Figure - available from: Journal of Engineering
This content is subject to copyright. Terms and conditions apply.
Linear separating hyperplanes for the nonseparable case of SVC by introducing the slack variable (ξ).
Source publication
Fraud in health insurance claims has become a significant problem whose rampant growth has deeply affected the global delivery of health services. In addition to financial losses incurred, patients who genuinely need medical care suffer because service providers are not paid on time as a result of delays in the manual vetting of their claims and ar...
Citations
... Predictive modeling has also enhanced fraud detection efforts by forecasting potential fraud scenarios and identifying high-risk areas. Earlier studies have emphasized the proactive nature of predictive modeling, which allows healthcare organizations to implement preventive measures before fraud occurs (Sowah et al., 2019). Our findings align with these studies and demonstrate that predictive modeling can improve detection rates and significantly save money. ...
Healthcare fraud poses a significant challenge, leading to substantial financial losses and compromising the quality of patient care. This study assesses the efficacy of advanced fraud detection systems, including data analytics, machine learning, predictive modeling, and natural language processing (NLP), in enhancing the detection and prevention of fraudulent activities in healthcare. By leveraging these technologies, healthcare organizations can process large volumes of complex data, adapt to evolving fraud patterns, and provide real-time monitoring. The findings indicate that data analytics effectively uncovers hidden patterns and anomalies, while machine learning and AI improve predictive accuracy by continuously learning from historical data. Predictive modeling enables proactive fraud prevention by forecasting potential fraud scenarios, and NLP extends detection capabilities to unstructured data such as clinical notes. The integration of these advanced technologies has resulted in significant financial savings and improved patient care, as demonstrated by case studies highlighting substantial reductions in fraudulent claims. The study concludes that adopting advanced fraud detection systems is essential for maintaining financial integrity and ensuring high-quality patient care in the evolving healthcare landscape.
... 11 while also considerably decreasing processing time. 25 In another instance, data from a performance-based payment programme for health centres in Zam- Table 1. Uses of machine learning in health financing and their potential risks and benefits ...
There is increasing use of machine learning for the health financing functions (revenue raising, pooling and purchasing), yet evidence lacks for its effects on the universal health coverage (UHC) objectives. This paper provides a synopsis of the use cases of machine learning and their potential benefits and risks. The assessment reveals that the various use cases of machine learning for health financing have the potential to affect all the UHC intermediate objectives – the equitable distribution of resources (both positively and negatively); efficiency (primarily positively); and transparency (both positively and negatively). There are also both positive and negative effects on all three UHC final goals, that is, utilization of health services in line with need, financial protection and quality care. When the use of machine learning facilitates or simplifies health financing tasks that are counterproductive to UHC objectives, there are various risks – for instance risk selection, cost reductions at the expense of quality care, reduced financial protection or over-surveillance. Whether the effects of using machine learning are positive or negative depends on how and for which purpose the technology is applied. Therefore, specific health financing guidance and regulations, particularly for (voluntary) health insurance, are needed. To inform the development of specific health financing guidance and regulation, we propose several key policy and research questions. To gain a better understanding of how machine learning affects health financing for UHC objectives, more systematic and rigorous research should accompany the application of machine learning.
... Medical Field High Quality [45] The study investigates the concordance of DSS and the recommendation of surgeons regarding back pain. 2019 Medical Field High Quality [47] This study uses data from National Health Insurance Scheme claims, acquired from the hospitals in Ghana, for identifying health insurance fraud and other irregularities. Genetic support vector machines (GSVMs), which are new hybridized data mining and statistical machine learning tools are used. ...
Context: The selection and use of appropriate multi-criteria decision making (MCDM) methods for solving complex problems is one of the challenging issues faced by decision makers in the search for appropriate decisions. To address these challenges, MCDM methods have effectively been used in the areas of ICT, farming, business, and trade, for example. This study explores the integration of machine learning and MCDM methods, which has been used effectively in diverse application areas. Objective: The objective of the research is to critically analyze state-of-the-art research methods used in intelligent decision support systems and to further identify their application areas, the significance of decision support systems, and the methods, approaches, frameworks, or algorithms exploited to solve complex problems. The study provides insights for early-stage researchers to design more intelligent and cost-effective solutions for solving problems in various application domains. Method: To achieve the objective, literature from the years 2015 to early 2020 was searched and considered in the study based on quality assessment criteria. The selected relevant literature was studied to respond to the research questions proposed in this study. To find answers to the research questions, pertinent literature was analyzed to identify the application domains where decision support systems are exploited, the impact and significance of the contributions, and the algorithms, methods, and techniques which are exploited in various domains to solve decision-making problems. Results: Results of the study show that decision support systems are widely used as useful decision-making tools in various application domains. The research has collectively studied machine learning, artificial intelligence, and multi-criteria decision-making models used to provide efficient solutions to complex decision-making problems. In addition, the study delivers detailed insights into the use of AI, ML and MCDM methods to the early-stage researchers to start their research in the right direction and provide them with a clear roadmap of research. Hence, the development of Intelligent Decision Support Systems (IDSS) using machine learning (ML) and multicriteria decision-making (MCDM) can assist researchers to design and develop better decision support systems. These findings can help researchers in designing more robust, efficient, and effective multicriteria-based decision models, frameworks, techniques, and integrated solutions.
