15 July 2025 in The Journal of Prosthetic Dentistry
18 February 2026 in IEEE Access
Healthcare industry faces significant challenges due to fraudulent medical insurance claims, which result in substantial financial losses. We propose an automated system using domain-specific Small Language Models (SLMs) with a narrower scope and smaller parameter count than general-purpose Large Language Models (LLMs), combined with optimization algorithms to improve fraud detection. Our approach integrates numerical features, such as age and claim amount, with textual descriptions, including diagnoses and procedures, into a unified textual representation for each medical activity. This representation captures complex patterns, enhancing the model’s predictive ability. SLMs fine-tuned on medical corpora transform these textual inputs into fixed-dimensional numerical embeddings, capturing semantic and contextual information. Swarm-intelligence-based optimization algorithms then refine feature selection, identifying the most informative subset of features to reduce dimensionality and computational overhead. The system achieves up to 87% accuracy and 96% specificity in classifying medical activities, demonstrating that domain-specific SLMs deliver competitive performance with lower computational costs compared to larger general-purpose models, making the system scalable and efficient. To our knowledge, this is the first work to combine domain-specific SLMs with optimization algorithms for fraud detection in medical claims. This novel approach improves classification accuracy while reducing computational overhead, demonstrating the potential of domain-specific generative AI in healthcare applications.