A Linguistic Analysis Examining the Impact of COVID-19 on Pneumonia Diagnosis and Disease Models.

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.

A deep learning approach for medication disposition and corresponding attributes extraction.

OBJECTIVE: This article summarizes our approach to extracting medication and corresponding attributes from clinical notes, which is the focus of track 1 of the 2022 National Natural Language Processing (NLP) Clinical Challenges(n2c2) shared task. METHODS: The dataset was prepared using Contextualized Medication Event Dataset (CMED), including 500 notes from 296 patients. Our system consisted of three components: medication named entity recognition (NER), event classification (EC), and context classification (CC). These three components were built using transformer models with slightly different architecture and input text engineering. A zero-shot learning solution for CC was also explored. RESULTS: Our best performance systems achieved micro-average F1 scores of 0.973, 0.911, and 0.909 for the NER, EC, and CC, respectively. CONCLUSION: In this study, we implemented a deep learning-based NLP system and demonstrated that our approach of (1) utilizing special tokens helps our model to distinguish multiple medications mentions in the same context; (2) aggregating multiple events of a single medication into multiple labels improves our model's performance.

Trends in Illness Severity, Hospitalization, and Mortality for Community-Onset Pneumonia at 118 US Veterans Affairs Medical Centers.

BACKGROUND: Deaths from pneumonia were decreasing globally prior to the COVID-19 pandemic, but it is unclear whether this was due to changes in patient populations, illness severity, diagnosis, hospitalization thresholds, or treatment. Using clinical data from the electronic health record among a national cohort of patients initially diagnosed with pneumonia, we examined temporal trends in severity of illness, hospitalization, and short- and long-term deaths. DESIGN: Retrospective cohort PARTICIPANTS: All patients >18 years presenting to emergency departments (EDs) at 118 VA Medical Centers between 1/1/2006 and 12/31/2016 with an initial clinical diagnosis of pneumonia and confirmed by chest imaging report. EXPOSURES: Year of encounter. MAIN MEASURES: Hospitalization and 30-day and 90-day mortality. Illness severity was defined as the probability of each outcome predicted by machine learning predictive models using age, sex, comorbidities, vital signs, and laboratory data from encounters during years 2006-2007, and similar models trained on encounters from years 2015 to 2016. We estimated the changes in hospitalizations and 30-day and 90-day mortality between the first and the last 2 years of the study period accounted for by illness severity using time covariate decompositions with model estimates. RESULTS: Among 196,899 encounters across the study period, hospitalization decreased from 71 to 63%, 30-day mortality 10 to 7%, 90-day mortality 16 to 12%, and 1-year mortality 29 to 24%. Comorbidity risk increased, but illness severity decreased. Decreases in illness severity accounted for 21-31% of the decrease in hospitalizations, and 45-47%, 32-24%, and 17-19% of the decrease in 30-day, 90-day, and 1-year mortality. Findings were similar among underrepresented patients and those with only hospital discharge diagnosis codes. CONCLUSIONS: Outcomes for community-onset pneumonia have improved across the VA healthcare system after accounting for illness severity, despite an increase in cases and comorbidity burden.

Analysis of a national response to a White House directive for ending veteran suicide.

OBJECTIVE: Analyze responses to a national request for information (RFI) to uncover gaps in policy, practice, and understanding of veteran suicide to inform federal research strategy. DATA SOURCE: An RFI with 21 open-ended questions generated from Presidential Executive Order #1386, administered nationally from July 3 to August 5, 2019. STUDY DESIGN: Semi-structured, open-ended responses analyzed using a collaborative qualitative and text-mining data process. DATA EXTRACTION METHODS: We aligned traditional qualitative methods with natural language processing (NLP) text-mining techniques to analyze 9040 open-ended question responses from 722 respondents to provide results within 3 months. Narrative inquiry and the medical explanatory model guided the data extraction and analytic process. RESULTS: Five major themes were identified: risk factors, risk assessment, prevention and intervention, barriers to care, and data/research. Individuals and organizations mentioned different concepts within the same themes. In responses about risk factors, individuals frequently mentioned generic terms like "illness" while organizations mentioned specific terms like "traumatic brain injury." Organizations and individuals described unique barriers to care and emphasized ways to integrate data and research to improve points of care. Organizations often identified lack of funding as barriers while individuals often identified key moments for prevention such as military transitions and ensuring care providers have military cultural understanding. CONCLUSIONS: This study provides an example of a rapid, adaptive analysis of a large body of qualitative, public response data about veteran suicide to support a federal strategy for an important public health topic. Combining qualitative and text-mining methods allowed a representation of voices and perspectives including the lived experiences of individuals who described stories of military transition, treatments that worked or did not, and the perspective of organizations treating veterans for suicide. The results supported the development of a national strategy to reduce suicide risks for veterans as well as civilians.

Development and evaluation of an interoperable natural language processing system for identifying pneumonia across clinical settings of care and institutions.

