The task of medical insurance anomaly detection faces the problem of inaccurate feature selection and insufficient computational efficiency. To improve detection accuracy and interpretability, a classification hybrid model based on counterfactual feature selection and enhanced frequent rule mining (CFEFS-FIM) was proposed. The model integrated counterfactual sample generation and a feature importance evaluation method to select the optimal feature subset. It employed an improved Apriori algorithm and an adaptive two-level hash index structure to efficiently mine frequent rules in large-scale data. The mined rules were then fused with a machine learning classifier to optimize prediction performance. Experiments were conducted on a medical insurance claim denial dataset. The results showed that CFEFS-FIM achieved approximately 5% improvement over the baseline model in multiple evaluation indicators with a runtime reduction of over 20%. This provides effective technical support for hospital cost management and medical insurance risk identification.
HAMIDZ, KHALIQUEF, MAHMOODS,et al.Healthcare insurance fraud detection using data mining[J].BMC Medical Informatics and Decision Making,2024,24(1):112.
[7]
DUPREEZ A, BHATTACHARYAS, BELINGP,et al.Fraud detection in healthcare claims using machine learning:A systematic review[J].Artificial Intelligence in Medicine,2025,160:103061.
[8]
SUESSERMANM, GORNYS, LASAGAD,et al.Procedure code overutilization detection from healthcare claims using unsupervised deep learning methods[J].BMC Medical Informatics and Decision Making,2023,23(1):196.
[9]
LUJ T, LINK B, CHENR C,et al.Health insurance fraud detection by using an attributed heterogeneous information network with a hierarchical attention mechanism[J].BMC Medical Informatics and Decision Making,2023,23(1):62.
[10]
ALFEOA, CIMINOM.Counterfactual-based feature importance for explainable regression of manufacturing production quality measure[C]//Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods.Rome:SCITEPRESS-Science and Technology Publications,2024:48-56.
[11]
GOMESC, JINZ, YANGH L.Insurance fraud detection with unsupervised deep learning[J].Journal of Risk and Insurance,2021,88(3):591-624.
[12]
MELLOM M, ROSES.Denial-artificial intelligence tools and health insurance coverage decisions[J].JAMA Health Forum,2024,5(3):e240622.
[13]
KHALIDA R, OWOHN, UTHMANIO,et al.Enhancing credit card fraud detection:An ensemble machine learning approach[J].Big Data and Cognitive Computing,2024,8(1):6.
[14]
MIENYEI D, SWARTT G.A hybrid deep learning approach with generative adversarial network for credit card fraud detection[J].Technologies,2024,12(10):186.
[15]
LIUY P, JIANGH K, YAOR H,et al.Counterfactual-augmented few-shot contrastive learning for machinery intelligent fault diagnosis with limited samples[J].Mechanical Systems and Signal Processing,2024,216:111507.
[16]
LIC Y, CHENGD B, ZHANGG X,et al.Contrastive learning for fair graph representations via counterfactual graph augmentation[J].Knowledge-Based Systems,2024,305:112635.
[17]
BODOFFD, GOLDMANM F.A fundamental question of counting in association rules[J].International Journal of Data Science and Analytics,2025,20(4):3889-3899.
[18]
CAOM J.An advanced apriori algorithm technology to enhance sports data mining[J].Information Resources Management Journal,2024,37(1):1-18.
[19]
PAMNANIH K, RAJAL, IVEST.Developing a novel H-Apriori algorithm using support-leverage matrix for association rule mining[J].International Journal of Information Technology,2024,16(8):5395-5405.
[20]
SARKARR, SUNJ P.Improved apriori method for safety signal detection using post-marketing clinical data[J].Mathematics,2024,12(17):2705.
ROSCHEWITZM, DE SOUSA RIBEIROF, XIAT, et al. Robust image representations with counterfactual contrastive learning[J]. Medical Image Analysis, 2025, 105: 103668.
