Big Data is changing how healthcare operates in the U.S., but how can data help empower patients to find the best care? That’s the question Dr. Gordon Gao will discuss in his talk, “Big Data in Healthcare: Enhancing Patient Empowerment and Care Delivery,” at thefinal Health Informatics Institute seminar of the 2017-2018 academic year.
Gao’s research focuses on Big Data in healthcare, health IT, patient empowerment, and quality transparency mechanisms, including online rating systems, quality certification and quality disclosure decisions. He will share insights from multiple projects using machine learning and deep learning based on big data generated by patients and providers.
Gao is Co-Director of the Center for Health Information and Decision Systems (CHIDS), Director of the CHIDS AI Lab, and Associate Professor at the Smith School of Business, University of Maryland, College Park. He received his Ph.D. from the University of Pennsylvania. His research interests include big data in healthcare, health IT, and quality transparency. His research has been funded by NSF and AHRQ, and he is also a recipient of an NSF CAREER Award.
Join us on Thursday, April 5, in 241 Russell Hall on UGA’s Health Sciences Campus. Refreshments served from 11:45, and the lecture begins at noon. All members of the UGA community are invited.
Data equals health. That is how providers must approach patient care if they want to improve the health of our communities, Dr. William Tierney told attendees at the March 1 Health Informatics Institute (HII) seminar, part of the Provost’s Notable Lecture Series.
Tierney trained to be a general internist, but he spent the majority of his career advancing the field of medical informatics and now serves as the Inaugural Chair of Population Health at the Dell Medical School at the University of Texas at Austin.
His lecture, “Information: The Lifeblood of Population Health,” tracked 40 years of innovation in health information science, starting with the early adoption of electronic medical records in the 1970s to how data are being used today inside and outside healthcare settings to help people live healthier lives.
Data is more important than ever, said Tierney, because it can help us see a more complete picture of health.
The U.S. is spending trillions of dollars on healthcare, more than any other developed nation, but our life expectancy, rates of chronic disease, and infant mortality rates remain some of the poorest among those same developed nations.
Our health is shaped by more than our access to quality healthcare, he said. In fact, almost 40 percent of our health is determined by social factors such as education, income, or where you live. Providers need to understand how these factors are affecting their patients’ health, said Tierney.
To do that, they need data, and Tierney encourages researchers and practitioners to make use of the multiple sources of data available to them.
For example, schools in Austin measure the body mass index of each student every year. These data can help providers more precisely target geographic areas where children are at elevated risk for obesity and intervene at a younger age.
In another striking example of how data can inform action, Tierney shared a demographic map of Austin, which clearly illustrated a delineation between the city’s white and minority neighborhoods. In a series of maps overlaid with health outcomes data, Tierney revealed that minority neighborhoods experience more poverty, lower access to grocery stores, and higher incidence of cancer and chronic disease.
In response, Tierney is leading a study to assess the social and structural health needs of low income neighborhoods in Austin, and Dell Medical School is committed to meeting these as well as clinical ones.
This project represents a shift in the mindset of medicine, said Tierney, and it will take some experimenting to find solutions to problems outside of the examination room.
“If you don’t have the data you need to answer the question, go get it,” he said. “We are in the early stages of the data revolution, and it’s up to us to shape the outcomes.”
Health is affected by actions of health care providers as well as other social, economic, and structural factors in the larger community, but we cannot overcome barriers to health without sufficiently detailed information to identify them, develop and implement solutions, and assess their effects on life’s quality or duration. To date, most health-related information has come from electronic medical record systems and public health surveys that are difficult to access and use. However, the past 10-15 years has seen the emergence of effective health information exchanges and accessible demographic, social, and environment data. New approaches will facilitate the combining of these data into a broad health data ecosystem that will better serve innovator wishing to help people overcome the medical and social barriers to getting and staying healthy.
Join the UGA Health Informatics Institute and College of Public Health on Thursday, March 1, 2018 as guest speaker Dr. William Tierney discusses 40 years of innovation in health information science and its successes, failures, and opportunities for saving American medicine. The lecture will begin at 12pm in Russell Hall room 241 on the Health Sciences Campus.
