PRESS-NEWS.org - Press Release Distribution
PRESS RELEASES DISTRIBUTION

New AI technique significantly boosts Medicare fraud detection

Study explores ‘vast sea’ of big Medicare data, parts B and D

New AI technique significantly boosts Medicare fraud detection
2024-01-31
(Press-News.org) Medicare is sporadically compromised by fraudulent insurance claims. These illicit activities often go undetected, allowing full-time criminals and unscrupulous health providers to exploit weaknesses in the system. Last year, the estimated annual fraud topped $100 billion according to the National Health Care Anti-Fraud Association, but it is likely much higher.

Traditionally, to detect Medicare fraud, a limited number of auditors, or investigators, are responsible for manually inspecting thousands of claims, but only have enough time to look for very specific patterns indicating suspicious behaviors. Moreover, there are not enough investigators to keep up with the various Medicare fraud schemes.

Utilizing big data, such as from patient records and provider payments, often is considered the best way to produce effective machine learning models to detect fraud. However, in the domain of Medicare insurance fraud detection, handling imbalanced big data and high dimensionality – data in which the number of features is staggeringly high so that calculations become extremely difficult – remains a significant challenge.

New research from the College of Engineering and Computer Science at Florida Atlantic University addresses this challenge by pinpointing fraudulent activity in the “vast sea” of big Medicare data. Since identification of fraud is the first step in stopping it, this novel technique could conserve substantial resources for the Medicare system.

For the study, researchers systematically tested two imbalanced big Medicare datasets, Part B and Part D.  Part B involves Medicare’s coverage of medical services like doctor’s visits, outpatient care, and other medical services not covered under hospitalization. Part D, on the other hand, relates to Medicare’s prescription drug benefit and covers medication costs. These datasets were labeled with the List of Excluded Individuals and Entities (LEIE). The LEIE is provided by the United States Office of the Inspector General.

Researchers delved deep into the influence of Random Undersampling (RUS), a straightforward, yet potent data sampling technique, and their novel ensemble supervised feature selection technique. RUS works by randomly removing samples from the majority class until a specific balance between the minority and majority classes is met.

The experimental design investigated various scenarios, ranging from using each technique in isolation to employing them in combination. Following analyses of the individual scenarios, researchers again selected the techniques that yielded the best results and performed an analysis of results between all scenarios.

Results of the study, published in the Journal of Big Data, demonstrate that intelligent data reduction techniques improve the classification of high imbalanced big Medicare data. The synergistic application of both techniques – RUS and supervised feature selection – outperformed models that utilize all available features and data. Findings showed that either combination of using the feature selection technique followed by RUS, or using RUS followed by the feature selection technique, yielded the best performance.

Consequently, in the classification of either dataset, researchers discovered that a technique with the largest amount of data reduction also yields the best performance, which is the technique of performing feature selection, then applying RUS. Reduction in the number of features leads to more explainable models and performance is significantly better than using all features. 

“The performance of a classifier or algorithm can be swayed by multiple effects,” said Taghi Khoshgoftaar, Ph.D., senior author and Motorola Professor, FAU Department of Electrical Engineering and Computer Science. “Two factors that can make data more difficult to classify are dimensionality and class imbalance. Class imbalance in labeled data happens when the overwhelming majority of instances in the dataset have one particular label. This imbalance presents obstacles, as it is possible for a classifier optimized for a metric such as accuracy, which will mislabel fraudulent activities as non-fraudulent to boost overall scores in terms of the metric.”  

For feature selection, researchers incorporated a supervised feature selection method based on feature ranking lists. Subsequently, through the implementation of an innovative approach, these lists were combined to yield a conclusive feature ranking. To furnish a benchmark, models also were built utilizing all features of the datasets. Upon the derivation of this consolidated ranking, features were selected based on their position in the list.

“Our systematic approach provided a greater comprehension regarding the interplay between feature selection and model robustness within the context of multiple learning algorithms,” said John T. Hancock, first author and a Ph.D. student in FAU’s Department of Electrical Engineering and Computer Science. “It is easier to reason about how a model performs classifications when it is built with fewer features.”

For both Medicare Part B and Part D datasets, researchers conducted experiments in five scenarios that exhausted the possible ways to utilize, or omit, the RUS and feature selection data reduction techniques. For both datasets, researchers found that data reduction techniques also improve classification results.

“Given the enormous financial implications of Medicare fraud, findings from this important study not only offer computational advantages but also significantly enhance the effectiveness of fraud detection systems,” said Stella Batalama, Ph.D., dean, FAU College of Engineering and Computer Science. “These methods, if properly applied to detect and stop Medicare insurance fraud, could substantially elevate the standard of health care service by reducing costs related to fraud.”

Study co-authors are Huanjing Wang, Ph.D., a professor of computer science, Western Kentucky University; and Qianxin Liang, a Ph.D. student in FAU's Department of Electrical Engineering and Computer Science.  

