Impact of 5 years of hepatitis C testing and treatment in the North East of England prisons.

Hepatitis C virus infection (HCV) is prevalent in prisons. Therefore, effective prison HCV services are critical for HCV elimination programmes. We aimed to evaluate the efficacy of a regional HCV prison testing and treatment programme. Between July 2017 and June 2022, data were collected prospectively on HCV test offer and uptake rates, HCV Antibody (HCV-Ab) and HCV-RNA positivity, treatment starts and outcomes for new inmates incarcerated in three prisons. Rates of HCV-Ab and RNA positivity at reception, incidence of new HCV infections and reinfection following treatment were determined. From a total of 39,652 receptions, 33,028 (83.3%) were offered HCV testing and 20,394 (61.7%) completed testing. Including all receptions, 24.5% of tests (n = 4995) were HCV-Ab positive and 8.4% of tests (n = 1713) were HCV-RNA positive. When considering the first test for each individual (median age 34 years; 88.1% male), 14.8% (n = 1869) and 7.2% (n = 905) were HCV-Ab and HCV-RNA positive, respectively. The incidence of new HCV-Ab and RNA positivity was 5.1 and 3.3 per 100 person-years, respectively. Of 1145 HCV viraemic individuals, 18 died within 6 months and 150 were rapidly transferred out of area, leaving 977 individuals with outcomes. Of these, 835 (85.5%) received antivirals and 47 spontaneously cleared the infection, leaving 95 (9.7%) untreated. 607 (72.7%) achieved SVR. 95 patients had reinfection post-treatment (rate 10.1 cases per 100 person-years). Testing for HCV has increased in our prisons and the majority with viraemia are initiated on antiviral treatment. Reassuringly, a significant fall in frequency of HCV-RNA positivity at prison reception was observed suggesting progress towards HCV elimination.

Adaptation of an NLP system to a new healthcare environment to identify social determinants of health.

Social determinants of health (SDoH) are increasingly important factors for population health, healthcare outcomes, and care delivery. However, many of these factors are not reliably captured within structured electronic health record (EHR) data. In this work, we evaluated and adapted a previously published NLP tool to include additional social risk factors for deployment at Vanderbilt University Medical Center in an Acute Myocardial Infarction cohort. We developed a transformation of the SDoH outputs of the tool into the OMOP common data model (CDM) for re-use across many potential use cases, yielding performance measures across 8 SDoH classes of precision 0.83 recall 0.74 and F-measure of 0.78.

Examining the association of social risk with heart failure readmission in the Veterans Health Administration.

BACKGROUND: Previous research has found that social risk factors are associated with an increased risk of 30-day readmission. We aimed to assess the association of 5 social risk factors (living alone, lack of social support, marginal housing, substance abuse, and low income) with 30-day Heart Failure (HF) hospital readmissions within the Veterans Health Affairs (VA) and the impact of their inclusion on hospital readmission model performance. METHODS: We performed a retrospective cohort study using chart review and VA and Centers for Medicare and Medicaid Services (CMS) administrative data from a random sample of 1,500 elderly (≥ 65 years) Veterans hospitalized for HF in 2012. Using logistic regression, we examined whether any of the social risk factors were associated with 30-day readmission after adjusting for age alone and clinical variables used by CMS in its 30-day risk stratified readmission model. The impact of these five social risk factors on readmission model performance was assessed by comparing c-statistics, likelihood ratio tests, and the Hosmer-Lemeshow goodness-of-fit statistic. RESULTS: The prevalence varied among the 5 risk factors; low income (47 % vs. 47 %), lives alone (18 % vs. 19 %), substance abuse (14 % vs. 16 %), lacks social support (2 % vs. <1 %), and marginal housing (< 1 % vs. 3 %) among readmitted and non-readmitted patients, respectively. Controlling for clinical factors contained in CMS readmission models, a lack of social support was found to be associated with an increased risk of 30-day readmission (OR 4.8, 95 %CI 1.35-17.88), while marginal housing was noted to decrease readmission risk (OR 0.21, 95 %CI 0.03-0.87). Living alone (OR: 0.9, 95 %CI 0.64-1.26), substance abuse (OR 0.91, 95 %CI 0.67-1.22), and having low income (OR 1.01, 95 %CI 0.77-1.31) had no association with HF readmissions. Adding the five social risk factors to a CMS-based model (age and comorbid conditions; c-statistic 0.62) did not improve model performance (c-statistic: 0.62). CONCLUSIONS: While a lack of social support was associated with 30-day readmission in the VA, its prevalence was low. Moreover, the inclusion of some social risk factors did not improve readmission model performance. In an integrated healthcare system like the VA, social risk factors may have a limited effect on 30-day readmission outcomes.

