Search

BackgroundPatient travel history can be crucial in evaluating evolving infectious disease events. Such information can be challenging to acquire in electronic health records, as it is often available only in unstructured text. ObjectiveThis study aims to assess the feasibility of annotating and automatically extracting travel history mentions from unstructured clinical documents in the Department of Veterans Affairs across disparate health care facilities and among millions of patients. Information about travel exposure augments existing surveillance applications for increased preparedness in responding quickly to public health threats. MethodsClinical documents related to arboviral disease were annotated following selection using a semiautomated bootstrapping process. Using annotated instances as training data, models were developed to extract from unstructured clinical text any mention of affirmed travel locations outside of the continental United States. Automated text processing models were evaluated, involving machine learning and neural language models for extraction accuracy. ResultsAmong 4584 annotated instances, 2659 (58%) contained an affirmed mention of travel history, while 347 (7.6%) were negated. Interannotator agreement resulted in a document-level Cohen kappa of 0.776. Automated text processing accuracy (F1 85.6, 95% CI 82.5-87.9) and computational burden were acceptable such that the system can provide a rapid screen for public health events. ConclusionsAutomated extraction of patient travel history from clinical documents is feasible for enhanced passive surveillance public health systems. Without such a system, it would usually be necessary to manually review charts to identify recent travel or lack of travel, use an electronic health record that enforces travel history documentation, or ignore this potential source of information altogether. The development of this tool was initially motivated by emergent arboviral diseases. More recently, this system was used in the early phases of response to COVID-19 in the United States, although its utility was limited to a relatively brief window due to the rapid domestic spread of the virus. Such systems may aid future efforts to prevent and contain the spread of infectious diseases.

Objective Study Setting and Design Data Sources and Analytic Sample Principal Findings Conclusions To evaluate the effect of enrolling in Supportive Services for Veteran Families (SSVF) on short‐ and long‐term housing outcomes among Veterans experiencing housing instability.We analyzed data from the Department of Veterans Affairs (VA) electronic health record (EHR) between October 2015 and December 2018 using the target trial emulation framework. Veterans were included in one or more trials if they were 18 years or older, had recent evidence of housing instability, had received care in VA for at least 1 year, and had never before enrolled in SSVF. Patients who enrolled in SSVF after meeting eligibility were assigned to the treatment group, while patients who did not enroll in SSVF were assigned to a control group. We extracted patients' housing outcomes from the EHR and modeled the probability of being unstably housed each day while accounting for confounders and irregular visit times.We extracted housing status and covariates from the VA Corporate Data Warehouse. Housing instability was ascertained using a combination of structured data elements and natural language processing.We identified 238,059 unique patients who met the eligibility criteria for one or more trials. The risk of housing instability decreased in both arms over the three years after initiating a trial but was lower among SSVF enrollees, with a risk difference of −12.9% (95% confidence band −14.6%, −11.2%) on Day 120 and an attenuated difference of −2.4% (−4.0%, −0.7%) on Day 1095.SSVF is one of the largest rapid rehousing and homelessness prevention programs in the nation. We found that SSVF improves housing outcomes over the three years following enrollment, but the effect reduces over time. These findings can inform policy and program design for improving housing outcomes for homeless‐experienced individuals. [ABSTRACT FROM AUTHOR]

Hospital quality-improvement initiatives that focus on diagnosis are challenging because clinicians who make the initial diagnosis are often not involved in deciding subsequent management and are unaware of the discharge diagnosis. A large Veterans Affairs study used natural language processing and diagnosis codes to determine the frequency of discordant diagnoses and to describe variables associated with discordance. Visual Abstract. Diagnostic Discordance, Uncertainty, and Treatment Ambiguity in Community-Acquired Pneumonia: Hospital quality-improvement initiatives that focus on diagnosis are challenging because clinicians who make the initial diagnosis are often not involved in deciding subsequent management and are unaware of the discharge diagnosis. A large Veterans Affairs study used natural language processing and diagnosis codes to determine the frequency of discordant diagnoses and to describe variables associated with discordance. Background: Evidence-based practice in community-acquired pneumonia often assumes an accurate initial diagnosis. Objective: To examine the evolution of pneumonia diagnoses among patients hospitalized from the emergency department (ED). Design: Retrospective nationwide cohort. Setting: 118 U.S. Veterans Affairs medical centers. Patients: Aged 18 years or older and hospitalized from the ED between 1 January 2015 and 31 January 2022. Measurements: Discordances between initial pneumonia diagnosis, discharge diagnosis, and radiographic diagnosis identified by natural language processing of clinician text, diagnostic coding, and antimicrobial treatment. Expressions of uncertainty in clinical notes, patient illness severity, treatments, and outcomes were compared. Results: Among 2   383   899 hospitalizations, 13.3% received an initial or discharge diagnosis and treatment of pneumonia: 9.1% received an initial diagnosis and 10.0% received a discharge diagnosis. Discordances between initial and discharge occurred in 57%. Among patients discharged with a pneumonia diagnosis and positive initial chest image, 33% lacked an initial diagnosis. Among patients diagnosed initially, 36% lacked a discharge diagnosis and 21% lacked positive initial chest imaging. Uncertainty was frequently expressed in clinical notes (58% in ED; 48% at discharge); 27% received diuretics, 36% received corticosteroids, and 10% received antibiotics, corticosteroids, and diuretics within 24 hours. Patients with discordant diagnoses had greater uncertainty and received more additional treatments, but only patients lacking an initial pneumonia diagnosis had higher 30-day mortality than concordant patients (14.4% [95% CI, 14.1% to 14.7%] vs. 10.6% [CI, 10.4% to 10.7%]). Patients with diagnostic discordance were more likely to present to high-complexity facilities with high ED patient load and inpatient census. Limitation: Retrospective analysis; did not examine causal relationships. Conclusion: More than half of all patients hospitalized and treated for pneumonia had discordant diagnoses from initial presentation to discharge. Treatments for other diagnoses and expressions of uncertainty were common. These findings highlight the need to recognize diagnostic uncertainty and treatment ambiguity in research and practice of pneumonia-related care. Primary Funding Source: The Gordon and Betty Moore Foundation. [ABSTRACT FROM AUTHOR]