- FAU –

 

About FAU’s College of Engineering and Computer Science:

The FAU College of Engineering and Computer Science is internationally recognized for cutting-edge research and education in the areas of computer science and artificial intelligence (AI), computer engineering, electrical engineering, biomedical engineering, civil, environmental and geomatics engineering, mechanical engineering, and ocean engineering. Research conducted by the faculty and their teams expose students to technology innovations that push the current state-of-the art of the disciplines. The College research efforts are supported by the National Science Foundation (NSF), the National Institutes of Health (NIH), the Department of Defense (DOD), the Department of Transportation (DOT), the Department of Education (DOEd), the State of Florida, and industry. The FAU College of Engineering and Computer Science offers degrees with a modern twist that bear specializations in areas of national priority such as AI, cybersecurity, internet-of-things, transportation and supply chain management, and data science. New degree programs include Master of Science in AI (first in Florida), Master of Science and Bachelor in Data Science and Analytics, and the new Professional Master of Science and Ph.D. in computer science for working professionals. For more information about the College, please visit eng.fau.edu.  

 

About Florida Atlantic University:
Florida Atlantic University, established in 1961, officially opened its doors in 1964 as the fifth public university in Florida. Today, the University serves more than 30,000 undergraduate and graduate students across six campuses located along the southeast Florida coast. In recent years, the University has doubled its research expenditures and outpaced its peers in student achievement rates. Through the coexistence of access and excellence, FAU embodies an innovative model where traditional achievement gaps vanish. FAU is designated a Hispanic-serving institution, ranked as a top public university by U.S. News & World Report and a High Research Activity institution by the Carnegie Foundation for the Advancement of Teaching. For more information, visit www.fau.edu.

 

 

END


[Attachments] See images for this press release:
New AI technique significantly boosts Medicare fraud detection

ELSE PRESS RELEASES FROM THIS DATE:

Fungal-rich soil may improve green roofs

Fungal-rich soil may improve green roofs
2024-01-31
Green roofs have become increasingly popular thanks to their benefits related to climate adaptation, mitigation, and urban biodiversity management. These vegetated surfaces on the rooftops of buildings absorb excess storm water, reduce energy use by insulating buildings, and cool neighborhoods, tempering urban heat islands, while also creating urban habitats for plants, pollinators, and wildlife. But, in the U.S., green roofs are typically planted with non-native plants in sterile soils, and their effectiveness declines over time. A Dartmouth-led research team set out to determine ...

Autoimmune disease and pregnancy

Autoimmune disease and pregnancy
2024-01-31
SEATTLE – For many aspiring mothers with autoimmune disease, pregnancy can be daunting and full of unknowns. In some cases, those suffering from specific autoimmune conditions have chosen to forego pregnancy altogether due to concerns about their disease treatments and adverse pregnancy outcomes. In a just-published study in the journal Lancet eClinical Health, researchers at the Institute for Systems Biology (ISB) and Providence showed nuanced pregnancy outcomes for pregnant individuals with autoimmune disease. The ...

Looking for love? Try finding purpose as well

2024-01-31
The world of online dating can be overwhelming with the dizzying array of options for attracting a partner but new research from Washington University in St. Louis shows that those looking for love may have more success if they also seek a sense of purpose in life. Researcher Isabella D’Ottone, in the lab of Patrick Hill, associate professor of psychological and brain sciences in Arts & Sciences, published a study about how that sense of purpose can affect how others may rate dating app profiles. Those whose profiles show a sense of purpose were rated higher on various scales for attractiveness compared ...

Brain changes behind pain sensitivity may affect older women more

2024-01-31
COLUMBUS, Ohio – A new study has found that the brain system enabling us to inhibit our own pain changes with age, and that gender-based differences in those changes may lead females to be more sensitive to moderate pain than males as older adults. Researchers used fMRI scans to examine brain responses in men and women who had rated the intensity and unpleasantness of pain during exposure to increasing levels of heat. The results suggested that established gender differences in pain perception could likely be traced at least ...

Enhancing solid-state phosphorescence in π-electronic molecules

Enhancing solid-state phosphorescence in π-electronic molecules
2024-01-31
Photoluminescent molecules, capable of absorbing and re-emitting light, play an important role in the development of technologies such as light-emitting diodes, sensors, and displays. Among them, ordered arrangements of π-electronic molecules such as crystals of organoplatinum(II) complexes, where a platinum(II) ion is coordinated by organic ligands in a square-planar arrangement, stand out for their applications in energy-efficient flexible displays. However, their luminescence in the solid state is short-lived due to the interaction between excitons (bound electron-hole pairs) of neighboring molecules. To address this ...

Bringing together real-world sensors and VR to improve building maintenance

Bringing together real-world sensors and VR to improve building maintenance
2024-01-31
A new system that brings together real-world sensing and virtual reality would make it easier for building maintenance personnel to identify and fix issues in commercial buildings that are in operation. The system was developed by computer scientists at the University of California San Diego and Carnegie Mellon University.  The system, dubbed BRICK, consists of a handheld device equipped with a suite of sensors to monitor temperature, CO2 and airflow. It is also equipped with a virtual reality environment that has access to the sensor data and metadata in a specific building while being ...

