Medicare Fraud Research Articles

The effects of class rarity on the evaluation of supervised healthcare fraud detection models

The United States healthcare system produces an enormous volume of data with a vast number of financial transactions generated by physicians administering healthcare services. This makes healthcare fraud difficult to detect, especially when there are considerably less fraudulent transactions (documented and readily available) than non-fraudulent. The ability to successfully detect fraudulent activities in healthcare, given such discrepancies, can garner up to $350 billion in recovered monetary losses. In machine learning, when one class has a substantially larger number of instances (majority) compared to the other (minority), this is known as class imbalance. In this paper, we focus specifically on Medicare, utilizing three ‘Big Data’ Medicare claims datasets with real-world fraudulent physicians. We create a training and test dataset for all three Medicare parts, both separately and combined, to assess fraud detection performance. To emulate class rarity, which indicates particularly severe levels of class imbalance, we generate additional datasets, by removing fraud instances, to determine the effects of rarity on fraud detection performance. Before a machine learning model can be distributed for real-world use, a performance evaluation is necessary to determine the best configuration (e.g. learner, class sampling ratio) and whether the associated error rates are low, indicating good detection rates. With our research, we demonstrate the effects of severe class imbalance and rarity using a training and testing (Train_Test) evaluation method via a hold-out set, and provide our recommendations based on the supervised machine learning results. Additionally, we repeat the same experiments using Cross-Validation, and determine it is a viable substitute for Medicare fraud detection. For machine learning with the severe class imbalance datasets, we found that, as expected, fraud detection performance decreased as the fraudulent instances became more rare. We apply Random Undersampling to both Train_Test and Cross-Validation, for all original and generated datasets, in order to assess potential improvements in fraud detection by reducing the adverse effects of class imbalance and rarity. Overall, our results indicate that the Train_Test method significantly outperforms Cross-Validation.

Approaches for identifying U.S. medicare fraud in provider claims data.

Quality and affordable healthcare is an important aspect in people's lives, particularly as they age. The rising elderly population in the United States (U.S.), with increasing number of chronic diseases, implies continuing healthcare later in life and the need for programs, such as U.S. Medicare, to help with associated medical expenses. Unfortunately, due to healthcare fraud, these programs are being adversely affected draining resources and reducing quality and accessibility of necessary healthcare services. The detection of fraud is critical in being able to identify and, subsequently, stop these perpetrators. The application of machine learning methods and data mining strategies can be leveraged to improve current fraud detection processes and reduce the resources needed to find and investigate possible fraudulent activities. In this paper, we employ an approach to predict a physician's expected specialty based on the type and number of procedures performed. From this approach, we generate a baseline model, comparing Logistic Regression and Multinomial Naive Bayes, in order to test and assess several new approaches to improve the detection of U.S. Medicare Part B provider fraud. Our results indicate that our proposed improvement strategies (specialty grouping, class removal, and class isolation), applied to different medical specialties, have mixed results over the selected Logistic Regression baseline model's fraud detection performance. Through our work, we demonstrate that improvements to current detection methods can be effective in identifying potential fraud.