... Ensemble methods combine multiple models to improve predictive accuracy, while deep learning models leverage complex neural architectures to learn intricate patterns from raw claim data automatically. These approaches have shown promise in achieving higher detection rates and reducing false positives, but they may require extensive computational resources and substantial labeled data for training [23]. ...
Medical claim insurance fraud poses a significant challenge for insurance companies and the healthcare system, leading to financial losses and reduced efficiency. In response to this issue, we present an intelligent machine- learning approach for fraud detection in medical claim insurance to enhance fraud detection accuracy and efficiency. This comprehensive study investigates the application of advanced machine learning algorithms for identifying fraudulent claims within the insurance domain. We thoroughly evaluate several candidate algorithms to select an appropriate machine learning algorithm, considering the unique characteristics of medical claim insurance data. Our chosen algorithm demonstrates superior capabilities in handling fraud detection tasks and is the foundation for our proposed intelligent approach. Our proposed approach incorporates domain knowledge and expert rules, augmenting the machine learning algorithm to address the intricacies of fraud detection within the insurance context. We introduce modifications to the algorithm, further enhancing its performance in detecting fraudulent medical claims. Through an extensive experimental setup, we evaluate the performance of our intelligent machine-learning approach. The results indicate significant accuracy, precision, recall, and F1-score improvements compared to traditional fraud detection methods. Additionally, we conduct a comparative analysis with other machine learning algorithms, affirming the superiority of our approach in this domain. The discussion section offers insights into the interpretability of the experimental findings and highlights the strengths and limitations of our approach. We conclude by emphasizing the significance of our research for the insurance industry and the potential impact on the healthcare system's efficiency and cost-effectiveness.
... Pada tanggal Januari 2022 di New York City Amerika Serikat, pihak berwenang Amerika Serikat menangkap 13 orang terpidana dengan tuduhan melakukan kecurangan pada layanan kesehatan, praktik cuci uang, dan penyuapan sebesar 100 juta USD. Dari [7]. Metode klasifikasi SVM adalah metode yang digunakan untuk mengklasifikasi data menjadi dua kelas berbeda yang pada kasus ini adalah menentukan data yang merupakan data fraud dan yang tidak [8]. ...
... Oleh karena itu untuk menyelesaikan permasalahan dimana data tidak dapat diklasifikasi secara linier, dapat digunakan konsep kernel untuk melihat relasi data point pada ruang berdimensi tinggi hanya dengan menggunakan dot product pada vektor data. Pada penelitian ini digunakan kernel non linier Gaussian Radial Basis Function (RBF) untuk menyelesaikannya permaslahan klasifikasi data klaim fraud pada data kesehatan [7]. Kernel RBF adalah kernel yang membantu mentransformasi data dari dimensi yang relatif rendah ke dimensi tak hingga dalam mencari hyperplane sehingga diperoleh Persamaan 5. ...
... 47 For digital submissions, it might take 2e4 weeks, whereas, for paper ones, it might be longer such as 4e8 weeks. 48 If firms adopt blockchain, the time to process these claims can be just 15 min. By removing intermediaries, firms can develop a logic, use it in the network, process swiftly, and make immediate payments to service providers. ...
Blockchain technology together with allied cryptocurrencies could have immense implications in both global health financing and global health equity and, eventually, contribute tremendously to universal health coverage. The Blockchain technology can ensure direct financial transactions for universal health coverage without third parties' interference, introduce novel multilateral financing options, enhance security, reduce fraud and corruption, and provide ample opportunities for free markets of health data, essential for discovery and innovation. Although blockchains present a secure, privacy-enabled, and accurate mechanism to store and exchange healthcare information and support for universal health coverage, there exist inherent dangers in the sectors that entail effective legal and regulatory measures. Additionally, there remains a significant knowledge gap encompassing the application of Blockchain technology in the universal healthcare systems, associated dilemmas, prospects, and policy options. This chapter aims to clarify the legal aspects of universal health coverage, application of Blockchain technology in diverse areas of healthcare systems, and regulatory and policy challenges along with their implications and finally, offers appropriate policy recommendations. To comprehend the relevant facts, findings, and issues, extensive literature was analyzed from both primary and secondary sources. The study employed the content analysis technique in reaching the concluding remarks by way of the authors' analysis. Finally, the findings have been demonstrated descriptively.
... Later, topological clustering, based on adaptive resonance theory, is used to analyze the patterns. Sowah et al. (2019) proposed a genetic support vector machine (GSVM), which is a novel technique which is dependent on genetic support vector machines. GSVM identifies the anomalies and is used to identify fraud. ...
