Search

IMPORTANCE: Carotid endarterectomy (CEA) among asymptomatic patients involves a trade-off between a higher short-term perioperative risk in exchange for a lower long-term risk of stroke. The clinical benefit observed in randomized clinical trials (RCTs) may not extend to real-world practice. OBJECTIVE: To examine whether early intervention (CEA) was superior to initial medical therapy in real-world practice in preventing fatal and nonfatal strokes among patients with asymptomatic carotid stenosis. DESIGN, SETTING, AND PARTICIPANTS: This comparative effectiveness study was conducted from August 28, 2018, to March 2, 2020, using the Corporate Data Warehouse, Suicide Data Repository, and other databases of the US Department of Veterans Affairs. Data analyzed were those of veterans of the US Armed Forces aged 65 years or older who received carotid imaging between January 1, 2005, and December 31, 2009. Patients without a carotid imaging report, those with carotid stenosis of less than 50% or hemodynamically insignificant stenosis, and those with a history of stroke or transient ischemic attack in the 6 months before index imaging were excluded. A cohort of patients who received initial medical therapy and a cohort of similar patients who received CEA were constructed and followed up for 5 years. The target trial method was used to compute weighted Kaplan-Meier curves and estimate the risk of fatal and nonfatal strokes in each cohort in the pragmatic sample across 5 years of follow-up. This analysis was repeated after restricting the sample to patients who met RCT inclusion criteria. Cumulative incidence functions for fatal and nonfatal strokes were estimated, accounting for nonstroke deaths as competing risks in both the pragmatic and RCT-like samples. EXPOSURES: Receipt of CEA vs initial medical therapy. MAIN OUTCOMES AND MEASURES: Fatal and nonfatal strokes. RESULTS: Of the total 5221 patients, 2712 (51.9%; mean [SD] age, 73.6 [6.0] years; 2678 men [98.8%]) received C

IMPORTANCE: As part of the Choosing Wisely campaign, primary care, surgery, and neurology societies have identified carotid imaging ordered for screening, preoperative evaluation, and syncope as frequently low value. OBJECTIVE: To determine the changes in overall and indication-specific rates of carotid imaging following Choosing Wisely recommendations. DESIGN, SETTING, AND PARTICIPANTS: This serial cross-sectional study compared annual rates of carotid imaging before Choosing Wisely recommendations (ie, 2007 to 2012) and after (ie, 2013 to 2016) among adults receiving care in the Veterans Health Administration (VHA) national health system. Data analysis was performed from April 10, 2019, to November 27, 2019. EXPOSURES: Release of the Choosing Wisely recommendations. MAIN OUTCOMES AND MEASURES: Annual rates of overall imaging, imaging ordered for stroke workup, imaging ordered for low-value indications (ie, screening owing to carotid bruit, preoperative evaluation, and syncope). Indications were identified using a text lexicon algorithm based on electronic health record review of a stratified random sample of 1000 free-text imaging orders. The subsequent performance of carotid procedures within 6 months after carotid imaging was assessed. RESULTS: Between 2007 and 2016, 809 071 carotid imaging examinations were identified (mean [SD] age of patients undergoing imaging, 69 [10] years; 776 632 [96%] men), of which 201 467 images (24.9%) were ordered for low-value indications (67 064 [8.2%] for carotid bruit, 25 032 [3.1%] for preoperative evaluation, and 109 400 [13.5%] for syncope), 257 369 (31.8%) for stroke workup, and 350 235 (43.3%) for other indications. Imaging for carotid bruits declined across the study period while there was no significant change in imaging for syncope or preoperative evaluation. Compared with the 6 years before, during the 4 years following Choosing Wisely recommendations, there was no change in the trend for syncope, a small decline in pre

