Informatics Research Seminar: Development of Hypertrophic Cardiomyopathy (HCM) Care Application

Speaker: Andrew Wang, MD
Presented from Duke University

Broadcast Link: Seminar

At Duke, all seminars live or broadcast will be held in Hock Auditorium from 4-5 pm.

Abstract:
The presentation will review the development of HCM Care, a website and application to improve patients’ understanding of a specific cardiovascular condition, hypertrophic cardiomyopathy (HCM).

Biosketch:
Dr. Andrew Wang is a Professor of Medicine in the Division of Cardiology at Duke University Medical Center.  His clinical research and work have focused on patients with structural heart diseases, including valvular heart disease, hypertrophic cardiomyopathy and infective endocarditis.  He is involved in multicenter registries and trials to evaluate novel therapies in these conditions.  He has directed the Duke Hypertrophic Cardiomyopathy Clinic since 2003.  In addition, he is the program director for the Cardiovascular Disease fellowship program.

The Informatics Research Seminar Series is sponsored by Duke University and a collaboration with UNC-Chapel Hill, NCCU, UNC-Charlotte, and ECU. This series explores key areas in Health Informatics and include research results, overview of programs of research, basic, applied, and evaluative projects, as well as research from varied epistemological stances.

Informatics Research Seminar: Advanced Analytics Adoption at UNC Health Care System — A Case Study

Speaker: Polly Mitchell-Guthrie, MBA
Presented from UNC-CH

Broadcast Link: Seminar

At Duke, all seminars live or broadcast will be held in Hock Auditorium from 4-5 pm.

Abstract:
UNC Health Care is one of the state’s leading and most innovative healthcare organizations, providing a full spectrum of health and wellness programs at hundreds of care locations across the state.  Enterprise Analytics and Data Sciences (EADS) is a new department at UNC using an innovative operating model and new technologies to create a place where our world-class care can be driven by insights gained through our enhanced capabilities of data and analytics. This session will demonstrate how a large healthcare system realized a vision for becoming a data-driven organization by adopting advanced analytics as a strategic imperative to support value-based healthcare.  A case study will be presented to illustrate.

Biosketch:
Polly Mitchell-Guthrie, MBA is the System Director of Analytical Consulting Services within Enterprise Analytics and Data Sciences at the University of North Carolina Health Care System. Previously she was Senior Manager of the Advanced Analytics Customer Liaison Group in SAS’ Research and Development Division, where her team served as a bridge between R&D and external customers and internal SAS divisions. Before that she was Director of the SAS Global Academic Program, leading SAS’ outreach to colleges and universities worldwide to incorporate SAS into their teaching. Polly began her career at SAS in Strategic Investments and later served in Alliances, after working in the nonprofit sector in philanthropy and social services. She has an MBA from the Kenan-Flagler Business School of the University of North Carolina at Chapel Hill, where she also received her BA in Political Science as a Morehead Scholar. She has held several leadership positions within INFORMS, a professional association, serving as the Chair and Vice Chair of the Analytics Certification Board and Secretary of the Analytics Society.

The Informatics Research Seminar Series is sponsored by Duke University and a collaboration with UNC-Chapel Hill, NCCU, UNC-Charlotte, and ECU. This series explores key areas in Health Informatics and include research results, overview of programs of research, basic, applied, and evaluative projects, as well as research from varied epistemological stances.

Informatics Research Seminar: Weighing the Odds — Problem List Omissions and Patient Portal Utility among Obese Patients

Speaker: Juhee Kim, ScD & Akshat Kapoor, PhD
Presented from ECU

Broadcast Link: Seminar

At Duke, all seminars live or broadcast will be held in Hock Auditorium from 4-5 pm.

