A novel, interactive Android app has been developed that monitors the health of type 2 diabetic patients in real-time, providing patients and their physicians with real-time feedback on all relevant parameters of diabetes. The app includes modules for recording carbohydrate intake and blood glucose; for reminding patients about the need to take medications on schedule; and for tracking physical activity, using movement data via Bluetooth from a pair of wearable insole devices. Two machine learning models were developed to detect seven physical activities: sitting, standing, walking, running, stair ascent, stair descent and use of elliptical trainers. The SVM and decision tree models produced an average accuracy of 85% for these seven activities. The decision tree model is implemented in an app that classifies human activity in real-time.

Ensuring the objectivity of systematic reviews and meta-analyses (SRMA) begins with comprehensive searches into diverse resources mining primary studies. Guidelines for systematic reviews recommend authors to routinely search of trial registries to identify unpublished studies. In this dissertation, I investigated the utilization of ClinicalTrials.gov (CTG), the world’s largest clinical trial registry that contains data from clinical trials of products that are subject to United States Food and Drug Administration (FDA) regulation, as an information resource in SRMAs. First, I examined the use of various information resources including CTG in SRMAs published from 2005-2016, and identified the factors associated with their use. Thereafter, to determine the accuracy of trial safety data reported at CTG, I compared the data at CTG with that in corresponding journal articles and FDA drug reviews. I found that trial safety data at both CTG and articles differed frequently from FDA drug reviews, but the differences were modest in magnitude. Finally, I repeated published meta-analysis (conducted using data from primary study articles) with data at CTG to find that most meta-analysis results were reproduced using CTG data. Taken together, this work suggests that CTG should not only be searched more often to find primary research for systematic reviews, but that data at CTG can also be used to conduct quantitative data synthesis.

Information technology (IT) has been rapidly integrated into the healthcare industry, including nursing, and has the ability to reduce errors, cut cost, and enhance patient care. However, approximately 45% of the current nurse workforce lacks adequate training in computer skills, which may hinder the adoption of health-related IT in the workplace. Characteristics of Rogers's diffusion of innovation (relative advantage, compatibility, complexity, trialability, and observability) guided this project. This project was conducted to address the problem of IT adoption on a local level and was designed to assess whether simulation training on a generic electronic health record (EHR) system would improve the knowledge, skill, and attitude of nurses with little or no experience with EHR. A convenience sample of nurses (n = 13) unfamiliar with EHR was obtained by posting flyers in long-term care or home health agencies. The nurses completed the P.A.T.C.H. assessment scale v. 3 (2011) before and after participating in the one-time simulation training on EHR. Scores on the P.A.T.C.H. were calculated according to the established scoring system and revealed a positive increase nurses' attitude and self-efficacy toward the EHR system. Posttest scores yielded an increase ranging from 0.5 to 5 points from pretest scores, with an average pretest score of 54.23 on a scale of 0-100. The results of this project are consistent with the literature and current research and illustrate the importance of addressing the need for interactive training. This project contributes to social change in practice by enhancing the awareness of EHR in nurses who are new users of IT and promoting the adoption of technology in healthcare.

In this research, we detail the development of a novel, easy-to-use system to facilitate electronic patient falls reporting within a long-term residential care facility (LTRCF) using off-the-shelf technology that can be inexpensively implemented in a wide variety of settings. We report the results of four complimentary system evaluation measures that take into consideration varied organizational stakeholders’ perspectives: 1) System-level benefits and costs, 2) System usability, via scenario-based use cases, 3) A holistic assessment of users’ physical, cognitive, and marcoergonomic (work system) challenges in using the system, and 4) User technology acceptance. We report the viability of collecting and analyzing data specific to each evaluation measure and detail the relative merits of each measure in judging whether the system is acceptable to each stakeholder. The electronic falls reporting system was successfully implemented, with 100% electronic submission rate at 3-months post-implementation period. The system-level benefits and costs approach showed that the electronic system required no initial investment costs aside from personnel costs and significant benefits accrued from user time savings. The usability analysis revealed several fixable design flaws and demonstrated the importance of scenario-based user training. The technology acceptance model showed that users perceived the reporting system to be useful and easy to use, even more so after implementation. Finally, the holistic human factors evaluation identified challenges encountered when nurses used the system as a part of their daily work, guiding further system redesign. The four-pronged evaluation framework accounted for varied stakeholder perspectives and goals and is a highly scalable framework that can be easily applied to Health IT (Information Technology) implementations in other LTRCFs.

