Enhancing Medicare Fraud Detection With a CNN-Transformer-XGBoost Framework and Explainable AI
Healthcare fraud is a critical challenge, contributing significantly to rising healthcare costs and financial losses. This article proposes a hybrid architecture for healthcare fraud detection, combining deep learning-based feature representation with gradient boosting classification and explainable...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10971341/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849420936735883264 |
|---|---|
| author | Mohammad Balayet Hossain Sakil Md Amit Hasan Md Shahin Alam Mozumder Md Rokibul Hasan Shafiul Ajam Opee M. F. Mridha Zeyar Aung |
| author_facet | Mohammad Balayet Hossain Sakil Md Amit Hasan Md Shahin Alam Mozumder Md Rokibul Hasan Shafiul Ajam Opee M. F. Mridha Zeyar Aung |
| author_sort | Mohammad Balayet Hossain Sakil |
| collection | DOAJ |
| description | Healthcare fraud is a critical challenge, contributing significantly to rising healthcare costs and financial losses. This article proposes a hybrid architecture for healthcare fraud detection, combining deep learning-based feature representation with gradient boosting classification and explainable AI techniques. The framework integrates convolutional neural networks (CNNs), transformers, and XGBoost to capture intricate patterns in claims data while maintaining interpretability through Shapley additive explanations. The model we proposed was tested on two datasets: the Medicare Provider Fraud dataset and the Healthcare Providers dataset. On the Medicare dataset, the framework achieved an F1-score of 0.95 on the training set and 0.92 on the test set, with an AUC-ROC of 0.98 and 0.97, respectively, outperforming state-of-the-art models such as LightGBM and CatBoost. On the Healthcare Providers dataset, the framework attained a test F1-score of 0.92 and an AUC-ROC of 0.96, consistently surpassing traditional models like Support Vector Machines and Random Forest. Key contributions include integrating domain-specific features, such as provider-patient interaction graphs and temporal patterns, and using explainability techniques to enhance trustworthiness. Furthermore, the framework demonstrated computational efficiency, with a training time of 150 seconds on the primary dataset, making it suitable for real-world deployment. |
| format | Article |
| id | doaj-art-385695bf791b4090845968539b85aeb4 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-385695bf791b4090845968539b85aeb42025-08-20T03:31:37ZengIEEEIEEE Access2169-35362025-01-0113796097962210.1109/ACCESS.2025.356257710971341Enhancing Medicare Fraud Detection With a CNN-Transformer-XGBoost Framework and Explainable AIMohammad Balayet Hossain Sakil0Md Amit Hasan1Md Shahin Alam Mozumder2Md Rokibul Hasan3Shafiul Ajam Opee4https://orcid.org/0009-0009-9526-647XM. F. Mridha5https://orcid.org/0000-0001-5738-1631Zeyar Aung6https://orcid.org/0000-0001-5990-9305College of Graduate and Professional Studies, Trine University, Angola, IN, USAMaster of Science in Information Technology (MSIT), Washington University of Science and Technology, Alexandria, VA, USAMaster of Science in Information Technology (MSIT), Washington University of Science and Technology, Alexandria, VA, USAHarrison College of Business and Computing, Southeast Missouri State University, Cape Girardeau, MO, USADepartment of Computer Science, American International University-Bangladesh (AIUB), Dhaka, BangladeshDepartment of Computer Science, American International University-Bangladesh (AIUB), Dhaka, BangladeshDepartment of Computer Science, Khalifa University, Abu Dhabi, United Arab EmiratesHealthcare fraud is a critical challenge, contributing significantly to rising healthcare costs and financial losses. This article proposes a hybrid architecture for healthcare fraud detection, combining deep learning-based feature representation with gradient boosting classification and explainable AI techniques. The framework integrates convolutional neural networks (CNNs), transformers, and XGBoost to capture intricate patterns in claims data while maintaining interpretability through Shapley additive explanations. The model we proposed was tested on two datasets: the Medicare Provider Fraud dataset and the Healthcare Providers dataset. On the Medicare dataset, the framework achieved an F1-score of 0.95 on the training set and 0.92 on the test set, with an AUC-ROC of 0.98 and 0.97, respectively, outperforming state-of-the-art models such as LightGBM and CatBoost. On the Healthcare Providers dataset, the framework attained a test F1-score of 0.92 and an AUC-ROC of 0.96, consistently surpassing traditional models like Support Vector Machines and Random Forest. Key contributions include integrating domain-specific features, such as provider-patient interaction graphs and temporal patterns, and using explainability techniques to enhance trustworthiness. Furthermore, the framework demonstrated computational efficiency, with a training time of 150 seconds on the primary dataset, making it suitable for real-world deployment.https://ieeexplore.ieee.org/document/10971341/Healthcare fraud detectionhybrid deep learningconvolutional neural networkstransformersXGBoostSHAP explainability |
| spellingShingle | Mohammad Balayet Hossain Sakil Md Amit Hasan Md Shahin Alam Mozumder Md Rokibul Hasan Shafiul Ajam Opee M. F. Mridha Zeyar Aung Enhancing Medicare Fraud Detection With a CNN-Transformer-XGBoost Framework and Explainable AI IEEE Access Healthcare fraud detection hybrid deep learning convolutional neural networks transformers XGBoost SHAP explainability |
| title | Enhancing Medicare Fraud Detection With a CNN-Transformer-XGBoost Framework and Explainable AI |
| title_full | Enhancing Medicare Fraud Detection With a CNN-Transformer-XGBoost Framework and Explainable AI |
| title_fullStr | Enhancing Medicare Fraud Detection With a CNN-Transformer-XGBoost Framework and Explainable AI |
| title_full_unstemmed | Enhancing Medicare Fraud Detection With a CNN-Transformer-XGBoost Framework and Explainable AI |
| title_short | Enhancing Medicare Fraud Detection With a CNN-Transformer-XGBoost Framework and Explainable AI |
| title_sort | enhancing medicare fraud detection with a cnn transformer xgboost framework and explainable ai |
| topic | Healthcare fraud detection hybrid deep learning convolutional neural networks transformers XGBoost SHAP explainability |
| url | https://ieeexplore.ieee.org/document/10971341/ |
| work_keys_str_mv | AT mohammadbalayethossainsakil enhancingmedicarefrauddetectionwithacnntransformerxgboostframeworkandexplainableai AT mdamithasan enhancingmedicarefrauddetectionwithacnntransformerxgboostframeworkandexplainableai AT mdshahinalammozumder enhancingmedicarefrauddetectionwithacnntransformerxgboostframeworkandexplainableai AT mdrokibulhasan enhancingmedicarefrauddetectionwithacnntransformerxgboostframeworkandexplainableai AT shafiulajamopee enhancingmedicarefrauddetectionwithacnntransformerxgboostframeworkandexplainableai AT mfmridha enhancingmedicarefrauddetectionwithacnntransformerxgboostframeworkandexplainableai AT zeyaraung enhancingmedicarefrauddetectionwithacnntransformerxgboostframeworkandexplainableai |