Research

Wanda Pratt's research is motivated by the problems patients face in finding, using, and managing information. Her research includes studying patients' work to understand their problems, developing new types of technology to address those problems, and evaluating the technology with patients. She leads the iMed research group.

See

NEWHelp with our research projects. We are looking for the following people to participate in our studies:

Current Projects

Managing Health Information in Your Life

pink ribbonWoman Taiming Information 
Patients are playing an increasingly prominent and active role in their health care today. Yet, few information tools exist to support patients in this active role. In particular, patients often must coordinate their health care across multiple clinicians, learn new health terminology, make treatment choices, manage their home care, track insurance benefits, etc. At the same time, patients are trying to maintain their normal professional and personal lives, but the intense information management demands information management work of patients. In this project, we focus on understanding and developing technology to help alleviate these personal health information management problems in breast cancer. Specifically, we are (1) studying and documenting breast cancer patients' personal health information management work, (2) developing new technology that helps these patients manage their personal health information, and (3) evaluating the effectiveness of our new technology in helping patients manage their personal health information and play an active role in their health care.

Funded by the National Library of Medicine


Change of Heart

mobile phoneMSPsharing health information 
 Our goal in this project is to leverage mobile technology and Microsoft HealthVault to help heart-disease patients lead heart-healthy lifestyles. We are using mobile phones and wearable sensors  to study contextual factors that shape the behavior change process of heart-disease patients. This information is stored in HealthVault to enable data trending, exploration, sharing, and use in combination with patients' other HealthVault records. In this project, we focus on patients who have had a cardiac event within the last five years and are now trying to incorporate health-related behavior changes into their daily life. As patients’ symptoms diminish and the demands of their daily lives return to their previous levels, heart-disease patients require additional support to avoid relapse and sustain heart-healthy lifestyles. To address these problems, we are developing novel mobile and web-based prototypes that encourage opportunistic engagement in healthy activities throughout the day. Our prototypes also enable patients to share their lifestyle information with selected members of their social network to seek social support and negotiate shared activities. Together, the support for collaboratively negotiated social routines and small daily decisions about healthy activities could enable creation of a sustainable, heart-healthy lifestyle.
Funded by Microsoft's Be Well Fund Award

Games for patients with diabetes

 hangman.jpg
We are developing casual, web-based and mobile-phone-based games to help diabetics attain better blood sugar control. The games focus on improving patients' ability to estimate carbohydrates and calories in food portions. In addition to assessing the impact of the games on dietary knowledge and food choices, our study will assess how the use of these games affects patients' blood sugar control.
Funded by the Robert Wood Johnson Foundation

Past Projects

LitLinker 

 
LitLinker 
The explosive growth in biomedical literature has made it difficult for researchers to keep up with the advancements, even in their own narrow specializations and to explore connections to their own work from other parts of the literature. LitLinker is a text mining system that incorporates knowledge based technologies, natural language processing techniques and data mining algorithms to mine the biomedical literature for new, potential causal links between biomedical terms.  
Funded by a National Science Foundation (NSF) Career Award

METIS

Based on studies of a public health research group and a complimentary and alternative medicine research group, we developed a new model that describes information synthesis behaviors and incorporates new ways to use all the information in medical studies. This model allows a researcher to incorporate typically unused information from an article by augmenting it with facts from an external database, such as those available from large epidemiological studies. We also created a system called METIS that semi-automates this process. One key component of this system extracts relevant data from the tables and full text of medical articles to compile that data into a statistical meta analysis, a numeric synthesis of multiple studies. At the end of the synthesis process, METIS generates quantitative and visual summaries that capture redundancies and contradictions between articles. We used this system to synthesize evidence on the effect of two risk factors (smoking and alcohol consumption) on breast cancer.
Funded by the California Breast Cancer Research Program

DynaCat

DynaCat addresses the problem of information overload that most people today experience regularly. In general, when people use computer-based tools to find answers to questions, they are often overwhelmed by a long list of search results. Many search tools address this problem by helping users to make their searches more specific. However, when dozens or hundreds of documents are relevant to their question, users need tools that help them to explore and to understand their search results, rather than ones that eliminate a portion of those results. To address this problem, I developed DynaCat, a tool that dynamically categorizes MEDLINE search results into a hierarchical organization by using knowledge of important kinds of queries and a model of the domain terminology for medicine. Results from an evaluation of the tool with breast cancer patients showed that DynaCat helps them find answers to those important types of questions more quickly and easily than when they use a relevance-ranking system or a clustering system.
Funded by the National Cancer Institute


Mt. Rainier Background Photo by Wanda Pratt
Original template from:
Website templates