ACM BCB Workshop on Methods and Applications in Healthcare Analytics

October 2, 2016.
This workshop  is held in conjunction with the ACM BCB conference in 2016 at Seattle, WA.

Confirmed Speakers

Prof. Daniela Witten's research involves the development of statistical machine learning methods for high-dimensional data, with applications to genomics and other fields. Daniela is a co-author (with Gareth James, Trevor Hastie, and Rob Tibshirani) of the very popular textbook "Introduction to Statistical Learning". She was a member of the Institute of Medicine committee that released the report "Evolution of Translational Omics". 

Daniela is the recipient of a number of honors, including a NDSEG Research Fellowship, an NIH Director's Early Independence Award, a Sloan Research Fellowship, and an NSF CAREER Award. Her work has been featured in the popular media: among other forums, in Forbes Magazine (three times), Elle Magazine, on KUOW radio, and as a PopTech Science Fellow. 

Daniela completed a BS in Math and Biology with Honors and Distinction at Stanford University in 2005, and a PhD in Statistics at Stanford University in 2010. Since 2014, Daniela is an associate professor in Statistics and Biostatistics at University of Washington.
Talk Title: Learning from Time
Abstract: TBD

Prof. Wanpracha Art Chaovalitwongse is 21st Century Leadership Chair in Engineering, Professor of Industrial Engineering, and Co-Director of the Institute of Advanced Data Analytics at the University of Arkansas, Fayetteville. He previously worked as Full Professor in the Departments of Industrial & Systems Engineering and Radiology (joint) and Adjunct Professor in the Department of Bioengineering at the University of Washington, Seattle (UW). There, he also served as Associate Director of the Integrated Brain Imaging Center (IBIC) at UW Medical Center. Before moving to Seattle, he worked as Visiting Associate Professor in the Department of Operations Research & Financial Engineering at Princeton University. He was also on the faculty in the Department of Industrial & Systems Engineering at Rutgers University. Before working in academia, he worked at the Corporate Strategic Research, ExxonMobil Research & Engineering. His research group conducts extensive Analytics research, ranging from basic computational science/statistics, applied mathematical modeling, and translational research at the interface of engineering, medicine, and other emerging disciplines. He holds three patents of novel optimization techniques in seizure prediction system, which have been licensed to use in IdentEvent® by Optima Neuroscience, Inc. His academic honors include 2003 Excellence in Research from the University of Florida, 2006 NSF CAREER Award, 2004 & 2008 (2-times winner) William Pierskalla Best Paper Award by the Institute for Operations Research and the Management Sciences (INFORMS), 2009 Outstanding Service Award by the Association of Thai Professionals in America and Canada, 2010 Rutgers Presidential Fellowship for Teaching Excellence, 2014 Finalist of the UW College of Engineering Faculty Innovator Award, 2016 Finalist of the UW College of Engineering Faculty Award in Teaching and Learning, 2016 Finalist of the UW Distinguished Teaching Award, and several other best student paper awards with his PhD students. He has been invited to give lectures in top universities around the world including MIT, Princeton University, University of Michigan, National University of Singapore, Peking University, Chinese Academy of Sciences, Seoul National University, and KAIST. He currently serves as Associate Editor and Editorial Board Member of 10 leading international journals. He has edited 4 books and published over 100 research articles including more than 80 journal papers. He is the immediate past Chair of INFORMS Data Mining (DM) Section, and the President of the Association of Thai Professionals in America and Canada (ATPAC), which is a non-profit organization that works closely with Thailand's Ministry of Science and Technology, the Office of the Higher Education Commission, and the Royal Embassy of Thailand in Washington DC.Talk Title: Optimization in Medical Analytics: From Data to Knowledge to Decisions
Abstract: Feature selection and classification are the central premise of data analytics. In this talk, I will discuss some recent advances in computational optimization techniques for feature selection and classification that have been developed in my group. Selecting an optimal set of features used in a prediction model is a combinatorial optimization problem, which can be computationally challenging. Yet, the feature set also needs to avoid overfitting the prediction model. The main driving application of our techniques is in medical analytics, which is to assist physicians in recognizing abnormality patterns (and/or patterns of interest) in medical signal and imaging data. While the main objective of most decision models is to provide an accurate decision or prediction outcome, clinical and scientific interpretation of such models is also extremely important. I will present four real life problems of our medical analytics: (1) motion management in radiation treatment planning for lung cancer, (2) prediction of surgical target in knee surgery, (3) diagnostic classification of developmental disorder, (4) prediction of neural response to visual stimuli, and (5) diagnostic classification of neurodegenerative disease.


