Search

Objectives: Structured data fields, including medication fields involving naloxone, are routinely used to identify opioid overdoses in emergency medical services (EMS) data; between January 2021 and March 2024, there were approximately 1.2 million instances of naloxone administration in the United States. To improve the accuracy of naloxone reporting, we developed methodology for identifying naloxone administration using both structured fields and unstructured patient care narratives for events documented by EMS., Methods: We randomly sampled 30,000 records from Kentucky's state-wide EMS database during 2019. We applied regular expressions (RegEx) capable of recognizing naloxone-related text patterns in each EMS patient's case narrative. Additionally, we applied natural language processing (NLP) techniques to extract important contextual factors such as route and dosage from these narratives. We manually reviewed cases where the structured data and unstructured data disagreed and developed an aggregate indicator for naloxone administration using either structured or unstructured data for each patient case., Results: There were 437 (1.45%) records with structured documentation of naloxone. Our RegEx method identified 547 naloxone administrations in the narratives; after manual review, we determined RegEx yielded acceptable false positives ( N  = 31, 5.6%), false negatives ( N  = 23, 4.2%) and performance (precision = 0.94, recall = 0.93). In total, 552 patients had naloxone administered after combining indicators from both structured fields and verified results from unstructured narratives. The NLP approach also identified 246 (47.4%) records that specified route of administration and 358 (69.0%) records with dosage delivered., Conclusions: An additional 115 (26.3%) patients receiving naloxone were identified by using unstructured case narratives compared to structured data. New surveillance methods that incorporate unstructured EMS narratives are critically needed to avoid substantial underestimation of naloxone utilization and enumeration of opioid overdoses.

Electronic health record (EHR) data are a rich and invaluable source of real-world clinical information, enabling detailed insights into patient populations, treatment outcomes, and healthcare practices. The availability of large volumes of EHR data are critical for advancing translational research and developing innovative technologies such as artificial intelligence. The Evolve to Next-Gen Accrual to Clinical Trials (ENACT) network, established in 2015 with funding from the National Center for Advancing Translational Sciences (NCATS), aims to accelerate translational research by democratizing access to EHR data for all Clinical and Translational Science Awards (CTSA) hub investigators. The present ENACT network provides access to structured EHR data, enabling cohort discovery and translational research across the network. However, a substantial amount of critical information is contained in clinical narratives, and natural language processing (NLP) is required for extracting this information to support research. To address this need, the ENACT NLP Working Group was formed to make NLP-derived clinical information accessible and queryable across the network. This article describes the implementation and deployment of NLP infrastructure across ENACT. First, we describe the formation and goals of the Working Group, the practices and logistics involved in implementation and deployment, and the specific NLP tools and technologies utilized. Then, we describe how we extended the ENACT ontology to standardize and query NLP-derived data, as well as how we conducted multisite evaluations of the NLP algorithms. Finally, we reflect on the experience and lessons learnt, which may be useful for other national data networks that are deploying NLP to unlock the potential of clinical text for research., Competing Interests: Competing Interests No competing interests were declared.

Introduction: The location of buprenorphine treatment providers in the United States is pivotal to the understanding of regional factors associated with prescription and uptake. We evaluated how distinct data sources of treatment providers and their associated locations contribute to the differences observed when measuring buprenorphine accessibility., Methods: We compared buprenorphine treatment provider data from the Drug Enforcement Administration (DEA) and data from the behavioral health treatment locator from the Substance Abuse and Mental Health Services Administration (SAMHSA) for July 2022. Both DEA and SAMHSA data, while similar in spirit, vary substantially in how and why each data set is collected. DEA registration was required by law, while SAMHSA data was an opt-in registry of provider-submitted details. Analyzing the underlying semantics of the data is important for understanding the contextual factors driving observable differences in analytical outputs. We measured accessibility using enhanced two-step floating catchment area (E2SFCA) analysis in three states participating in the HEALing Communities Study (Kentucky, Ohio, Massachusetts). Within communities, we compared decile rankings of accessibility per census tract using each data source. We linked prescribing data from Kentucky's prescription drug monitoring program (PDMP) to measure accessibility using providers prescribing buprenorphine. We explored the significance of localized rank exchanges using neighbor set local indicators of mobility association (LIMA)., Results: The number and rate of providers per capita differed substantially at the community level between data sources in the three states. These differences were less impactful in the spatial context of buprenorphine accessibility, which required both supply and demand in regions smaller than our intervention communities. Shifts did occur when measuring the intercommunity decile ranking of accessibility of census tracts, but LIMA results indicated that these rank exchanges were not significant., Conclusions: When analyzing accessibility within a community using E2SFCA analyses, either DEA or SAMHSA data sources are acceptable; linkage to Kentucky's PDMP demonstrated that SAMHSA provider data is equally suitable to PDMP data for research studies involving spatial relationships with providers while being both significantly easier to obtain and less sensitive. When analyzing treatment provider rates per capita, results may vary substantially across these different data sources. Therefore, context must be considered when choosing an appropriate data source to use., Competing Interests: Declaration of competing interest The authors have no conflicts of interest to declare., (Copyright © 2025 Elsevier Inc. All rights reserved.)