RESUMO
Background: Paroxysmal atrial fibrillation (AF) often eludes early diagnosis, resulting in significant morbidity and mortality. Artificial intelligence (AI) has been used to predict AF from sinus rhythm electrocardiograms (ECGs), but AF prediction using sinus rhythm mobile electrocardiograms (mECG) remains unexplored. Objective: The purpose of this study was to investigate the utility of AI to predict AF events prospectively and retrospectively using sinus rhythm mECG data. Methods: We trained a neural network to predict AF events from sinus rhythm mECGs obtained from users of the Alivecor KardiaMobile 6L device. We tested our model on sinus rhythm mECGs within ±0-2 days, ±3-7 days, and ±8-30 days from AF events to determine the optimal screening window. Finally, we tested our model on mECGs from before an AF event to determine whether AF can be predicted prospectively. Results: We included 73,861 users with 267,614 mECGs (mean age 58.14 years; 35% women). Users with paroxysmal AF contributed 60.15% of mECGs. Model performance on the test set comprising control and study samples across all windows of interest showed an area under the curve (AUC) score of 0.760 (95% confidence interval [CI] 0.759-0.760), sensitivity of 0.703 (95% CI 0.700-0.705), specificity of 0.684 (95% CI 0.678-0.685), and accuracy of 69.4% (95% CI 0.692-0.700). Model performance was better on ±0-2 day samples (sensitivity 0.711; 95% CI 0.709-0.713) and worse on the ±8-30 day window (sensitivity 0.688; 95% CI 0.685-0.690), with performance on the ±3-7 day window falling in between (sensitivity 0.708; 95% CI 0.704-0.710). Conclusion: Neural networks can predict AF using a widely scalable and cost-effective mobile technology prospectively and retrospectively.
RESUMO
BACKGROUND: Dental care expenses are reported to present higher financial barriers than any other type of health care service in the United States. Social media platforms such as Twitter have become a source of public health communication and surveillance. Previous studies have demonstrated the usefulness of Twitter in exploring public opinion on aspects of dental care. To date, no studies have leveraged Twitter to examine public sentiments regarding dental care affordability in the United States. OBJECTIVE: The aim of this study is to understand public perceptions of dental care affordability in the United States on the social media site, Twitter. METHODS: Tweets posted between September 1, 2017, and September 30, 2021, were collected using the Snscrape application. Query terms were selected a priori to represent dentistry and financial aspects associated with dental treatment. Data were analyzed qualitatively using both deductive and inductive approaches. In total, 8% (440/5500) of all included tweets were coded to identify prominent themes and subthemes. The entire sample of included tweets were then independently coded into thematic categories. Quantitative data analyses included geographic distribution of tweets by state, volume analysis of tweets over time, and distribution of tweets by content theme. RESULTS: A final sample of 5314 tweets were included in the study. Thematic analysis identified the following prominent themes: (1) general sentiments (1614 tweets, 30.4%); (2) delaying or forgoing dental care (1190 tweets, 22.4%); (3) payment strategies (1019 tweets, 19.2%); (4) insurance (767 tweets, 14.4%); and (5) policy statements (724 tweets, 13.6%). Geographic distributions of the tweets established California, Texas, Florida, and New York as the states with the most tweets. Qualitative analysis revealed barriers faced by individuals to accessing dental care, strategies taken to cope with dental pain, and public perceptions on aspects of dental care policy. The volume and thematic trends of the tweets corresponded to relevant societal events, including the COVID-19 pandemic and debates on health care policy resulting from the election of President Joseph R. Biden. CONCLUSIONS: The findings illustrate the real-time sentiment of social media users toward the cost of dental treatment and suggest shortcomings in funding that may be representative of greater systemic failures in the provision of dental care. Thus, this study provides insights for policy makers and dental professionals who strive to increase access to dental care.
RESUMO
INTRODUCTION AND AIMS: This article examines the feasibility of leveraging Twitter to detect posts authored by people who use opioids (PWUO) or content related to opioid use disorder (OUD), and manually develop a multidimensional taxonomy of relevant tweets. DESIGN AND METHODS: Twitter messages were collected between June and October 2017 (n = 23 827) and evaluated using an inductive coding approach. Content was then manually classified into two axes (n = 17 420): (i) user experience regarding accessing, using, or recovery from illicit opioids; and (ii) content categories (e.g. policies, medical information, jokes/sarcasm). RESULTS: The most prevalent categories consisted of jokes or sarcastic comments pertaining to OUD, PWUOs or hypothetically using illicit opioids (63%), informational content about treatments for OUD, overdose prevention or accessing self-help groups (20%), and commentary about government opioid policy or news related to opioids (17%). Posts by PWUOs centered on identifying illicit sources for procuring opioids (i.e. online, drug dealers; 49%), symptoms and/or strategies to quell opioid withdrawal symptoms (21%), and combining illicit opioid use with other substances, such as cocaine or benzodiazepines (17%). State and public health experts infrequently posted content pertaining to OUD (1%). DISCUSSION AND CONCLUSIONS: Twitter offers a feasible approach to identify PWUO. Further research is needed to evaluate the efficacy of Twitter to disseminate evidence-based content and facilitate linkage to treatment and harm reduction services.