 Time Presenter/Authors Title
 8:30-8:35Organizers Opening Remarks
 8:35-9:10Peter Haug and Jeffrey FerraroUsing a Semi-Automated Modeling Environment to Construct a Bayesian, Sepsis Diagnostic System
 9:10-10:10Wanpracha Art ChaovalitwongseOptimization in Medical Analytics: From Data to Knowledge to Decisions
 10:10-10:30Coffee Break 
 10:30-11:05Alexander TitusRebecca Faill and Amar DasAutomatic Classification of Co-Occurring Patient Events
Orhan Abar, Richard J Charnigo, Abner Rayapati and Ramakanth Kavuluru
On Interestingness Measures for Mining Statistically Significant and Novel Clinical Associations from EMRs
 11:40-1:30  Lunch Break
 1:30-2:30Daniela Witten Learning from Time
 2:30-3:05 Ryan Bridges, Jette Henderson, Joyce Ho, Byron Wallace and Joydeep Ghosh Automated Verification of Phenotypes using PubMed
3:05-3:30 Coffee Break
 3:30-4:05 Mayana Pereira, Vikhyati Singh, Chun Pan Hon, T. Greg McKelvey, Shanu Sushmita and Martine De Cock Predicting Future Frequent Users of Emergency Departments in California State
 4:05-4:40 Mattia Prosperi, Alejandro Pironti, Francesca Incardona, Giuseppe Tradigo and Maurizio Zazzi Predicting human-immunodeficiency virus rebound after therapy initiation/switch using genetic, laboratory, and clinical data
 4:40-5:15 Giovanni Canino, Qiulings Suo, Pietro H. Guzzi, Giuseppe Tradigo, Aidong Zhang and Pierangelo Veltri Feature Selection Model for Diagnosis, Electronic Medical Records and Geographical Data Correlation
 5:15-5:20  Closing Remarks


Healthcare is undergoing a massive transition, due to changes in payment incentives, growth of clinical data warehouses, advances in genome sequencing technology and digital imaging,  as well as the increased role of the patient in managing their own health information and rapid accumulation of biomedical knowledge. As a result, data analytics techniques, for knowledge discovery and deriving data driven insights from various data sources, are increasingly important  in modern healthcare. Although, effective analytical approaches have been applied in many healthcare problems, several challenges remain including: data heterogeneity, sparsity, irregular sampling and the difficulty of drawing inferences from such data. This proposed workshop will focus on novel methodologies and their applications in addressing these emerging healthcare analytics problems from both academia and industry.

Topics to Be Covered
  • Analytics Methodologies
    • Active Learning
    • Clinical alerting and outlier detection
    • Cloud/Distributed-computing models and scalability 
    • Collaborative care delivery models 
    • Combining knowledge and data drive insights
    • Disease progression modeling
    • Intelligent payment models 
    • Privacy-preserving methods
    • Sparse modeling and optimization methods 
    • Temporal analysis
    • Visual analytics
  • Healthcare Applications
    • Clinical dashboards
    • Clinical decision support system
    • Clinical pathway analysis
    • Comparative effectiveness research
    • Precision medicine

Important Dates

  • Submission Deadline: June 26, 2016.
  • Notification: July 20, 2016.
  • Camera-Ready: July 27, 2016.

Submission Instruction

All submissions should be made to manuscripts should not exceed 10 pages in ACM template on 8.5 x 11 inch paper. The workshop's technical program committee will review all submissions on the basis of their originality, technical soundness, significance, presentation, and relevance to the conference attendees.


Program Committee