Nithin Reddy Desani’s Advanced AI Technique for Medicare Fraud Detection

Share this news:

Novel Non-Linear Logistic Regression Analysis achieves 99.2% accuracy in identifying fraudulent medicare claims, promising enhanced fraud-protection benefits and a reduced systemic healthcare burden for all.

Photo Credit: Nithin Reddy Desani


A team of independent researchers has published a research paper introducing a novel artificial intelligence technique for Medicare fraud detection. The new method, developed using Non-Linear Logistic Regression Analysis (NL-LRA), demonstrates a high level of accuracy in identifying fraudulent Medicare claims.


Medicare fraud remains a major challenge, costing the U.S. federal healthcare system approximately $13 billion annually. More traditional fraud detection methods often struggle with issues like data imbalance, missing values, and high dimensionality, leading to lower accuracy and overfitting. The research team’s new technique, NL-LRA, faces these commonplace issues through the combined use of advanced machine learning (ML) algorithms and tree-based methods, providing both high accuracy and interpretability in fraud detection processes.


"Our research is simply the next big step above the already-existing fraud detection methods," says Nithin Reddy Desani, contributing author of the research paper. "We incorporated Penalized Logistic Tree Regression, which allows for a 99.2% accuracy rate in identifying fraudulent claims. This is all done while maintaining high precision and recall rates of 94.5% and 99.09%, respectively."


The study utilizes the Synthetic Minority Oversampling Technique (SMOTE) to address data imbalance issues and employs Linear Discriminant Analysis (LDA) for feature selection, resulting in a stronger and more reliable fraud detection system. The research also introduces a LIME-based explainability model, making the AI's decision-making process transparent and interpretable for healthcare providers and administrators.


"LIME-based explainability is practically a requirement when offering AI-based systems to those outside the field. Even better, AI-driven fraud detection can become more transparent and accountable with this system," explains Desani. "Of course, transparency and regulatory compliance are requirements for healthcare providers. If you don’t know what’s going on under the hood, how can you know if it’s actually detecting fraud cases accurately? The last thing anyone wants is to deny medical help to those who actually need it. That’s why further research into these methods is so important."


The research team's findings have been validated through comprehensive testing and comparative analysis against existing methods, including CatBoost and Autoencoder techniques. The results demonstrate superior performance across all key metrics, establishing it as the first among a new wave of potential healthcare fraud prevention systems suitable for national adoption in the future.


The complete research paper, including detailed methodology and results, is available for review through academic channels.

About the Research Team


The research team comprises independent researchers and industry professionals specializing in data engineering, machine learning, and healthcare analytics. Led by Saigurudatta Pamulaparthyvenkata, the team includes experienced professionals from various technology backgrounds, dedicated to advancing the field of healthcare fraud detection through advanced AI solutions.

Contact Info:
Name: Alex Sterling
Email: Send Email
Organization: Global Recognition Awards
Website: https://globalrecognitionawards.org/

Release ID: 89145717

CONTACT ISSUER
Name: Alex Sterling
Email: Send Email
Organization: Global Recognition Awards
REVIEWED BY
Editor Profile Picture
This content is reviewed by our News Editor, Hui Wong.

If you need any help with this piece of content, please contact us through our contact form
SUBSCRIBE FOR MORE