Big Data fraud detection using multiple medicare data sources

In the United States, advances in technology and medical sciences continue to improve the general well-being of the population. With this continued progress, programs such as Medicare are needed to help manage the high costs associated with quality healthcare. Unfortunately, there are individuals who commit fraud for nefarious reasons and personal gain, limiting Medicare’s ability to effectively provide for the healthcare needs of the elderly and other qualifying people. To minimize fraudulent activities, the Centers for Medicare and Medicaid Services (CMS) released a number of “Big Data” datasets for different parts of the Medicare program. In this paper, we focus on the detection of Medicare fraud using the following CMS datasets: (1) Medicare Provider Utilization and Payment Data: Physician and Other Supplier (Part B), (2) Medicare Provider Utilization and Payment Data: Part D Prescriber (Part D), and (3) Medicare Provider Utilization and Payment Data: Referring Durable Medical Equipment, Prosthetics, Orthotics and Supplies (DMEPOS). Additionally, we create a fourth dataset which is a combination of the three primary datasets. We discuss data processing for all four datasets and the mapping of real-world provider fraud labels using the List of Excluded Individuals and Entities (LEIE) from the Office of the Inspector General. Our exploratory analysis on Medicare fraud detection involves building and assessing three learners on each dataset. Based on the Area under the Receiver Operating Characteristic (ROC) Curve performance metric, our results show that the Combined dataset with the Logistic Regression (LR) learner yielded the best overall score at 0.816, closely followed by the Part B dataset with LR at 0.805. Overall, the Combined and Part B datasets produced the best fraud detection performance with no statistical difference between these datasets, over all the learners. Therefore, based on our results and the assumption that there is no way to know within which part of Medicare a physician will commit fraud, we suggest using the Combined dataset for detecting fraudulent behavior when a physician has submitted payments through any or all Medicare parts evaluated in our study.

The effects of varying class distribution on learner behavior for medicare fraud detection with imbalanced big data.

Healthcare in the United States is a critical aspect of most people's lives, particularly for the aging demographic. This rising elderly population continues to demand more cost-effective healthcare programs. Medicare is a vital program serving the needs of the elderly in the United States. The growing number of Medicare beneficiaries, along with the enormous volume of money in the healthcare industry, increases the appeal for, and risk of, fraud. In this paper, we focus on the detection of Medicare Part B provider fraud which involves fraudulent activities, such as patient abuse or neglect and billing for services not rendered, perpetrated by providers and other entities who have been excluded from participating in Federal healthcare programs. We discuss Part B data processing and describe a unique process for mapping fraud labels with known fraudulent providers. The labeled big dataset is highly imbalanced with a very limited number of fraud instances. In order to combat this class imbalance, we generate seven class distributions and assess the behavior and fraud detection performance of six different machine learning methods. Our results show that RF100 using a 90:10 class distribution is the best learner with a 0.87302 AUC. Moreover, learner behavior with the 50:50 balanced class distribution is similar to more imbalanced distributions which keep more of the original data. Based on the performance and significance testing results, we posit that retaining more of the majority class information leads to better Medicare Part B fraud detection performance over the balanced datasets across the majority of learners.

Avoiding and Managing Medicare Fraud and Abuse Investigations of Mohs Surgery

Avoiding and Managing Medicare Fraud and Abuse Investigations of Mohs Surgery

Strategies for Fighting Medicare Fraud.

In 2014, the United States spent approximately $3 trillion on health care. Medicare accounted for $554 billion of these costs, and approximately $60 billion were squandered because of incorrect billing methods, abuse, and fraud. Types of fraud included kickbacks, upcoding, and organized fraudulent crimes. To reduce the financial burden associated with these activities, the United States has created various fraud prevention programs. The purpose of this study was to identify methods of Medicare fraud, examine the various programs implemented by the US government to combat fraud and abuse, and determine the effectiveness of these programs. Although fraud prevention strategies have proven to be effective, the furtherance of these strategies is imperative to continually combat rising health care expenditures in the United States. Benefits of increased fraud prevention and detection are discussed in detail.

Medicare and the affordable care act: Fraud control efforts and results

ABSTRACTMedicare fraud and abuse costs are estimated at 3–10% of overall Medicare spending, which is expected to expand considerably until 2024 and as such the amount of fraud dollars would be expected to increase proportionally. The purpose of this research was to determine how recent reforms, especially the Patient Protection and Accountable Care Act, may affect Medicare fraud and abuse and to uncover the best strategies to combat Medicare fraud. Methodology: the methodology for this qualitative study was a literature review. Seven electronic databases and five websites were utilized. Fifty-six sources were referenced for this literature review. The breadth of fraud and abuse within Medicare as well as recent reforms to fight fraud including legislative reforms, delivery system reforms, and other reforms including the formation of HEAT fraud fighting taskforces are examined. Legislative reforms are noted to be incompatible with the ACA’s new P4P delivery and reimbursement reforms. Medicare fraud requires comprehensive detection and prevention measures. Benefits of implementing this dual method of fraud fighting are discussed.