Potential link between high maternal cortisol, unpredicted birth complications

2024-01-31
PULLMAN, Wash. – A snippet of hair can reveal a pregnant person’s stress level and may one day help warn of unexpected birth problems, a study indicates. Washington State University researchers measured the stress hormone cortisol in hair samples of 53 women in their third trimester. Of that group, 13 women who had elevated cortisol levels later experienced unpredicted birth complications, such as an early birth or hemorrhaging. While more research is needed with larger groups, this preliminary finding could eventually lead to a non-invasive way to identify those ...

Virtual reality treatment for palliative care shown to help patients ‘flourish’ during relaxation therapy

2024-01-31
Palliative care is the interdisciplinary medical specialty of caring for people with serious and often terminal illnesses. Its aim is to improve quality of life for such patients and their families, by relieving symptoms and stress. Palliative care is widely considered to be a human right, even if the World Health Organization estimates that only 14% of the approximately 56.8 million people who need it each year worldwide actually receive it. Since seriously ill patients often experience stress, psychological interventions such as relaxation therapy play an important role in palliative care. Now, researchers have shown in a ground-breaking clinical trial ...

Antiviral color nanocoating technology

Antiviral color nanocoating technology
2024-01-31
Since the onset of COVID-19, we've become accustomed to seeing antiviral films attached to elevator buttons and public transportation handles. However, conventional antiviral films are made by mixing antiviral metal particles with polymers. Due to the manufacturing process, only a very small fraction of these metal particles is exposed on the surface. As a result, contrary to the belief that these films will protect us from viruses, the actual antiviral effect upon contact with the film surface is not ...

Key LiDAR sensor elements for autonomous vehicles are now made with our technology

Key LiDAR sensor elements for autonomous vehicles are now made with our technology
2024-01-31
LiDAR sensors are indispensable for the realization of advanced technologies such as advanced driver assistance systems (ADAS), autonomous driving, and AR/VR. In particular, short- and mid-range LiDAR used in AR/VR devices and smartphones requires better distance (depth) resolution to detect the shape of a person or object more accurately, and so a single-photon detector with better timing jitter performance is required. LiDAR measures distance and creates a 3D image by calculating the time it takes for a photon emitted by the transmitter to strike an object, reflect, and arrive back at the ...

LAST 30 PRESS RELEASES:

Korea University study reveals hidden complexity in recurrent brain tumors

How an immune cell receptor dampens the fight against fungal infection

SeoulTech researchers uncover high PAHs in common foods

Precision in the pancreas: New test transforms hereditary pancreatitis diagnosis and care

Peer-reviewed study validates Mentavi’s online ADHD diagnostic evaluation in the Journal of Clinical Psychiatry

Machine embroidery encodes skin-like tension lines in textiles, enabling mass-customizable wearables

Customized gene-editing technology shows potential to treat lethal pediatric disease

Johns Hopkins researchers discover new methods for making smaller microchips

Durham University scientists play key role in testing superconducting materials for world’s largest fusion energy project

Drug-resistant fungus Candidozyma auris confirmed to spread rapidly in European hospitals: ECDC calls for urgent action

New evidence of long-distance travelers in Seddin during the Bronze Age

Newly dated 85-million-year-old dino eggs could improve understanding of Cretaceous climate

From noise to power: A symmetric ratchet motor discovery

Family-based intervention programs are insufficient to prevent childhood obesity, major study finds

Emotions expressed in real-time barrage comments relate to purchasing intentions and imitative behavior

Your genes could prune your gut bugs and protect you from disease

EMBARGOED MEDIA RELEASE: Breathlessness increases long-term mortality risk, Malawi study finds

Permeable inspection of pharmaceuticals goes in-line

Warming rivers in Alaska threaten Chinook salmon populations and Indigenous food security

New multi-disciplinary approach sheds light on the role of mitochondrial DNA mutations in cancer

Worms reveal just how cramped cells really are

Alzheimer’s disease digital resources lacking for Latinos, Hispanics in Los Angeles years after COVID-19, study finds

Chronic disease deaths decline globally, but progress is slowing

The Lancet: Chronic disease deaths decline globally, but progress is slowing

The Lancet: Parent-focused programs insufficient to prevent obesity in toddlers, finds meta-analysis; authors call for a re-think of childhood obesity prevention approaches

Study sheds light on hurdles faced in transforming NHS healthcare with AI

Astrocytic “brake” that blocks spinal cord repair identified

As farm jobs decline, food industry work holds steady

Kennesaw State researcher aiming to move AI beyond the cloud

Revolutionizing impedance flow cytometry with adjustable microchannel height

[Press-News.org] New AI technique significantly boosts Medicare fraud detection
Study explores ‘vast sea’ of big Medicare data, parts B and D