Improving Fraud and Abuse Detection in General Physician Claims: A Data Mining Study

Tribulations and future opportunities for artificial intelligence in precision medicine

Upon a diagnosis, the clinical team faces two main questions: what treatment, and at what dose? Clinical trials' results provide the basis for guidance and support for official protocols that clinicians use to base their decisions. However, individuals do not consistently demonstrate the reported response from relevant clinical trials. The decision complexity increases with combination treatments where drugs administered together can interact with each other, which is often the case. Additionally, the individual's response to the treatment varies with the changes in their condition. In practice, the drug and the dose selection depend significantly on the medical protocol and the medical team's experience. As such, the results are inherently varied and often suboptimal. Big data and Artificial Intelligence (AI) approaches have emerged as excellent decision-making tools, but multiple challenges limit their application. AI is a rapidly evolving and dynamic field with the potential to revolutionize various aspects of human life. AI has become increasingly crucial in drug discovery and development. AI enhances decision-making across different disciplines, such as medicinal chemistry, molecular and cell biology, pharmacology, pathology, and clinical practice. In addition to these, AI contributes to patient population selection and stratification. The need for AI in healthcare is evident as it aids in enhancing data accuracy and ensuring the quality care necessary for effective patient treatment. AI is pivotal in improving success rates in clinical practice. The increasing significance of AI in drug discovery, development, and clinical trials is underscored by many scientific publications. Despite the numerous advantages of AI, such as enhancing and advancing Precision Medicine (PM) and remote patient monitoring, unlocking its full potential in healthcare requires addressing fundamental concerns. These concerns include data quality, the lack of well-annotated large datasets, data privacy and safety issues, biases in AI algorithms, legal and ethical challenges, and obstacles related to cost and implementation. Nevertheless, integrating AI in clinical medicine will improve diagnostic accuracy and treatment outcomes, contribute to more efficient healthcare delivery, reduce costs, and facilitate better patient experiences, making healthcare more sustainable. This article reviews AI applications in drug development and clinical practice, making healthcare more sustainable, and highlights concerns and limitations in applying AI.

The Experiences of Strategic Purchasing of Healthcare in Nine Middle-Income Countries: A Systematic Qualitative Review

BACKGROUND

Efforts to move towards universal health coverage (UHC) aim to rebalance health financing in ways that increase efficiency, equity, and quality. Resource constraints require a shift from passive to strategic purchasing (SP). In this paper, we report on the experiences of SP in public sector health insurance schemes in nine middle-income countries to understand what extent SP has been established, the challenges and facilitators, and how it is helping countries achieve their UHC goals.

METHODS

We conducted a systematic search to identify papers on SP. Nine countries were selected for case study analysis. We extracted data from 129 articles. We used a common framework to compare the purchasing arrangements and key features in the different schemes. The evidence was synthesised qualitatively.

RESULTS

Five countries had health technology assessment (HTA) units to research what services to buy. Most schemes had reimbursement mechanisms that enabled some degree of cost control. However, we found evidenced-based changes to the reimbursement mechanisms only in Thailand and China. All countries have some form of mechanism for accreditation of health facilities, although there was considerable variation in what is done. All countries had some strategy for monitoring claims, but they vary in complexity and the extent of implementation; three countries have implemented e-claim processing enabling a greater level of monitoring. Only four countries had independent governance structures to provide oversight. We found delayed reimbursement (six countries), failure to provide services in the benefits package (four countries), and high out-of-pocket (OOP) payments in all countries except Thailand and Indonesia, suggesting the schemes were failing their members.

CONCLUSION

We recommend investment in purchaser and research capacity and a focus on strong governance, including regular engagement between the purchaser, provider and citizens, to build trusting relationships to leverage the potential of SP more fully, and expand financial protection and progress towards UHC.

Understanding conflicts of interest in rational drug prescription in a developing country: A stakeholder analysis, healthcare guidelines and ethical public health issues

Background

Rational drug prescription (RDP) is one of the main components of the healthcare systems. Irrational prescribing can bring about numerous negative consequences for the patients and governmental agencies. This study aims to analyze the involvement of stakeholders in rational drug prescribing, their position (opponent or proponent), and the rationale behind it.

Methods

This was a qualitative study conducted in 2019. Semi-structured face-to-face interviews were conducted with 40 stakeholders. Purposive and snowball sampling techniques with maximum heterogeneity were adopted to select the interviewees. Data was analyzed by MAXQDA software using thematic approach.