Home Healthcare and the Medicare Fraud Strike Force.

Home Healthcare and the Medicare Fraud Strike Force.

Home Healthcare and the Medicare Fraud Strike Force.

Modern federal healthcare fraud investigations use big data to find outliers among providers who are then targeted for enforcement actions. This approach is being used to pursue an outsized number of criminal cases against home healthcare agencies, resulting in decades-long prison sentences and tens of millions in fines. But it is remarkably transparent, giving home healthcare providers ample opportunity to stay out of harm's way. The government has provided the statistical characteristics by which it searches for fraud among home healthcare agencies, along with the benchmarks it uses to determine who is an outlier. And enforcement actions against home healthcare agencies have consistently targeted the same conduct: payments to payment recruiters and physicians in return for referring patients who often do not need the services billed. This article provides practical advice on how home healthcare agencies can gauge and limit their own legal exposure by monitoring their statistics against the government's benchmarks and by instituting basic controls to prevent targeted conduct.

Ohio Companies, Execs Pay $19.5 Million to Resolve Medicare Fraud Allegations

Ohio Companies, Execs Pay $19.5 Million to Resolve Medicare Fraud Allegations

Genesis to Pay $53.6 Million to Settle Medicare Fraud Claims Against Companies It Acquired

Genesis to Pay $53.6 Million to Settle Medicare Fraud Claims Against Companies It Acquired

Examining the network components of a Medicare fraud scheme: the Mirzoyan-Terdjanian organization

White-collar crime researchers have noted the stagnating nature of white-collar crime research and data, calling for use of a wider-range of methodological procedures to uncover the empirical reality of white-collar crime and offending in the U.S. Using a collection of archival data, the present study examines the structural components of the Mirzoyan-Terdjanian organization, a transnational organized crime network that defrauded the United States Medicare system out of more than $100 million. Policy implications that can be derived from the use of social networking techniques will be discussed.

Improving Orthopedic Resident Knowledge of Documentation, Coding, and Medicare Fraud

Most residency programs still lack formal education and training on the basic clinical documentation and coding principles. Today's physicians are continuously being held to increasing standards for correct coding and documentation, yet little has changed in the residency training curricula to keep pace with these increasing standards. Although there are many barriers to implementing these topics formally, the main concern has been the lack of time and resources. Thus, simple models may have the best chance for success at widespread implementation. The first goal of the study was to assess a group of orthopedic residents' fund of knowledge regarding basic clinical documentation guidelines, coding principles, and their ability to appropriately identify cases of Medicare fraud. The second goal was to analyze a single, high-yield educational session's effect on overall resident knowledge acquisition and awareness of these concepts. Orthopedic residents belonging to 1 of 2 separate residency programs voluntarily and anonymously participated. All were asked to complete a baseline assessment examination, followed by attending a 45-minute lecture given by the same orthopedic faculty member who remained blinded to the test questions. Each resident then completed a postsession examination. Each resident was also asked to self-rate his or her documentation and coding level of comfort on a Likert scale (1-5). Statistical significance was set at p < 0.05. A total of 32 orthopedic residents were participated. Increasing postgraduate year-level of training correlated with higher Likert-scale ratings for self-perceived comfort levels with documentation and coding. However, the baseline examination scores were no different between senior and junior residents (p > 0.20). The high-yield teaching session significantly improved the average total examination scores at both sites (p < 0.01), with overall improvement being similar between the 2 groups (p > 0.10). The current healthcare environment necessitates better physician awareness regarding clinical documentation guidelines and coding principles. Very few adjustments to incorporate these teachings have been made to most residency training curricula, and the lack of time and resources remains the concern of many surgical programs. We have demonstrated that orthopedic resident knowledge in these important areas drastically improves after a single, high-yield 45-minute teaching session.