Regular physical activity, timely medication, controlled diet, and blood glucose monitoring is crucial for any diabetic patient. Laxity on following these treatment regimens can cause severe health complexity. Moreover, A physician’s surveillance on a patient, based on the patient’s real-time progress is difficult with the existing health care system. This research aims to provide a more accurate objective data in real-time to the physicians to help both patients and providers. The data being generated is mined later to investigate interesting questions regarding diabetic care. The resultant system is a mobile healthcare monitoring system for type – 2 diabetic patients that traces patients daily progress. Although many mobile apps provide self-monitoring tools for the patient, an interactive platform for monitoring all relevant parameters of diabetes where patients and physicians both are end users is unique. The Android app is designed with 3 major modules and two submodules: 1. Carb Intake Tracker (CIT), 2. Blood Glucose Tracker (BGT), 3. Physical Activity Tracker (PAT), 4. Medicine and 5. Blood Glucose (BG) reading reminder. Since Carb is an important factor for a diabetic patient’s meals, the CIT provides a platform to record daily meals from which the patient can see the total carb intake. Through BGT, patients can record their fasting or non-fasting blood glucose reading. The PAT collects a patient’s movement data via Bluetooth from a pair of wearable insole devices, and processing the data identifies and records the current activity. The PAT can detect if the patient is active in sedentary, as well as the type of exercise done by the patient. Using BG reminder and medicine reminder, the patient can set reminders which supports the apps self-monitoring aspect. All the data collected by CIT, BGT, and PAT are stored in Microsoft Azure cloud database, an authorized physician can access the database and see graphical statistics of a patient’s diet, physical activity, and glycemic index level. The app portrays statistics of carbs taken over a period, calories burned, and Glucose level trends through graphical representation. This has two advantages: 1. Patients can improve lifestyle observing records and following reminders, 2. Physicians can prescribe actions perceiving a patient’s trends over time. This research presents unique collaborative interaction between diabetic patients and physicians to create a real time patient portal based on android APIs and wearable devices.

Picture Archiving and Communication Systems (PACS) have been traditionally constrained to the premises of the healthcare provider. This has limited the availability of these systems in many parts of the world and mandated major costs in infrastructure for those who employ them. Public cloud services could be a solution that eases the cost of ownership and provides greater flexibility for PACS implementations. This could make it possible to bring medical imaging services to places where it was previously unavailable and reduce the costs associated with these services for those who utilize them. Moving these systems to public cloud infrastructure requires that an authentication and encryption policy for communications is established within the PACS environment to mitigate the risks incurred by using the Internet for the communication of medical data. This thesis proposes a framework which can be used to create an authenticated and encrypted channel to secure the communications with a cloud-based PACS. This framework uses the Transport Layer Security (TLS) protocol and X.509 certificates to create a secured channel. An enterprise style PKI is used to provide a trust model to authorize endpoints to access the system. The validity of this framework was tested by creating a prototype cloud-based PACS with secured communications. Using this framework will provide a system based on trusted industry standards which will protect the confidentiality and integrity of medical data in transit when using a cloud-based PACS service.

Background Due to the COVID-19 pandemic, there was a significant reduction in in-person healthcare visits as a precautionary measure to minimize the risk of infection for both patients and healthcare provides. Consequently, there was a remarkable surge in the adoption of telehealth services, although mental healthcare services were already using it more frequently than primary and specialty care services before the pandemic. Despite the continued increase in telehealth services, there are differing views among healthcare providers on the efficacy of providing healthcare services remotely, leading to an opportunity to investigate this matter further. Objective The primary goal of this study was to evaluate differences in perceptions and attitudes, experience with patient interactions and overall telehealth experiences between mental health providers and non-mental health providers. Methods The proposed study collected primary data through surveying providers across the United States from November 2022-March 2023. The surveys were conducted through REDCap, and disseminated through research staff outreach and recruitment. Providers were asked to complete a 33-item survey, which took them about 30 minutes to finish and queried them about their satisfaction, utilization, and experiences with telehealth. The provider survey was disseminated to both mental health providers and non-mental health providers who use telehealth technology. Descriptive analysis was conducted to determine the characteristics of the population surveyed. Data was then dichotomized by mental health providers vs. non-mental health providers. Differences in mean responses for all variables between mental health and non-mental health providers was assessed using Mann-Whitney U (MW) tests. Results A Mann-Whitney Wilcoxon test indicated that the satisfaction with the telemedicine platform was greater for non-mental healthcare providers than mental healthcare providers (p < .05). A Mann-Whitney Wilcoxon test indicated that the reliability of the telemedicine app for facilitating health care services, that the ability to trust the telemedicine application to work, the lack of physical contact during a video visit being a problem, the video visits being a convenient form of healthcare delivery, the visits on the telehealth system are the same as in-person visits, and that continued use of telehealth services in the future was greater for mental healthcare providers than non-mental healthcare providers (p < .05). Conclusions Looking forward, we expect to see more extensive studies involving providers from various regions and the implementation of additional approaches to enhance their experiences.