Objective: To evaluate the feasibility, accuracy, and interoperability of a natural language processing (NLP) system that extracts diagnostic assertions of pneumonia in different clinical notes and institutions. Materials and Methods: A rule-based NLP system was designed to identify assertions of pneumonia in 3 types of clinical notes from electronic health records (EHRs): emergency department notes, radiology reports, and discharge summaries. The lexicon and classification logic were tailored for each note type. The system was first developed and evaluated using annotated notes from the Department of Veterans Affairs (VA). Interoperability was assessed using data from the University of Utah (UU). Results: The NLP system was comprised of 782 rules and achieved moderate-to-high performance in all 3 note types in VA (precision/recall/f1: emergency = 88.1/86.0/87.1; radiology = 71.4/96.2/82.0; discharge = 88.3/93.0/90.1). When applied to UU data, performance was maintained in emergency and radiology but decreased in discharge summaries (emergency = 84.7/94.3/89.3; radiology = 79.7/100.0/87.9; discharge = 65.5/92.7/76.8). Customization with 34 additional rules increased performance for all note types (emergency = 89.3/94.3/91.7; radiology = 87.0/100.0/93.1; discharge = 75.0/95.1/83.4). Conclusion: NLP can be used to accurately identify the diagnosis of pneumonia across different clinical settings and institutions. A limited amount of customization to account for differences in lexicon, clinical definition of pneumonia, and EHR structure can achieve high accuracy without substantial modification.

Automated Travel History Extraction From Clinical Notes for Informing the Detection of Emergent Infectious Disease Events: Algorithm Development and Validation.

BACKGROUND: Patient 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. OBJECTIVE: This 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. METHODS: Clinical 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. RESULTS: Among 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. CONCLUSIONS: Automated 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.

Computerized Mortality Prediction for Community-acquired Pneumonia at 117 Veterans Affairs Medical Centers.

Rationale: Computerized severity assessment for community-acquired pneumonia could improve consistency and reduce clinician burden. Objectives: To develop and compare 30-day mortality-prediction models using electronic health record data, including a computerized score with all variables from the original Pneumonia Severity Index (PSI) except confusion and pleural effusion ("ePSI score") versus models with additional variables. Methods: Among adults with community-acquired pneumonia presenting to emergency departments at 117 Veterans Affairs Medical Centers between January 1, 2006, and December 31, 2016, we compared an ePSI score with 10 novel models employing logistic regression, spline, and machine learning methods using PSI variables, age, sex and 26 physiologic variables as well as all 69 PSI variables. Models were trained using encounters before January 1, 2015; tested on encounters during and after January 1, 2015; and compared using the areas under the receiver operating characteristic curve, confidence intervals, and patient event rates at a threshold PSI score of 970. Results: Among 297,498 encounters, 7% resulted in death within 30 days. When compared using the ePSI score (confidence interval [CI] for the area under the receiver operating characteristic curve, 0.77-0.78), performance increased with model complexity (CI for the logistic regression PSI model, 0.79-0.80; CI for the boosted decision-tree algorithm machine learning PSI model using the Extreme Gradient Boosting algorithm [mlPSI] with the 19 original PSI factors, 0.83-0.85) and the number of variables (CI for the logistic regression PSI model using all 69 variables, 0.84-085; CI for the mlPSI with all 69 variables, 0.86-0.87). Models limited to age, sex, and physiologic variables also demonstrated high performance (CI for the mlPSI with age, sex, and 26 physiologic factors, 0.84-0.85). At an ePSI score of 970 and a mortality-risk cutoff of <2.7%, the ePSI score identified 31% of all patients as being at "low risk"; the mlPSI with age, sex, and 26 physiologic factors identified 53% of all patients as being at low risk; and the mlPSI with all 69 variables identified 56% of all patients as being at low risk, with similar rates of mortality, hospitalization, and 7-day secondary hospitalization being determined. Conclusions: Computerized versions of the PSI accurately identified patients with pneumonia who were at low risk of death. More complex models classified more patients as being at low risk of death and as having similar adverse outcomes.

Launching into clinical space with medspaCy: a new clinical text processing toolkit in Python.

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.

Detecting Adverse Drug Events with Rapidly Trained Classification Models.

INTRODUCTION: Identifying occurrences of medication side effects and adverse drug events (ADEs) is an important and challenging task because they are frequently only mentioned in clinical narrative and are not formally reported. METHODS: We developed a natural language processing (NLP) system that aims to identify mentions of symptoms and drugs in clinical notes and label the relationship between the mentions as indications or ADEs. The system leverages an existing word embeddings model with induced word clusters for dimensionality reduction. It employs a conditional random field (CRF) model for named entity recognition (NER) and a random forest model for relation extraction (RE). RESULTS: Final performance of each model was evaluated separately and then combined on a manually annotated evaluation set. The micro-averaged F1 score was 80.9% for NER, 88.1% for RE, and 61.2% for the integrated systems. Outputs from our systems were submitted to the NLP Challenges for Detecting Medication and Adverse Drug Events from Electronic Health Records (MADE 1.0) competition (Yu et al. in http://bio-nlp.org/index.php/projects/39-nlp-challenges , 2018). System performance was evaluated in three tasks (NER, RE, and complete system) with multiple teams submitting output from their systems for each task. Our RE system placed first in Task 2 of the challenge and our integrated system achieved third place in Task 3. CONCLUSION: Adding to the growing number of publications that utilize NLP to detect occurrences of ADEs, our study illustrates the benefits of employing innovative feature engineering.