INTRODUCTION: Polycystic Ovary Syndrome (PCOS) is the most common endocrinopathy causing infertility in women of reproductive age. According to the Rotterdam criteria, a PCOS diagnosis should be given if at least two of the following are met: 1) hyperandrogenism; 2) oligo-anovulation; and 3) polycystic ovarian morphology. Previous studies analyzing the prevalence of PCOS have done so in unselected and clinical populations but few studies have attempted to characterize the syndrome and its long-term outcomes within Electronic Health Records using International Classification of Disease (ICD) codes. OBJECTIVES: With a hospital-based electronic health record dataset, this thesis seeks to: (1) characterize PCOS in reproductively aged women (18-34) using the diagnostic codes (ICD-9 and ICD-10) versus the Rotterdam criteria, (2) determine the prevalence of metabolic syndrome (MetS), Type 2 Diabetes, and cardiac events in women above age 35, (3) determine age of diagnosis for MetS and time to diagnosis of MetS. METHODS: The following 3 cohorts were queried on the Research Patient Data Registry (RPDR): 1) patients aged 18-34 with classic PCOS (phenotype A and B) but without an ICD diagnosis for PCOS, 2) patients aged 18-34 with a PCOS ICD-9/10 diagnosis and 3) patients above age 35 with a history or current diagnosis of PCOS. Their electronic health records (between January 1 , 2003 and December 31 , 2020) were ascertained from 9 Mass General Brigham institutions after IRB approval and analyzed on Software for Statistics and Data Science (STATA). RESULTS: Overall, RPDR identified 12,669 patients aged 18-34 who fit the Rotterdam criteria (under multiple phenotypes), 4646 of which had classic PCOS but lacked an ICD- 9/10 code for PCOS. RPDR also identified 9341 women aged 35 and above with a past or current diagnosis of PCOS. Hispanics/Latinas (18-34) were two times more likely to be undiagnosed when compared to Non-Hispanic Whites (OR: 2.25, 95% CI: 1.98-2.56). The prevalence of MetS, specified by a diagnostic code (277.7 or E88.81), and other cardiac conditions in women above age 35 were considerably lower than those found in the current literature. CONCLUSION: Databases such as RPDR allow for a detailed analysis of patient demographics, labs, procedures and diagnoses. Additionally, it allows for larger cohorts of patients matching more specific criteria to be ascertained. Future studies should compare the prevalence of individual features of MetS by ICD codes and analyze the cardiology reports to determine if the events are being reported but not codified. / 2023-11-30

Indiana University-Purdue University Indianapolis (IUPUI) / In the age of big data, better use of large, real-world datasets is needed, especially ultra-large databases that leverage health information exchange (HIE) systems to gather data from multiple sources. Promising as this process is, there have been challenges analyzing big data in healthcare due to big data attributes, mainly regarding volume, variety, and velocity. Thus, these health data require not only computational approaches but also context-based controls.In this research, we systematically examined associations among select neural and dermal conditions in an ultra-large healthcare database derived from an HIE, in which computational approaches with epidemiological measures were used. After a systematic cleaning, a binary logistic model-based methodology was used to search for associations, controlling for race and gender. Age groups were chosen using an algorithm to find the highest incidence rates for each condition pair. A binomial test was conducted to check for significant temporal direction among conditions to infer cause and effect. Gene-disease association data were used to evaluate the association among the conditions and assess the shared genetic background. The results were adjusted for multiple testing, and network graphs of significant associations were created. Findings among methodologies were compared to each other and with prior studies in the literature. In the results, seemingly distant neural and dermal conditions had an extensive number of associations. Controlling for race and gender tightened these associations, especially for racial factors affecting dermal conditions, like melanoma, and gender differences on conditions like migraine. Temporal and gene associations helped explain some of the results, but not all. Network visualizations summarized results, highlighting central conditions and stronger associations. Healthcare data are confounded by many factors that hide associations of interest. Triangulating associations with separate analyses helped with the interpretation of results. There are still numerous confounders in these data that bias associations. Aside from what is known, our approach with limited variables may inform hypothesis generation. Using additional variables with controlled-computational methods that require minimal external input may provide results that can guide healthcare, health policy, and further research.