Results

Iranian Food and Drug Administration employs the highest authority on the rational prescribing policy. Although the Ministry of Health and Medical Education, the Social Security Organization as one of the main health insurance organizations, pharmaceutical companies, and the Medical Council of the Islamic Republic of Iran, are among agencies that have great authority to improve rational prescribing, they fail to act professionally as they have conflicting interests. Remarkably, the Iran Food and Drug Administration, insurance organizations, family physicians, and patients, highly support the rational prescribing policy while the pharmaceutical companies display the least support for it.

Conclusions

To make the prescription and using drugs more rational, policy makers should focus on different sources of conflicts of interest that different actors have. They should devise legal, behavior and financial policies accordingly to lessen or at least neutralize these conflicting interests, otherwise achieving RDP would be impossible in short and long terms.

Why Not Blow the Whistle on Health Care Insurance Fraud? Evidence from Jiangsu Province, China

Purpose

To identify the factors that influence whistleblowing behavior as it relates to health care insurance fraud in Jiangsu Province, China.

Methods

To construct a factor model and formulate research hypotheses using the Motivation–Opportunity–Ability framework. We designed a questionnaire containing 24 items and distributed it on-site to 2081 respondents in Jiangsu Province, China. Afterward, we applied structural equation modeling to validate the research hypotheses.

Results

Policy awareness negatively contributes to whistleblowing behavior, risk perception does not reduce the incentive to blow the whistle, and an inability to recognize fraud is another critical barrier to converting whistleblowing intentions into behavior.

Conclusion

Practices that are likely to promote citizen whistleblowing on insurance fraud may focus on the constraints identified by the comprehensive Motivation–Opportunity–Ability framework.

How to detect healthcare fraud? "A systematic review"

OBJECTIVE

To identify the method used in detecting fraud cases.

METHODS

Articles searching by using topic-appropriate keywords and incorporated into search engines (data-based) journals Pubmed/Medline, Cochrane, Wiley, ScienceDirect, and secondary data-based Google scholar. Then data extraction is done based on inclusion criteria. The selected articles have the aim of investigating/detecting cases of fraud that have occurred in the health sector or other related sectors that support the study.

RESULTS

The findings of the nine reviewed articles have suggested that most of the fraud perpetrators are performed by medical personnel (doctors) and providers. Many types of fraud occur such as insurance claims or medical actions that are completely unadministered nor following the procedure and duplicating claims. The methods that appropriate to be used in detecting fraud are secondary data tracking, information, and technology specialist provision.

CONCLUSION

Secondary data tracking is the most widely used method in fraud detection. Fraud perpetrators are ones who dominated by medical circles with fictitious claim cases. Perpetrators tend not to act themselves but in organizations with network.

Healthcare Fraud Data Mining Methods: A Look Back and Look Ahead

Healthcare fraud is an expensive, white-collar crime in the United States, and it is not a victimless crime. Costs associated with fraud are passed on to the population in the form of increased premiums or serious harm to beneficiaries. There is an intense need for digital healthcare fraud detection systems to evolve in combating this societal threat. Due to the complex, heterogenic data systems and varied health models across the US, implementing digital advancements in healthcare is difficult. The end goal of healthcare fraud detection is to provide leads to the investigators that can then be inspected more closely with the possibility of recoupments, recoveries, or referrals to the appropriate authorities or agencies. In this article, healthcare fraud detection systems and methods found in the literature are described and summarized. A tabulated list of peer-reviewed articles in this research domain listing the main objectives, conclusions, and data characteristics is provided. The potential gaps identified in the implementation of such systems to real-world healthcare data will be discussed. The authors propose several research topics to fill these gaps for future researchers in this domain.

Surveillance in Next-Generation Personalized Healthcare: Science and Ethics of Data Analytics in Healthcare

Advances in science and technology have allowed for incredible improvements in healthcare. Additionally, the digital revolution in healthcare provides new ways of collecting and storing large volumes of patient data, referred to as big healthcare data. As a result, healthcare providers are now able to use data to gain a deeper understanding of how to treat an individual in what is referred to as personalized healthcare. Regardless, there are several ethical challenges associated with big healthcare data that affect how personalized healthcare is delivered. To highlight these issues, this article will review the role of big data in personalized healthcare while also discussing the ethical challenges associated with it. The article will also discuss public health surveillance, its implications, and the challenges associated with collecting participants' information. The article will proceed by highlighting next generation technologies, including robotics and 3D printing. The article will conclude by providing recommendations on how patient privacy can be protected in next-generation personalized healthcare.

