Healthcare is an integral component in peoples lives, especially for the rising elderly population, and must be affordable. The United States Medicare program is vital in serving the needs of the elderly. The growing number of people enrolled in the Medicare program, along with the enormous volume of money involved, increases the appeal for, and risk of, fraudulent activities. For many real-world applications, including Medicare fraud, the interesting observations tend to be less frequent than the normative observations. This difference between the normal observations and those observations of interest can create highly imbalanced datasets. The problem of class imbalance, to include the classification of rare cases indicating extreme class imbalance, is an important and well-studied area in machine learning. The effects of class imbalance with big data in the real-world Medicare fraud application domain, however, is limited. In particular, the impact of detecting fraud in Medicare claims is critical in lessening the financial and personal impacts of these transgressions. Fortunately, the healthcare domain is one such area where the successful detection of fraud can garner meaningful positive results. The application of machine learning techniques, plus methods to mitigate the adverse effects of class imbalance and rarity, can be used to detect fraud and lessen the impacts for all Medicare beneficiaries. This dissertation presents the application of machine learning approaches to detect Medicare provider claims fraud in the United States. We discuss novel techniques to process three big Medicare datasets and create a new, combined dataset, which includes mapping fraud labels associated with known excluded providers. We investigate the ability of machine learning techniques, unsupervised and supervised, to detect Medicare claims fraud and leverage data sampling methods to lessen the impact of class imbalance and increase fraud detection performance. Additionally, we extend the study of class imbalance to assess the impacts of rare cases in big data for Medicare fraud detection. / Includes bibliography. / Dissertation (Ph.D.)--Florida Atlantic University, 2018. / FAU Electronic Theses and Dissertations Collection

Effective classification with imbalanced data is an important area of research, as high class imbalance is naturally inherent in many real-world applications, e.g. anomaly detection. Modeling such skewed data distributions is often very difficult, and non-standard methods are sometimes required to combat these negative effects. These challenges have been studied thoroughly using traditional machine learning algorithms, but very little empirical work exists in the area of deep learning with class imbalanced big data. Following an in-depth survey of deep learning methods for addressing class imbalance, we evaluate various methods for addressing imbalance on the task of detecting Medicare fraud, a big data problem characterized by extreme class imbalance. Case studies herein demonstrate the impact of class imbalance on neural networks, evaluate the efficacy of data-level and algorithm-level methods, and achieve state-of-the-art results on the given Medicare data set. Results indicate that combining under-sampling and over-sampling maximizes both performance and efficiency. / Includes bibliography. / Thesis (M.S.)--Florida Atlantic University, 2019. / FAU Electronic Theses and Dissertations Collection

Following implementation of the Patient Protection and Affordable Care Act, hospitals have seen a reduction in Medicare reimbursement for 30-day post-discharge readmissions of acute myocardial infarction patient. The purpose of this project was to develop a plan for a navigator program to improve a patient's health status post discharge and reduce readmission rates. The Johns Hopkins nursing evidence-based practice model and guidelines were used in determining the quality of obtained experimental and non-experimental studies with or without meta-analysis and popular source articles. The literature revealed the most successful programs involved providing best practices for a navigator program allowed better patient education, discharge planning, safety and quality of care, improved communication and post-discharge follow-up, and improved facility finances to achieve positive results for the patient and the hospital. Watson's caring theory was used as the theoretical framework since it incorporated the aspect of caring to create a good working nurse-patient relationship. A navigator program training module, job description, objectives, program forms, mission and goal statements, and a health care team were developed and seen as crucial to the success of the program and its evaluation process. Using navigator practices, based on evidence, formed the infrastructure and management process for the facility and health care providers, thereby increasing the quality of patient care. The resulting social change was positive, benefiting the patient, family, the organization, and the region served. With implementation, this project was anticipated to reduce 30-day readmissions and increased facility reimbursement.

acase@tulane.edu / 1 / Yongkang Zhang

Thesis (Ph. D.)--University of Notre Dame, 2004. / Thesis directed by Teresa Ghilarducci for the Department of Economics. "April 2004." Includes bibliographical references (leaves 148-153).

Thesis (M.S.) in Resource Economics and Policy--University of Maine, 2009. / Includes vita. Includes bibliographical references (leaves 62-68).

Thesis (Ph. D.)--University of Chicago, Irving B. Harris Graduate School of Public Policy Studies, August, 2001. / Includes bibliographical references. Also available on the Internet.