William Tierney, MD, is a general internist, medical informaticist, and inaugural Chair of the Department of Population Health in the Dell Medical School at the University of Texas at Austin. He and his department are playing a leading role in the Dell Medical School’s mission to help Austin, Texas become a model healthy city. Previously at the Regenstrief Institute, he helped develop, implement, and study one of the country’s first electronic health record systems and the country’s first, largest, and most comprehensive health information exchange. He is a member of the National Academy of Medicine, Master of the American College of Physicians, and Fellow and President-elect of the American College of Medical Informatics.
Decisions about how to prevent disease and promote health are increasingly relying on data science, but how accessible is data science to the scientific community? Chad Heilig is the Associate Director for Data Science in the Center for Epidemiology, Surveillance, and Laboratory Services at the Centers for Disease Control and Prevention, and he argues that every scientist who wants to do good things with data should have the intellectual support to do so.
Join the Health Informatics Institute Thursday, February 1, in 241 Russell Hall, Health Sciences Campus, as Dr. Heilig presents “Who Gets to Do Data Science?”
This presentation lays out a working definition of data science and, more importantly, who practices data science and how. To keep up with rapidly changing methods, technology, and tools, self-learning problem-solvers need know-how to bridge domain knowledge and methods, love of knowledge to drive problem-solving with data, and a supportive culture of mentors and peers.
Refreshments served from 11:45 until noon. Presentation from noon until 1 PM.
The 2017 – 2018 Health Informatics Institute seminar series continues this Thursday, January 11, 2018, at 12 p.m., in 241 Russell Hall on the Health Sciences Campus.
Thursday’s seminar features Jim Jellison, Director of Practice Support at the Public Health Informatics Institute (PHII). Jellison focuses on interoperability between information systems used by public health and clinical care. He has nearly 20 years of experience evaluating technical and social aspects of health information systems. Jim is an alumnus of the CDC Informatics Fellowship where he worked with the National Environmental Public Health Tracking Network. Prior to his CDC fellowship, Jim was with the Nashville Health Department in roles related to geographic information systems, surveillance, emergency preparedness, and environmental health. Jim holds a Master of Public Health (MPH) in Epidemiology from East Tennessee State University and a Bachelor of Arts in the Social Sciences from Michigan State University.
The presentation is titled “Building Informatics Capabilities in State and Local Public Health Agencies” and will discuss how the PHII is preparing public health officers throughout rural and urban communities to adopt and utilize informatics in daily practice.
It’s no secret that the United States is struggling to figure out how to deliver effective, affordable healthcare. The U.S. spends $3.2 trillion on health services, 18 percent of its GDP, but it still ranks 31st in health outcomes among developed nations.
“Health informatics is positioned to be a solution,” said Dr. Dale Green, associate professor of health policy and management and Health Informatics Institute associate director at UGA’s College of Public Health. Green worked for years as a board-certified physician in the Athens area, eventually specializing in clinical informatics.
Green participated in a panel discussion of the needs and uses of informatics at a half-day workshop, “Advancing Informatics in Government and Industry,” hosted by the University of Georgia on December 1. The event aimed to promote discussion of how academia, industry and government can work together to address critical challenges in cybersecurity, data analytics and data science.
The healthcare industry has adapted to major changes in health data reporting, mostly incentivized by federal organizations like the Centers for Medicare & Medicaid Services. But this limited form of clinical informatics is just the tip of the iceberg in health informatics.
“The problem with informatics as a discipline is that it has a different definition depending on who you ask, but generally I want to bring the human element to the technology,” said Green.
In healthcare, most data sources are points of transaction. The insurance codes associated with medical billing are a common example. When information is attached only to payment types and amounts, the context of that information can get lost, says Green.
The reasons why a person comes to interact with the healthcare system, often related to lifestyle, are questions informatics can help answer. Data from smartphones and health devices like FitBits can shape our understanding of the behaviors that lead to positive or negative health outcomes.
Green cautions, however, that constant data sharing carries the risk of privacy loss. Issues related to security and privacy have become barriers to adopting informatics technologies across industries.
“Changes in healthcare in particular are slow,” said Green. “They are people-driven.”
Healthcare providers need to be trained on how to best use this data, he adds. A lot of data is only as good as how it is applied. Predictive modeling and risk stratification are two areas where data is already improving care. Health services utilization is another.
