Explore the vast range of titles available.

Despite a dramatic increase in the number of people with generalized anxiety disorder (GAD), a substantial number still do not seek help from health professionals, resulting in reduced quality of life. With the growth in popularity of social media platforms, individuals have become more willing to express their emotions through these channels. Therefore, social media data have become valuable for identifying mental health status. This study investigated the social media posts and behavioral patterns of people with GAD, focusing on language use, emotional expression, topics discussed, and engagement to identify digital markers of GAD, such as anxious patterns and behaviors. These insights could help reveal mental health indicators, aiding in digital intervention development. Data were first collected from Twitter (subsequently rebranded as X) for the GAD and control groups. Several preprocessing steps were performed. Three measurements were defined based on Linguistic Inquiry and Word Count for linguistic analysis. GuidedLDA was also used to identify the themes present in the tweets. Additionally, users' behaviors were analyzed using Twitter metadata. Finally, we studied the correlation between the GuidedLDA-based themes and users' behaviors. The linguistic analysis indicated differences in cognitive style, personal needs, and emotional expressiveness between people with and without GAD. Regarding cognitive style, there were significant differences (P<.001) for all features, such as insight (Cohen d=1.13), causation (Cohen d=1.03), and discrepancy (Cohen d=1.16). Regarding personal needs, there were significant differences (P<.001) in most personal needs categories, such as curiosity (Cohen d=1.05) and communication (Cohen d=0.64). Regarding emotional expressiveness, there were significant differences (P<.001) for most features, including anxiety (Cohen d=0.62), anger (Cohen d=0.72), sadness (Cohen d=0.48), and swear words (Cohen d=2.61). Additionally, topic modeling identified 4 primary themes (ie, symptoms, relationships, life problems, and feelings). We found that all themes were significantly more prevalent for people with GAD than for those without GAD (P<.001), along with significant effect sizes (Cohen d>0.50; P<.001) for most themes. Moreover, studying users' behaviors, including hashtag participation, volume, interaction pattern, social engagement, and reactive behaviors, revealed some digital markers of GAD, with most behavior-based features, such as the hashtag (Cohen d=0.49) and retweet (Cohen d=0.69) ratios, being statistically significant (P<.001). Furthermore, correlations between the GuidedLDA-based themes and users' behaviors were also identified. Our findings revealed several digital markers of GAD on social media. These findings are significant and could contribute to developing an assessment tool that clinicians could use for the initial diagnosis of GAD or the detection of an early signal of worsening in people with GAD via social media posts. This tool could provide ongoing support and personalized coping strategies. However, one limitation of using social media for mental health assessment is the lack of a demographic representativeness analysis.

Machine learning (ML) has attracted much attention with the hope that it could make use of large, routinely collected datasets and deliver accurate personalised prognosis. The aim of this systematic review is to identify and critically appraise the reporting and developing of ML models for predicting outcomes after stroke. We searched PubMed and Web of Science from 1990 to March 2019, using previously published search filters for stroke, ML, and prediction models. We focused on structured clinical data, excluding image and text analysis. This review was registered with PROSPERO (CRD42019127154). Eighteen studies were eligible for inclusion. Most studies reported less than half of the terms in the reporting quality checklist. The most frequently predicted stroke outcomes were mortality (7 studies) and functional outcome (5 studies). The most commonly used ML methods were random forests (9 studies), support vector machines (8 studies), decision trees (6 studies), and neural networks (6 studies). The median sample size was 475 (range 70-3184), with a median of 22 predictors (range 4-152) considered. All studies evaluated discrimination with thirteen using area under the ROC curve whilst calibration was assessed in three. Two studies performed external validation. None described the final model sufficiently well to reproduce it. The use of ML for predicting stroke outcomes is increasing. However, few met basic reporting standards for clinical prediction tools and none made their models available in a way which could be used or evaluated. Major improvements in ML study conduct and reporting are needed before it can meaningfully be considered for practice.