Abstract:
There is a great need for the long-term maintenance of a healthy body weight in health care setting. The WHO BMI cut points for weight status have been adopted by clinical guidelines as a strategy to aid decision making in clinical practice. Despite the promising potential in patient engagement and chronic disease management among portal users, it is unknown whether the obesity classification may influence patient portal use as a means of provider and patient communication and patient engagement.  We examine patient portal use to identify any association with obesity classification. Furthermore, obesity is a continuing national epidemic and the condition can have physical, psychological as well as a social impact on one’s well-being. Consequently, it is critical to accurately diagnose and document obesity in an electronic medical record (EMR), so that the information can be used and shared to improve clinical decision making and health communication via patient portal use, and in turn, the patient’s prognosis. It is therefore worthwhile to identify the various factors that play a role in documenting obesity diagnoses and methods to improve current documentation practices and consumer health informatics.

Biosketch:
Juhee Kim, ScD, is an associate professor in the Department of Public Health at East Carolina University.  As a nutritional and MCH epidemiologist, she has extended research experience at community and clinical settings. She established a clinic-based research program, Patient Engagement and Consumer Health Informatics (PEACHI), at ECU Physicians Clinics.  Her research aims to understand patients’ needs and modifiable health behaviors to improve health care services and outcomes to improve health disparities.

Akshat Kapoor, PhD, is an assistant professor in the Department of Health Services and Information Management at East Carolina University. Prior to earning his PhD in Biomedical and Health Informatics from the University of Wisconsin-Milwaukee, he received an M.S. in Bioinformatics from Marquette University, His research focuses on improving patient engagement and patient-provider communication via use of innovative technologies, such as apps, social media, and interactive educational resources, to aid patients in the self-management of their medical conditions. His research emphasizes how healthcare organizations can innovate and effectively engage patients and communities in playing an active role in their own health.

 

The Informatics Research Seminar Series is sponsored by Duke University and a collaboration with UNC-Chapel Hill, NCCU, UNC-Charlotte, and ECU. This series explores key areas in Health Informatics and include research results, overview of programs of research, basic, applied, and evaluative projects, as well as research from varied epistemological stances.

Informatics Research Seminar: Using EMR Data for Clinical Research– Experience and Practical Implications

Speaker: Alexander Turchin, MD, MS
Presented from Duke University

Broadcast Link: Seminar

At Duke, all seminars live or broadcast will be held in Hock Auditorium from 4-5 pm.

Abstract:
Electronic medical records (EMR) represent a rich source of clinical data that can be utilized for research, quality assurance, and pay-for-performance, among others. However, it is important to recognize that, like any other data source, EMR data has its own pitfalls that need to be approached in a rigorous fashion. In particular, a large fraction of data in EMR is “locked” in narrative documents and can therefore be especially challenging to extract. This presentation will discuss issues users can expect to encounter when analyzing EMR data and how they can be approached. The presentation will specifically focus on using natural language processing to extract data from narrative electronic documents, using publicly available NLP platform Canary (http://canary.bwh.harvard.edu) as an example. The discussion will be illustrated by specific instances of clinical research using EMR data, including narrative text.

Biosketch:
Alexander Turchin, MD, MS is Director of Clinical Informatics at Baim Institute for Clinical Research, Director of Informatics Research at the Division of Endocrinology at Brigham and Women’s Hospital and Associate Professor of Medicine at Harvard Medical School. Dr. Turchin is a graduate of Johns Hopkins University School of Medicine and Massachusetts Institute of Technology (Medical Informatics). His research focuses on analysis of electronic medical record data; he uses advanced informatics technologies including natural language processing to study quality of care and outcomes in chronic endocrine diseases. Dr. Turchin is a Fellow of the American College of Medical Informatics and has published over 80 papers and book chapters; his research has been funded by AHRQ, NIH and private foundations.

The Informatics Research Seminar Series is sponsored by Duke University and a collaboration with UNC-Chapel Hill, NCCU, UNC-Charlotte, and ECU. This series explores key areas in Health Informatics and include research results, overview of programs of research, basic, applied, and evaluative projects, as well as research from varied epistemological stances.