[23]
AND Z, WANGF, ZHANGS C, et al. Exploiting non-likelihood adversarial training for Chinese counterfactual data augmentation[J]. Engineering Applications of Artificial Intelligence, 2025, 156: 111149.
[24]
ZUOL S, MAKM W. Vector quantization-based counterfactual augmentation for speech-based depression detection under data scarcity[J]. IEEE Journal of Biomedical and Health Informatics, 2025, 29(10): 7559-7567.
[25]
YUN, CHENL, YIX Y, et al. Attention learning with counterfactual intervention based on feature fusion for fine-grained feature learning[J]. Digital Signal Processing, 2025, 163: 105215.
[26]
YANX, JIANGY T, LIUW Y, et al. Transforming multidimensional time series into interpretable event sequences for advanced data mining[C]//2024 5th International Conference on Intelligent Computing and Human-Computer Interaction (ICHCI). Nanchang:IEEE, 2024: 126-130.
[27]
SANTOSOM H. Application of association rule method using apriori algorithm to find sales patterns case study of indomaret tanjung anom[J]. Brilliance: Research of Artificial Intelligence, 2021, 1(2): 54-66.
[28]
WANGX H, YANZ M, ZENGY B, et al. Research on correlation factor analysis and prediction method of overhead transmission line defect state based on association rule mining and RBF-SVM[J]. Energy Reports, 2021, 7: 359-368.
[29]
XUR H, LUOF. Risk prediction and early warning for air traffic controllers’ unsafe acts using association rule mining and random forest[J]. Safety Science, 2021, 135: 105125.
AL-SARAYRAHA. Recent advances and applications of apriori algorithm in exploring insights from healthcare data patterns[J]. PatternIQ Mining, 2024, 1(2): 27-39.
[32]
ZHENGW D, AIY B, ZHANGW D. Research on indoor object detection and scene recognition algorithm based on apriori algorithm and mobile-EFSSD model[J]. Mathematics, 2025, 13(15): 2408.
[33]
RIYADH ALBOALEBRAHM, AL-AUGBYS. Unveiling the causes of fatal road accidents in Iraq: An association rule mining approach using the apriori algorithm[J]. Journal of Cyber Security and Risk Auditing, 2025, 2025(2): 1-11.
[34]
NEMATIZ, MOHAMMADIA, BAYATA, et al. Fraud prediction in financial statements through comparative analysis of data mining methods[J]. International Journal of Finance & Managerial Accounting, 2025,10(38):151-166.
MANZALIY, ELFARM. Optimizing the number of branches in a decision forest using association rule metrics[J]. Knowledge and Information Systems, 2024, 66(6): 3261-3281.
[38]
CHENH Q, YANGM H, TANGX. Association rule mining of aircraft event causes based on the Apriori algorithm[J]. Scientific Reports, 2024, 14: 13440.
[39]
RAHMANA, DEBNATHT, KUNDUD, et al. Machine learning and deep learning-based approach in smart healthcare: Recent advances, applications, challenges and opportunities[J]. AIMS Public Health, 2024, 11(1): 58-109.
[40]
LIY, ZHANGH Y. Big data technology for teaching quality monitoring and improvement in higher education - joint K-means clustering algorithm and Apriori algorithm[J]. Systems and Soft Computing, 2024, 6: 200125.
[41]
TARIGANP M S, HARDINATAJ T, QURNIAWANH, et al. Implementation of data mining using apriori algorithm in determining inventory (Case study: Sinar Harahap store)[J].Janitra Journal of Informatics and Information Systems, 2022, 2(1): 9-19.
[42]
HICKSS A, STRÜMKEI, THAMBAWITAV, et al. On evaluation metrics for medical applications of artificial intelligence[J]. Scientific Reports, 2022, 12: 5979.
OMOTEHINWAT O, OYEWOLAD O, MOUNGE G. Optimizing the light gradient-boosting machine algorithm for an efficient early detection of coronary heart disease[J]. Informatics and Health, 2024, 1(2): 70-81.