Objectives: Age is important for prognosis in community‐onset pneumonia, but how it influences admission decisions in the emergency department (ED) is not well characterized. Using clinical data from the electronic health record in a national cohort, we examined pneumonia hospitalization patterns, variation, and relationships with mortality among older versus younger Veterans. Methods: In a retrospective cohort of patients ≥ 18 years presenting to EDs with a diagnosis of pneumonia at 118 VA Medical Centers January 1, 2006, to December 31, 2016, we compared observed, predicted, and residual hospitalization risk for Veterans < 70, 70–79, and ≥ 80 years of age using generalized estimating equations and machine learning models with 71 patient factors. We examined facility variation in residual hospitalization across facilities and explored whether facility differences in hospitalization risk correlated with differences in 30‐day mortality. Results: Among 297,498 encounters, 165,003 (55%) were for Veterans < 70 years, 61,076 (21%) 70–80, and 71,419 (24%) ≥ 80. Hospitalization rates were 52%, 67%, and 76%, respectively. After other patient factors were adjusting for, age 70–79 had an odds ratio (OR) of 1.39 (95% confidence interval [CI] 1.34–1.44) and ≥ 80 had an OR of 2.1 (95% CI 2.0–2.2) compared to age < 70. There was substantial variation in hospitalization across facilities among Veterans < 70 (<35% hospitalization at the lowest decile of facilities vs. > 66% at the highest decile) that was similar but with higher risk for patients 70–79 years (54% vs. 82%) and ≥ 80 years (59% vs. 85%) and remained after accounting for patient factors, with no consistently positive or negative associations with facility‐level 30‐day mortality. Conclusions: Older Veterans with community‐onset pneumonia experience high risk of hospitalization, with widespread facility variation that has no clear relationship to short‐term mortality. [ABSTRACT FROM AUTHOR]

Written clinical language embodies and reflects the clinician's mental models of disease. Prior to the COVID-19 pandemic, pneumonia was shifting away from concern for healthcare-associated pneumonia and toward recognition of heterogeneity of pathogens and host response. How these models are reflected in clinical language or whether they were impacted by the pandemic has not been studied. We aimed to assess changes in the language used to describe pneumonia following the COVID-19 pandemic. [ABSTRACT FROM AUTHOR]

Written clinical language embodies and reflects the clinician's mental models of disease. Prior to the COVID-19 pandemic, pneumonia was shifting away from concern for healthcare-associated pneumonia and toward recognition of heterogeneity of pathogens and host response. How these models are reflected in clinical language or whether they were impacted by the pandemic has not been studied. We aimed to assess changes in the language used to describe pneumonia following the COVID-19 pandemic.

The Electronic Health Record (EHR) contains information about social determinants of health (SDoH) such as homelessness. Much of this information is contained in clinical notes and can be extracted using natural language processing (NLP). This data can provide valuable information for researchers and policymakers studying long-term housing outcomes for individuals with a history of homelessness. However, studying homelessness longitudinally in the EHR is challenging due to irregular observation times. In this work, we applied an NLP system to extract housing status for a cohort of patients in the US Department of Veterans Affairs (VA) over a three-year period. We then applied inverse intensity weighting to adjust for the irregularity of observations, which was used generalized estimating equations to estimate the probability of unstable housing each day after entering a VA housing assistance program. Our methods generate unique insights into the long-term outcomes of individuals with a history of homelessness and demonstrate the potential for using EHR data for research and policymaking., (©2023 AMIA - All rights reserved.)

Despite impressive success of machine learning algorithms in clinical natural language processing (cNLP), rule-based approaches still have a prominent role. In this paper, we introduce medspaCy, an extensible, open-source cNLP library based on spaCy framework that allows flexible integration of rule-based and machine learning-based algorithms adapted to clinical text. MedspaCy includes a variety of components that meet common cNLP needs such as context analysis and mapping to standard terminologies. By utilizing spaCy's clear and easy-to-use conventions, medspaCy enables development of custom pipelines that integrate easily with other spaCy-based modules. Our toolkit includes several core components and facilitates rapid development of pipelines for clinical text., (©2021 AMIA - All rights reserved.)

Free-text reports in electronic health records (EHRs) contain medically significant information - signs, symptoms, findings, diagnoses - recorded by clinicians during patient encounters. These reports contain rich clinical information which can be leveraged for surveillance of disease and occurrence of adverse events. In order to gain meaningful knowledge from these text reports to support surveillance efforts, information must first be converted into a structured, computable format. Traditional methods rely on manual review of charts, which can be costly and inefficient. Natural language processing (NLP) methods offer an efficient, alternative approach to extracting the information and can achieve a similar level of accuracy. We developed an NLP system to automatically identify mentions of surgical site infections in radiology reports and classify reports containing evidence of surgical site infections leveraging these mentions. We evaluated our system using a reference standard of reports annotated by domain experts, administrative data generated for each patient encounter, and a machine learning-based approach.