Background Well-established electronic data capture in UK general practice means that algorithms, developed on patient data, can be used for automated clinical decision support systems (CDSSs). These can predict patient risk, help with prescribing safety, improve diagnosis and prompt clinicians to record extra data. However, there is persistent evidence of low uptake of CDSSs in the clinic. We interviewed UK General Practitioners (GPs) to understand what features of CDSSs, and the contexts of their use, facilitate or present barriers to their use. Methods We interviewed 11 practicing GPs in London and South England using a semi-structured interview schedule and discussed a hypothetical CDSS that could detect early signs of dementia. We applied thematic analysis to the anonymised interview transcripts. Results We identified three overarching themes: trust in individual CDSSs; usability of individual CDSSs; and usability of CDSSs in the broader practice context, to which nine subthemes contributed. Trust was affected by CDSS provenance, perceived threat to autonomy and clear management guidance. Usability was influenced by sensitivity to the patient context, CDSS flexibility, ease of control, and non-intrusiveness. CDSSs were more likely to be used by GPs if they did not contribute to alert proliferation and subsequent fatigue, or if GPs were provided with training in their use. Conclusions Building on these findings we make a number of recommendations for CDSS developers to consider when bringing a new CDSS into GP patient records systems. These include co-producing CDSS with GPs to improve fit within clinic workflow and wider practice systems, ensuring a high level of accuracy and a clear clinical pathway, and providing CDSS training for practice staff. These recommendations may reduce the proliferation of unhelpful alerts that can result in important decision-support being ignored.

In Chinese traditional culture, discussions surrounding death are often considered taboo, leading to a poor quality of death, and limited public awareness and knowledge about palliative and end-of-life care (PEoLC). However, the increasing prevalence of social media in health communication in China presents an opportunity to promote and educate the public about PEoLC through online discussions. This study aimed to examine the factors influencing public engagement in PEoLC discussions on a Chinese social media platform and develop practice recommendations to promote such engagement. We gathered 30,811 PEoLC-related posts on Weibo, the largest social media platform in China. Guided by the elaboration likelihood model, our study examined factors across 4 dimensions: content theme, mood, information richness, and source credibility. Content theme was examined using thematic analysis, while sentiment analysis was used to determine the mood of the posts. The impact of potential factors on post engagement was quantified using negative binomial regression. Organizational accounts exhibited lower engagement compared to individual accounts (incidence rate ratio [IRR]<1; P<.001), suggesting an underuse of organizational accounts in advocating for PEoLC on Weibo. Posts centered on PEoLC-related entertainment (films, television shows, and books; IRR=1.37; P<.001) or controversial social news (IRR=1.64; P<.001) garnered more engagement, primarily published by individual accounts. An interaction effect was observed between content theme and post mood, with posts featuring more negative sentiment generally attracting higher public engagement, except for educational-related posts (IRR=2.68; P<.001). Overall, organizations faced challenges in capturing public attention and involving the public when promoting PEoLC on Chinese social media platforms. It is imperative to move beyond a traditional mode to incorporate cultural elements of social media, such as engaging influencers, leveraging entertainment content and social news, or using visual elements, which can serve as effective catalysts in attracting public attention. The strategies developed in this study are particularly pertinent to nonprofit organizations and academics aiming to use social media for PEoLC campaigns, fundraising efforts, or research dissemination.

Background The National Early Warning Score (NEWS2) is currently recommended in the UK for the risk stratification of COVID-19 patients, but little is known about its ability to detect severe cases. We aimed to evaluate NEWS2 for the prediction of severe COVID-19 outcome and identify and validate a set of blood and physiological parameters routinely collected at hospital admission to improve upon the use of NEWS2 alone for medium-term risk stratification. Methods Training cohorts comprised 1276 patients admitted to King’s College Hospital National Health Service (NHS) Foundation Trust with COVID-19 disease from 1 March to 30 April 2020. External validation cohorts included 6237 patients from five UK NHS Trusts (Guy’s and St Thomas’ Hospitals, University Hospitals Southampton, University Hospitals Bristol and Weston NHS Foundation Trust, University College London Hospitals, University Hospitals Birmingham), one hospital in Norway (Oslo University Hospital), and two hospitals in Wuhan, China (Wuhan Sixth Hospital and Taikang Tongji Hospital). The outcome was severe COVID-19 disease (transfer to intensive care unit (ICU) or death) at 14 days after hospital admission. Age, physiological measures, blood biomarkers, sex, ethnicity, and comorbidities (hypertension, diabetes, cardiovascular, respiratory and kidney diseases) measured at hospital admission were considered in the models. Results A baseline model of ‘NEWS2 + age’ had poor-to-moderate discrimination for severe COVID-19 infection at 14 days (area under receiver operating characteristic curve (AUC) in training cohort = 0.700, 95% confidence interval (CI) 0.680, 0.722; Brier score = 0.192, 95% CI 0.186, 0.197). A supplemented model adding eight routinely collected blood and physiological parameters (supplemental oxygen flow rate, urea, age, oxygen saturation, C-reactive protein, estimated glomerular filtration rate, neutrophil count, neutrophil/lymphocyte ratio) improved discrimination (AUC = 0.735; 95% CI 0.715, 0.757), and these improvements were replicated across seven UK and non-UK sites. However, there was evidence of miscalibration with the model tending to underestimate risks in most sites. Conclusions NEWS2 score had poor-to-moderate discrimination for medium-term COVID-19 outcome which raises questions about its use as a screening tool at hospital admission. Risk stratification was improved by including readily available blood and physiological parameters measured at hospital admission, but there was evidence of miscalibration in external sites. This highlights the need for a better understanding of the use of early warning scores for COVID.