BACKGROUND: Clinical Natural Language Processing (NLP) systems require a semantic schema comprised of domain-specific concepts, their lexical variants, and associated modifiers to accurately extract information from clinical texts. An NLP system leverages this schema to structure concepts and extract meaning from the free texts. In the clinical domain, creating a semantic schema typically requires input from both a domain expert, such as a clinician, and an NLP expert who will represent clinical concepts created from the clinician's domain expertise into a computable format usable by an NLP system. The goal of this work is to develop a web-based tool, Knowledge Author, that bridges the gap between the clinical domain expert and the NLP system development by facilitating the development of domain content represented in a semantic schema for extracting information from clinical free-text. RESULTS: Knowledge Author is a web-based, recommendation system that supports users in developing domain content necessary for clinical NLP applications. Knowledge Author's schematic model leverages a set of semantic types derived from the Secondary Use Clinical Element Models and the Common Type System to allow the user to quickly create and modify domain-related concepts. Features such as collaborative development and providing domain content suggestions through the mapping of concepts to the Unified Medical Language System Metathesaurus database further supports the domain content creation process. Two proof of concept studies were performed to evaluate the system's performance. The first study evaluated Knowledge Author's flexibility to create a broad range of concepts. A dataset of 115 concepts was created of which 87 (76 %) were able to be created using Knowledge Author. The second study evaluated the effectiveness of Knowledge Author's output in an NLP system by extracting concepts and associated modifiers representing a clinical element, carotid stenosis, from 34 clinical fre

BACKGROUND: The Simple Knowledge Organization System (SKOS) was introduced to the wider research community by a 2005 World Wide Web Consortium (W3C) working draft, and further developed and refined in a 2009 W3C recommendation. Since then, SKOS has become the de facto standard for representing and sharing thesauri, lexicons, vocabularies, taxonomies, and classification schemes. In this paper, we describe the development of a web-based, free, open-source SKOS editor built for the development, curation, and management of small to medium-sized lexicons for health-related Natural Language Processing (NLP). RESULTS: The web-based SKOS editor allows users to create, curate, version, manage, and visualise SKOS resources. We tested the system against five widely-used, publicly-available SKOS vocabularies of various sizes and found that the editor is suitable for the development and management of small to medium-size lexicons. Qualitative testing has focussed on using the editor to develop lexical resources to drive NLP applications in two domains. First, developing a lexicon to support an Electronic Health Record-based NLP system for the automatic identification of pneumonia symptoms. Second, creating a taxonomy of lexical cues associated with Diagnostic and Statistical Manual of Mental Disorders (DSM-5) diagnoses with the goal of facilitating the automatic identification of symptoms associated with depression from short, informal texts. CONCLUSIONS: The SKOS editor we have developed is - to the best of our knowledge - the first free, open-source, web-based, SKOS editor capable of creating, curating, versioning, managing, and visualising SKOS lexicons.

Extracting information from mental health records can be useful for large-scale clinical studies (e.g., to predict medication adherence or to understand medication effects) in this clinical specialty largely underserved by the Natural Language Processing (NLP) community. Vocabularies that contain medical terms for specific clinical use-cases, such as signs, symptoms, histories, social risk factors, are valuable resources for the development of NLP systems that aid clinicians in extracting information from text. Substance abuse is an important variable for many clinical use-cases, but, to our knowledge, there are no publicly available vocabularies that cover these types of terms. In this study, we apply and combine three methods for generating vocabularies related to substance abuse. We propose a simple and systematic method to generate highly relevant vocabularies and evaluate these vocabularies with respect to size and content, as well as coverage and relevance when applied to authentic psychiatric notes., QC 20211221

