Exploring a Hybrid Deep Learning Approach for Anomaly Detection in Mental Healthcare Provider Billing: Addressing Label Scarcity through Semi-Supervised Anomaly Detection

TL;DR

This paper presents a hybrid deep learning method combining LSTM and Transformers, enhanced with pseudo-labeling techniques, to improve anomaly detection in mental healthcare billing data characterized by class imbalance and label scarcity.

Contribution

It introduces a novel hybrid deep learning approach with pseudo-labeling for healthcare billing anomaly detection, addressing challenges of label scarcity and complex patterns.

Findings

iForest LSTM achieved 0.963 recall on declaration-level data

Hybrid iForest-based model achieved 0.744 recall on operation-level data

Hybrid approach shows promise in imbalanced anomaly detection scenarios

Abstract

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.