Search

Discrete phylogeography using software such as BEAST considers the sampling location of each taxon as fixed; often to a single location without uncertainty. When studying viruses, this implies that there is no possibility that the location of the infected host for that taxa is somewhere else. Here, we relaxed this strong assumption and allowed for analytic integration of uncertainty for discrete virus phylogeography. We used automatic language processing methods to find and assign uncertainty to alternative potential locations. We considered two influenza case studies: H5N1 in Egypt; H1N1 pdm09 in North America. For each, we implemented scenarios in which 25 per cent of the taxa had different amounts of sampling uncertainty including 10, 30, and 50 per cent uncertainty and varied how it was distributed for each taxon. This includes scenarios that: (i) placed a specific amount of uncertainty on one location while uniformly distributing the remaining amount across all other candidate locations (correspondingly labeled 10, 30, and 50); (ii) assigned the remaining uncertainty to just one other location; thus 'splitting' the uncertainty among two locations (i.e. 10/90, 30/70, and 50/50); and (iii) eliminated uncertainty via two predefined heuristic approaches: assignment to a centroid location (CNTR) or the largest population in the country (POP). We compared all scenarios to a reference standard (RS) in which all taxa had known (absolutely certain) locations. From this, we implemented five random selections of 25 per cent of the taxa and used these for specifying uncertainty. We performed posterior analyses for each scenario, including: (a) virus persistence, (b) migration rates, (c) trunk rewards, and (d) the posterior probability of the root state. The scenarios with sampling uncertainty were closer to the RS than CNTR and POP. For H5N1, the absolute error of virus persistence had a median range of 0.005-0.047 for scenarios with sampling uncertainty-(i) and (ii) above-versus a range of 0.063-0.075 for CNTR and POP. Persistence for the pdm09 case study followed a similar trend as did our analyses of migration rates across scenarios (i) and (ii). When considering the posterior probability of the root state, we found all but one of the H5N1 scenarios with sampling uncertainty had agreement with the RS on the origin of the outbreak whereas both CNTR and POP disagreed. Our results suggest that assigning geospatial uncertainty to taxa benefits estimation of virus phylogeography as compared to ad-hoc heuristics. We also found that, in general, there was limited difference in results regardless of how the sampling uncertainty was assigned; uniform distribution or split between two locations did not greatly impact posterior results. This framework is available in BEAST v.1.10. In future work, we will explore viruses beyond influenza. We will also develop a web interface for researchers to use our language processing methods to find and assign uncertainty to alternative potential locations for virus phylogeography.

Abstract Background Prescription medication (PM) misuse/abuse has emerged as a national crisis in the United States, and social media has been suggested as a potential resource for performing active monitoring. However, automating a social media-based monitoring system is challenging—requiring advanced natural language processing (NLP) and machine learning methods. In this paper, we describe the development and evaluation of automatic text classification models for detecting self-reports of PM abuse from Twitter. Methods We experimented with state-of-the-art bi-directional transformer-based language models, which utilize tweet-level representations that enable transfer learning (e.g., BERT, RoBERTa, XLNet, AlBERT, and DistilBERT), proposed fusion-based approaches, and compared the developed models with several traditional machine learning, including deep learning, approaches. Using a public dataset, we evaluated the performances of the classifiers on their abilities to classify the non-majority “abuse/misuse” class. Results Our proposed fusion-based model performs significantly better than the best traditional model (F1-score [95% CI]: 0.67 [0.64–0.69] vs. 0.45 [0.42–0.48]). We illustrate, via experimentation using varying training set sizes, that the transformer-based models are more stable and require less annotated data compared to the other models. The significant improvements achieved by our best-performing classification model over past approaches makes it suitable for automated continuous monitoring of nonmedical PM use from Twitter. Conclusions BERT, BERT-like and fusion-based models outperform traditional machine learning and deep learning models, achieving substantial improvements over many years of past research on the topic of prescription medication misuse/abuse classification from social media, which had been shown to be a complex task due to the unique ways in which information about nonmedical use is presented. Several challenges associated with the lack of context and the nature of social media language need to be overcome to further improve BERT and BERT-like models. These experimental driven challenges are represented as potential future research directions.

