Filtering by
- Member of: ASU Electronic Theses and Dissertations
Social media sites focusing on health-related topics are rapidly gaining popularity among online health consumers, also known as "e-patients". The increasing adoption of social media by e-patients and their demand for reliable health information has prompted several health care organizations (HCOs) to establish their social media presence. HCOs are using social media to connect with current and potential e-patients, and improve patient education and overall quality of care. A significant benefit for HCOs in using social media could potentially be the improvement of their quality of care, as perceived by patients. Perceived quality of care is a key determinant of patients' experience and satisfaction with health care services, and has been a major focus of research. However, there is very little research on the relationship between patients' online social media experience and their perceived quality of care. The objective of this research was to evaluate e-patients' online experience with an HCO's social media sites and examine its impact on their perceived quality of care. Research methodology included a combination of qualitative and quantitative approaches. Data for this study was collected from Mayo Clinic's social media sites through an online survey. Descriptive statistics were used to identify basic demographic profiles of e-patients. Linear regression analysis was used to examine the relationship between online experience and perceived quality of care. Qualitative data was analyzed using thematic analysis. Results showed a positive relationship between online experience and perceived quality of care. Qualitative data provided information about e-patients' attitudes and expectations from healthcare social media. Overall, results yielded insights on design and management of social media sites for e-patients, and integration of these online applications in the health care delivery process. This study is of value to HCOs, health communicators and social media designers, and will also serve as a foundation for subsequent studies in the area of health care social media.
The first topic is a Mixed Effects Transfer Learning (METL) model that can flexibly incorporate mixed effects and a general-form covariance matrix to better account for similarity and heterogeneity across subjects. I further develop computationally efficient procedures to handle unknown parameters and large covariance structures. Domain relations, such as domain similarity and domain covariance structure, are automatically quantified in the estimation steps. I demonstrate METL in an application of smartphone-based telemonitoring of PD.
The second topic focuses on an MRI-based transfer learning algorithm for non-invasive surgical guidance of glioblastoma patients. Limited biopsy samples per patient create a challenge to build a patient-specific model for glioblastoma. A transfer learning framework helps to leverage other patient’s knowledge for building a better predictive model. When modeling a target patient, not every patient’s information is helpful. Deciding the subset of other patients from which to transfer information to the modeling of the target patient is an important task to build an accurate predictive model. I define the subset of “transferrable” patients as those who have a positive rCBV-cell density correlation, because a positive correlation is confirmed by imaging theory and the its respective literature.
The last topic is a Privacy-Preserving Positive Transfer Learning (P3TL) model. Although negative transfer has been recognized as an important issue by the transfer learning research community, there is a lack of theoretical studies in evaluating the risk of negative transfer for a transfer learning method and identifying what causes the negative transfer. My work addresses this issue. Driven by the theoretical insights, I extend Bayesian Parameter Transfer (BPT) to a new method, i.e., P3TL. The unique features of P3TL include intelligent selection of patients to transfer in order to avoid negative transfer and maintain patient privacy. These features make P3TL an excellent model for telemonitoring of PD using an At-Home Testing Device.
Health care providers (HCPs) are an important source of physical activity (PA) information. Two studies were conducted to qualitatively and quantitatively examine nurse practitioners'(NPs) and physician assistants' current PA counseling practices, knowledge and confidence to provide PA counseling and providers' perceptions about their current PA counseling practices. The specific aims for these two studies included quantitatively and qualitatively identifying the prevalence of PA counseling, perceived counseling knowledge and confidence, and educational training related to counseling. In study 1, survey respondents were currently practicing NPs and physician assistants. Participants completed a modified version of the Promotion of Physical Activity by Nurse Practitioners Questionnaire either online or in person during a population specific conference. The majority of both NP and physician assistant respondents reported routinely counseling patients about PA. There were no differences in perceived knowledge or confidence to provide PA counseling between the two populations. Approximately half of all respondents reported receiving training to provide PA counseling as part of their educational preparation for becoming a health practitioner. Nearly three-quarters of respondents reported interest in receiving additional PA counseling training. In study 2, five focus groups (FGs), stratified by practice type, were conducted with NPs and physician assistants. Both NPs and physician assistants reported discussing PA with their patients, particularly those with chronic illness. Participants reported that discussing lifestyle modifications with patients was the most common type of PA counseling provided. Increased confidence to counsel was associated with having PA knowledge and providing simple counseling, such as lifestyle modifications. Barriers to counseling included having more important things to discuss, lack of time during appointments, the current healthcare system, lack of reimbursement and perceived patient financial barriers. PA recommendation knowledge was highly variable, with few participants reporting specific guidelines. FG participants, while not familiar with the American College of Sports Medicines' "Exercise is Medicine" initiative indicated interest in its use and learning more about it. The findings of these two studies indicate that while NPs and physician assistants are knowledgeable, confident and currently providing some amount of PA counseling to patients, additional training in PA counseling is needed and desired.