Legislators: Investigate Medicare Fraud Before Paying Doctors

Legislators: Investigate Medicare Fraud Before Paying Doctors

When Biosafety Meets the Federal False Claims Act

A recent lawsuit potentially paves the way for whistleblowers to apply the federal False Claims Act and its vast civil remedies against research institutions for allegedly failing to adhere to federal standards for the performance of biological research in a research setting. Despite the absence of any injury alleged, if the plaintiffs prevail in a lawsuit filed on behalf of the United States, they may recover a portion of the total recovery due to the government under provisions that incentivize whistleblowers to bring such claims to combat fraud, waste, and abuse against government programs. Typically applied against health care entities for Medicare fraud and against defense contractors with procurement contracts, the application of the False Claims Act and its whistleblower provisions have become more prevalent in federally funded research over the past 2 decades. Here, 2 former biosafety officers of a major research institution claim that their former employer and others violated the False Claims Act when routinely failing to comply with the National Institutes of Health guidelines and continued to apply for federal grants with knowledge that it was not compliant. In a field that has historically relied on internal oversight, this case marks yet another potential legal cause of action that may arise.

Medicare at 50: Reflections From Former CMS Administrator Donald M. Berwick.

On July 30, 1965, Pres ident Lyndon B. Johnson signed into law the landmark bill creating Medicare and Medicaid. In honor of the 50th anniversary of Medicare and Medicaid, Donald M. Berwick, MD, who served as administrator of the Centers for Medicare & Medicaid Services (CMS) from 2010 to 2011, provided insights into Medicare, the federal health care program for elderly Americans. Dr Berwick serves on JAMA’s editorial board and is president emeritus of and a senior fellow at the Institute for Healthcare Improvement (IHI) in Cambridge, Massachusetts. Dr Berwick, a pediatrician, is widely knownasanexpertonhealthcarepolicyand health carequality issues.Hehasheldmany notable positions in health care, including serving as a faculty member at Harvard Medical School andHarvard School of PublicHealth,vicechairof theUSPreventiveServicesTaskForce, thefirst independentmember of the American Hospital Association’s board of trustees, chair of the National Advisory Council of theAgency forHealthcare Research and Quality, and a member of PresidentClinton’sAdvisoryCommissionon Consumer Protection and Quality in the Health Care Industry. He has written more than 160 scientific articles and 5 books, includingEscapeFire:Designs for theFutureof Health Care. In this interview, Dr Berwick discusses, amongother things, the shift topayingdoctors participating in Medicare based on the qualityof careprovided topatients, the role of accountable careorganizations (ACOs) in improvingqualityofcareandreducingcosts, and the progress that has beenmade in reducing Medicare fraud. The following is an edited transcriptofhis interviewwith JAMA.

Does Medical School Training Relate to Practice? Evidence from Big Data.

On April 2nd, 2014, the Department of Health and Human Services (HHS) announced a historic policy in its effort to increase the transparency in the American healthcare system. The Center for Medicare and Medicaid Service (CMS) would publicly release a dataset containing information about the types of Medicare services, requested charges, and payments issued by providers across the country. In its release, HHS stated that the data would shed light on “Medicare fraud, waste, and abuse.” While this is most certainly true, we believe that it can provide so much more. Beyond the purely financial aspects of procedure charges and payments, the procedures themselves may provide us with additional information, not only about the Medicare population, but also about the physicians themselves. The procedures a physician performs are for the most part not novel, but rather recommended, observed, and studied. However, whether a physician decides on advocating a procedure is somewhat discretionary. Some patients require a clear course of action, while others may benefit from a variety of options. This article poses the following question: How does a physician's past experience in medical school shape his or her practicing decisions? This article aims to open the analysis into how data, such as the CMS Medicare release, can help further our understanding of knowledge transfer and how experiences during education can shape a physician's decision's over the course of his or her career. This work begins with an evaluation into similarities between medical school charges, procedures, and payments. It then details how schools' procedure choices may link them in other, more interesting ways. Finally, the article includes a geographic analysis of how medical school procedure payments and charges are distributed nationally, highlighting potential deviations.

