysis for target validation and toxicity analysis

  16. Bullet    Data-mining and machine learning in designing therapeutic agents.

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

  18. Bullet    Patent mining and analysis for pharmaceutical research.

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

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

  21. Bullet    Pharmacovigilance and post-market surveillance.

  22. Bullet    Impact of social networks on personalized medicine.

  23. Bullet    Medical device fault detection and prevention.

  24. Bullet    Pattern recognition in medical images and data.

Important Dates:

  1. Bullet    Jun 11, 2011: Manuscripts Due.

  2. Bullet    Jul  1, 2011: Author Notification.

  3. Bullet    Jul  21, 2011: Camera-ready papers.

  4. Bullet    Sep    9, 2011: Workshop Day

Workshop Organizers:

Workshop  Co-Chairs:

  1. Bullet   Huzefa Rangwala, George Mason University, US.

  2. Bullet    Andrea Tagarelli, University of Calabria, IT.

  3. Bullet    Nikil Wale, Pfizer, US.

  4. Bullet    George Karypis, University of Minnesota, US.

Program Committee


  1. Bullet     Shivani Agarwal, Indian Institute of Science, India

  2. Bullet     Sophia Ananiadou, National Centre for Text Mining, University of Manchester

  3. Bullet     Karsten Borgwardt, Max Planck Institute, Germany

  4. Bullet     Eric Gifford, CS CoE, Pfizer Inc, Groton, USA

  5. Bullet     Max Kuhn, Bio-statistics, Pfizer Inc, Groton, USA

  6. Bullet     Jessica Lin, George Mason University

  7. Bullet     Huan Luke, University of Kansas

  8. Bullet     Zoran Obradovic, Information Science and Technology Center, Temple University

  9. Bullet   Ketan Patel, CS CoE, Pfizer Inc, Sandwich UK

  10. Bullet     Jan Ramon, Katholieke Universiteit Leuven

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

  12. Bullet     Alfonso Valencia, Spanish National Cancer Research Center

  13. Bullet     Ian A Watson, Eli lilly and Company, Indianapolis, USA

  14. Bullet     Ying Zhao, Tshingua University, China

Submission Instructions:

Submission Link:

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

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 of Data Mining and Bioinformatics