A major goal for healthcare-related IT is to develop trusted healthcare systems that offer relevant decision support to clinicians and patients, and in particular, provide “just in time, just for me” advice at the point of care. In this proposed integrative research project, we will develop advanced data, text, and web mining algorithms and other computational techniques to process healthcare big data, to provide patient care decision support, and to enable socially-enhanced patient empowerment. We will leverage our research team members’ computational and social science experience, and extensive healthcare knowledge,by taking a data-centric and cyber community-oriented approach. Our specific research objectives are three-fold: (1) developing technical approaches to support cyber-enabled patient empowerment; (2) developing personalized healthcare and community mapping techniques; and (3) conducting theory-driven assessment and evaluation research.
To achieve the first objective, our research will aim at (a) developing domain-dependent text processing techniques to extract symptom-disease-treatment (SDT)information in health social media with high precision, (b) developing novel sentiment analysis techniques suitable for extracting the emotional responses associated with health-related social media content, and (c)developing evolutionary topic detection techniques for patient community question-answering. Accomplishing the second objective, we will develop computational techniques to identify participant interaction networks in social media sites, develop community mapping and visualization techniques for health social media contents, and create a diabetes patient portal system (DiabeticLink) for finding similar patients and mapping the patient community as part of patient empowerment. To evaluate the proposed research, we plan to implement a cloud-based mobile app to access DiabeticLink and perform multi-stage patient-group field evaluation studies.
The primary intellectual merit of our research resides in: (a) developing advanced data and text mining techniques to represent and process health social media big data; (b) advancing research for SDT extraction, health sentiment analysis, evolutionary patientcaretopic extraction, and patient interaction network analysis; and (c) developing and assessingthe DiabeticLink system with the aim to gain insights concerning the development of socially-enhanced patient empowerment systems.
The broader impacts of this research include: (a) supporting the healthcare community in making use of health social media big data in a highly relevant and critical health domain (diabetes); (b) incorporating analytical results into a high-quality diabetes patient portal system; (c) developing and assessing cloud-based mobile app for patient support; and (d) evaluating the value and impact of the proposed advanced patient support tools for critical diabetic patient groups.
We thank the following agencies and companies for providing research funding support:
|Taiwan National Science Council||July 2012-December, 2014|
|“Taiwan Smart Health Cloud”|
|Danish NSF with South Denmark Univeristy||August 2012-July 2015|
|Patients@home: Innovative Welfare Technology for the 21st Century”|
|NSF, REU (Research Experience for Undergraduate)||April 2010-September 2010|
|“A National Center of Excellence for Infectious Disease Informatics”|
|NSF, Information Technology Research (ITR) Program||August 2004-July 2009|
|“A National Center of Excellence for Infectious Disease Informatics” (IIS-0428241)|
|NSF, REU (Research Experience for Undergraduate)||August 2008-July 2009|
- Dr. Hsinchun Chen, firstname.lastname@example.org
- Daniel Zeng, email@example.com
- Randall A. Brown, firstname.lastname@example.org
- Sherri Compton, email@example.com
- Joshua Chuang, firstname.lastname@example.org
- Yu-Kai Lin, email@example.com
- Xiao Liu, firstname.lastname@example.org
- Xiaobo Cao, email@example.com
- Weifeng Li, firstname.lastname@example.org
- Shu-Hsing Li, email@example.com, National Taiwan University
- Celia Yang, National Taiwan Univeristy
- Fred Yang, National Taiwan Univeristy
- Paul Hu, firstname.lastname@example.org, University of Utah
- Uffe Kock Wiil, email@example.com, University of Asouth Denmark
Today’s healthcare has become cost-prohibitive for many and suffers substantially from medical errors and waste (National Research Council, 2009). Anderson &Markovich (2009) reported that the U.S. spends $1.7 trillion annually (16% of GDP) on healthcare, yet produces significantly lower health outcomes than many other developed countries. Many new government initiatives have been started recently to address these continuing problems and improve healthcare-related outcomes. For example, as part of the 2009 federal stimulus package, the HITECH Act for healthcare information technology (IT) stipulates that healthcare entities in the U.S. need to use IT to fix ingrained problems, with $19 billion in 2011 and a total of $50 billion allocated to this effort over the next 5 years. In January 2009, China’s government announced a plan to spend more than $120 billion on the first phase of a 10-year overhaul of its healthcare system (Fairclough, 2009). In academia there has also been significant recent interest in adopting and advancing IT for effective healthcare. The 2009 National Research Council report on “Computational Technology for Effective Health Care” suggests an overarching grand research challenge of developing “patient-centered cognitive support.” This report also points out several IT-centric research challenges, including: virtual patient modeling, healthcare automation, healthcare data sharing and collaboration, and healthcare data management at scale. A major research goal of these programs is to develop trusted healthcare systems that provide relevant decision support to clinicians and patients, and offer “just in time, just for me” advice at the point of care.