Establishing the need and identifying goals for a curriculum in medical business ethics: a survey of students and residents at two medical centers in Missouri.

BackgroundIn recent years, issues in medical business ethics (MBE), such as conflicts of interest (COI), Medicare fraud and abuse, and the structure and functioning of reimbursement systems, have received significant attention from the media and professional associations in the United States. As a result of highly publicized instances of financial interests altering physician decision-making, major professional organizations and government bodies have produced reports and guidelines to encourage self-regulation and impose rules to limit physician relationships with for-profit entities. Nevertheless, no published curricula exist in the area of MBE. This study aimed to establish a baseline level of knowledge and the educational goals medical students and residents prioritize in the area of MBE.Methods732 medical students and 380 residents at two academic medical centers in the state of Missouri, USA, completed a brief survey indicating their awareness of major MBE guidance documents, knowledge of key MBE research, beliefs about the goals of an education in MBE, and the areas of MBE they were most interested in learning more about.ResultsMedical students and residents had little awareness of recent and major reports on MBE topics, and had minimal knowledge of basic MBE facts. Residents scored statistically better than medical students in both of these areas. Medical students and residents were in close agreement regarding the goals of an MBE curriculum. Both groups showed significant interest in learning more about MBE topics with an emphasis on background topics such as “the business aspects of medicine” and “health care delivery systems”.ConclusionsThe content of major reports by professional associations and expert bodies has not trickled down to medical students and residents, yet both groups are interested in learning more about MBE topics. Our survey suggests potentially beneficial ways to frame and embed MBE topics into the larger framework of medical education.

Medicare fraud in the United States: can it ever be stopped?

The majority of the United States health care fraud has been focused on the major public program, Medicare. The yearly financial loss from Medicare fraud has been estimated at about $54 billion. The purpose of this research study was to explore the current state of Medicare fraud in the United States, identify current policies and laws that foster Medicare fraud, and determine the financial impact of Medicare fraud. The methodology for this study was a literature review. Research was conducted using a scholarly online database search and government Web sites. The number of individuals charged with criminal fraud increased from 797 cases in fiscal year 2008 to 1430 cases in fiscal year 2011-an increase of more than 75%. According to 2010 data, of the 7848 subjects investigated for criminal fraud, 25% were medical facilities, and 16% were medical equipment suppliers. In 2009 and 2010, the Health Care Fraud and Abuse Control Program recovered approximately $25.2 million of taxpayers' money. Educating providers about the policies and laws designed to prevent fraud would help them to become partners. Many new programs and partnerships with government agencies have also been developed to combat Medicare fraud. Medicare fraud has been a persistent crime, and laws and policies alone have not been enough to control the problem. With investments in governmental partnerships and new systems, the United States can reduce Medicare fraud but probably will not stop it altogether.

The Sunshine Act: Even SPF 100 Won't Help

They called it Sunshine because legislators wanted to shed light on doctors receiving money from drug and device manufacturers. As I reported in Aesthetic Society News 3 years ago,1 the dawn of the Physicians Payment and Sunshine Act was Senators Grassley and Kohl introducing Senate Bill 301 in 2009. SB 301 failed to spark but was rekindled in the Affordable Care Act,2 which became law in 2010. Its catchy title was lost in translation. On February 8, 2013, the Centers for Medicare & Medicaid Services (CMS) published the final rule and renamed it the National Physician Payment Transparency Program: OPEN PAYMENTS. Everyone is still calling it the Sunshine Act, and so am I. So what is the sun shining on? Surprisingly, the Sunshine Act isn't focused on illegal kickbacks but on legal payments to doctors by industry that didn't necessarily rise to the level of Medicare fraud. Nevertheless, the genesis of the Sunshine Act arose from anti-kickback and False Claims Act prosecutions of hospitals, pharmacies, and manufacturers. For instance: