Search

Background: Natural language processing (NLP) is increasingly being used to extract structured information from unstructured text to assist clinical decision-making and aid healthcare research. The availability of expert-annotated documents for the development and validation of NLP applications is limited. We created synthetic clinical documents to address this, and to validate the Extraction of Epilepsy Clinical Text version 2 (ExECTv2) NLP pipeline., Methods: We created 200 synthetic clinic letters based on hospital outpatient consultations with epilepsy specialists. The letters were double annotated by trained clinicians and researchers according to agreed guidelines. We used the annotation tool, Markup, with an epilepsy concept list based on the Unified Medical Language System ontology. All annotations were reviewed, and a gold standard set of annotations was agreed and used to validate the performance of ExECTv2., Results: The overall inter-annotator agreement (IAA) between the two sets of annotations produced a per item F1 score of 0.73. Validating ExECTv2 using the gold standard gave an overall F1 score of 0.87 per item, and 0.90 per letter., Conclusion: The synthetic letters, annotations, and annotation guidelines have been made freely available. To our knowledge, this is the first publicly available set of annotated epilepsy clinic letters and guidelines that can be used for NLP researchers with minimum epilepsy knowledge. The IAA results show that clinical text annotation tasks are difficult and require a gold standard to be arranged by researcher consensus. The results for ExECTv2, our automated epilepsy NLP pipeline, extracted detailed epilepsy information from unstructured epilepsy letters with more accuracy than human annotators, further confirming the utility of NLP for clinical and research applications., (© 2024. The Author(s).)

Objective: People with epilepsy (PWE) may be at an increased risk of severe COVID-19. It is important to characterize this risk to inform PWE and for future health and care planning. We assessed whether PWE were at higher risk of being hospitalized with, or dying from, COVID-19., Methods: We performed a retrospective cohort study using linked, population-scale, anonymized electronic health records from the SAIL (Secure Anonymised Information Linkage) databank. This includes hospital admission and demographic data for the complete Welsh population (3.1 million) and primary care records for 86% of the population. We identified 27 279 PWE living in Wales during the study period (March 1, 2020 to June 30, 2021). Controls were identified using exact 5:1 matching (sex, age, and socioeconomic status). We defined COVID-19 deaths as having International Classification of Diseases, 10th Revision (ICD-10) codes for COVID-19 on death certificates or occurring within 28 days of a positive SARS-CoV-2 polymerase chain reaction (PCR) test. COVID-19 hospitalizations were defined as having a COVID-19 ICD-10 code for the reason for admission or occurring within 28 days of a positive SARS-CoV-2 PCR test. We recorded COVID-19 vaccinations and comorbidities known to increase the risk of COVID-19 hospitalization and death. We used Cox proportional hazard models to calculate hazard ratios., Results: There were 158 (.58%) COVID-19 deaths and 933 (3.4%) COVID-19 hospitalizations in PWE, and 370 (.27%) deaths and 1871 (1.4%) hospitalizations in controls. Hazard ratios for COVID-19 death and hospitalization in PWE compared to controls were 2.15 (95% confidence interval [CI] = 1.78-2.59) and 2.15 (95% CI = 1.94-2.37), respectively. Adjusted hazard ratios (adjusted for comorbidities) for death and hospitalization were 1.32 (95% CI = 1.08-1.62) and 1.60 (95% CI = 1.44-1.78)., Significance: PWE are at increased risk of being hospitalized with, and dying from, COVID-19 when compared to age-, sex-, and deprivation-matched controls, even when adjusting for comorbidities. This may have implications for prioritizing future COVID-19 treatments and vaccinations for PWE., (© 2024 The Authors. Epilepsia published by Wiley Periodicals LLC on behalf of International League Against Epilepsy.)

Objective: This study was undertaken to characterize changes in health care utilization and mortality for people with epilepsy (PWE) during the COVID-19 pandemic., Methods: We performed a retrospective study using linked, individual-level, population-scale anonymized health data from the Secure Anonymised Information Linkage databank. We identified PWE living in Wales during the study "pandemic period" (January 1, 2020-June 30, 2021) and during a "prepandemic" period (January 1, 2016-December 31, 2019). We compared prepandemic health care utilization, status epilepticus, and mortality rates with corresponding pandemic rates for PWE and people without epilepsy (PWOE). We performed subgroup analyses on children (<18 years old), older people (>65 years old), those with intellectual disability, and those living in the most deprived areas. We used Poisson models to calculate adjusted rate ratios (RRs)., Results: We identified 27 279 PWE who had significantly higher rates of hospital (50.3 visits/1000 patient months), emergency department (55.7), and outpatient attendance (172.4) when compared to PWOE (corresponding figures: 25.7, 25.2, and 87.0) in the prepandemic period. Hospital and epilepsy-related hospital admissions, and emergency department and outpatient attendances all reduced significantly for PWE (and all subgroups) during the pandemic period. RRs [95% confidence intervals (CIs)] for pandemic versus prepandemic periods were .70 [.69-.72], .77 [.73-.81], .78 [.77-.79], and .80 [.79-.81]. The corresponding rates also reduced for PWOE. New epilepsy diagnosis rates decreased during the pandemic compared with the prepandemic period (2.3/100 000/month cf. 3.1/100 000/month, RR = .73, 95% CI = .68-.78). Both all-cause deaths and deaths with epilepsy recorded on the death certificate increased for PWE during the pandemic (RR = 1.07, 95% CI = .997-1.145 and RR = 2.44, 95% CI = 2.12-2.81). When removing COVID deaths, RRs were .88 (95% CI = .81-.95) and 1.29 (95% CI = 1.08-1.53). Status epilepticus rates did not change significantly during the pandemic (RR = .95, 95% CI = .78-1.15)., Significance: All-cause non-COVID deaths did not increase but non-COVID deaths associated with epilepsy did increase for PWE during the COVID-19 pandemic. The longer term effects of the decrease in new epilepsy diagnoses and health care utilization and increase in deaths associated with epilepsy need further research., (© 2024 The Authors. Epilepsia published by Wiley Periodicals LLC on behalf of International League Against Epilepsy.)

