The 5th Big Data Analytic Technology for Bioinformatics and Health Informatics Workshop (KDDBHI 2018)

In conjunction with 2018 IEEE International Conference on Big Data, Dec. 10 - 13, Seattle, WA

The 5th workshop on Big Data Analytic Technology for Bioinformatics and Health Informatics (KDDBHI 2018)

Monday, Dec. 10th, 2018, The Westin Hotel, Seattle, WA

Conference Room: CASCADE II, Floor 2

Workshop Chairs: Donghui Wu and Xin Deng


8:30 – 8:35

Chairs’ Welcome Remarks

Donghui Wu


8:35 – 9:00

Retrofitting Word Embeddings with the UMLS Metathesaurus for Clinical Information Extraction (moved to 2:30)

Mohammed Alawad, S M Shamimul Hasan, Blair Christian, and Georgia Tourassi

9:00 – 9:25

Clinical Text Classification with Word Embedding Features vs. Bag-of-Words Features

Yijun Shao, Stephanie Taylor, Nell Marshall, Craig Morioka, and Qing Zeng-Treitler

9:25 – 10:00

Panel: NLP and EMR Text Extraction and Understanding

Panel Chair: Donghui Wu

10:00 – 10:20

Coffee Break

10:20 – 10:50

Invited Talk: Protein Structure Modeling driven by Deep Learning and Contact Distance Prediction

Professor Jianlin Cheng, University of Missouri

10:50 – 11:20

A Hybrid Approach to Identifying Key Factors in Environmental Health Studies

Shi Dong, Zlatan Feric, Xiangyu Li, Sheikh Mokhlesur Rahman, Guanyu Li, Chieh Wu, April Z. Gu, Jennifer Dy, David Kaeli, John Meeker, Ingrid Y. Padilla, Jose Cordero, Carmen Velez Vega, Zaira Rosario, and Akram Alshawabkeh

11:20 – 11:50

Towards Biological Sequence Data Service with Insights

Huaming Chen, Jun Shen, Lei Wang, and Chi-Hung Chi

11:50 – 12:00

Morning Session Remarks/Afternoon Session Promotion

Donghui Wu

12:00 – 1:30

Lunch on Your Own

1:30 – 2:00

A Novel Deep Learning Pipeline to Analyze Temporal Clinical Data

Terri Workman, Michael Hirezi, Eduardo Trujillo-Rivera, Anita Patel, Julia Heneghan, James Bost, Qing Zeng-Treitler, and Murray Pollack,

2:00 – 2:30

Research Hypothesis Generation Using Link Prediction in a Bipartite Graph

Jung-Hun Kim and Aviv Segev

2:30 – 3:00

Retrofitting Word Embeddings with the UMLS Metathesaurus for Clinical Information Extraction (New time slot)

Mohammed Alawad, S M Shamimul Hasan, Blair Christian, and Georgia Tourassi

3:00 – 3:30

Spatio-Temporal Convolutional Neural Network For Elderly Fall Detection In Depth Video Cameras

Maryam Rahnemoonfar and Hend Alkittawi

3:30 – 3:50

Coffee Break

3:50 – 4:50

Panel: Transforming Health Care Delivery via Deep Learning and Machine Learning

Panel Chair: Donghui Wu

Closing Remarks


Workshop Introduction and Motivation

The emerging fusion of Bioinformatics and Health Informatics has promoted research and development in target drugs, personalized medicine, clinical decision support and population health management, etc. and collaborations among researchers in bioinformatics and health informatics and clinicians as well as data scientists. It also demands big data analytics incorporating latest advancements in data mining, machine learning, statistical methodology and big data. Precision Medicine and All People Health Initiatives promote more investment and research in precision medicine, an innovative approach to disease prevention and treatment that takes into account individual differences in people’s genes, environments, and lifestyles. In turn, it also creates higher demands for big data analytics for connecting genetic data, personal gene data, drug information, medical record, and clinical outcomes.

The goal of this workshop is to provide a platform for professionals, researchers, clinicians, and data scientists to share opinions and exchange ideas, so as to facilitate fusion of Bioinformatics, Health Informatics, Personalized Medicine, Population Health and Data Science. Ultimately it contributes to better quality of life of patients and healthier population as well as big data analytic technology advancements that support and promote such research activities.

