Background: Electronic Health Records (EHR) are digital versions of patients' charts (HealthIT.gov, 2013). The government has incentivized current use to allow all healthcare organizations to progress from paper charting. Goals of EHR adoption include improving workflow, documentation, and to improve the quality of care being provided (Weiner, Fowles, & Chan, 2012). Objective: The purpose of this DNP project was to conduct a readiness assessment of the asthma and allergy specialty organization's staff members to identify perceived barriers and advantages of adopting an EHR. Design: This project was guided by the Institute for Healthcare Improvement (IHI) Model for Improvement (Institute for Healthcare Improvement [IHI], 2016). This model was incorporated with the PDSA cycle and DOQ-IT EHR Implementation Roadmap. Descriptive statistics were used for data analysis. Setting: Allergy and asthma specialty practice consisting of 12 clinics within the Denver Metro and Northern Colorado area. Participants: 155 members of the organization including physicians, nurse practitioners, physician assistants, nurses, medical assistants, front office and administrative staff. Measurements: 60 out of 155 staff members completed the readiness assessment survey from HealthInsight (HealthInsight, n.d.).Results: A response rate of 38.7% (n=60) of participants completed the readiness assessment survey. The top two barriers were medical records being unavailable (n= 48, 80%) and the inability to read what is written in the medical record (n= 51, 85%). The top barrier for adopting EHR is having the system freeze or crash (n=36, 65%), followed by, 22 participants or 40% stating EHR is depersonalizing in an exam room. The highest advantage identified was the reduction in paper-based medical charting and filing (n=56, 93%). The second highest advantage was more timely access to patient records (n=55, 92%).Conclusion: Perceived barriers and advantages for EHR adoption within the organization are similar to what literature has currently identified. The information gained from this study will provide a better understanding of the decision and adoption process. The information will help the organization decide whether or not to adopt EHR and how to successfully move through the DOQ-IT EHR Implementation Roadmap, IHI Model for Improvement and PDSA cycle.

Alzheimer’s disease is typically detected using a combination of cognitive-behavioral assessment exams and interviews of both the patient and a family member or caregiver, both administered and interpreted by a trained physician. This procedure, while standard in medical practice, can be time consuming and expensive for both the patient and the diagnostician especially because proper training is required to interpret the collected information and determine an appropriate diagnosis. The use of machine learning techniques to augment diagnostic procedures has been previously examined in limited capacity but to date no research examines real-world medical applications of predictive analytics for health records and cognitive exam scores. This dissertation seeks to examine the efficacy of detecting cognitive impairment due to Alzheimer’s disease using machine learning, including multi-modal neural network architectures, with a real-world clinical dataset used to determine the accuracy and applicability of the generated models. An in-depth analysis of each type of data (e.g. cognitive exams, questionnaires, demographics) as well as the cognitive domains examined (e.g. memory, attention, language) is performed to identify the most useful targets, with cognitive exams and questionnaires being found to be the most useful features and short-term memory, attention, and language found to be the most important cognitive domains. In an effort to reduce medical costs and streamline procedures, optimally predictive and efficient groups of features were identified and selected, with the best performing and economical group containing only three questions and one cognitive exam component, producing an accuracy of 85%. The most effective diagnostic scoring procedure was examined, with simple threshold counting based on medical documentation being identified as the most useful. Overall predictive analysis found that Alzheimer’s disease can be detected most accurately using a bimodal multi-input neural network model using separated cognitive domains and questionnaires, with a detection accuracy of 88% using the real-world testing set, and that the technique of analyzing domains separately serves to significantly improve model efficacy compared to models that combine them. / Includes bibliography. / Dissertation (Ph.D.)--Florida Atlantic University, 2019. / FAU Electronic Theses and Dissertations Collection

