DMBIH WORKSHOP 2017

Data Mining in Biomedical Informatics and Healthcare (DMBIH) Workshop 2017

New Orleans, LA, USA. November 18-21, 2017
In conjunction with the IEEE ICDM 2017

The Fifth Workshop on Data Mining in Biomedical Informatics and Healthcare aims to provide a forum for data miners, informacists, data scientists, and clinical researchers to share their latest investigations in applying data mining techniques to biomedical and healthcare data. The increasing availability of large and complex data sets to the research community, triggers the need to develop more advanced and sophisticated data analytical techniques to exploit and manage these big data. The broader context of the workshop comprehends artificial intelligence, information retrieval, machine learning, and knowledge extraction methods using biomedical image analysis and natural language processing. Submissions are invited to address the need for developing new methods to mine, summarize and integrate the huge volume and diverse modalities of the structured and unstructured biomedical and healthcare data that can potentially lead to significant advances in the field.

Overview

Last Years' Workshop Page
2016:  http://idal.uv.es/dmbih16/

Sponsors:

  • School of Engineering and Computer Science, Oakland University
  • College of Computing and Digital Media, DePaul University

Topics of interest include but are not limited to:

  • Classifying and clustering big data in electronic health records (EHRs)
  • Classifying and clustering temporal data in EHRs and biomedical data in high dimensional spaces
  • Application of deep learning methods to clinical data
  • Topic modeling / detection in large amounts of clinical textual data
  • Data preprocessing and cleansing to deal with noise and missing data in large biomedical or population health data sets
  • Algorithms to speed up the analysis of big biomedical data
  • Novel visualization techniques to facilitate the query and analysis of clinical data
  • Statistics and probability in large-scale data mining
  • Evidence-based medicine
  • Medical image data mining
  • HIPAA compliance data mining
  • Pharmacogenomics data mining
  • Biological markers detection
  • Biological and clinical data analysis and integration for translational research
  • Computational genetics, genomics and proteomics
Organization

Workshop Chairs
Mohammad-Reza Siadat, Oakland University
Daniela Stan Raicu, DePaul University

Workshop Organization Committee
Samah Jamal Fodeh, Yale University
José D. Martín-Guerrero, University of Valencia
Daniela Stan Raicu, DePaul University
Mohammad-Reza Siadat, Oakland University

Program Committee
  • Sameer Antani, NIH National Library of Medicine
  • Suzan Arslanturk, Wayne State University
  • Abbas Babajani-Feremi, University of Tennessee Health Science Center
  • Hamidreza Chitsaz, Colorado State University
  • Carlo Combi, Universita’ degli Studi di Verona, Italy
  • Rosa Figueroa, University of Utah
  • Jacob Furst, DePaul University
  • Darrin Hanna, Oakland University
  • Adam Gaweda, University of Louisville
  • Jonathan Gemmell, DePaul University
  • Maryellen Giger, University of Chicago
  • Hamid Soltanian-Zadeh, Henry Ford health System
  • Juan Gómez, University of Valencia, Spain
  • Ali Haddad, Yale University
  • Kourosh Jafari-Khouzani, Harvard University
  • Ian H. Jarman, Liverpool John Moores University, UK
  • Wen-Yang Lin, National University of Kaohsiung, Taiwan
  • Paulo J. G. Lisboa, Liverpool John Moores University, UK
  • Theophilus Ogunyemi, Oakland University
  • Doug Redd, George Washington University 
  • Ishwar Sethi, Oakland University
  • Emilio Soria, University of Valencia, Spain
  • Joan Vila Francés, University of Valencia, Spain

 

Important Dates
Workshop paper submissions: August 17, 2017
Workshop paper notifications: September 11, 2017
Workshop date: November 18, 2017
Conference: November 18 -21, 2017
Paper Submission

Submission and Procedures

Paper submissions will be done through the IEEE ICDM Workshop CyberChair submission system. To submit a paper, visit the following webpage:

https://wi-lab.com/cyberchair/2017/icdm17/scripts/ws_submit.php?subarea=SP and click on: “The FifthWorkshop on Data Mining in Biomedical Informatics and Healthcare (DMBIH'17)” As per ICDM instructions, papers are limited to a maximum of ten pages including the bibliography and appendices. The submissions should follow the IEEE ICDM format requirements (http://www.ieee.org/conferences_events/conferences/publishing/templates.html). All accepted workshop papers will be published in formal proceedings by the IEEE Computer Society Press. One paper will be selected for the best paper award, which will be awarded at the workshop.

Journal’s Special Issue

Extended versions of workshop papers which are accepted and presented in this workshop (DMBIH’17) will be considered for publication in a special issue of the International Journal of Knowledge Discovery in Bioinformatics (IJKDB).