Automatic Extraction of Skin and Soft Tissue Infection Status from Clinical Notes.

The reliable identification of skin and soft tissue infections (SSTIs) from electronic health records is important for a number of applications, including quality improvement, clinical guideline construction, and epidemiological analysis. However, in the United States, types of SSTIs (e.g. is the infection purulent or non-purulent?) are not captured reliably in structured clinical data. With this work, we trained and evaluated a rule-based clinical natural language processing system using 6,576 manually annotated clinical notes derived from the United States Veterans Health Administration (VA) with the goal of automatically extracting and classifying SSTI subtypes from clinical notes. The trained system achieved mention- and document-level performance metrics of the range 0.39 to 0.80 for mention level classification and 0.49 to 0.98 for document level classification.

Identifying clinical phenotypes of frontotemporal dementia in post-9/11 era veterans using natural language processing.

Introduction: Frontotemporal dementia (FTD) encompasses a clinically and pathologically diverse group of neurodegenerative disorders, yet little work has quantified the unique phenotypic clinical presentations of FTD among post-9/11 era veterans. To identify phenotypes of FTD using natural language processing (NLP) aided medical chart reviews of post-9/11 era U.S. military Veterans diagnosed with FTD in Veterans Health Administration care. Methods: A medical record chart review of clinician/provider notes was conducted using a Natural Language Processing (NLP) tool, which extracted features related to cognitive dysfunction. NLP features were further organized into seven Research Domain Criteria Initiative (RDoC) domains, which were clustered to identify distinct phenotypes. Results: Veterans with FTD were more likely to have notes that reflected the RDoC domains, with cognitive and positive valence domains showing the greatest difference across groups. Clustering of domains identified three symptom phenotypes agnostic to time of an individual having FTD, categorized as Low (16.4%), Moderate (69.2%), and High (14.5%) distress. Comparison across distress groups showed significant differences in physical and psychological characteristics, particularly prior history of head injury, insomnia, cardiac issues, anxiety, and alcohol misuse. The clustering result within the FTD group demonstrated a phenotype variant that exhibited a combination of language and behavioral symptoms. This phenotype presented with manifestations indicative of both language-related impairments and behavioral changes, showcasing the coexistence of features from both domains within the same individual. Discussion: This study suggests FTD also presents across a continuum of severity and symptom distress, both within and across variants. The intensity of distress evident in clinical notes tends to cluster with more co-occurring conditions. This examination of phenotypic heterogeneity in clinical notes indicates that sensitivity to FTD diagnosis may be correlated to overall symptom distress, and future work incorporating NLP and phenotyping may help promote strategies for early detection of FTD.

Development and optimisation of a reception testing protocol designed to eliminate HCV in the UK prison population.

Background & Aims: Micro-elimination of hepatitis C virus (HCV) in high-risk populations is a feasible approach towards achieving the World Health Organization's targets for viral hepatitis elimination by 2030. Prisons represent an area of high HCV prevalence and so initiatives that improve testing and treatment of residents are needed to eliminate HCV from prisons. This initiative aimed to improve the HCV screening and treatment rates of new residents arriving at prisons in England. Methods: A rapid test and treat pathway was developed and implemented in 47 prisons in England between May 2019 and October 2021 as a healthcare service improvement initiative. Prison healthcare staff performed opt-out HCV testing for all new residents at each prison within 7 days of arrival, and those who were positive for HCV RNA were offered treatment with direct-acting antivirals (DAAs). The Hepatitis C Trust provided peer support for all residents on treatment and those who were released into the community. Results: Of 107,260 new arrivals, 98,882 (92.2%) were offered HCV antibody testing, 63,137 (63.9%) were tested and 1,848 were treated. Testing rates increased from 53.7% in Year 1 to 86.0% in Year 3. Between May 2020 and October 2021, 40,727 residents were tested, 2,286 residents were positive for HCV antibodies and 940 residents were HCV RNA positive, giving an antibody prevalence of 5.6% and an RNA prevalence of 2.3%. A total of 921 residents were referred for treatment and 915 initiated DAA treatment (97.3% of whom were HCV RNA positive). Conclusions: This initiative showed that an opt-out HCV test and treat initiative in prison receptions is feasible and can be adapted to the needs of individual prisons as a viable way to achieve HCV micro-elimination. Impact and implications: Prisons represent an area of high HCV prevalence and so initiatives that improve testing and treatment of residents are needed to eliminate HCV from prisons. The reception testing protocol improved HCV screening in new arrivals across 47 prisons in England and could be a viable way for countries to achieve HCV micro-elimination in their prison systems. The reception testing protocol presented here can be adapted to the individual needs of prisons, globally, to improve HCV screening and treatment in this setting.