Of late, insurance fraud detection has assumed immense significance owing to the huge financial & reputational losses fraud entails and the phenomenal success of the fraud detection techniques. Insurance is majorly divided into two categories: (i) Life and (ii) Non-life. Non-life insurance in turn includes health insurance and auto insurance among other things. In either of the categories, the fraud detection techniques should be designed in such a way that they capture as many fraudulent transactions as possible. Owing to the rarity of fraudulent transactions, in this paper, we propose a chaotic variational autoencoder (C-VAE to perform one-class classification (OCC) on genuine transactions. Here, we employed the logistic chaotic map to generate random noise in the latent space. The effectiveness of C-VAE is demonstrated on the health insurance fraud and auto insurance datasets. We considered vanilla Variational Auto Encoder (VAE) as the baseline. It is observed that C-VAE outperformed VAE in both datasets. C-VAE achieved a classification rate of 77.9% and 87.25% in health and automobile insurance datasets respectively. Further, the t-test conducted at 1% level of significance and 18 degrees of freedom infers that C-VAE is statistically significant than the VAE.
... A DSM based on AHP was created to determine the eligibility of surety bond insurance claims [6]. The genetic support vector machine approach was used to create a DSM to detect possible claim fraud [7]. A Bayesian quantile regression model made by [8] to detect which part of the claim distribution number has the greatest effect in vehicle insurance in Malaysia. ...
Insurance industry in Indonesia has shown promising result based on premium growth in 2014-2018, as recorded in Indonesia General Insurance Market Update 2019. With the increase of premium, the claim rate also grows. Insurance companies face challenges in processing the claims. Many factors need to be carefully considered before making a claim decision. This paper proposes a decision support model (DSM) to score claim cases and to propose claim risk category (CRC) and claim decision (CD). The model was built with 13 parameters, divided into non-fuzzy group and fuzzy group. The analytic hierarchy process (AHP) method was used to determine the priority weight (PW) among parameters. The Tsukamoto's fuzzy logic (FL) method was applied to process the fuzzy parameters. A simple mathematics method (SMM) was exercised to calculate the non-fuzzy parameters, and to aggregate the result into claim risk score (CRS). Finally, CRC and CD were derived from the CRS using a rule base. The model was tested using 19611 actual claim history records. The result was: 6171 (31.47%) accepted with CRC= low, 3459 (17.64%) pending (CRC medium), and 9981 (50.89%) pending (CRC high). The DSM model was implemented in python with Google COLAB and Datapane to create various graphics.
... Linear regression is used to validate this scoring model. Sowah et al. [62] developed a decision-making method for detecting the HI fraud. SVM based on genetic algorithms, is utilized to classify fraudulent insurance claims from the National HI Scheme dataset. ...
Nowadays, health insurance has become an essential part of people's lives as the number of health issues increases. Healthcare emergencies can be troublesome for people who can't afford huge expenses. Health insurance helps people cover healthcare services expenses in case of a medical emergency and provides financial backup against indebtedness risk. Health insurance and its several benefits can face many security, privacy, and fraud issues. For the past few years, fraud has been a sensitive issue in the health insurance domain as it incurs high losses for individuals, private firms, and governments. So, it is essential for national authorities and private firms to develop systems to detect fraudulent cases and payments. A high volume of health insurance data in electronic form is generated, which is highly sensitive and attracts malicious users. Motivated by these facts, we present a systematic survey for Artificial Intelligence (AI) and blockchain-enabled secure health insurance fraud detection in this paper. This paper presents a taxonomy of various security issues in health insurance. We proposed a blockchain and AI-based secure and intelligent system to detect health insurance fraud. Then a case study related to health insurance fraud is presented. Finally, the open issues and research challenges in implementing the blockchain and an AI-empowered health insurance fraud detection system is presented.
... As a result, patients who need treatment for health services are hampered [1]. There are 3 categories of fraud in health insurance, first is giving expensive therapy that is not needed by the patient or giving medication that exceeds the dose, second is avoiding bills exceeding the ceiling value, third is acting as if the patient has gone home and immediately submitting a claim and fraud is carried out by demanding own expenses [2]. ...
... The results of the study found that GSVM was able to detect and classify fraud. Faster processing time when processing claims and increasing classification accuracy based on linear SVM classification (80.67%), polynomial (81.22%) and kernel radial basis function (RBF) (87.91%) [2]. ...
Health insurance helps people to obtain quality and affordable health services. The claim billing process is manually input code to the system, this can lack of errors and be suspected of being fraudulent. Claims suspected of fraud are traced manually to find incorrect inputs. The increasing volume of claims causes a decrease in the accuracy of tracing claims suspected of fraud and consumes time and energy. As an effort to prevent and reduce the occurrence of fraud, this study aims to determine the pattern of data on the occurrence of fraud based on the formation of data groupings. Data was prepared by combining claims for inpatient bills and patient bills from hospitals in 2020. Two methods were used in this study to form clusters, DBSCAN and KMeans. To find out the outliers in the cluster, Local Outlier Factor (LOF) was added. The results from experiments show that both methods can detect outlier data and distribute outlier data in the formed cluster. Variable that high effect becomes data outlier is the length of stay, claims code, and condition of patient when discharged from the hospital. Accuracy K-Means is 0.391, 0.003 higher than DBSCAN, which is 0.389.