Rationale: The Cancer Agency Information System (CAIS) is the primary patient record for the British Columbia Cancer Agency (BCCA) but is only accessible on fixed computer workstations. The BCCA clinics have significant space limitations resulting in multiple healthcare providers sharing each workstation. Furthermore, workstations are not available in the patient examination rooms leading to multiple visit interruptions. Given that timely and efficient access to patient electronic records is fundamental in providing optimal patient care, the iPad Mobility Project was launched to introduce and evaluate the effect of mobile technologies and applications in improving access to CAIS and supporting clinicians’ workflow. Methods The project evaluation framework was created in collaboration with the project stakeholders including BCCA clinicians. The framework included pre- and post-implementation questionnaires, pre- and post-implementation observational sessions, and post-implementation semi-structured interviews. Survey questionnaires mainly included standardized scales used to measure user expectations and perceptions before and after information systems implementation. Also, based on Canada Infoway System and Use Survey, the post-implementation questionnaire included questions that measure the mobile system success in terms of information quality, system quality, service quality, user satisfaction, and use measures. The response rate was 84% (n=44) for the baseline survey and 76% (n=52) for the post-implementation survey. Also, baseline and post-implementation observational sessions (n=5, n=6 respectively) were conducted to provide real-time data about the use of the available record keeping systems before and after the mobile system implementation. Post-implementation semi-structured interviews (n=11) were conducted to allow clinicians to reflect on their use of the iPad and VitalHub Chart application. Results: The results showed an overwhelmingly positive attitude to the use of the iPad and the VitalHub Chart application to support clinicians’ mobile workflow through enhanced access to CAIS. Perceived benefits were related to three major categories: information accessibility and inter-professional communication; workflow efficiency and provider productivity, and patient care quality and safety. Conversely, perceived challenges were related to three major categories: software related challenges, hardware related challenges, and network infrastructure-related issues. Furthermore, the results showed that the success of mobile computing technology depends on its ability to support access to patients’ electronic records and other central clinical information systems, on mobile devices and their applications’ ergonomic features, and on end-user participation in mobile computing projects. Implications Mobile computing technologies have the potential to improve data accessibility, communication mechanisms, patient care quality, and workflow efficiency. However, realizing the full potential benefits of mobile computing technologies rely on several factors. Healthcare organizations need to have clear understanding of end users’ needs, expectations, clinical tasks, and workflow. Engaging end-users in mobile computing technologies projects from the early stages of the project is essential to identify the various complex human, organizational, and contextual factors that affect the success of enterprise-wide mobile computing technology projects. Due to their inherent limitations, mobile computing technologies should be considered as complementary to and not as replacement to fixed computer workstations. Also, evaluating mobile technologies and applications usability is essential for both the success and safety of such innovative solutions. / Graduate / 0723 / 0566 / banimelh@uvic.ca

Background: The increasing use of electronic health records (EHR) provides a novel opportunity to evaluate hospital-based nutritional outcomes, such as malnutrition. There is no universally accepted screening tool for the detection of malnutrition. However, assessment for malnutrition should be made early, be simple, based on scientific evidence, and include data on age, gender, and disease severity. The malnutrition screening tool (MST) used in this study is a two question tool that assesses two parameters commonly seen when diagnosing malnutrition (weight loss and loss of appetite). Objective: The purpose of this study is to determine the ability of the MST used at a tertiary or quaternary hospital to accurately identify patients with malnutrition by comparing it against the Academy of Nutrition and Dietetics and American Society for Parenteral and Enteral Nutrition criteria for malnutrition. Participants/setting: A descriptive cohort study was conducted that included 167 patients admitted to Emory University Hospital between October 1 - 14, 2014. MST score, malnutrition diagnostic criteria, and demographic and anthropometric characteristics were obtained to describe and assess the study population. Statistical Analysis: Frequency statistics were used to describe the demographic and anthropometric characteristics and MST score results. Normality statistics were used to determine the distribution of continuous variables. A Chi Square table was used to determine the significance of the association between the MST score and diagnosis of malnutrition made by the Registered Dietitian (RD) as well as the sensitivity and specificity of the MST. Results: A total of 167 patients (48.5% male, 51.5% Caucasian, non-Hispanic) were admitted during the study period. The vast majority of the patient population with malnutrition (79%), as diagnosed by the RD, was identified as such by the MST (p < 0.01). The sensitivity and specificity of the MST was 79% and 62%, respectively. Conclusion: The MST is a useful screening tool for malnutrition in adults admitted to a large urban university hospital. There is a lack of research validating the MST in the adult outpatient population. Therefore, future studies are necessary to evaluate the effectiveness of the MST in this population.