Informatics Research Seminar: Women & Obesity: Reasons for Evidence Behind National Weight Loss Programs

 

Speaker: Nia S. Mitchell, MD, MPH
Presented from NCCU

Broadcast Link: Seminar

Abstract:
In this seminar, Dr. Mitchell will be sharing information on the problem of obesity in the US and suggest reasons for the epidemic, including portion sizes, decreased physical activity and medications. She will also provide scientific evidence and data analysis behind the many national weight loss programs. The obesity epidemic in the US continues and many providers feel that they do not have the time or training to effectively counsel or treat patients for successful weight loss. Dr. Mitchell will focus on reasons for excess weight and obesity in women. She will define “obesity” and describe some of the reasons why it occurs in women with a discussion of health, medications (including birth control and anti-depressants), food, and differences in weight gain for men and women. Comparing calorie intake with exercise, such as pizza and raking leaves, Dr. Mitchell will provide practical examples when looking at the data and facts about weight gain from the National Academy of Medicine. She will also explain Body Mass Index (BMI) as it relates to African American women and associations between BMI and various health problems. Dr. Mitchell will present evidence from data collections and analysis of the effectiveness of popular national weight-loss programs. Using evidence from randomized control trials (RCTs) and analysis of cohort studies, she will present comparative data on 3 popular programs: Weight Watchers, Jenny Craig, and TOPS Club, Inc. (a non-profit organization). What are the retention rates and what happens after one leaves such a program? Weight loss programs, as Dr. Mitchell will explain, can make a difference with weight-related health problems, even when one loses only 5%. She will describe an appropriate weight loss program for obese patients using current evidence.

Biosketch:
Dr. Nia Schwann Mitchell. MD, MPH is an Assistant Professor of Medicine in the Division of General Medicine, Dept. of Medicine, at the School of Medicine at Duke University. Dr. Mitchell studied at the Washington University School of medicine, completing her M.D. in 2005. She received her Masters of Public Health (MPH) from the University of Colorado in 2010, and also did her internal medicine residency (2005-2008) and a primary care research fellowship (2008-2010) there. She is completing work on a National Institutes of Health (NIH) grant about the Evaluation of Low Cost National Weight Loss Programs in Underserved Populations. Among articles on weight loss, she recently has co-authored articles on “Factors Associated with the Achievement of Clinically Significant Weight Loss by Women in a National Nonprofit Weight Loss Program” (Journal of Women’s Health, August, 2017) and “Time to RE-AIM: Why Community Weight Loss Programs Should be Included in Academic Obesity Research” (Preventing Chronic Disease, March, 2016). As an Internal Medicine Doctor and a Primary Care Doctor, she sees patients at the Duke Diet and Fitness Center and Duke Outpatient Clinic. Dr. Mitchell and her weight loss research has also been featured on MSN’s “30 Best Ways to Lose Weight after 30.”

The Informatics Research Seminar Series is sponsored by Duke University and a collaboration with UNC-Chapel Hill, NCCU, UNC-Charlotte, and ECU. This series explores key areas in Health Informatics and include research results, overview of programs of research, basic, applied, and evaluative projects, as well as research from varied epistemological stances.

Informatics Research Seminar: From Medical Big Data to a Learning Health System

Speaker: Michael Pencina, PhD
Presented from Duke University

Broadcast Link: Seminar

Abstract:
The availability of medical “big data” creates an unprecedented opportunity to improve patient care and health system effectiveness.  Creation of a truly learning health system requires a team science approach built on collaboration between clinical, data, analysis and implementation subject matter experts.  In this presentation we illustrate how various data sources and analytic techniques can be used to address questions in a pragmatic manner.  We focus on the use of electronic health records with modern analytic techniques including machine learning methods and illustrate their applications with concrete examples from the Duke Health System.

Biosketch:
Dr. Michael Pencina is a Professor of Biostatistics and Bioinformatics at Duke University and Director of Biostatistics at Duke Clinical Research Institute. He serves as a key institutional leader overseeing the strategic and operational direction of the biostatistics talent and resources at the DCRI. Dr. Pencina has authored more than 150 manuscripts that have been published in peer-reviewed journals, and has co-authored over 140 publications in peer-reviewed journals and is an expert in risk prediction model development. He is also actively involved in the design, conduct and analysis of clinical trials in the fields of cardiovascular disease outcomes, medical devices and psychiatry, interacting with investigators from various academic and industry institutions and with the Food and Drug Administration. He has been an invited speaker at numerous national and international symposia and workshops. Dr. Pencina serves as an Associate Editor of Statistics in Medicine and statistical reviewer for Circulation and has been a reviewer for other leading journals in biostatistics and medicine, including the New England Journal of Medicine, JAMA and Biometrics.