Background: Mental health problems are widely recognized as a major public health challenge worldwide. This concern highlights the need to develop effective tools for detecting mental health disorders in the population. Social networks are a promising source of data wherein patients publish rich personal information that can be mined to extract valuable psychological cues; however, these data come with their own set of challenges, such as the need to disambiguate between statements about oneself and third parties. Traditionally, natural language processing techniques for social media have looked at text classifiers and user classification models separately, hence presenting a challenge for researchers who want to combine text sentiment and user sentiment analysis. Objective: The objective of this study is to develop a predictive model that can detect users with depression from Twitter posts and instantly identify textual content associated with mental health topics. The model can also address the problem of anaphoric resolution and highlight anaphoric interpretations. Methods: We retrieved the data set from Twitter by using a regular expression or stream of real-time tweets comprising 3682 users, of which 1983 self-declared their depression and 1699 declared no depression. Two multiple instance learning models were developed—one with and one without an anaphoric resolution encoder—to identify users with depression and highlight posts related to the mental health of the author. Several previously published models were applied to our data set, and their performance was compared with that of our models. Results: The maximum accuracy, F1 score, and area under the curve of our anaphoric resolution model were 92%, 92%, and 90%, respectively. The model outperformed alternative predictive models, which ranged from classical machine learning models to deep learning models. Conclusions: Our model with anaphoric resolution shows promising results when compared with other predictive models and provides valuable insights into textual content that is relevant to the mental health of the tweeter.

Evidence that thiopurines impact on the risk of surgery in elderly onset inflammatory bowel disease (EO-IBD) is lacking. We aimed to compare the rates of surgery in EO-IBD (>60 years at diagnosis) with adult-onset IBD (18–59 yrs), and examine the impact of thiopurines on surgical risk in EO-IBD.MethodsUsing a U.K. database between 1990 and 2010, we compared rates of surgery between adult-onset IBD and EO-IBD using survival analysis. Ulcerative colitis (UC) and Crohn's disease (CD) were analyzed separately. Cox proportional hazard modeling was used to determine the adjusted relative risk of surgery. We further assessed the impact of duration of thiopurine treatment on risk of surgery.ResultsWe identified 2758 of 9515 patients with UC and 1349 of 6490 patients with CD, with EO-IBD. Cumulative 1, 5, and 10 years risk of colectomy was similar in EO-UC (2.2, 4.5, and 5.8%, respectively) and AO-UC (2.2, 5.0, and 7.3%, respectively; P = 0.15). Cumulative 1, 5, and 10 years risk of first intestinal surgery was lower in EO-CD (9.5, 14.6, and 17.9%, respectively) than AO-CD (12.2, 19.0, and 24.4%, respectively; P < 0.001). Early steroid use, steroid dependency, and thiopurine use was associated with higher risk of colectomy in EO-UC. Among EO-UC receiving thiopurines for >12 months, there was a 70% reduction in risk of colectomy (hazard ratio. 0.30; 95% confidence interval, 0.15–0.58). Thiopurines were not associated with a reduced risk of surgery in EO-CD.ConclusionsRisk of colectomy in EO-UC does not differ from AO-UC, but the risk of surgery in EO-CD is significantly lower than in AO-CD. Sustained thiopurine use of 12 months or more duration in EO-UC reduces the risk colectomy, but does not impact on the risk of surgery in EO-CD. These findings are important given the greater risk of thiopurine-associated lymphoma in the elderly.

Backgrounds We aimed to develop and validate machine learning (ML) models for 30-day stroke mortality for mortality risk stratification and as benchmarking models for quality improvement in stroke care. Methods Data from the UK Sentinel Stroke National Audit Program between 2013 to 2019 were used. Models were developed using XGBoost, Logistic Regression (LR), LR with elastic net with/without interaction terms using 80% randomly selected admissions from 2013 to 2018, validated on the 20% remaining admissions, and temporally validated on 2019 admissions. The models were developed with 30 variables. A reference model was developed using LR and 4 variables. Performances of all models was evaluated in terms of discrimination, calibration, reclassification, Brier scores and Decision-curves. Results In total, 488,497 stroke patients with a 12.3% 30-day mortality rate were included in the analysis. In 2019 temporal validation set, XGBoost model obtained the lowest Brier score (0.069 (95% CI: 0.068–0.071)) and the highest area under the ROC curve (AUC) (0.895 (95% CI: 0.891–0.900)) which outperformed LR reference model by 0.04 AUC ( p  < 0.001) and LR with elastic net and interaction term model by 0.003 AUC (p < 0.001). All models were perfectly calibrated for low (< 5%) and moderate risk groups (5–15%) and ≈1% underestimation for high-risk groups (> 15%). The XGBoost model reclassified 1648 (8.1%) low-risk cases by the LR reference model as being moderate or high-risk and gained the most net benefit in decision curve analysis. Conclusions All models with 30 variables are potentially useful as benchmarking models in stroke-care quality improvement with ML slightly outperforming others.