Background: Clinical Natural Language Processing (NLP) systems require a semantic schema comprised of domain-specific concepts, their lexical variants, and associated modifiers to accurately extract information from clinical texts. An NLP system leverages this schema to structure concepts and extract meaning from the free texts. In the clinical domain, creating a semantic schema typically requires input from both a domain expert, such as a clinician, and an NLP expert who will represent clinical concepts created from the clinician's domain expertise into a computable format usable by an NLP system. The goal of this work is to develop a web-based tool, Knowledge Author, that bridges the gap between the clinical domain expert and the NLP system development by facilitating the development of domain content represented in a semantic schema for extracting information from clinical free-text. Results: Knowledge Author is a web-based, recommendation system that supports users in developing domain content necessary for clinical NLP applications. Knowledge Author's schematic model leverages a set of semantic types derived from the Secondary Use Clinical Element Models and the Common Type System to allow the user to quickly create and modify domain-related concepts. Features such as collaborative development and providing domain content suggestions through the mapping of concepts to the Unified Medical Language System Metathesaurus database further supports the domain content creation process. Two proof of concept studies were performed to evaluate the system's performance. The first study evaluated Knowledge Author's flexibility to create a broad range of concepts. A dataset of 115 concepts was created of which 87 (76%) were able to be created using Knowledge Author. The second study evaluated the effectiveness of Knowledge Author's output in an NLP system by extracting concepts and associated modifiers representing a clinical element, carotid stenosis, from 34 clinical free

Background: Clinical Natural Language Processing (NLP) systems require a semantic schema comprised of domain-specific concepts, their lexical variants, and associated modifiers to accurately extract information from clinical texts. An NLP system leverages this schema to structure concepts and extract meaning from the free texts. In the clinical domain, creating a semantic schema typically requires input from both a domain expert, such as a clinician, and an NLP expert who will represent clinical concepts created from the clinician's domain expertise into a computable format usable by an NLP system. The goal of this work is to develop a web-based tool, Knowledge Author, that bridges the gap between the clinical domain expert and the NLP system development by facilitating the development of domain content represented in a semantic schema for extracting information from clinical free-text. Results: Knowledge Author is a web-based, recommendation system that supports users in developing domain content necessary for clinical NLP applications. Knowledge Author's schematic model leverages a set of semantic types derived from the Secondary Use Clinical Element Models and the Common Type System to allow the user to quickly create and modify domain-related concepts. Features such as collaborative development and providing domain content suggestions through the mapping of concepts to the Unified Medical Language System Metathesaurus database further supports the domain content creation process. Two proof of concept studies were performed to evaluate the system's performance. The first study evaluated Knowledge Author's flexibility to create a broad range of concepts. A dataset of 115 concepts was created of which 87 (76%) were able to be created using Knowledge Author. The second study evaluated the effectiveness of Knowledge Author's output in an NLP system by extracting concepts and associated modifiers representing a clinical element, carotid stenosis, from 34 clinical free

The Health Insurance Portability and Accountability Act (HIPAA) Safe Harbor method requires removal of 18 types of protected health information (PHI) from clinical documents to be considered "de-identified" prior to use for research purposes. Human review of PHI elements from a large corpus of clinical documents can be tedious and error-prone. Indeed, multiple annotators may be required to consistently redact information that represents each PHI class. Automated de-identification has the potential to improve annotation quality and reduce annotation time. For instance, using machine-assisted annotation by combining de-identification system outputs used as pre-annotations and an interactive annotation interface to provide annotators with PHI annotations for "curation" rather than manual annotation from "scratch" on raw clinical documents. In order to assess whether machine-assisted annotation improves the reliability and accuracy of the reference standard quality and reduces annotation effort, we conducted an annotation experiment. In this annotation study, we assessed the generalizability of the VA Consortium for Healthcare Informatics Research (CHIR) annotation schema and guidelines applied to a corpus of publicly available clinical documents called MTSamples. Specifically, our goals were to (1) characterize a heterogeneous corpus of clinical documents manually annotated for risk-ranked PHI and other annotation types (clinical eponyms and person relations), (2) evaluate how well annotators apply the CHIR schema to the heterogeneous corpus, (3) compare whether machine-assisted annotation (experiment) improves annotation quality and reduces annotation time compared to manual annotation (control), and (4) assess the change in quality of reference standard coverage with each added annotator's annotations.