Schedule of Program

9:00-9:10 am

Opening Remarks and Introduction

9:10-10:00 am

Keynote Presentation

Dr. Kenji Suzuki, Illinois Institute of Technology

10:00-10:15 am

Coffee Break

10:15-10:45 am

Discovery of Informal Topics from Post Traumatic Stress Disorder Forums

Reilly Grant, David Kucher, Ana León, Jonathan Gemmell, and Daniela Raicu

10:45-11:15 am

Detecting Opioid Users from Twitter and Understanding their Perceptions toward MAT

Yiming Zhang, Yujie Fan, Yanfang Ye, Xin Li, and Wanhong Zheng

11:15-11:45 am

An CNN-LSTM Attention Approach to Understanding User Query Intent from Online Health Communities

Ruichu Cai, Binjun Zhu, Lei Ji, Tianyong Hao, Jun Yan, and Wenyin Liu

11:45-1:00 pm

Lunch

1:00-1:30 pm

Deep Physiological Arousal Detection in a Driving Simulator using Wearable Sensors

Aaqib Saeed, Stojan Trajanovski, Maurice van Keulen, and Jan van Erp

1:30-2:00 pm

RESTRAC: REference sequence based Space TRAnsformation for Clustering

AKM Tauhidul Islam, Sakti Pramanik, Vahid Mirjalili, and Shamik Sural

2:00-2:30 pm

Process-oriented Iterative Multiple Alignment for Medical Process Mining

Shuhong Chen, Sen Yang, Moliang Zhou, Randall S. Burd, and Ivan Marsic

2:30-3:00 pm

GB-R: A Fast and Effective Gray-Box Reconstruction of Cascade Time-Series

Hyun Ah Song, Fan Yang, Zongge Liu, Wilbert van Panhuis, Nicholas Sidiropoulos, Christos Faloutsos, and Vladimir Zadorozhny

3:00-3:15 pm

Coffee Break

3:15-3:45 pm

Semi-Supervised Prediction of Comorbid Rare Conditions from Medical Claims Data

Chirag Nagpal

3:45-4:15 pm

Exploiting PubMed for Protein Molecular Function Prediction via NMF based Multi-Label Classification

Samah Fodeh, Aditya Tiwari, and Hong Yu

4:15-4:45 pm

Probable Biomarker Identification using Recursive Feature Extraction and Network Analysis

Arpit Mishra, Abhishek Gupta, Umesh Maheswari, and Laeeq Siddique

4:45-5:00 pm

Closing Remarks and Best Paper Award

Keynote Speaker

Photo of Kenji Suzuki in a tan jacketKenji Suzuki, Ph.D. (by Published Work; Nagoya University) worked at Hitachi Medical Corporation, Japan, Aichi Prefectural University, Japan, as a faculty member, and in Department of Radiology, University of Chicago, as Assistant Professor. In 2014, he joined Department of Electric and Computer Engineering and Medical Imaging Research Center, Illinois Institute of Technology, as Associate Professor. In 2017, he was jointly appointed in World Research Hub Initiative at Tokyo Institute of Technology as Full Professor (Specially Appointed). He published more than 320 papers (including 110 peer-reviewed journal papers). His papers were cited more than 8,500 times by other researchers. He has an h-index of 42. He is inventor on 30 patents (including 13 granted patents), which were licensed to several companies and commercialized. He published 10 books and 22 book chapters, and edited 13 journal special issues. He was awarded/co-awarded more than 25 grants as PI including NIH R01 and ACS. He served as the Editor of a number of leading international journals, including Pattern Recognition and Medical Physics. He served as a referee for 80 international journals, an organizer of 30 international conferences, and a program committee member of 150 international conferences. He received 25 awards, including 3 RSNA Certificate of Merit Awards, IEEE Outstanding Member Award, Cancer Research Foundation Young Investigator Award, Kurt Rossmann Award for Excellence in Teaching from Univ of Chicago, IEICE 2014 Best Journal Paper Award, EANM Most Cited Journal Paper Award 2016, and 2017 Albert Nelson Marquis Lifetime Achievement Award.

Presentation abstract for "Deep and Shallow Machine Learning in Medical Image Analysis and Diagnosis"

Deep and Shallow Machine Learning in Medical Image Analysis and Diagnosis
Kenji Suzuki, Ph.D.

Machine leaning (ML) in computational (artificial) intelligence has become one of the most active areas of research in the medical imaging field including medical image analysis and computer-aided diagnosis (CAD), because “learning from examples or data” is crucial to handling a large amount of data (“Big data”) coming from medical imaging informatics systems. Recently, as the available computational power increased dramatically, image-based ML or “deep learning”, which uses pixel/voxel values in patches in images directly instead of features calculated from segmented regions as input information, emerged. Image-based ML, including massive-training artificial neural networks and convolutional neural networks, is an end-to-end ML model that enables a direct mapping from the raw input data to the desired outputs, eliminating the need for handcrafted features in feature-based ML. Image-based ML is a versatile, powerful framework that can acquire image-processing and analysis functions through training with image examples. In this talk, deep and shallow image-based MLs are overviewed to make clear a) the basic principles of the image-based ML, b) differences and advantages over feature-based ML, and c) its applications to 1) separation of bones from soft tissue in chest radiographs, 2) CAD for lung nodule detection in chest radiography and thoracic CT, 3) distinction between benign and malignant nodules in CT, and 4) polyp detection and classification in CT colonography. The effectiveness of the above technologies was rigorously evaluated in task-based observer performance studies, and some of the technologies were translated into clinical practice.

