Toward the Application of Natural Language Processing in Electronic Health Record Analysis for Taxonomy Development

Electronic health records (EHRs) are pivotal resources for nurse practice because they increase the timeliness and reliability of patient information at the point of care and support access by multiple healthcare providers and the individual patients themselves. However, it is widely recognized that data extraction from EHRs is challenging due to the variability in the language used in clinical care notes and the lack of standardized terminology across healthcare systems. The broad objective of this dissertation is to develop taxonomy-based classification models for nursing care by applying feature engineering approaches to EHRs that include nursing care of ostomy patients following ostomy surgery. The clinical significance of this work is to better understand practice-level differences and terminology differences in ostomy nursing care for acute-care settings. This dissertation addresses three specific aims. Aim 1 identified machine learning methodologies and their parameters for training natural language processing (NLP) models to extract non-coded data from EHRs. Aim 2 conducted a retrospective analysis on EHRs relevant to ostomy surgery to assess ostomy nursing care and patient outcomes in acute-care systems. AIM 3 developed a taxonomy-based risk model applicable to ostomy nursing care. This dissertation contributes to the growing field of Natural Language Process in healthcare by demonstrating how taxonomy-based classification models can be applied to extract and analyze nurse care data from EHRs. The findings show the critical role of data extraction and bridging the gap between clinical practice and machine learning, ultimately enhancing the usability of nursing-related information within EHR systems.