In a recent research commentary article by Wactlar, Pavel and Barkis, entitled “Can Computer Science Save Healthcare?” (Wactlar, et al., 2011) the authors discuss ways that computer science, or more generally, IT research could help to resolve some of the healthcare crises in America. They propose a program of research and development along four technology thrusts to enable this vision: (1) creating an interoperable, digital infrastructure of universal health data and knowledge, (2) utilizing diverse data to provide automated and augmented insight, discovery, and evidence-based health and wellness decision support, (3) a cyber-based empowering of patients and healthy individuals to play a substantial role in their own health and treatment, and (4) monitoring and assisting individuals with intelligent systems: sensors, devices and robotics, to maintain function and independence.
Thrust areas 2 and 3, healthcare decision support and cyber-enabled patient empowerment, are of particular relevance to our proposed research. Given the growing numbers of electronic health records, results of clinical trials, high-throughput genomic research findings, the biomedical research literature, and even health-related social data, healthcare is entering the realm of “Health Big Data.” Advanced data mining, machine learning, natural language processing, and data visualization research, carefully developed with clinical consideration in the diagnosis, treatment, and patient care cycle, are critically needed. Moreover, patients and their families are and should be full healthcare decision partners. Patients who actively participate in their healthcare have better outcomes and a perceived quality of life that is better than those who do not (Bandura, 2007). Patient empowerment can be supported by new communication and sensor technologies, decision support systems, and health social media tools.
In light of the emerging Health 2.0 opportunities, the proposed project focuses on health big data research relating to health social media content management and analytics, patient community portal development, mobile and cloud-based health app delivery, and patient community support assessment. We aim to develop advanced social media analytics techniques and tools for patient community networks, symptom-disease-treatment associations, health community question-answering, and patient portal system support. The proposed techniques and tools will be developed and evaluated for diabetes, the seventh leading cause of death in the U.S. Our technical research will be guided and assessed by seasoned endocrinologists and health clinicians in our highly inter-disciplinary team. We also plan to conduct several field studies assessing the usability and value of our proposed diabetic patient support portal for selected diabetic patient groups.
We have composed an excellent and experienced research team of accomplished computer/information scientists, nutritional scientist, and medical professionals. Leveraging our data, text, and web mining experience and extensive healthcare knowledge, we will take a data-centric and patient-centered approach in developing algorithms and techniques to support cyber-enabled patient empowerment, and personalized healthcare and community mapping. The specific research objectives of this highly integrative project include:
- Cyber-enabled Patient Empowerment
- Develop text processing techniques to extract symptom-disease-treatment information embedded in health social media sites.
- Develop sentiment analysis techniques suitable for extracting the emotional responses associated with health-related social media content.
- Develop evolutionary topic detection techniques for patient community question-answering.
- Personalized Healthcare and Community Mapping
- Develop computational techniques to identify participant interaction networks in social media sites.
- Develop community mapping and visualization techniques for health social media contents.
- Develop a diabetes patient portal system, DiabeticLink, for finding similar patients and mapping the patient community.
- Assessment and Evaluation
- Perform technology assessment on the proposed data mining, text mining, and visualization techniques.
- Develop a cloud-based mobile app to access DiabeticLink patient portal system and perform multi-stage patient-group field evaluation studies.
We present our research plan encompassing three areas: cyber-enabled patient empowerment, personalized healthcare and community mapping, and assessment and evaluation. Our research framework is shown below.
- Y. Lin, H. Chen, R. Brown, S. Li, and H. Yang, “Time-to-Event Predictive Modeling for Chronic Conditions using Electronic Heal Records,” IEEE Intelligent Systems, Volume 29, Number 3, Pages 14-21, 2014.
- Y. C. Ku, C. Chao, Y. Zhang, and H. Chen, “Text Mining Self-disclosing Health Information for Public Health Service,” Journal of the American Society for Information Science and Technology, forthcoming, 2014.
- Y K. Lin, R. A. Brown, and H. Chen, “MedTime: A Temporal Information Extraction System for Clinical Narratives,” Proceedings of the 2012 i2b2 Workshop on Challenges in Natural Language Processing for Clinical Data, Chicago, IL, USA: i2b2, 2012 (MedTime ranked #4 among 12 entries).
- H. Chen, “Smart Health and Wellbeing,” IEEE Intelligent Systems, Volume 26, Number 5, Pages 78-79, September/October, 2011
- H. Chen, D. Zeng, and P. Yan, “Infectious Disease Informatics: Syndromic Surveillance for Public Health and Biodefense,” Springer, 2010. (translated into Chinese, 传染病信息学,科学出版社, 2011)
- Y. Chen, S. Brown, P. J. Hu, and H. Chen, “Managing Emerging Infectious Diseases with Information Systems: Reconceptualizing Outbreak Management through the Lens of Loose Coupling,” Information Systems Research, Volume 22, Number 3, Pages 447-468, September 2011.