Background: In the current policy environment hospital readmissions are receiving considerable attention due to a provision in the Affordable Care Act (2010), that penalize hospitals through reduced payments for excess readmissions (the hospital readmissions reduction program (HRRP)). This program primarily holds hospitals accountable, although a multitude of factors not directly in control of hospitals can be contributory to readmissions. Of these, whether or not patients are discharged to an appropriate post-discharge care setting can be one contributory factor, and, this study evaluated the association between post-discharge care setting and hospital revisits. Methods: A retrospective analysis of the 2008 Medicare Current Beneficiary Survey (MCBS) was conducted. Three post-discharge care settings were evaluated: 1) routine discharge to home; 2) home with home healthcare; and 3) skilled nursing facility. Two outcomes were assessed: 1) 30-day all-cause hospital readmissions; and 2) 30-day all-cause hospital revisits (combination of inpatient admissions and emergency department visits). Analyses were carried out among patients with hospitalizations for any reason, as well as among a subgroup that were hospitalized for one of seven priority conditions identified in the HRRP. Weighted logistic regression analyses that incorporated information on the complex survey design were conducted. Results: Of the MCBS sample representing 46,048,125 Medicare beneficiaries (unweighted N=11,723), 4.9 percent (N= 2,293,629; unweighted N=670) contributed at least one index hospitalization to the analysis. Among hospitalization for any reason, 30-day all-cause hospital readmissions and revisits was 12.3 percent and 17.8 percent, respectively. The subgroup consisted of 31.8 percent of hospitalizations for any reason (N=730,174; unweighted N=216). Readmissions and revisits in the subgroup were 17.8 percent, and 24.5 percent, respectively. Post-discharge care setting was not significantly associated with either readmissions (P=0.966) or revisits (P=0.728) for hospitalizations for any reason. Findings for the subgroup were similar with no significant association between post-discharge care setting with either readmissions (P=0.850) or revisits (P=0.483). Conclusion: Absence of a difference in readmissions and revisits by post-discharge care setting suggests that the choice of discharge status might be appropriate following an inpatient admission. However, further research with larger sample sizes for conditions in the subgroup both together and separately is recommended.

Health and health care are dominant economic and political issues in the United States and many other countries. This dissertation contains two essays addressing different subjects within the field of health economics. The first essay is labor market oriented: An Economic Analysis of the Effects of Obesity on Wages. It examines the effects of overweight and obesity on the wages of men and women. The second essay, An Economic Analysis of the Impact on Health Care of Certain Medicare Provisions of the Balanced Budget Act of 1997 examines changes in the treatment of Medicare patients in light of reimbursement changes brought about by the Balanced Budget Act of 1997. This analysis contained in An Economic Analysis of Obesity on Wages improves on previous work by using a dataset that can allow health effects to be better examined. Three series of regressions are performed, where log wage income is regressed on a series of variables including categorical variables based on body mass index. In contrast to some previous research, this analysis finds that the wages of obese individuals are not depressed by excess weight. It is possible that, because of the increasing prevalence of overweight and obesity over the last 20 years, any associated stigma has dwindled. An Economic Analysis of the Impact on Health Care of the Balanced Budget Act of 1997 examines the effects of one of the provisions of the Balanced Budget Act of 1997. Specifically, the analysis examines the implementation of the Post Acute Care Transfer policy, a change to Medicare Part A, caused the length of stay for patients grouped in certain targeted diagnosis related groups (DRGs) to increase, keeping with the goal of the policy change. In analyzing the short-stay patients, the data show that patients who were grouped into the pilot DRGs and were transferred after 10/01/98 (the effective date of the policy) were not in the hospital longer than before 10/01/98, implying that hospitals might not have been exploiting a financial loophole, as thought by the Health Care Financing Administration, now the Centers for Medicare and Medicaid Services.

The Enhanced Primary Care Package aimed to improve health and quality of life through enhancing primary health care for those over 75 years, Aboriginal and Torres Strait Islanders over 55 years and those with chronic conditions and multidisciplinary needs. A multi-level approach was implemented to promote the package. West Vic Division of General Practice conducted the General Practice Education Support and Community Linkages implementation program for the package in Western Victoria and focused on health assessments for those over 75 years. This research investigated what factors affected change in rural general practitioner practice through surveying general practitioners and collecting Health Insurance Commission data prior to and following the program. Patients were also interviewed to determine acceptance of health assessments and nurse involvement. The program increased awareness, but had little effect on increasing uptake, as only 53% of general practitioners began undertaking health assessments. However the general practitioners indicated an increased frequency of health assessment prescription. Health Insurance Commission data suggested an immediate increase in the use of the assessments, however the rate fluctuated and then declined. Lack of sustained uptake of the program was not associated with remuneration, as 77% of general practitioners did not regard finance as a barrier. Respondents’ major barrier was time (40% pre-education, 73% post-education). This data reflected a rural environment where general practitioners face competing priorities, time constraints, workforce shortage and long consultation lists. A notable change did however occur from practice nurse employment as the involvement of a practice nurse generally resulted in patient satisfaction with the assessment. It was apparent that a complex multifaceted and longer-term view is needed to address factors which limit rural general practitioners’ ability to change. This needs to be addressed at the Commonwealth level and not in isolation in order to produce an integrated framework to enhance and promote, rather than demand change. / Master of Applied Science