 

The Informatics Research Seminar Series is sponsored by Duke University and a collaboration with UNC-Chapel Hill, NCCU, UNC-Charlotte, and ECU. This series explores key areas in Health Informatics and include research results, overview of programs of research, basic, applied, and evaluative projects, as well as research from varied epistemological stances.

Informatics Research Seminar: Data Collection: Precision Medicine and Learning Health Systems

Speaker: Stephanie Bryant, MS
Presented from NCCU

Broadcast Link: Seminar

The Informatics Research Seminar Series is sponsored by Duke University and a collaboration with UNC-Chapel Hill, NCCU, UNC-Charlotte, and ECU. This series explores key areas in Health Informatics and include research results, overview of programs of research, basic, applied, and evaluative projects, as well as research from varied epistemological stances.

Abstract:
The presentation on “Data Collection: Precision Medicine and Learning Health Systems”  will describe how data networks store, display and transmit health related information in various forms encompassing paper, digital communication systems, and mobile computing systems. Large scale data collection efforts acquire health related data from multiple sources via health data networks and systems. Issues and challenges of large scale data collection efforts in gathering high quality health data will be discussed. Technologies that address some of the challenges of large scale health data collection systems will be introduced.

Precision medicine and learning health systems are current initiatives in large scale health data collection. These initiatives extend the concepts of health data networks to include complex analysis and dissemination of multisource health related information. The aims and challenges of these initiatives will be discussed. The presenter will share aspects of her doctoral research focusing on technologies and progress toward a nationwide learning health system.

Biosketch:
Stephanie Bryant, MS,  is currently a doctoral candidate at Indiana State University in the Technology Management program, specializing in Digital Communication Systems. Her background includes Bachelor and Master of Science degrees in Computer Engineering, consisting of topics in Computer Science and Electrical Engineering. Ms. Bryant has more than 20 years of experience researching and developing integrated software solutions that may contain hardware components for research and production environments. Her qualification and skills encompass technology research, software system development, and technical management. Ms. Bryant has authorship in more than 15 journal articles, presentations, and technical reports. Her doctoral research focuses on exploring technology trends and progress in realizing a nationwide Learning Health System (LHS), a large scale system of systems for collecting, analyzing, and sharing knowledge and insights derived from health related information.

Informatics Research Seminar: Medication Reconciliation– Two Halves of the Story

Speaker: David Michael, MD
Presented from ECU

Broadcast Link: Seminar

The Informatics Research Seminar Series is sponsored by Duke University and a collaboration with UNC-Chapel Hill, NCCU, UNC-Charlotte, and ECU. This series explores key areas in Health Informatics and include research results, overview of programs of research, basic, applied, and evaluative projects, as well as research from varied epistemological stances.

Abstract: 
Medication reconciliation is defined by the Institute for Health as the process of creating the most accurate list possible of a patient’s medications.  Even though this sounds simple, up to 67% of patients admitted to the hospital have unintended medication discrepancies.  These discrepancies often persist at discharge and can lead to patient harm.   Medication reconciliation is too often used to describe both halves, the medication history and the clinical decisions of what medications the patient should take.   Upon analysis, we discovered disparate processes for each from hospital to hospital.  Standardization of the process with ongoing feedback through clinical decision support through our EHR has led to significant improvements, decreasing the number of patients at risk by as much as 80% on some services.   What we learned and what strategies we’re putting into place will be discussed.