Palliative and end-of-life care (PEoLC) played a critical role in relieving distress and providing grief support in response to the heavy toll caused by the COVID-19 pandemic. However, little is known about public opinions concerning PEoLC during the pandemic. Given that social media have the potential to collect real-time public opinions, an analysis of this evidence is vital to guide future policy-making. This study aimed to use social media data to investigate real-time public opinions regarding PEoLC during the COVID-19 crisis and explore the impact of vaccination programs on public opinions about PEoLC. This Twitter-based study explored tweets across 3 English-speaking countries: the United States, the United Kingdom, and Canada. From October 2020 to March 2021, a total of 7951 PEoLC-related tweets with geographic tags were retrieved and identified from a large-scale COVID-19 Twitter data set through the Twitter application programming interface. Topic modeling realized through a pointwise mutual information-based co-occurrence network and Louvain modularity was used to examine latent topics across the 3 countries and across 2 time periods (pre- and postvaccination program periods). Commonalities and regional differences among PEoLC topics in the United States, the United Kingdom, and Canada were identified specifically: cancer care and care facilities were of common interest to the public across the 3 countries during the pandemic; the public expressed positive attitudes toward the COVID-19 vaccine and highlighted the protection it affords to PEoLC professionals; and although Twitter users shared their personal experiences about PEoLC in the web-based community during the pandemic, this was more prominent in the United States and Canada. The implementation of the vaccination programs raised the profile of the vaccine discussion; however, this did not influence public opinions about PEoLC. Public opinions on Twitter reflected a need for enhanced PEoLC services during the COVID-19 pandemic. The insignificant impact of the vaccination program on public discussion on social media indicated that public concerns regarding PEoLC continued to persist even after the vaccination efforts. Insights gleaned from public opinions regarding PEoLC could provide some clues for policy makers on how to ensure high-quality PEoLC during public health emergencies. In this post-COVID-19 era, PEoLC professionals may wish to continue to examine social media and learn from web-based public discussion how to ease the long-lasting trauma caused by this crisis and prepare for public health emergencies in the future. Besides, our results showed social media's potential in acting as an effective tool to reflect public opinions in the context of PEoLC.

IntroductionLong COVID, a new condition whose origins and natural history are not yet fully established, currently affects 1.5 million people in the UK. Most do not have access to specialist long COVID services. We seek to optimise long COVID care both within and outside specialist clinics, including improving access, reducing inequalities, helping self-management and providing guidance and decision support for primary care. We aim to establish a ‘gold standard’ of care by systematically analysing current practices, iteratively improving pathways and systems of care.Methods and analysisThis mixed-methods, multisite study is informed by the principles of applied health services research, quality improvement, co-design, outcome measurement and learning health systems. It was developed in close partnership with patients (whose stated priorities are prompt clinical assessment; evidence-based advice and treatment and help with returning to work and other roles) and with front-line clinicians. Workstreams and tasks to optimise assessment, treatment and monitoring are based in three contrasting settings: workstream 1 (qualitative research, up to 100 participants), specialist management in 10 long COVID clinics across the UK, via a quality improvement collaborative, experience-based co-design and targeted efforts to reduce inequalities of access, return to work and peer support; workstream 2 (quantitative research, up to 5000 participants), patient self-management at home, technology-supported monitoring and validation of condition-specific outcome measures and workstream 3 (quantitative research, up to 5000 participants), generalist management in primary care, harnessing electronic record data to study population phenotypes and develop evidence-based decision support, referral pathways and analysis of costs. Study governance includes an active patient advisory group.Ethics and disseminationLOng COvid Multidisciplinary consortium Optimising Treatments and servIces acrOss the NHS study is sponsored by the University of Leeds and approved by Yorkshire & The Humber—Bradford Leeds Research Ethics Committee (ref: 21/YH/0276). Participants will provide informed consent. Dissemination plans include academic and lay publications, and partnerships with national and regional policymakers.Trial registration number NCT05057260, ISRCTN15022307.