Natural Language Processing to identify pneumonia from radiology reports.

PURPOSE: This study aimed to develop Natural Language Processing (NLP) approaches to supplement manual outcome validation, specifically to validate pneumonia cases from chest radiograph reports. METHODS: We trained one NLP system, ONYX, using radiograph reports from children and adults that were previously manually reviewed. We then assessed its validity on a test set of 5000 reports. We aimed to substantially decrease manual review, not replace it entirely, and so, we classified reports as follows: (1) consistent with pneumonia; (2) inconsistent with pneumonia; or (3) requiring manual review because of complex features. We developed processes tailored either to optimize accuracy or to minimize manual review. Using logistic regression, we jointly modeled sensitivity and specificity of ONYX in relation to patient age, comorbidity, and care setting. We estimated positive and negative predictive value (PPV and NPV) assuming pneumonia prevalence in the source data. RESULTS: Tailored for accuracy, ONYX identified 25% of reports as requiring manual review (34% of true pneumonias and 18% of non-pneumonias). For the remainder, ONYX's sensitivity was 92% (95% CI 90-93%), specificity 87% (86-88%), PPV 74% (72-76%), and NPV 96% (96-97%). Tailored to minimize manual review, ONYX classified 12% as needing manual review. For the remainder, ONYX had sensitivity 75% (72-77%), specificity 95% (94-96%), PPV 86% (83-88%), and NPV 91% (90-91%). CONCLUSIONS: For pneumonia validation, ONYX can replace almost 90% of manual review while maintaining low to moderate misclassification rates. It can be tailored for different outcomes and study needs and thus warrants exploration in other settings.

Chronic hepatitis C elimination prison initiative: HCV-intensive test and treat, a whole prisoner population HCV test-and-treat program in England.

Background and Aim: Prison residents are at high risk for hepatitis C virus (HCV) infection. HCV test-and-treat initiatives within prisons provide an opportunity to engage with prison residents and achieve HCV micro-elimination. The aim of the prison HCV-intensive test and treat initiative was to screen over 95% of all prison residents for HCV infection within a defined number of days determined by the size of the prison population and to initiate treatment within 7-14 days of a positive HCV RNA diagnosis. Methods: An HCV-intensive test and treat toolkit was developed based on learnings from pilot HCV-intensive test and treat events. From January 2020 to September 2021, 13 HCV-intensive test and treat events took place at prisons in England selected based on high levels of reception blood-borne virus testing and good access to peers from The Hepatitis C Trust. Results: Among a total of 8487 residents, 8139 (95.9%) underwent testing for HCV. Across the 13 prisons included, HCV antibody and RNA prevalence was 8.2% and 1.5%, respectively. The treatment initiation rate among HCV RNA-positive individuals (n = 124) was 79.0%. Conclusion: The HCV-intensive test and treat initiative presented here provides a feasible and rapid test-and-treat process to achieve HCV elimination within individual prisons. The HCV-intensive test and treat toolkit can be adapted for rapid HCV testing and treatment events at other prisons in the United Kingdom and worldwide.

Examining the Interfacility Variation of Social Determinants of Health in the Veterans Health Administration.

INTRODUCTION: Recently, numerous studies have linked social determinants of health (SDoH) with clinical outcomes. While this association is well known, the interfacility variability of these risk favors within the Veterans Health Administration (VHA) is not known. Such information could be useful to the VHA for resource and funding allocation. The aim of this study is to explore the interfacility variability of 5 SDoH within the VHA. METHODS: In a cohort of patients (aged ≥ 65 years) hospitalized at VHA acute care facilities with either acute myocardial infarction (AMI), heart failure (HF), or pneumonia in 2012, we assessed (1) the proportion of patients with any of the following five documented SDoH: lives alone, marginal housing, alcohol use disorder, substance use disorder, and use of substance use services, using administrative diagnosis codes and clinic stop codes; and (2) the documented facility-level variability of these SDoH. To examine whether variability was due to regional coding differences, we assessed the variation of living alone using a validated natural language processing (NLP) algorithm. RESULTS: The proportion of veterans admitted for AMI, HF, and pneumonia with SDoH was low. Across all 3 conditions, lives alone was the most common SDoH (2.2% [interquartile range (IQR), 0.7-4.7]), followed by substance use disorder (1.3% [IQR, 0.5-2.1]), and use of substance use services (1.2% [IQR, 0.6-1.8]). Using NLP, the proportion of hospitalized veterans with lives alone was higher for HF (14.4% vs 2.0%, P < .01), pneumonia (11% vs 1.9%, P < .01), and AMI (10.2% vs 1.4%, P < .01) compared with International Classification of Diseases, Ninth Edition codes. Interfacility variability was noted with both administrative and NLP extraction methods. CONCLUSIONS: The presence of SDoH in administrative data among patients hospitalized for common medical issues is low and variable across VHA facilities. Significant facility-level variation of 5 SDoH was present regardless of extraction method.