Biosketch:
David Michael, MD is a general internist with over 20 years as a primary care physician.  As a primary care physician, he became interested in informatics when using a predictive analytics tool to change behavior and modifiable risk.  Dr. Michael became the first Chief Medical Informatics Officer at Vidant Health in 2011 and board certified in the new specialty of Clinical Informatics in 2014.  The new Vidant Health Clinical Informatics Team has continued to grow under his leadership.  The team continues to impact the optimization and usability of the Epic EHR, Population Health initiatives and analytics. Dr. Michael completed medical school at The Ohio State University and his residency in internal medicine at The Brody School of Medicine at ECU.  He is board certified in internal medicine and clinical informatics.  He is a member of ACP, AMIA, AAPL, and AMDIS.  He serves on the national physician committee for HIMSS.

Informatics Research Seminar: Reduction of Re-Admissions to Hospitals Based on Actionable Knowledge Discovery and Personalization

Speaker: Zbigniew W. Ras, PhD, DSc
Presented from UNC-C

Broadcast Link: Seminar

The Informatics Research Seminar Series is sponsored by Duke University and a collaboration with UNC-Chapel Hill, NCCU, UNC-Charlotte, and ECU. This series explores key areas in Health Informatics and include research results, overview of programs of research, basic, applied, and evaluative projects, as well as research from varied epistemological stances.

Abstract:
The concept of procedure paths as a sequence of procedures that a given patient undertakes to reach a desired treatment will be introduced. By clustering patients into subgroups that exhibit similar properties, the predictability of their procedure paths is improved, which is evaluated by calculating the entropy to measure the level of predictability of following procedures. The clustering approach is used essentially as a way to personalize patients according to their properties. The results presented are based on Florida HCUP datasets.

Biosketch:
Zbigniew Ras, PhD, DSc is a professor of computer science at the University of North Carolina, Charlotte. He holds a professorship position in the Institute of Computer Science at Warsaw University of Technology as well as at the Polish-Japanese Academy of Information Technology, both in Poland. His PhD degree is from University of Warsaw and his DSc Degree from the Polish Academy of Sciences. In 2012, he was awarded a National Professorship Title by the President of Poland. Dr. Ras’ areas of specialization includes Knowledge Discovery and Data Mining, Recommender Systems, Music Information Retrieval, Flexible Query Answering, and Health Informatics. He is Editor-in-Chief of the Journal of Intelligent Information Systems (Springer), Editor-in Chief of the International Journal of Social Network Mining (IJSNM), and he served as the Deputy Editor-in-Chief of Fundamenta Informaticae Journal (IOS Press), till 2010. He is the author of more than 350 publications and the editor of more than 45 books published by Springer and North Holland. He has received many awards including the Harshini V. de Silva Graduate Mentor Award, UNC-Charlotte, 2009; Finalist for the Bank of America Award for Teaching Excellence, UNC-Charlotte, 2008; the COIT Graduate Faculty Excellence in Teaching Award, UNC-Charlotte, 2003; and the Alcoa Foundation Outstanding Faculty Award, UNC Charlotte, 1999-2000. He received competitive grants and contracts from NSF, DOD/ARO, SAS, ONR, ORNL, DOE, IBM, Committee for Scientific Research (Poland), and AMVIS (Czech Republic).

For a complete seminar schedule, visit the DCHI website:

http://dukeinformatics.org/education/informatics-seminars/

 

CEU Credit:

In support of improving patient care, the Duke University Health System Department of Clinical Education and Professional Development is accredited by the American Nurses Credentialing Center (ANCC), the Accreditation Council for Pharmacy Education (ACPE), and the Accreditation Council for Continuing Medical Education (ACCME), to provide continuing education for the health care team.

Duke University Health System Department of Clinical Education and Professional Development designates this live activity for 1 Credit.

Locations:          

Duke:  Hock Auditorium – Hock Plaza 2424 Erwin Road, Durham, NC 27705
UNC-Chapel Hill:  Health Science Library, Room 227
NCCU-Durham:  Room 364, James E. Shepard Memorial Library
UNC-Charlotte:  Fretwell 126
ECU-Greenville:  Health Sciences Building, Room 1355

Parking at Duke:

A printed, bar coded parking pass is required for entry to and exit from the garage. Parking passes must be requested at least 48 hours in advance of the seminar.  Email healthinformatics@duke.edu  to request a parking pass. The pass will be emailed to you in PDF format and must be printed for scanning at the gate. The system will not scan bar codes from smartphones.