JOURNAL SPECIAL ISSUE

We invite the authors to submit their papers to the Knowledge
Discovery in Biomedicine special issue of the International Journal of
Knowledge Discovery in Bioinformatics (IJKDB). Please see the details
below.

********************* CALL FOR PAPERS *********************

SUBMISSION DUE DATE:12/30/2017

SPECIAL ISSUE ON Knowledge Discovery in Biomedicine

International Journal of Knowledge Discovery in Bioinformatics (IJKDB)

Guest Editor: Samah Fodeh, Yale University, USA


INTRODUCTION:

Given that biomedical and healthcare applications are producing
increasingly large amounts of digital data, more advanced and
sophisticated data analytical techniques are needed to exploit and
manage these data. Within this context of the big data revolution, we
start this special issue on developing new and novel analytical
methods to exploit and mine biomedical and healthcare data. The
broader context of the special issue concerns machine learning and
data mining, i.e., clustering, classification, summarization, topic
modeling, visualization, information retrieval and data integration.
Submissions should include methods to mine, summarize and integrate
data modalities. Different types of data can be used to validate the
methods including genomic, proteomic phenotypic, molecular (including
–omics), physiological, anatomical, clinical, behavioral,
environmental, social media, and many other types of biological and
biomedical data.


OBJECTIVE OF THE SPECIAL ISSUE:

IJKDB is particularly interested in publishing methodological reviews
on topics listed below and focuses on papers that introduce
methodological innovations. Please also note that unpublished or
updated versions of papers submitted to both the fifth Data Mining in
Biomedical Informatics and Healthcare (DMBIH’05) Workshop held in
conjunction with the IEEE International Conference on Data Mining
(ICDM’17) and the first Medical Informatics and Healthcare (MIH’17)
Workshop held with the 23rd ACM SIGKDD Conference of Knowledge
Discovery and Data Mining will be considered for publication in this
special issue.


RECOMMENDED TOPICS:

Topics to be discussed in this special issue include (but are not
limited to) the following:

Classifying and clustering big clinical data in electronic health records (EHRs)
Classifying and clustering big biomedical data in high dimensional spaces
Topic modeling / detection in large amounts of clinical textual data
Data preprocessing and cleansing to deal with noise and missing data
in large biomedical or population health data sets
EHR summarization

Algorithms to speed up the analysis of big biomedical data
Novel visualization techniques to facilitate the query and analysis of
biomedical data
Longitudinal analysis of clinical notes and surveys and time series analysis
Statistics and probability in large-scale data mining
Medical image data mining
Biological markers detection
Biological and clinical data analysis and integration for translational research
Computational genetics, genomics and proteomics


SUBMISSION PROCEDURE:

Researchers and practitioners are invited to submit papers for this
special theme issue on Knowledge Discovery in Biomedicine on or before
1/30/2017. All submissions must be original and may not be under
review by another publication. INTERESTED AUTHORS SHOULD CONSULT THE
JOURNAL’S GUIDELINES FOR MANUSCRIPT SUBMISSIONS at
http://www.igi-global.com/journals/guidelines-for-submission.aspx. All
submitted papers will be reviewed on a double-blind, peer review
basis. Papers must follow APA style for reference citations.


ABOUT International Journal of Knowledge Discovery in Bioinformatics (IJKDB):

IJKDB collects the most significant research and latest practices in
computational knowledge discovery approaches to bioinformatics.
Containing articles on topics such as systems biology, protein
structure, gene expression, and biological data integration, this
journal presents a cross-disciplinary approach to the field useful for
researchers, practitioners, academicians, mathematicians,
statisticians, and computer scientists involved in the many facets of
bioinformatics.

This journal is an official publication of the Information Resources
Management Association

www.igi-global.com/IJKDB


Editor-in-Chief: George Perry (University of Texas at San Antonio,
USA) and Clyde F. Phelix (University of Texas at San Antonio, USA)

Published: Quarterly (both in Print and Electronic form)


PUBLISHER:

The International Journal of Knowledge Discovery in Bioinformatics
(IJKDB) is published by IGI Global (formerly Idea Group Inc.),
publisher of the “Information Science Reference” (formerly Idea Group
Reference), “Medical Information Science Reference”, “Business Science
Reference”, and “Engineering Science Reference” imprints. For
additional information regarding the publisher, please visit
www.igi-global.com.


All inquiries should be should be directed to the attention of:
Samah Fodeh
Guest Editor
International Journal of Knowledge Discovery in Bioinformatics (IJKDB)
E-mail: samah.fodeh@yale.edu


All manuscript submissions to the special issue should be sent through
the online submission system:

http://www.igi-global.com/authorseditors/titlesubmission/newproject.aspx