Moonstone: a novel natural language processing system for inferring social risk from clinical narratives.

BACKGROUND: Social risk factors are important dimensions of health and are linked to access to care, quality of life, health outcomes and life expectancy. However, in the Electronic Health Record, data related to many social risk factors are primarily recorded in free-text clinical notes, rather than as more readily computable structured data, and hence cannot currently be easily incorporated into automated assessments of health. In this paper, we present Moonstone, a new, highly configurable rule-based clinical natural language processing system designed to automatically extract information that requires inferencing from clinical notes. Our initial use case for the tool is focused on the automatic extraction of social risk factor information - in this case, housing situation, living alone, and social support - from clinical notes. Nursing notes, social work notes, emergency room physician notes, primary care notes, hospital admission notes, and discharge summaries, all derived from the Veterans Health Administration, were used for algorithm development and evaluation. RESULTS: An evaluation of Moonstone demonstrated that the system is highly accurate in extracting and classifying the three variables of interest (housing situation, living alone, and social support). The system achieved positive predictive value (i.e. precision) scores ranging from 0.66 (homeless/marginally housed) to 0.98 (lives at home/not homeless), accuracy scores ranging from 0.63 (lives in facility) to 0.95 (lives alone), and sensitivity (i.e. recall) scores ranging from 0.75 (lives in facility) to 0.97 (lives alone). CONCLUSIONS: The Moonstone system is - to the best of our knowledge - the first freely available, open source natural language processing system designed to extract social risk factors from clinical text with good (lives in facility) to excellent (lives alone) performance. Although developed with the social risk factor identification task in mind, Moonstone provides a powerful tool to address a range of clinical natural language processing tasks, especially those tasks that require nuanced linguistic processing in conjunction with inference capabilities.

Identification of trauma patients at a level 1 trauma center utilizing natural language processing.

Trauma centers use trauma registries to collect information on injured patients they receive. The information is used for evaluation of care rendered, research, system and process improvement, and evaluation of injury prevention programs. Identification of patients qualifying for inclusion in registries can be problematic. Searching for those who meet inclusion criteria is often time consuming and inefficient. This has changed at a Salt Lake City trauma center, with an application designed to automate the process of identifying trauma patients. This program uses natural language processing and decision support technologies and is in daily use by the trauma team registry personnel.

Normalizing acronyms and abbreviations to aid patient understanding of clinical texts: ShARe/CLEF eHealth Challenge 2013, Task 2.

BACKGROUND: The ShARe/CLEF eHealth challenge lab aims to stimulate development of natural language processing and information retrieval technologies to aid patients in understanding their clinical reports. In clinical text, acronyms and abbreviations, also referenced as short forms, can be difficult for patients to understand. For one of three shared tasks in 2013 (Task 2), we generated a reference standard of clinical short forms normalized to the Unified Medical Language System. This reference standard can be used to improve patient understanding by linking to web sources with lay descriptions of annotated short forms or by substituting short forms with a more simplified, lay term. METHODS: In this study, we evaluate 1) accuracy of participating systems' normalizing short forms compared to a majority sense baseline approach, 2) performance of participants' systems for short forms with variable majority sense distributions, and 3) report the accuracy of participating systems' normalizing shared normalized concepts between the test set and the Consumer Health Vocabulary, a vocabulary of lay medical terms. RESULTS: The best systems submitted by the five participating teams performed with accuracies ranging from 43 to 72 %. A majority sense baseline approach achieved the second best performance. The performance of participating systems for normalizing short forms with two or more senses with low ambiguity (majority sense greater than 80 %) ranged from 52 to 78 % accuracy, with two or more senses with moderate ambiguity (majority sense between 50 and 80 %) ranged from 23 to 57 % accuracy, and with two or more senses with high ambiguity (majority sense less than 50 %) ranged from 2 to 45 % accuracy. With respect to the ShARe test set, 69 % of short form annotations contained common concept unique identifiers with the Consumer Health Vocabulary. For these 2594 possible annotations, the performance of participating systems ranged from 50 to 75 % accuracy. CONCLUSION: Short form normalization continues to be a challenging problem. Short form normalization systems perform with moderate to reasonable accuracies. The Consumer Health Vocabulary could enrich its knowledge base with missed concept unique identifiers from the ShARe test set to further support patient understanding of unfamiliar medical terms.