After parking, proceed to the 4th Floor of the parking garage and exit across the driveway to enter the building lobby.  Sign in at the desk; take the elevator down to the ground floor to Hock Auditorium.  (Exit left off the elevator and walk down the hall, the auditorium will be on your right.)

Questions: healthinformatics@duke.edu

Interested in keeping up with timely news from Duke Center for Health Informatics?

Visit our website often!

Informatics Research Seminar: Machine Learning: For Robust and Redefined Data-Driven Decision Making

Speaker: Michael Kosorok, PhD
Presented from UNC-CH

Broadcast Link: Seminar

The Informatics Research Seminar Series is sponsored by Duke University and a collaboration with UNC-Chapel Hill, NCCU, UNC-Charlotte, and ECU. This series explores key areas in Health Informatics and include research results, overview of programs of research, basic, applied, and evaluative projects, as well as research from varied epistemological stances.

 Abstract: 
An overview of how data science and big data have become relevant to biomedical research will be presented, including the roles of machine learning and statistics in data-driven decision making and precision medicine and the potential pitfalls of “big data hubris.” Several ongoing projects using machine learning for precision medicine will be described, including work on patient-derived xenograft mouse models for cancer, type 1 diabetes, and alcohol dependency. Sequential multiple assignment randomized trials (SMARTs) for precision medicine research will also be introduced.

Biosketch:,
Michael R. Kosorok, PhD, MS is the W.R. Kenan, Jr. Distinguished Professor and Chair of Biostatistics, Professor of Statistics and Operations Research, and Member of the Lineberger Comprehensive Cancer Center at the University of North Carolina at Chapel Hill. His research interests are in biostatistics, data science, machine learning, and precision medicine. He has authored over 130 peer-reviewed journal publications and two books, one on the theoretical foundations of biostatistics (Introduction to Empirical Processes and Semiparametric Inference, 2008, Springer) and one, co-authored with Erica E.M. Moodie, on current data science methods in precision medicine (Adaptive Treatment Strategies in Practice: Planning Trials and Analyzing Data for Personalized Medicine, 2016, ASA-SIAM). He is an honorary fellow of the American Statistical Association, the Institute of Mathematical Statistics, and the American Association for the Advancement of Science.

For a complete seminar schedule, visit the DCHI website:

http://dukeinformatics.org/education/informatics-seminars/

 

CEU Credit:

In support of improving patient care, the Duke University Health System Department of Clinical Education and Professional Development is accredited by the American Nurses Credentialing Center (ANCC), the Accreditation Council for Pharmacy Education (ACPE), and the Accreditation Council for Continuing Medical Education (ACCME), to provide continuing education for the health care team.

Duke University Health System Department of Clinical Education and Professional Development designates this live activity for 1 Credit.

Locations:          

Duke:  Hock Auditorium – Hock Plaza 2424 Erwin Road, Durham, NC 27705
UNC-Chapel Hill:  Health Science Library, Room 227
NCCU-Durham:  Room 364, James E. Shepard Memorial Library
UNC-Charlotte:  Fretwell 126
ECU-Greenville:  Health Sciences Building, Room 1355

Parking at Duke:

A printed, bar coded parking pass is required for entry to and exit from the garage. Parking passes must be requested at least 48 hours in advance of the seminar.  Email healthinformatics@duke.edu  to request a parking pass. The pass will be emailed to you in PDF format and must be printed for scanning at the gate. The system will not scan bar codes from smartphones.

After parking, proceed to the 4th Floor of the parking garage and exit across the driveway to enter the building lobby.  Sign in at the desk; take the elevator down to the ground floor to Hock Auditorium.  (Exit left off the elevator and walk down the hall, the auditorium will be on your right.)

Questions: healthinformatics@duke.edu

 

Interested in keeping up with timely news from Duke Center for Health Informatics?

Visit our website often!