Exploring a Hybrid Deep Learning Approach for Anomaly Detection in Mental Healthcare Provider Billing: Addressing Label Scarcity through Semi-Supervised Anomaly Detection
This addresses fraud detection in mental healthcare billing, an incremental improvement over existing methods by handling label scarcity and complex patterns.
The study tackled anomaly detection in mental healthcare billing by exploring a hybrid deep learning approach combining LSTM and Transformers with pseudo-labeling, achieving a recall of 0.963 on declaration-level data and 0.744 on operation-level data.
The complexity of mental healthcare billing enables anomalies, including fraud. While machine learning methods have been applied to anomaly detection, they often struggle with class imbalance, label scarcity, and complex sequential patterns. This study explores a hybrid deep learning approach combining Long Short-Term Memory (LSTM) networks and Transformers, with pseudo-labeling via Isolation Forests (iForest) and Autoencoders (AE). Prior work has not evaluated such hybrid models trained on pseudo-labeled data in the context of healthcare billing. The approach is evaluated on two real-world billing datasets related to mental healthcare. The iForest LSTM baseline achieves the highest recall (0.963) on declaration-level data. On the operation-level data, the hybrid iForest-based model achieves the highest recall (0.744), though at the cost of lower precision. These findings highlight the potential of combining pseudo-labeling with hybrid deep learning in complex, imbalanced anomaly detection settings.