No description available.

The adoption of healthcare information technology (HIT) has been advocated by various groups as critical in addressing the growing crisis in the healthcare industry. Despite the plethora of evidence on the benefits of HIT, however, the healthcare industry lags behind many other economic sectors in the adoption of information technology. A significant number of healthcare providers still keep patient information on paper. With the recent trends of reimbursement reduction and rapid technological advances, therefore, it would be critical to understand differences in structural characteristics and healthcare performance between providers that do and that do not adopt HIT. This is accomplished in this research, first by identifying organizational and contextual factors associated with the adoption of HIT in US acute care hospitals and second by examining the relationships between the adoption of HIT and two important healthcare outcomes: patient safety and quality of care. After conducting literature a review, the structure-process-outcome model and diffusion of innovations theory were used to develop a conceptual framework. Hypotheses were developed and variables were selected based on the conceptual framework. Publicly available secondary data were obtained from the American Hospital Association (AHA), the Health Information and Management Systems Society (HIMSS), and the Healthcare Cost and Utilization Project (HCUP) databases. The information technologies were grouped into three clusters: clinical, administrative, and strategic decision making ITs. After the data from the three sources were cleaned and merged, regression models were built to identify organizational and contextual factors that affect HIT adoption and to determine the effects of HIT adoption on patient safety and quality of care. Most prior studies on HIT were restricted in scope as they primarily focused on a limited number of technologies, single healthcare outcomes, individual healthcare institutions, limited geographic locations, and/or small market segments. This limits the generalizability of the findings and makes it difficult to draw definitive conclusions. The new contribution of the present study lies in the fact that it uses nationally representative latest available data and it incorporates a large number of technologies and two risk adjusted healthcare outcomes. Large size and urban location were found to be the most influential hospital characteristics that positively affect information technology adoption. However, the adoption of HIT was not found to significantly affect hospitals' performance in terms of patient safety and quality of care measures. Perhaps a remarkable finding of this study is the better quality of care performance of hospitals in the Midwest, South, and West compared to hospitals in the Northeast despite the fact that the latter reported higher HIT adoption rates. In terms of theoretical implications, this study confirms that organizational and contextual factors (structure) affect adoption of information technology (process) which in turn affects healthcare outcomes (outcome), though not consistently, validating Avedis Donabedian's structure-process-outcome model. In addition, diffusion of innovations theory links factors associated with resource abundance, access to information, and prestige with adoption of information technology. The present findings also confirm that hospitals with these attributes adopted more technologies. The methodological implication of this study is that the lack of a single common variable and uniformity of data among the data sources imply the need for standardization in data collection and preparation. In terms of policy implication, the findings in this study indicate that a significant number of hospitals are still reluctant to use clinical HIT. Thus, even though the passage of the American Recovery and Reinvestment Act (ARRA) of 2009 was a good stimulus, a more aggressive policy intervention from the government is warranted in order to direct the healthcare industry towards a better adoption of clinical HIT.

Context: Computerized clinical decision support systems (CCDSSs) give practitioners patient-specific care advice and are considered an important increment to electronic clinical documentation and order entry systems. Despite decades of research on CCDSS, results from rigorous clinical evaluations remain mixed and systems vary greatly in design and implementation. Objective: To identify factors differentiating CCDSSs that improve the process of care or patient outcomes from those that do not. Data Sources: We searched major bibliographic databases and scanned reference lists for eligible articles up to January 2010. Study selection: 162 eligible comparisons from randomized controlled trials of CCDSS to non-CCDSS care. We deemed successful those systems that improved either 50% of reported process of care outcomes or 50% of patient outcomes. We extracted system characteristics hypothesized to impact patient care and tested them for association with system effectiveness in logistic models. Results: Our primary analysis showed that CCDSSs presented in electronic health records or order entry systems were less likely to be effective than their counterparts (OR, 0.37; 95% CI, 0.17 to 0.80). Systems more likely to succeed than their counterparts provided advice for patients in addition to practitioners (OR, 2.77; 95% CI, 1.07 to 7.17), required from practitioners a reason to override advice (OR, 11.23; 95% CI, 1.98 to 63.72), or were evaluated by their developers (OR, 4.35; 95% CI, 1.66 to 11.44). These findings remained consistent across different statistical methods, sensitivity analyses, and adjustment for other potentially important factors. Conclusions: We identified several factors that may partially explain why some systems succeed and others fail. Primary studies should investigate the impact and optimal implementation of advice provided to patients and practitioners and advice that requires reasons to be overridden. Researchers should also address the reasons for failure of advice presented within charting and order entry systems. / Master of Science (MSc)