Automated qEEG Case Study Generation with Retrieval-Augmented AI and Clinical Data Integration

Abstract

Netanel Stern*

Quantitative electroencephalography (qEEG) offers objective biomarkers of brain function across neuropsychiatric conditions, but clinical EEG case reports are traditionally labor-intensive to produce. We describe a reproducible Python-based pipeline that automatically processes raw BrainVision EEG data, extracts spectral qEEG features, integrates patient clinical scores (e.g. Brief Psychiatric Rating Scale, BPRS), retrieves relevant literature via Europe PMC, and uses a retrievalaugmented large language model (RAG-LLM) to generate structured narrative case reports. EEG preprocessing (filtering, artifact removal, referencing) and feature computation (power in delta, theta, alpha, beta bands, etc.) are implemented using open-source MNE-Python tools in a BIDS-compliant framework [1,2] . Patient metadata such as age, diagnosis, and BPRS severity provide clinical context alongside EEG features (e.g. the known increase in theta power and theta/beta ratio in schizophrenia [3]. Key EEG findings are combined with dynamically retrieved evidence from Europe PMC – an openaccess repository of ~36 million biomedical abstracts and 5 million full-text articles– to ground the report in up-to-date knowledge. Using a RAG-LLM approach, the system formulates context-aware prompts that guide the model to cite recent studies and summarize findings [4]. For example, prior work has shown retrieval-augmented LLMs significantly improve accuracy in clinical question answering compared to base models, and in dedicated frameworks (e.g. EEG-MedRAG) unify EEG domain knowledge and patient data for diagnostic guidance [5,6]. Our pipeline yields a draft case report that mimics the structure of a clinician’s report: background, methods, results (EEG summary and clinical scores), and an evidence-supported discussion.

HTML PDF