As the digitisation of healthcare progresses, there are still problems in terms of usability. With the goal of exploring solutions to these, an email inspired design for an electronic health record system was implemented using modern web technologies. The implementation was then evaluated in a series of usability tests conducted with five orthopaedic surgeons. Participants were asked to perform small tasks on a mocked data set, and the sessions were concluded with debriefing interviews. The focus was on the areas that are new in this design. The results suggest that the general design works, and no critical flaws were identified at this stage. Most of the issues that were found are likely to be solved with more training and experience, but there is still room for improvement. Participants had positive reactions overall, and plenty of feedback was collected regarding areas of improvement and feature suggestions. Due to the limitations of the test, the findings mostly relate to the intuitiveness of the design. To draw stronger conclusions regarding the viability of the design in a real environment, further testing with more data, realistic test tasks and more prerequisite training is necessary. / Digitiseringen inom sjukvården ökar, men det finns fortfarande problem när det kommer till användbarheten av de digitala system som finns på marknaden. Med målet att utforska lösningar på dessa problem implementerades i detta arbete en e-post-inspirerad gränssnittsdesign för ett digitalt journalsystem med hjälp av moderna webb-teknologier. Implementationen utvärderades genom användartester där fem ortopediska kirurger deltog. Deltagarna ombads använda gränssnittet för att utföra små testuppgifter med påhittad patientdata, och sessionerna avslutades med intervjufrågor. Fokuset var på de delar som är nya i den här designen jämfört med redan existerande system. Resultatet visar att det generella upplägget fungerar, och inga kritiska brister upptäcktes i detta stadie. De flesta av problemen som uppdagades kan troligen lösas genom att användarna ges möjlighet till mer träning och får mer erfarenhet, men det finns fortfarande förbättringutrymme. Deltagarna hade positiva reaktioner i allmänhet, och många förslag kring förbättringsområden och önskemål kring utökad funktionalitet samlades upp. På grund av användartestets begränsningar belyser resultaten i detta test mest vilka delar av gränssnittet som är intuitiva eller ej, medan det som är mer intressant för den här typen av dagligen använda system egentligen är huruvida de är effektiva att använda i det dagliga arbetet. För att kunna dra säkrare slutsatser kring om den här designen skulle fungera i riktiga arbetssituationer behövs mer testning med större mängder patientdata, mer realistiska testuppgifter och mer tid för deltagarna att lära sig systemet i förväg.

Lung cancer affects many individuals each year and accounts for many deaths around the globe. Lung cancer screening is a preventative health measure that has the ability to detect lung cancer earlier. The purpose of this project was to focus on the education of nursing staff within a community health system, with subsequent implementation of an electronic health record clinical decision support system, to create a direct referral pathway to lung cancer screening, delivered through patient education. The concept of prevention was the framework for this project design, which was further organized around the plan-do-study -act model, while taking into consideration the health belief model and theory of interpersonal relations. Using systemized dashboard reports within the electronic health record software, specific variables were targeted for data collection and analyzed for the purpose of this project. Final data demonstrated an increase of triple the programmatic volume of the previous year, directly following the implementation of the above initiative. Further comparative statistics bespeak to the significant needs of the community regarding tobacco dependence and lung cancer screening. High-risk individuals who are current or former smokers will benefit from this initiative by receiving education about lung cancer screening and tobacco dependence treatment while within the care of the community based health system. A nursing-driven pathway to preventative care could also serve other cancer screening programs effectively, as well as be applied to a variety of chronic disease comorbidities to make a significant positive social change.

The American Recovery and Reinvestment Act (ARRA) of 2009 authorized the distribution of about $30 billion incentive funds to accelerate electronic health record (EHR) applications to improve the quality of care, safety, privacy, care coordination, and patients' involvement in healthcare. EHR use has the potential of saving $731 in costs for hospitals per patient admission; however, most hospitals are not applying EHR to reach the level at which cost savings are possible. The purpose of this single case study was to explore strategies that IT leaders in hospitals can use to apply EHR to achieve the cost saving benefits. The participants were IT leaders and EHR super users at a large hospital in Texas with successful experience in applying EHR. Information systems success model formed the conceptual framework for the study. I conducted face-to-face interviews and analyzed organizational documents. I used qualitative textual data analysis method to identify themes. Five themes emerged from this study, which are ensuring information quality, ensuring system quality, assuring service quality, promoting usability, and maximizing net benefits of the EHR system. The findings of this study included four strategies to apply EHR; these strategies include engaging training staff, documenting accurately and in a timely manner, protecting patient data, and enforcing organizational best practice policies to maximize reimbursement and cost savings. The findings of this study could contribute to positive social change for the communities because EHR successful application includes lower cost for hospitals that may lead to the provision of affordable care to more low-income patients.

Electronic health records (EHRs) have been in use since the 1960s. U.S. rural hospital leaders and administrators face significant pressure to implement health information technology because of the American Recovery and Reinvestment Act of 2009. However, some leaders and managers of small rural hospital lack strategies to develop and implement EHRs. The focus of this descriptive phenomenological study was to explore lived experiences of hospital leaders and administrators who have used successful strategies to implement EHRs in small rural hospitals. Diffusion of innovation theory shaped the theoretical framework of this study. Data were collected through telephone interviews conducted with participants who successfully deployed EHRs at 10 hospitals in the Appalachian regions of Maryland, Virginia, and West Virginia. Data analysis occurred using a modified Husserlian approach in search of common themes from interview transcripts. The main themes were strategies to address standards and incentives, implementation, and challenges. The exploration of these strategies provides insight that small rural hospital leaders and administrators could consider for implementing EHRs. The study findings might enable small rural hospital leaders and administrators to contribute to positive social change by engaging communities in using EHRs; these findings may also expand information sharing among individuals and organizations and build social relationships with an expectation of future benefits. Results from this study are designed to inform other small rural hospital leaders and administrators to conduct further research on successful strategies for implementation of EHRs.