Background: Cancer multidisciplinary team (MDT) meetings are under intense pressure to reform given the rapidly rising incidence of cancer and national mandates for protocolized streaming of cases. The aim of this study was to validate a natural language processing (NLP)-based web platform to automate evidence-based MDT decisions for skin cancer with basal cell carcinoma as a use case., Methods: A novel and validated NLP information extraction model was used to extract perioperative tumour and surgical factors from histopathology reports. A web application with a bespoke application programming interface used data from this model to provide an automated clinical decision support system, mapped to national guidelines and generating a patient letter to communicate ongoing management. Performance was assessed against retrospectively derived recommendations by two independent and blinded expert clinicians., Results: There were 893 patients (1045 lesions) used to internally validate the model. High accuracy was observed when compared against human predictions, with an overall value of 0.92. Across all classifiers the virtual skin MDT was highly specific (0.96), while sensitivity was lower (0.72)., Conclusion: This study demonstrates the feasibility of a fully automated, virtual, web-based service model to host the skin MDT with good system performance. This platform could be used to support clinical decision-making during MDTs as 'human in the loop' approach to aid protocolized streaming. Future prospective studies are needed to validate the model in tumour types where guidelines are more complex., (© The Author(s) 2024. Published by Oxford University Press on behalf of BJS Foundation Ltd.)

Introduction: Data supporting the current British Association of Dermatologists guidelines for the management of basal cell carcinoma (BCC) are based on historic studies and do not consider the updated Royal College of Pathologists (RCPath) histological reporting standards. The aim of this study was to use natural language processing (NLP)-derived data and undertake a multivariate analysis with updated RCPath standards, providing a contemporary update on the excision margins required to achieve histological clearance in BCC., Methods: A validated NLP information extraction model was used to perform a rapid multi-centre, pan-specialty, consecutive retrospective analysis of BCCs, managed with surgical excision using a pre-determined clinical margin, over a 17-year period (2004-2021) at Swansea Bay University Health Board. Logistic regression assessed the relationship between the peripheral and deep margins and histological clearance., Results: We ran our NLP algorithm on 34,955 BCCs. Out of the 1447 BCCs that met the inclusion criteria, the peripheral margin clearance was not influenced by the BCC risk level (p = 0.670). A clinical peripheral margin of 6 mm achieved a 95% histological clearance rate (95% confidence interval [CI], 0.93-0.98). Tumour thickness inversely affected deep-margin histological clearance (OR 0.720, 95% CI, 0.525-0.991, p < 0.05). Depth level 2 had a 97% probability of achieving deep-margin histological clearance across all tumour thicknesses., Conclusion: Updated RCPath reporting standards minimally impact the peripheral margin histological clearance in BCC. Larger clinical peripheral margins than those indicated by current guidelines may be necessary to achieve excision rates of ≥95%. These findings emphasise the need for continuous reassessment of clinical standards to enhance patient care., Competing Interests: Declaration of Competing Interest None., (Copyright © 2023. Published by Elsevier Ltd.)

Objective: This study was undertaken to develop a novel pathway linking genetic data with routinely collected data for people with epilepsy, and to analyze the influence of rare, deleterious genetic variants on epilepsy outcomes., Methods: We linked whole-exome sequencing (WES) data with routinely collected primary and secondary care data and natural language processing (NLP)-derived seizure frequency information for people with epilepsy within the Secure Anonymised Information Linkage Databank. The study participants were adults who had consented to participate in the Swansea Neurology Biobank, Wales, between 2016 and 2018. DNA sequencing was carried out as part of the Epi25 collaboration. For each individual, we calculated the total number and cumulative burden of rare and predicted deleterious genetic variants and the total of rare and deleterious variants in epilepsy and drug metabolism genes. We compared these measures with the following outcomes: (1) no unscheduled hospital admissions versus unscheduled admissions for epilepsy, (2) antiseizure medication (ASM) monotherapy versus polytherapy, and (3) at least 1 year of seizure freedom versus <1 year of seizure freedom., Results: We linked genetic data for 107 individuals with epilepsy (52% female) to electronic health records. Twenty-six percent had unscheduled hospital admissions, and 70% were prescribed ASM polytherapy. Seizure frequency information was linked for 100 individuals, and 10 were seizure-free. There was no significant difference between the outcome groups in terms of the exome-wide and gene-based burden of rare and deleterious genetic variants., Significance: We successfully uploaded, annotated, and linked genetic sequence data and NLP-derived seizure frequency data to anonymized health care records in this proof-of-concept study. We did not detect a genetic influence on real-world epilepsy outcomes, but our study was limited by a small sample size. Future studies will require larger (WES) data to establish genetic variant contribution to epilepsy outcomes., (© 2023 The Authors. Epilepsia published by Wiley Periodicals LLC on behalf of International League Against Epilepsy.)