Classifying free-text triage chief complaints into syndromic categories with natural language processing.

OBJECTIVE: Develop and evaluate a natural language processing application for classifying chief complaints into syndromic categories for syndromic surveillance. INTRODUCTION: Much of the input data for artificial intelligence applications in the medical field are free-text patient medical records, including dictated medical reports and triage chief complaints. To be useful for automated systems, the free-text must be translated into encoded form. METHODS: We implemented a biosurveillance detection system from Pennsylvania to monitor the 2002 Winter Olympic Games. Because input data was in free-text format, we used a natural language processing text classifier to automatically classify free-text triage chief complaints into syndromic categories used by the biosurveillance system. The classifier was trained on 4700 chief complaints from Pennsylvania. We evaluated the ability of the classifier to classify free-text chief complaints into syndromic categories with a test set of 800 chief complaints from Utah. RESULTS: The classifier produced the following areas under the ROC curve: Constitutional = 0.95; Gastrointestinal = 0.97; Hemorrhagic = 0.99; Neurological = 0.96; Rash = 1.0; Respiratory = 0.99; Other = 0.96. Using information stored in the system's semantic model, we extracted from the Respiratory classifications lower respiratory complaints and lower respiratory complaints with fever with a precision of 0.97 and 0.96, respectively. CONCLUSION: Results suggest that a trainable natural language processing text classifier can accurately extract data from free-text chief complaints for biosurveillance.

Towards a Generalizable Time Expression Model for Temporal Reasoning in Clinical Notes.

Accurate temporal identification and normalization is imperative for many biomedical and clinical tasks such as generating timelines and identifying phenotypes. A major natural language processing challenge is developing and evaluating a generalizable temporal modeling approach that performs well across corpora and institutions. Our long-term goal is to create such a model. We initiate our work on reaching this goal by focusing on temporal expression (TIMEX3) identification. We present a systematic approach to 1) generalize existing solutions for automated TIMEX3 span detection, and 2) assess similarities and differences by various instantiations of TIMEX3 models applied on separate clinical corpora. When evaluated on the 2012 i2b2 and the 2015 Clinical TempEval challenge corpora, our conclusion is that our approach is successful - we achieve competitive results for automated classification, and we identify similarities and differences in TIMEX3 modeling that will be informative in the development of a simplified, general temporal model.

Evaluating the state of the art in disorder recognition and normalization of the clinical narrative.

OBJECTIVE: The ShARe/CLEF eHealth 2013 Evaluation Lab Task 1 was organized to evaluate the state of the art on the clinical text in (i) disorder mention identification/recognition based on Unified Medical Language System (UMLS) definition (Task 1a) and (ii) disorder mention normalization to an ontology (Task 1b). Such a community evaluation has not been previously executed. Task 1a included a total of 22 system submissions, and Task 1b included 17. Most of the systems employed a combination of rules and machine learners. MATERIALS AND METHODS: We used a subset of the Shared Annotated Resources (ShARe) corpus of annotated clinical text--199 clinical notes for training and 99 for testing (roughly 180 K words in total). We provided the community with the annotated gold standard training documents to build systems to identify and normalize disorder mentions. The systems were tested on a held-out gold standard test set to measure their performance. RESULTS: For Task 1a, the best-performing system achieved an F1 score of 0.75 (0.80 precision; 0.71 recall). For Task 1b, another system performed best with an accuracy of 0.59. DISCUSSION: Most of the participating systems used a hybrid approach by supplementing machine-learning algorithms with features generated by rules and gazetteers created from the training data and from external resources. CONCLUSIONS: The task of disorder normalization is more challenging than that of identification. The ShARe corpus is available to the community as a reference standard for future studies.

Methodology to develop and evaluate a semantic representation for NLP.

Natural language processing applications that extract information from text rely on semantic representations. The objective of this paper is to describe a methodology for creating a semantic representation for information that will be automatically extracted from textual clinical records. We illustrate two of the four steps of the methodology in this paper using the case study of encoding information from dictated dental exams: (1) develop an initial representation from a set of training documents and (2) iteratively evaluate and evolve the representation while developing annotation guidelines. Our approach for developing and evaluating a semantic representation is based on standard principles and approaches that are not dependent on any particular domain or type of semantic representation.