“As a provider, how can I help a patient use X or Y service,” said Green. “That’s where we go next.”
Google uses it. Netflix uses it. It’s why these systems seem to know you and what you want to search for or watch. Deep learning is a type of machine learning model that can take in large amounts of data and use it to interpret new data as a person might, even predicting behavior. It’s been described as cutting edge of the cutting edge of artificial intelligence, and deep learning can play a crucial role in improving how public health informatics can use data to improve health and prevent disease.
In the final Health Informatics Institute seminar of the fall semester, the CDC’s Scott Lee will “Deep Learning Applied to Public Health Surveillance: Two Case Studies and an Overview of the Current State of the Art” on December 7th at 12:00 p.m. in 235 Russell Hall on the Health Sciences Campus.
The third in the Health Informatics Institute’s Seminar Series features the University of Georgia’s Lan Mu discuss how geographic information system (GIS) methods can be used to improve public health. GIS is a system designed to capture, store, manipulate, analyze, manage, and present spatial or geographic data, and its uses in the age of informatics is invaluable.
Join us on November 2 at 12:00 p.m. in room 241 Russell Hall on the Health Sciences Campus for Dr. Mu’s presentation entitled, “GIScience for Health and the Environment: Working with data from Social and Physical Environments to Social Media.”
Mu, Lan is a professor of geography at the University of Georgia. Her research interests include GIScience for health and the environment, spatial analysis and modeling, computational geometry, cartography and geovisualization. She also serves as the program coordinator of UGA’s undergraduate and graduate GIScience Certificate Programs.
There is invaluable information health professionals can learn from the devices most of us interact with almost every hour of the day, but gathering and translating that data from our cell phones and FitBits into knowledge we can use presents a challenge. To discuss how to tackle that challenge, the second Health Informatics Institute seminar of the 2017 – 2018 series welcomes James M. Regh, a leading expert in gathering massive amounts of data from mobile and wearable devices.
Join us on October 5th, in room 241 Russell Hall, Health Sciences Campus, at 12:00 p.m. to hear Dr. Regh “Big Data in Behavioral Medicine.”
Dr. Rehg is a Professor in the School of Interactive Computing at the Georgia Institute of Technology, where he is Director of the Center for Behavioral Imaging and co-Director of the Center for Health Analytics and Informatics (CHAI) and the Computational Perception Lab (CPL). He received his Ph.D. from CMU in 1995 and worked at the Cambridge Research Lab of DEC (and then Compaq) from 1995-2001, where he managed the computer vision research group. He received an NSF CAREER award in 2001 and a Raytheon Faculty Fellowship from Georgia Tech in 2005. He and his students have received best student paper awards at ICML 2005, BMVC 2010, Mobihealth 2014, and Face and Gesture 2015, and a 2013 Method of the Year Award from the journal Nature Methods.
Dr. Rehg serves on the Editorial Board of the Intl. J. of Computer Vision, and he served as the Program co-Chair for ACCV 2012 and General co-Chair for CVPR 2009, and is serving as Program co-Chair for CVPR 2017. He has authored more than 100 peer-reviewed scientific papers and holds 25 issued US patents. His research interests include computer vision, machine learning, robot perception and mobile health. Dr. Rehg was the lead PI on an NSF Expedition to develop the science and technology of Behavioral Imaging, the measurement and analysis of social and communicative behavior using multi-modal sensing, with applications to developmental disorders such as autism. He is currently the Deputy Director of the NIH Center of Excellence on Mobile Sensor Data-to-Knowledge (MD2K), which is developing novel on-body sensing and predictive analytics for improving health outcomes.
The Health Informatics Institute (HII) announces the addition of a brown bag seminar series. This informal series provides a forum for researchers to discuss future or ongoing health informatics-related work, with the goal of receiving feedback, finding collaborators, identifying projects for future grant submissions, etc.
Tim Heckman, HII director, will give the first presentation on October 12th at 12:00 p.m. in the Rhodes Garden Level Room on the Health Sciences Campus. Following brown bag talks will meet at the same time and location:
November 9: Steve Bellan, assistant professor of epidemiology and biostatistics, UGA College of Public Health
December 14: Lesley Clack, assistant professor of health policy and management,UGA College of Public Health