Introduction: Routinely collected healthcare data are a powerful research resource, but often lack detailed disease-specific information that is collected in clinical free text such as histopathology reports. We aim to use natural Language Processing (NLP) techniques to extract detailed clinical and pathological information from histopathology reports to enrich routinely collected data., Methods: We used the general architecture for text engineering (GATE) framework to build an NLP information extraction system using rule-based techniques. During validation, we deployed our rule-based NLP pipeline on 200 previously unseen, de-identified and pseudonymised basal cell carcinoma (BCC) histopathological reports from Swansea Bay University Health Board, Wales, UK. The results of our algorithm were compared with gold standard human annotation by two independent and blinded expert clinicians involved in skin cancer care., Results: We identified 11,224 items of information with a mean precision, recall, and F1 score of 86.0% (95% CI: 75.1-96.9), 84.2% (95% CI: 72.8-96.1), and 84.5% (95% CI: 73.0-95.1), respectively. The difference between clinician annotator F1 scores was 7.9% in comparison with 15.5% between the NLP pipeline and the gold standard corpus. Cohen's Kappa score on annotated tokens was 0.85., Conclusion: Using an NLP rule-based approach for named entity recognition in BCC, we have been able to develop and validate a pipeline with a potential application in improving the quality of cancer registry data, supporting service planning, and enhancing the quality of routinely collected data for research., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (© 2022 Ali, Strafford, Dobbs, Fonferko-Shadrach, Lacey, Pickrell, Hutchings and Whitaker.)

Across various domains, such as health and social care, law, news, and social media, there are increasing quantities of unstructured texts being produced. These potential data sources often contain rich information that could be used for domain-specific and research purposes. However, the unstructured nature of free-text data poses a significant challenge for its utilisation due to the necessity of substantial manual intervention from domain-experts to label embedded information. Annotation tools can assist with this process by providing functionality that enables the accurate capture and transformation of unstructured texts into structured annotations, which can be used individually, or as part of larger Natural Language Processing (NLP) pipelines. We present Markup (https://www.getmarkup.com/) an open-source, web-based annotation tool that is undergoing continued development for use across all domains. Markup incorporates NLP and Active Learning (AL) technologies to enable rapid and accurate annotation using custom user configurations, predictive annotation suggestions, and automated mapping suggestions to both domain-specific ontologies, such as the Unified Medical Language System (UMLS), and custom, user-defined ontologies. We demonstrate a real-world use case of how Markup has been used in a healthcare setting to annotate structured information from unstructured clinic letters, where captured annotations were used to build and test NLP applications., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Dobbie, Strafford, Pickrell, Fonferko-Shadrach, Jones, Akbari, Thompson and Lacey.)

Objective: To characterize trends in incidence, prevalence, and health care outcomes in the idiopathic intracranial hypertension (IIH) population in Wales using routinely collected health care data., Methods: We used and validated primary and secondary care IIH diagnosis codes within the Secure Anonymised Information Linkage databank to ascertain IIH cases and controls in a retrospective cohort study between 2003 and 2017. We recorded body mass index (BMI), deprivation quintile, CSF diversion surgery, and unscheduled hospital admissions in case and control cohorts., Results: We analyzed 35 million patient-years of data. There were 1,765 cases of IIH in 2017 (85% female). The prevalence and incidence of IIH in 2017 was 76/100,000 and 7.8/100,000/y, a significant increase from 2003 (corresponding figures = 12/100,000 and 2.3/100,000/y) ( p < 0.001). IIH prevalence is associated with increasing BMI and increasing deprivation. The odds ratio for developing IIH in the least deprived quintile compared to the most deprived quintile, adjusted for sex and BMI, was 0.65 (95% confidence interval 0.55 to 0.76). Nine percent of IIH cases had CSF shunts with less than 0.2% having bariatric surgery. Unscheduled hospital admissions were higher in the IIH cohort compared to controls (rate ratio 5.28, p < 0.001) and in individuals with IIH and CSF shunts compared to those without shunts (rate ratio 2.02, p < 0.01)., Conclusions: IIH incidence and prevalence is increasing considerably, corresponding to population increases in BMI, and is associated with increased deprivation. This has important implications for health care professionals and policy makers given the comorbidities, complications, and increased health care utilization associated with IIH., (Copyright © 2021 The Author(s). Published by Wolters Kluwer Health, Inc. on behalf of the American Academy of Neurology.)