PROJECTS

FEATURED PROJECTS

Patients As Safeguards

In today’s complex health care system, medical errors cause substantial harm and even death among hundreds of thousands of Americans each year. Although this problem has received national attention, including efforts to encourage patients to speak up about errors, very little work has actively involved patients in preventing, detecting, and recovering from these errors. Through this work, we will explore and develop new technologies to support patients and caregivers as important safeguards in hospital care. Our aims are to (1) Identify information that would increase patients’ and their caregivers’ situation awareness as well as enable them to recognize potential safety concerns, (2) Support patients and their caregivers in capturing and managing information that could identify potential harm, and (3) Determine strategies to support clear communication among patients, caregivers, and health-care providers about these important safety concerns.

PAST PROJECTS

REMIND: Exploring Reminders and Notifications for Chronic Disease Management

Patient reminders and notifications help people reach their health goals. We know little, though, about how to design reminder and notification systems that address the range of patients’ chronic and preventive health care needs. In two populations of patients with different chronic and preventive care needs (asthma and diabetes), we are employing a mixed methods approach to identify the needs and preferences of patients for notifications and reminders and then clarify core design elements through building and testing prototypes of a patient health reminder and notification system. This project will lay the formative groundwork for designing comprehensive reminder and notification systems that best support individuals with chronic diseases.

Peer Mentoring

Our long-term goal is to enhance the health and well-being of individuals through effective peer mentoring among patients in peer health communities. A key requirement for meeting this goal is successfully connecting patients with suitable peer mentors who can share advice based on common circumstances. As a first step, the proposed project will leverage the rich source of peer health community data to facilitate peer mentoring. In the context of CancerConnect.com, our partnering organization’s online cancer community, we will develop social matching approaches that identify candidate mentors and match them with peers seeking help with personal health problems. Through a series of three studies, we will (1) Profile community members by identifying critical mentorship characteristics from community data through a comparative study of automated text extraction versus direct user entry of data (2) Develop social matching tools that connect peers for mentorship by iterating between rapid prototyping of system components and usability testing with cancer patients, and (3) Assess the value of the social matching approach for peer mentoring by obtaining feedback from community members through online community-based field evaluation.

Assessing the Trigger and Symptom Monitoring Needs of Individuals with Tourette Syndrome (TS)

Tourette Syndrome is marked by motor and occasionally vocal tics which can cause daily distraction, stigma, and even self-harm for individuals with the disorder. The tics may often appear to wax and wane without much apparent cause, and while a number of environmental factors (sleep, stress, exercise, and more) may affect symptom prevalence, little effort has been made to empirically study these external factors, and it seems likely that aggravating factors may vary from individual to individual. Further, the success of therapies such as Cognitive Behavioral Therapy (CBT) hinge largely on the ability of individuals to monitor their tic symptoms and causal factors that may aggravate them. We are in the process of designing, developing, and assessing the use of a mobile application to better enable individuals to monitor and review their symptoms and causal factors related to them, and are currently speaking with Tourette’s-affected individuals to better understand their needs and potential uses for such an app. It is hoped that such an application may help those with TS to gain better control over their symptoms through daily symptom control and increased efficacy of therapy.

Designing a System to Improve Social Media Monitoring by Emergency Response Professionals and Volunteers

Social media are a potentially valuable source for public health for obtaining situational awareness information during crisis events. Consistently, ?digital volunteers? and others are coming together to filter and process this data into usable resources, often coordinating their work within distributed online groups. However, current tools and practices are frequently unable to keep up with the speed and volume of incoming data during large events. We are conducting contextual interviews with emergency response professionals and digital volunteers to examine the ad hoc, collaborative practices that have emerged to help process this data and to help us to support and leverage these efforts in the design of a new system to support these individuals’ efforts. We are currently in the process of iteratively designing and testing a system to support these efforts, focusing on ways to design in order to support current group values, work practices, volunteer motivations, and organizational structures, but also to allow these groups to increase the scale and efficiency of their operations.