- N. Suakkaphong, Z. Zhang, and H. Chen, “Disease Named Entity Recognition using Semisupervised Learning and Conditional Random Fields,” Journal of the American Society for Information Science and Technology, Volume 62, Number 4, Pages 727-737, 2011.
- D. Zeng, H. Chen, C. Castillo-Chavez, W. B. Lober, and M. Thurmond (Eds.), “Infectious Disease Informatics and Biosurveillance,” Springer, 2010.
- X. Li, H. Chen, J. Li, and Z. Zhang, “Gene Function Prediction with Gene Interaction Networks: A Context Graph Kernel Approach Relations,” IEEE Transactions on Information Technology in Biomedicine, Volume 14, Number 1, Pages 119-128, 2010.
- H. Chen, S. F. Fuller, C. Friedman, and W. Hersh (Eds.), “Medical Informatics: Knowledge Management and Data Mining in Biomedicine,” Springer, 2005.
2013 - 2014
- J. Chuang, O. Hsiao, P. Wu, J. Chen, X. Liu, H. De La Cruz, S. Li, and H. Chen, “DiabeticLInk: An Integrated and Intelligent Cyber-enabled Health Social Platform for Diabetic Patients,” International Conference on Smart Health, ICSH 2014, Beijing, China, July 2014. Proceedings. Lecture Notes in Computer Science 8549, Springer 2014.
- X. Li, T. Zhang, L. Song, Y. Zhang, C. Xing, and H. Chen, “A Control Study on the Effects of HRV Biofeedback Therapy in Patients with Post-stroke Depression,” International Conference on Smart Health, ICSH 2014, Beijing, China, July 2014. Proceedings. Lecture Notes in Computer Science 8549, Springer 2014.
- X. Song, S. Jiang, X. Yan, and H. Chen, “Collaborative Friendship Betworks in Online Healthcare Communities: An Exponential Random Graph Model Analysis,” International Conference on Smart Health, ICSH 2014, Beijing, China, July 2014. Proceedings. Lecture Notes in Computer Science 8549, Springer 2014.
- Y. Yin, Y. Zhang, X. Liu, Y. Zhang, C. Xing, and H. Chen, “HealthQA: A Chinese QA Summary System for Smart Health,” International Conference on Smart Health, ICSH 2014, Beijing, China, July 2014. Proceedings. Lecture Notes in Computer Science 8549, Springer 2014.
- X. Liu, J. Liu, and H. Chen, “Identifying Adverse Drug Events from Health Social Media: A Case Study on Heart Disease Discussion Forums,” International Conference on Smart Health, ICSH 2014, Beijing, China, July 2014. Proceedings. Lecture Notes in Computer Science 8549, Springer 2014.
- X. Chen, Y. Zhang, C. Xing, X. Liu, and H. Chen, “Diabetes-related Topic Detection in Chinese Health Websites Using Deep Learning,” International Conference on Smart Health, ICSH 2014, Beijing, China, July 2014. Proceedings. Lecture Notes in Computer Science 8549, Springer 2014.
- S. Yu, H. Zhu, S. Jiang, and H. Chen, “Emoticon Analysis for Chinese Health and Fitness Topics,” International Conference on Smart Health, ICSH 2014, Beijing, China, July 2014. Proceedings. Lecture Notes in Computer Science 8549, Springer 2014.
- X. Liu and H. Chen, “AZDrugMiner: An Information Extraction System for Mining Patient-Reported Adverse Drug Events in Online Patient Forums,” International Conference on Smart Health, ICSH 2013, Beijing, China, August 2013. Proceedings. Lecture Notes in Computer Science 8040, Springer 2013.
- H. Chen, S. Compton, and O. Hsiao, “DiabeticLink: A Health Big Data System for Patient Empowerment and Personalized Healthcare,” International Conference on Smart Health, ICSH 2013, Beijing, China, August 2013. Proceedings. Lecture Notes in Computer Science 8040, Springer 2013.
- C. Yang, H. Chen, H. Wactlar, C. Combi, and X. Tang, SHB 2012: International Workshop on Smart Health and Wellbeing. ACM International Conference on Information and Knowledge Management,(CIKM), Hawaii, October 29-November 2, 2012.
- Y. Ku, C. Chiu, Y. Zhang, L. Fan, and H. Chen, “Global Disease Surveillance using Social Media: HIV/AIDS Content Intervention in Web Forums,” Proceedings of 2010 IEEE International Conference on Intelligence and Security Informatics, ISI 2010, Vancouver, Canada, May 2010.
For additional information, please contact us.