This is the fifth annual KDDBHI workshop continuing on the success of three prior workshops. The First KDDBHI workshop was debuted at KDD 2014, New York, NY. The Second KDDBHI workshop is held in conjunction with ACM BCB 2015 conference, Atlanta, GA. The Third KDDBHI workshop is held at IEEE Big Data 2016 Conference, Washington, D.C. The fourth KDDBHI workshop is held at IEEE Big Data 2017 Conference, Boston, MA. In this fifth workshop, we continue to attract more research and applications of big data analytics, technology and platforms for precision medicine, personalized medicine, and other clinical innovations, in particular, the integration and fabrication of big data from patient gene sequencing, patient life style and socio-economic data, electronic medical records, drug design and targeting, and population and individual level drug treatments, and medical and pharmacy claims.

Workshop Topics and Target Audience

As increasingly massive amounts of computational biological information, including genome sequences, protein sequences, gene expression data, becomes available, more efficient, sensitive, and specific big data analytic technology in Bioinformatics become critically in need. For example, terabytes or more of raw data are easily generated in next-generation sequencing experiments. Also, in biological and biomedical imaging process and analysis, large volumes of data are generated. Consequently, how to store, achieve, index, manage, learn, mine, and visualize the big data is clearly a challenge to the research community.

Similarly, for the past decade, there have been a variety of efforts and progresses from healthcare organizations and companies in digitizing, storing, analyzing medical data. For instance, predictive analytics and risk adjustment allow insurance companies and healthcare organizations to predict the future costs for budgets and population health management, perform risk adjustment, develop the treatment guidelines, plan care management strategies, and measure physician performance.

With The emergence and advancements in Precision Medicine and Personalized Medicine, it calls for further fusion of Bioinformatics, Health Informatics, Clinical Outcome and Population Health, and application of big data analytics to the ever growing big data. For instance, the integration of genetic test results, patient-specific sequencing, expression profiling, tissue image data, and clinical data in a patient medical record provides opportunities for personalized medicine, target drug research, and treatment effectiveness research, which are all necessary components of precision medicine. The recent advancement in big data technology and research, make it now the perfect time to marry the research and application.

Featured Topics (Big Data Research and Applications in)

· Precision Medicine & Personalized Medicine

· Health Analytics and Informatics

· Target Drug Design and Discovery

· RNAseq and Microarray Gene expression Data Analysis

· Gene Regulatory Network Construction

· Next-generation Sequencing (NGS) Analysis

· Functional Genomics

· Population, Evolution, and Comparative Genomics

· Transnational Bioinformatics

· Protein Structure Prediction

· Protein Function Analysis

· Healthcare and Healthcare Delivery

· Healthcare policy research

· Healthcare outcomes research, monitoring and evaluation

· Hospital Information System

· Electronic Medical Record and Electronic Health Record

· Population Health and Public Health Management

· Mobile Health and Sensor Applications

· Other areas related to healthcare informatics and analytics

· Other areas related to proteomics and genomics

Target Audience

The goal of this workshop is to bring together practitioners, researchers, clinicians, and data scientists in the area of Bioinformatics and Health Informatics to share latest findings in the field, exchange ideas on how to improve the strategies, address real-world problems in Bioinformatics and Healthcare, and explore the intersections between Bioinformatics and Health Informatics and new research areas brought by advancement in big data analytics, data mining, machine learning and statistical learning.

Workshop Chairs

Donghui Wu, PhD, MBA, Advanced Analytics, Machine Learning and Artificial Intelligence, KDDBHI, Dallas, TX, donghui.wu@ieee.org

Xin Deng, PhD, Data Scientist , Microsoft Corporation, Redmond, WA, xinde@microsoft.com

The 5th workshop on Big Data Analytic Technology for Bioinformatics and Health Informatics (KDDBHI 2018)

Monday, Dec. 10th, 2018, The Westin Hotel, Seattle, WA

Conference Room: CASCADE II, Floor 2


Workshop Chairs: Donghui Wu and Xin Deng


8:00 – 8:10

Chairs’ Welcome Remarks

Donghui Wu

8:10 – 8:35

Improving Health Big Data Integration via Word2Vec and Long Short-Term Memory Networks

Zhaohui Liang, Jimmy Xiangji Huang, and Honglai Zhang

8:35 – 9:00

Retrofitting Word Embeddings with the UMLS Metathesaurus for Clinical Information Extraction

Mohammed Alawad, S M Shamimul Hasan, Blair Christian, and Georgia Tourassi

9:00 – 9:25

Clinical Text Classification with Word Embedding Features vs. Bag-of-Words Features

Yijun Shao, Stephanie Taylor, Nell Marshall, Craig Morioka, and Qing Zeng-Treitler

9:25 – 10:00

Panel: NLP and EMR Text Extraction and Understanding

Panel Chair: Donghui Wu

10:00 – 10:20

Coffee Break

10:20 – 10:50

Mining Discriminative Patterns from fMRI-based Complete Functional Connectivity Networks (withdrawn)