Critical Analysis of Corruption in Iran's Health Care System and Its Control Strategies

Context: according to the corruption perceptions index (CPI) 2018, Iran ranked 148 among 183 countries. This position shows the crucial importance of considering corruption and its negative effect on Iran and its health care system. In this review, we aimed to shed the light on corrupt practices in Iran’s health care system and recommend some practical strategies to combat them. Evidence Acquisition: This is a narrative review based on Vian's conceptual model of corruption in the health sector to evaluate and analyze corruption in Iran's health system. Review of the literature and documents without any time limitation were conducted in several databases including PubMed, Scopus, Web of Science, Google Scholar, and Farsi sources including Iran Medex, scientific information database )SID(, and Magiran, and also the official websites of the Ministry of Health and news agencies. Results: Unfortunately, to the best of our review, there is less published evidence about the extent and types of corruption in Iran's health system. Based on Vian’s model, reviewed literature revealed that Iran's health system is prone to corruption. This system is monopolistic and self-authorized, low transparent and accountable, and required law enforcement in many areas. Evidence to clarify the situation of citizen voice was not found. Conclusions: Based on this study, evidence shows corruption in financing, service provision, and resource generation of Iran's health system. It could affect not only performance of this system but also its responsiveness and effectiveness. To combat, Iran should apply multiple strategies such as; improving good governance, strengthening legal system over the health system, reducing monopoly and discretion stepwise and manageable, enhancing community participation, and finally updating ethics codes in the health system.

Fourteen years of manifestations and factors of health insurance fraud, 2006-2020: a scoping review

BACKGROUND

Healthcare fraud entails great financial and human losses; however, there is no consensus regarding its definition, nor is there an inventory of its manifestations and factors. The objective is to identify the definition, manifestations and factors that influence health insurance fraud (HIF).

METHODS

A scoping review on health insurance fraud published between 2006 and 2020 was conducted in ACM, EconPapers, PubMed, ScienceDirect, Scopus, Springer and WoS.

RESULTS

Sixty-seven studies were included, from which we identified 6 definitions, 22 manifestations (13 by the medical provider, 7 by the beneficiary and, 2 by the insurance company) and 47 factors (6 macroenvironmental, 15 mesoenvironmental, 20 microenvironmental, and 6 combined) associated with health insurance fraud. We recognized the elements of fraud and its dependence on the legal framework and health coverage. From this analysis, we propose the following definition: "Health insurance fraud is an act of deception or intentional misrepresentation to obtain illegal benefits concerning the coverage provided by a health insurance company". Among the most relevant manifestations perpetuated by the provider are phantom billing, falsification of documents, and overutilization of services; the subscribers are identity fraud, misrepresentation of coverage and alteration of documents; and those perpetrated by the insurance company are false declarations of benefits and falsification of reimbursements. Of the 47 factors, 25 showed an experimental influence, including three in the macroenvironment: culture, regulations, and geography; five in the mesoenvironment: characteristics of provider, management policy, reputation, professional role and auditing; 12 in the microenvironment: sex, race, condition of insurance, language, treatments, chronic disease, future risk of disease, medications, morale, inequity, coinsurance, and the decisions of the claims-adjusters; and five combined factors: the relationships between beneficiary-provider, provider-insurance company, beneficiary-insurance company, managers and guānxi.

CONCLUSIONS

The multifactorial nature of HIF and the characteristics of its manifestations depend on its definition; Identifying the influence of the factors will support subsequent attempts to combat HIF.

Precision Medicine, AI, and the Future of Personalized Health Care

The convergence of artificial intelligence (AI) and precision medicine promises to revolutionize health care. Precision medicine methods identify phenotypes of patients with less‐common responses to treatment or unique healthcare needs. AI leverages sophisticated computation and inference to generate insights, enables the system to reason and learn, and empowers clinician decision making through augmented intelligence. Recent literature suggests that translational research exploring this convergence will help solve the most difficult challenges facing precision medicine, especially those in which nongenomic and genomic determinants, combined with information from patient symptoms, clinical history, and lifestyles, will facilitate personalized diagnosis and prognostication.