Magister Commercii - MCom / This study aimed to understand the readiness and perceptions of Electronic Health Record (EHR) adoption among dentists in the public service of the Western Cape. A qualitative study design was chosen due to a lack of understanding of the phenomena. Additionally, the research sought to identify the factors that would potentially influence readiness and perceptions in order to identify how these factors could potentially influence EHR adoption among dentists.

Melanoma is one of the fastest growing cancers in the world, and can affect patients earlier in life than most other cancers. Therefore, it is imperative to be able to identify patients at high risk for melanoma and enroll them in screening programs to detect the cancer early. Electronic health records collect an enormous amount of data about real-world patient encounters, treatments, and outcomes. This data can be mined to increase our understanding of melanoma as well as build personalized models to predict risk of developing the cancer. Cancer risk models built from structured clinical data are limited in current research, with most studies involving just a few variables from institutional databases or registries. This dissertation presents data processing and machine learning approaches to build melanoma risk models from a large database of de-identified electronic health records. The database contains consistently captured structured data, enabling the extraction of hundreds of thousands of data points each from millions of patient records. Several experiments are performed to build effective models, particularly to predict sentinel lymph node metastasis in known melanoma patients and to predict individual risk of developing melanoma. Data for these models suffer from high dimensionality and class imbalance. Thus, classifiers such as logistic regression, support vector machines, random forest, and XGBoost are combined with advanced modeling techniques such as feature selection and data sampling. Risk factors are evaluated using regression model weights and decision trees, while personalized predictions are provided through random forest decomposition and Shapley additive explanations. Random undersampling on the melanoma risk dataset shows that many majority samples can be removed without a decrease in model performance. To determine how much data is truly needed, we explore learning curve approximation methods on the melanoma data and three publicly-available large-scale biomedical datasets. We apply an inverse power law model as well as introduce a novel semi-supervised curve creation method that utilizes a small amount of labeled data. / Includes bibliography. / Dissertation (Ph.D.)--Florida Atlantic University, 2019. / FAU Electronic Theses and Dissertations Collection

By the end of 2015, Medicare-eligible physicians at primary care practices (PCP) who do not use an electronic health record (EHR) system will incur stiff penalties if they fail to meet the deadline for using EHRs. Yet, less than 30% of rural primary clinics have fully functional EHR systems. The purpose of this phenomenology study was to explore rural primary care physicians and physician assistants' experiences regarding overcoming barriers to implementing EHRs. Complex adaptive systems formed the conceptual framework for this study. Data were collected through face-to-face interviews with a purposeful sample of 21 physicians and physician assistants across 2 rural PCPs in the southeastern region of Missouri. Participant perceptions were elicited regarding overcoming barriers to implementing EHRs under the American Recovery and Reinvestment Act, Health Information Technology for Economic and Clinical Health, and the Patient Protection and Affordable Care Act legislation. Interview questions were transcribed and processed through qualitative software to discern themes of how rural PCP physicians and physician assistants might overcome barriers to implementing electronic health records. Through the exploration of the narrative segments, 4 emergent themes were common among the participants: (a) limited finances to support EHRs, (b) health information exchange issues, (c) lack of business education, and (d) lack of transformation at rural medical practices. The implications for positive social change include the potential implementation of EHRs particularly in physician practices in rural communities, which could provide cost-efficient health care services for those communities and a more sustainable future at primary care practices.