Shah Muhammad Hamdi, Yubao Wu, Berkay Aydin, Soukaina Filali Boubrahimi, Rafal Angryk, Lisa Crystal Krishnamurthy, and Robin Morris

10:50 – 11:20

Development of a Radiology Decision Support System for the Classification of MRI Brain Scans

Alwin Yaoxian Zhang, Sean Shao Wei Lam, Nan Liu, James Yan Pang, Ling Ling Chan, and Phua Hwee Tang

11:20 – 11:50

Towards Biological Sequence Data Service with Insights

Huaming Chen, Jun Shen, Lei Wang, and Chi-Hung Chi

11:50 – 12:00

Morning Session Remarks/Afternoon Session Promotion

Donghui Wu

12:00 – 1:30

Lunch on Your Own

1:30 – 2:00

A Novel Deep Learning Pipeline to Analyze Temporal Clinical Data

Terri Workman, Michael Hirezi, Eduardo Trujillo-Rivera, Anita Patel, Julia Heneghan, James Bost, Qing Zeng-Treitler, and Murray Pollack,

2:00 – 2:30

Research Hypothesis Generation Using Link Prediction in a Bipartite Graph

Jung-Hun Kim and Aviv Segev

2:30 – 3:00

Class Imbalance in Cancer Risk Modeling: A Cloud Computing Approach

Aaron Richter and Taghi Khoshgoftaar

3:00 – 3:30

Spatio-Temporal Convolutional Neural Network For Elderly Fall Detection In Depth Video Cameras

Maryam Rahnemoonfar and Hend Alkittawi

3:30 – 3:50

Coffee Break

3:50 – 4:20

SimREC: Analyzing FDA Adverse Event Reporting System Data for Post-approval Research of Biosimilar Drugs

Rithika Lakshminarayanan, Anurag Joshi, and Rahul Majethia

4:20 – 4:50

Optimization Framework for Flavour and Nutrition Balanced Recipe: A Data Driven Approach

Isura Nirmal, Amith Caldera, and Roshan Dela Bandara

4:50 – 5:20

A Hybrid Approach to Identifying Key Factors in Environmental Health Studies

Shi Dong, Zlatan Feric, Xiangyu Li, Sheikh Mokhlesur Rahman, Guanyu Li, Chieh Wu, April Z. Gu, Jennifer Dy, David Kaeli, John Meeker, Ingrid Y. Padilla, Jose Cordero, Carmen Velez Vega, Zaira Rosario, and Akram Alshawabkeh

5:20 – 6:00

Panel: Transforming Health Care Delivery via Deep Learning and Machine Learning

Panel Chair: Donghui Wu

Closing Remarks


Program Committee

Dr. Paul Bradley, Chief Data Scientist at ZirMed, Chicago, Illinois

Dr. Xin Deng, Data Scientist, Microsoft Corporation, Redmond, WA

Dr. Vincent Emanuele, Manager of Data Sciences at Wellcentive, Atlanta, GA

Dr. Daisy Wang, Assistant Professor, & Director of Data Science Research Lab, Computer and Information Science and Engineering (CISE), College of Engineering, University of Florida, Gainesville, FL

Dr. Ouyang Weiwei, Data Scientist, United Healthcare, Mini

Dr. Donghui Wu, Head of Advanced Analytics, Machine Learning and Artificial Intelligence, Dallas, TX

Dr. Mohammed J. Zaki, Professor, Department of Computer Science, Rensselaer Polytechnic Institute, Troy, NY

Workshop Key Dates

Oct.15, 2018: Due date for full workshop papers submission

Nov. 4, 2018: Notification of paper acceptance to authors

Nov.18, 2018: Camera-ready of accepted papers

Dec. 10, 2018: Workshop Date

Dec. 11-13, 2018: 2018 IEEE International Conference on Big Data (IEEE BigData 2017)


Prior KDDBHI Workshops

2014 KDDBHI Workshop @ KDD 2014 The 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 24-27, 2014, New Yrok, New York.

2015 KDDBHI Workshop @ ACM BCB 2015 The 6th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics , September 09 -12, 2015, Atlanta, GA.

2016 KDDBHI Workshop @ IEEE BigData2016 2016 IEEE International Conference on Big Data December 5 - December 8, 2016, Washington DC, USA

2017 KDDBHI Workshop @ IEEE BigData2017 2017 IEEE International Conference on Big Data December 11 - December 14, 2016, Boston, MA, USA