Combating Health Care Fraud and Abuse: Conceptualization and Prototyping Study of a Blockchain Antifraud Framework

BACKGROUND

An estimated US $2.6 billion loss is attributed to health care fraud and abuse. With traditional health care claims verification and reimbursement, the health care provider submits a claim after rendering services to a patient, which is then verified and reimbursed by the payer. However, this process leaves out a critical stakeholder: the patient for whom the services are actually rendered. This lack of patient participation introduces a risk of fraud and abuse. Blockchain technology enables secure data management with transparency, which could mitigate this risk of health care fraud and abuse.

OBJECTIVE

The aim of this study is to develop a framework using blockchain to record claims data and transactions in an immutable format and to enable the patient to act as a validating node to help detect and prevent health care fraud and abuse.

METHODS

We developed a health care fraud and abuse blockchain technical framework and prototype using key blockchain tools and application layers including consensus algorithms, smart contracts, tokens, and governance based on digital identity on the Ethereum platform (Ethereum Foundation).

RESULTS

Our technical framework maps to the claims adjudication process and focuses on Medicare claims, with the US Centers for Medicare and Medicaid Services (CMS) as the central authority. A prototype of the framework system was developed using the blockchain platform Ethereum (Ethereum Foundation), with its design features, workflow, smart contract functions, system architecture, and software implementation outlined. The software stack used to build the system consisted of a front-end user interface framework, a back-end processing server, and a blockchain network. React was used for the user interface framework, and NodeJS and an Express server were used for the back-end processing server; Solidity was the smart contract language used to interact with a local Ethereum blockchain network.

CONCLUSIONS

The proposed framework and the initial prototype have the potential to improve the health care claims process by using blockchain technology for secure data storage and consensus mechanisms, which make the claims adjudication process more patient-centric for the purposes of identifying and preventing health care fraud and abuse. Future work will focus on the use of synthetic or historic CMS claims data to assess the real-world viability of the framework.

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.

Hypothesis-Free Search for Connections between Birth Month and Disease Prevalence in Large, Geographically Varied Cohorts

We have sought to replicate and extend the Season-wide Association Study (SeaWAS) of Boland, et al.1 in identifying birth month-disease associations from electronic health records (EHRs). We used methodology similar to that implemented by Boland on three geographically distinct cohorts, for a total of 11.8 million individuals derived from multiple data sources. We were able to identify eleven out of sixteen literature-supported birth month associations as compared to seven of sixteen for SeaWAS. Of the nine novel cardiovascular birth month associations discovered by SeaWAS, we were able to replicate four. None of the novel non-cardiovascular associations discovered by SeaWAS emerged as significant relations in our study. We identified thirty birth month disease associations not previously reported; of those, only six associations were validated in more than one cohort. These results suggest that differences in cohort composition and location can cause consequential variation in results of hypothesis-free searches.

Reducing medical claims cost to Ghana's National Health Insurance scheme: a cross-sectional comparative assessment of the paper- and electronic-based claims reviews

BACKGROUND

A robust medical claims review system is crucial for addressing fraud and abuse and ensuring financial viability of health insurance organisations. This paper assesses claims adjustment rate of the paper- and electronic-based claims reviews of the National Health Insurance Scheme (NHIS) in Ghana.

METHODS

The study was a cross-sectional comparative assessment of paper- and electronic-based claims reviews of the NHIS. Medical claims of subscribers for the year, 2014 were requested from the claims directorate and analysed. Proportions of claims adjusted by the paper- and electronic-based claims reviews were determined for each type of healthcare facility. Bivariate analyses were also conducted to test for differences in claims adjustments between healthcare facility types, and between the two claims reviews.

RESULTS

The electronic-based review made overall adjustment of 17.0% from GHS10.09 million (USD2.64 m) claims cost whilst the paper-based review adjusted 4.9% from a total of GHS57.50 million (USD15.09 m) claims cost received, and the difference was significant (p < 0.001). However, there were no significant differences in claims cost adjustment rate between healthcare facility types by the electronic-based (p = 0.0656) and by the paper-based reviews (p = 0.6484).

CONCLUSIONS

The electronic-based review adjusted significantly higher claims cost than the paper-based claims review. Scaling up the electronic-based review to cover claims from all accredited care providers could reduce spurious claims cost to the scheme and ensure long term financial sustainability.