Urinary incontinence affects up to 70% of residents living in a long-term care facility and can affect their quality of life. Specifically, urinary incontinence has a direct impact on older adults in regards to self-esteem, pressure ulcer development, falls, urinary tract infections, and psychosocial wellbeing. The goal of this quality improvement pilot project was to determine if an electronic health record (EHR) assessment tool could help older adults remain continent longer and assist in maintaining an independent lifestyle. Orem's self-care deficit theory and social cognitive theory were used to determine how the electronic health record incontinence template could be used to monitor residents for incontinence and affect the incidence of incontinence. Out of 25 residents, 13 met the requirements for inclusion in the pilot study. Quantitative data were collected and documented in the EHR for 4 weeks and compared to the immediate 4 week period post-implementation of the EHR template. Descriptive analyses of pre- and post-implementation EHR assessments showed there were no EHR assessments completed pre-implementation and 2 residents out of 13 had EHR assessments completed post-implementation. The available data suggested that the EHR template, if edited, could be effective for tracking incontinence. The template needed to address bladder incontinence only rather than bowel and bladder. Feedback from nursing staff indicated that a future study should be conducted over a longer period than 4 weeks to see if results would remain consistent. Nurses working in the long term care environment would benefit from reading this project. This study contributes to social change as evidenced by the residents who remained continent longer by having individual toileting plans partially developed by the template; therefore, they remained a viable part of the community.

There is a marked trend of using information technologies to improve healthcare. Among all the health IT, electronic health record (EHR) systems hold great promises as they modernize the paradigm and practice of care provision. However, empirical studies in the literature found mixed evidence on whether EHRs improve quality of care. I posit two explanations for the mixed evidence. First, most prior studies failed to account for system use and only focused on EHR purchase or adoption. Second, most existing EHR systems provide inadequate clinical decision support and hence, fail to reveal the full potential of digital health. In this dissertation I address two broad research questions: a) Does meaningful use of EHRs improve quality of care? and b) How do we advance clinical decision making through innovative computational techniques of healthcare analytics? To these ends, the dissertation comprises four essays. The first essay examines whether meaningful use of EHRs improve quality of care through a natural experiment. I found that meaningful use significantly improve quality of care, and this effect is greater in historically disadvantaged hospitals such as small, non-teaching, or rural hospitals. These empirical findings present salient practical and policy implications about the role of health IT. On the other hand, in the other three essays I work with real-world EHR data sets and propose healthcare analytics frameworks and methods to better utilize clinical text (Essay II), integrate clinical guidelines and EHR data for risk prediction (Essay III), and develop a principled approach for multifaceted risk profiling (Essay IV). Models, frameworks, and design principles proposed in these essays advance not only health IT research, but also more broadly contribute to business analytics, design science, and predictive modeling research.

The overall aim of this thesis was to investigate predefined headings in a Swedish county council multi-professional EHR system in terms of their shared application, what aspects of health and health care they reflected, and their correspondence to legal requirements. An analysis of 3 596 predefined headings, applied to 20 398 104 occasions by eight professional groups, was conducted. Less than 2% of the predefined headings were applied by all eight professional groups, whereas 60% were not shared at all between the professional groups. A classification of the predefined headings revealed that 13% were “Specialist terms”, which were the least ambiguous predefined headings, 46% were “Terms for specific purposes”, which are less ambiguous than the “Common words” (28%), which were the most ambiguous predefined headings according to the sociolinguistic method employed. The remaining predefined headings (13%) were sorted into “Unclassified headings”. A qualitative content analysis of the predefined headings yielded 23 subcategories grouped into five categories: Description of the patient, Health care process, Resources employed, Administrative documentation, and Development and research. A comparison of the 23 subcategories to the Patient Data Act showed, first, that 15 of 23 subcategories corresponded to four legal requirements, second, that there were legal requirements with a focus on patient rights that were not being met, and third, that there were eight subcategories of predefined headings that could not be attributed to the legal provisions of the Patient Data Act. In conclusion, the proportion of shared predefined headings in the EHRs was limited. The predefined headings in the multi-professional EHRs did not constitute a joint language for specific purposes. A meaningful structure comprising categories and subcategories of different aspects of health and health care as reflected in the applied predefined headings was identified. The structure reflected a wide range of health and health care. No subcategory corresponded to the three legal requirements concerning patient rights. Future research should include professionals’ and patients’ understanding of predefined headings, the correspondence of documented notes to predefined headings and how the documentation in the EHR has had an impact on patient safety.