The electronic health record (EHR) is an important part of the effort to improve health care and reduce costs in the United States. Primary care providers, among the largest group of caregivers in the nation, often experience difficulty with implementation and utilization of EHRs. Efforts to enhance the provider's effectiveness in the use of the EHR should result in improved patient outcomes as well as decreasing the overall cost of health care. Guided by the diffusion of innovation theory, this project was initiated to develop a plan for improved usage of the EHR in a primary care setting. A survey and observations were used to better understand how the providers and staff were using the EHR. Observations and a survey of 11 participants were completed. The observations utilizing a mock patient revealed issues related to the usability of screen information, information availability, and user preference for documentation. The mock patient scenario took 25-35 minutes, on average, to complete. All participants stated they had stayed late to input information on actual clinic patients or to clarify their documentation. The same 11 participants completed the Primary Care Information Project (PCIP) Post-Electronic Health Record Implementation: Survey of Providers responses. Descriptive statistics were used to analyze the results. Most participants indicated that the screen font was difficult to read (72.7%), they had difficulty using the EHR (72.8%) and were not satisfied with its use (63.6%). The project recommendations include working with the vendor to improve information access and ongoing training. Improvements to the EHR should support social change by improving access to information at the point of care, enhancing quality treatment and improving patient care outcomes.

Medication errors are among the most common causes of unintended harm to patients and have led to many deaths. Some categories of medication errors include; medications administered to the wrong person; medications administered at the wrong time, through the wrong route; administration of the wrong medication and/or dose; and the omission of medications. Guided by the logic model, the just culture model, and the Knowles theory of andragogy, the purpose of the project was to determine if providing information related to evidence-based strategies to reduce medication errors would result in safer medication administration practices and improved patient outcomes A survey was administered to 11 medical and nursing staff at an outpatient internal medical clinic to determine their knowledge about medications errors prior to providing evidence-based information on strategies to reduce medication errors. After the educational session, a survey was conducted to determine staff members' retention of knowledge. A significant increase in the percent of correct responses to the survey from 68% to 100% after the educational session (t = -3.9; p = 0.001)) shows that the educational in-service had a positive outcome in increasing staff members' knowledge about reducing medication errors in an out-patient internal medicine clinic. Improving clinic staff knowledge and behaviors regarding medication administration has the potential to bring about social change by decreasing medication errors, improving patient safety, and improving health outcomes.

Indiana University-Purdue University Indianapolis (IUPUI) / Phenotyping definitions are essential in cohort identification when conducting clinical research, but they become an obstacle when they are not readily available. Developing new definitions manually requires expert involvement that is labor-intensive, time-consuming, and unscalable. Moreover, automated approaches rely mostly on electronic health records’ data that suffer from bias, confounding, and incompleteness. Limited efforts established in utilizing text-mining and data-driven approaches to automate extraction and literature-based knowledge discovery of phenotyping definitions and to support their scalability. In this dissertation, we proposed a text-mining pipeline combining rule-based and machine-learning methods to automate retrieval, classification, and extraction of phenotyping definitions’ information from literature. To achieve this, we first developed an annotation guideline with ten dimensions to annotate sentences with evidence of phenotyping definitions' modalities, such as phenotypes and laboratories. Two annotators manually annotated a corpus of sentences (n=3,971) extracted from full-text observational studies’ methods sections (n=86). Percent and Kappa statistics showed high inter-annotator agreement on sentence-level annotations. Second, we constructed two validated text classifiers using our annotated corpora: abstract-level and full-text sentence-level. We applied the abstract-level classifier on a large-scale biomedical literature of over 20 million abstracts published between 1975 and 2018 to classify positive abstracts (n=459,406). After retrieving their full-texts (n=120,868), we extracted sentences from their methods sections and used the full-text sentence-level classifier to extract positive sentences (n=2,745,416). Third, we performed a literature-based discovery utilizing the positively classified sentences. Lexica-based methods were used to recognize medical concepts in these sentences (n=19,423). Co-occurrence and association methods were used to identify and rank phenotype candidates that are associated with a phenotype of interest. We derived 12,616,465 associations from our large-scale corpus. Our literature-based associations and large-scale corpus contribute in building new data-driven phenotyping definitions and expanding existing definitions with minimal expert involvement.

Blockchain is an interesting technology, with different projects developing every day since it first gained its light back in 2008. More and more research finds blockchain useful in several different sectors. One of the sectors being healthcare, specifically for electronic health records (EHR). EHR contains highly sensitive data which is critical to protect and, just in the year 2019, 41,232,527 records were deemed stolen. Blockchain can provide several benefits when it comes to EHR, such as increased security, availability, and privacy, however, it needs to be done correctly. Due to blockchain being a rather novel technology, there is room for improvement when it comes to integrating blockchain with EHR. In this thesis a framework for EHR in the healthcare sector is proposed, using Ethereum based smart contracts together with decentralized off-chain storage using InterPlanetary File System (IPFS) and strong symmetric encryption. The framework secures the records and provides a scalable solution. Furthermore, a discussion and evaluation regarding several security aspects that the framework excels on as well as what the framework could improve on.