NLP Framework for Automated Symptom Severity Staging in Heart Failure and COPD Clinical Notes Using Ontology Integration: A Study Protocol

Background: Heart failure (HF) and chronic obstructive pulmonary disease (COPD) are among the leading causes of morbidity and mortality globally, with effective management heavily dependent on accurate severity staging using the New York Heart Association (NYHA) and Global Initiative for Chronic Obstructive Lung Disease (GOLD) classification systems. However, severity information is frequently embedded within unstructured clinical narratives rather than standardized Electronic Health Record (EHR) fields, limiting automated clinical decision support, disease surveillance, and retrospective healthcare analytics. Existing Natural Language Processing (NLP) approaches primarily rely on rule-based keyword extraction or supervised deep learning methods requiring large annotated corpora, which are often unavailable in many healthcare settings. Equally, most current systems inadequately integrate clinical ontologies for semantic reasoning and explainable classification, limiting interoperability and clinical applicability. Objective: This study aims to develop and evaluate an ontology-integrated NLP framework for automated extraction and severity staging of HF and COPD symptoms from de-identified clinical notes using NYHA and GOLD classification systems. Methods: The study will employ a Design Science Research (DSR) methodology to design, implement, and evaluate a hybrid NLP framework integrating rule-based extraction, SNOMED-CT ontology reasoning, and a Bidirectional Long Short-Term Memory with Conditional Random Field (Bi-LSTM-CRF) deep learning architecture for clinical sequence labeling. Approximately 1,000 de-identified clinical notes will be sampled proportionately from publicly available repositories including MIMIC-III/IV, eICU Collaborative Research Database, AmsterdamUMCdb, and MTSamples. Clinical text preprocessing will include tokenization, lemmatization, dependency parsing, abbreviation expansion, and negation detection. Ontology-guided semantic normalization will map extracted symptom entities to standardized SNOMED-CT concepts to support severity staging. Framework performance will be evaluated using precision, recall, F1-score, Cohens Kappa, sensitivity, specificity, positive predictive value, negative predictive value, confusion matrices, and correlation analyses against confirmed diagnoses and guideline-based severity classifications. Expected Outcomes: The proposed framework is expected to automate NYHA and GOLD severity staging across heterogeneous clinical note types without reliance on manually annotated severity labels. The ontology-integrated architecture is anticipated to improve semantic consistency, interpretability, and explainability of NLP outputs while enhancing EHR analytics, retrospective clinical audit, and AI-assisted clinical decision support. Conclusion: Findings from this study may provide a scalable and transferable framework for automated severity classification in data-rich but label-poor healthcare environments.