mHealth Wound-Tracking App (“mPOWEr”)

A group of UW researchers is developing an mHealth platform to engage patients in wound tracking to identify and manage surgical site infections (SSI) occurring after hospital discharge. Post-discharge SSIs are a common and serious problem following surgery, and occur at a critical care transition when patients are physically and emotionally stressed. By taking a user-centered approach to design, we are creating an “app” that enables patients to track wound symptoms and photographs and securely communicate with their clinicians to identify and treat complications early. To date, we have conducted a foundational needs assessment among patients and clinicians, and iteratively prototyped the app based on rounds of feedback from patients, patient advocates, clinicians and usability experts. We are currently conducting usability testing with recently discharged surgical patients and will be piloting the platform (consisting of patient app and clinician dashboard) at 2 sites later this year. Future work will involve conducting a clinical trial to evaluate the platform’s effect on clinical outcomes, patient engagement and healthcare utilization.

Operationalizing Outlier Detection in Community Health Worker Programs in Development Settings

The past several years have seen a significant expansion in the use of mobile phones in developing country contexts, enabling the recent establishment of the nascent field of mobile health. Mobile phones can enable the efficient collection of pertinent health data by low-skilled health workers in sparsely populated rural areas, as well as the transmission of this health data to urban regions where trained professional may make and communicate important decisions in response to the collected data. However, many of these rural programs are poorly supervised, and the quality of collected data may suffer as a result due to any number of reasons including fraud, poor training, or anomalous underlying data within the studied population. We are working toward developing a set of algorithms that can help detect and classify anomalies in health worker data to better enable NGOs, governments, and other care organizations to better assess community health worker data quality. Building on recent efforts to use unsupervised multinomial techniques for outlier detection, we are working toward outlining the steps required to turn a set of statistical tests into a framework that can be implemented by health organizations, and are working to calibrate these algorithms on a series of datasets from partner health organizations. It is hoped as well that these techniques may be expanded to improve mobile data collection quality in agriculture and perhaps other development domains as well.

SleepTight

Many factors, such as meals, exercise, caffeine, alcohol, tobacco, and medication, can significantly impact sleep quality. Monitoring and reflecting on these factors and their impact on sleep can be enlightening, but they are difficult to track automatically. Thus, we designed SleepTight, an Android app widget, to make it easy for people to capture these sleep-related factors along with sleep measures. People can reflect on their sleeping patterns and sleep-related factors with the help of SleepTight’s visualizations.

Understanding Patient Information Needs in the Hospital

Inpatient care is an increasingly complex, dynamic environment. In this setting, however, patients typically have access to very little information about the current state of their care other than through ad hoc interactions with their providers. The goal of this project is to assess through observations, surveys and interviews what information patients and family members would like to know at different points in their care, how to deliver that information. Specifically, we aim to identify information that would increase patients’ and their caregivers’ situational awareness as well as enable them to recognize potential safety concerns. The mixed methods approach will feed into participatory design sessions to develop and test technology probes.

Understanding Physician Chart Biopsy within the EMR

Because of regulatory guidelines and increased care complexity, physicians spend a substantial amount of their time performing handoffs of patients to other providers. Within this context, physicians often perform a rapid chart review (?chart biopsy?) when receiving a set of new patients. Through this project, we are conducting simulated handoffs with physicians in order to assess their information seeking strategies within an EMR. This work will inform how to better consolidate information that is needed for different clinicians as they create mental models for different patients, enhancing our ability to build tools that can support effective and safe handoff process.

YouTube Health Vloggers

Health video blogs (vlogs) allow individuals with chronic illnesses to share their stories, experiences, and knowledge with the general public. Furthermore, health vlogs help in creating a connection between the vlogger and the viewers. We conducted a qualitative study examining the various methods that health vloggers use to establish a connection with their viewers as well as the comments said between vloggers and viewers. We found that vloggers used genres to express specific messages to their viewers while using the uniqueness of video to establish a deeper connection with their viewers. Health vloggers also explicitly sought interaction with their viewers.