Selective Fine-Tuning of GPT Architectures for Parameter-Efficient Clinical Text Classification

The rapid expansion of electronic health record (EHR) systems has generated large volumes of unstructured clinical narratives that contain valuable information for disease identification, patient cohort discovery, and clinical decision support. Extracting structured knowledge from these free-text documents remains challenging because clinical language is highly specialized, labeled datasets are limited, and full fine-tuning of large pretrained language models can require substantial computational resources. Efficient adaptation strategies are therefore essential for practical clinical natural language processing applications. This study proposes a parameter-efficient selective fine-tuning framework for adapting GPT-2 to clinical text classification tasks. Instead of updating the entire pretrained model, the majority of network parameters are frozen, and only the final Transformer block, the final layer normalization module, and a lightweight classification head are updated during training. This design substantially reduces the number of trainable parameters while preserving the contextual representation capabilities learned during pretraining. The proposed approach is evaluated using radiology reports from the MIMIC-IV-Note dataset with automatically derived CheXpert-style labels. Experiments on 50,000 radiology reports demonstrate that selective fine-tuning achieves approximately 91% classification accuracy while updating fewer than 6% of the model parameters. Comparative experiments with head-only training and full-model fine-tuning show that the proposed method provides a favorable balance between predictive performance and computational efficiency. These results indicate that selective fine-tuning offers an efficient and scalable framework for clinical text classification.

ARIES: A Scalable Multi-Agent Orchestration Framework for Real-Time Epidemiological Surveillance and Outbreak Monitoring

Global health surveillance is currently facing a challenge of Knowledge Gaps. While general-purpose AI has proliferated, it remains fundamentally unsuited for the high-stakes epidemiological domain due to chronic hallucinations and an inability to navigate specialized data silos. This paper introduces ARIES (Agentic Retrieval Intelligence for Epidemiological Surveillance), a specialized, autonomous multi-agent framework designed to move beyond static, disease-specific dashboards toward a dynamic intelligence ecosystem. Built on a hierarchical command structure, ARIES utilizes GPTs to orchestrate a scalable swarm of sub-agents capable of autonomously querying World Health Organization (WHO), Center for Disease Control and Prevention (CDC), and peer-reviewed research papers. By automating the extraction and logical synthesis of surveillance data, ARIES provides a specialized reasoning that identifies emergent threats and signal divergence in near real-time. This modular architecture proves that a task-specific agentic swarm can outperform generic models, offering a robust, extensible for next-generation outbreak response and global health intelligence.