BackgroundDiabetes mellitus is a major global public health issue where self-management is critical to reducing disease burden. Social media has been a powerful tool to understand public perceptions. Public perception of the drugs used for the treatment of diabetes may be useful for orienting interventions to increase adherence. ObjectiveThe aim of this study was to explore the public perceptions of anti-diabetic drugs through the analysis of health-related tweets mentioning such medications. MethodsThis study uses an infoveillance social listening approach to monitor public discourse using Twitter data. We coded 4000 tweets from January 1, 2019 to October 1, 2019 containing key terms related to anti-diabetic drugs by using qualitative content analysis. Tweets were coded for whether they were truly about an anti-diabetic drug and whether they were health-related. Health-related tweets were further coded based on who was tweeting, which anti-diabetic drug was being tweeted about, and the content discussed in the tweet. The main outcome of the analysis was the themes identified by analyzing the content of health-related tweets on anti-diabetic drugs. ResultsWe identified 1664 health-related tweets on 33 anti-diabetic drugs. A quarter (415/1664) of the tweets were confirmed to have been from people with diabetes, 17.9% (298/1664) from people posting about someone else, and 2.7% (45/1664) from health care professionals. However, the role of the tweeter was unidentifiable in two-thirds of the tweets. We identified 13 themes, with the health consequences of the cost of anti-diabetic drugs being the most extensively discussed, followed by the efficacy and availability. We also identified issues that patients may conceal from health care professionals, such as purchasing medications from unofficial sources. ConclusionsThis study uses an infoveillance approach using Twitter data to explore public perceptions related to anti-diabetic drugs. This analysis gives an insight into the real-life issues that an individual faces when taking anti-diabetic drugs, and such findings may be incorporated into health policies to improve compliance and efficacy. This study suggests that there is a fear of not having access to anti-diabetic drugs due to cost or physical availability and highlights the impact of the sacrifices made to access anti-diabetic drugs. Along with screening for diabetes-related health issues, health care professionals should also ask their patients about any non–health-related concerns regarding their anti-diabetic drugs. The positive tweets about dietary changes indicate that people with type 2 diabetes may be more open to self-management than what the health care professionals believe.

BackgroundIn the United States, the rapidly evolving COVID-19 outbreak, the shortage of available testing, and the delay of test results present challenges for actively monitoring its spread based on testing alone. ObjectiveThe objective of this study was to develop, evaluate, and deploy an automatic natural language processing pipeline to collect user-generated Twitter data as a complementary resource for identifying potential cases of COVID-19 in the United States that are not based on testing and, thus, may not have been reported to the Centers for Disease Control and Prevention. MethodsBeginning January 23, 2020, we collected English tweets from the Twitter Streaming application programming interface that mention keywords related to COVID-19. We applied handwritten regular expressions to identify tweets indicating that the user potentially has been exposed to COVID-19. We automatically filtered out “reported speech” (eg, quotations, news headlines) from the tweets that matched the regular expressions, and two annotators annotated a random sample of 8976 tweets that are geo-tagged or have profile location metadata, distinguishing tweets that self-report potential cases of COVID-19 from those that do not. We used the annotated tweets to train and evaluate deep neural network classifiers based on bidirectional encoder representations from transformers (BERT). Finally, we deployed the automatic pipeline on more than 85 million unlabeled tweets that were continuously collected between March 1 and August 21, 2020. ResultsInterannotator agreement, based on dual annotations for 3644 (41%) of the 8976 tweets, was 0.77 (Cohen κ). A deep neural network classifier, based on a BERT model that was pretrained on tweets related to COVID-19, achieved an F1-score of 0.76 (precision=0.76, recall=0.76) for detecting tweets that self-report potential cases of COVID-19. Upon deploying our automatic pipeline, we identified 13,714 tweets that self-report potential cases of COVID-19 and have US state–level geolocations. ConclusionsWe have made the 13,714 tweets identified in this study, along with each tweet’s time stamp and US state–level geolocation, publicly available to download. This data set presents the opportunity for future work to assess the utility of Twitter data as a complementary resource for tracking the spread of COVID-19.

BackgroundSocial media data are being increasingly used for population-level health research because it provides near real-time access to large volumes of consumer-generated data. Recently, a number of studies have explored the possibility of using social media data, such as from Twitter, for monitoring prescription medication abuse. However, there is a paucity of annotated data or guidelines for data characterization that discuss how information related to abuse-prone medications is presented on Twitter. ObjectiveThis study discusses the creation of an annotated corpus suitable for training supervised classification algorithms for the automatic classification of medication abuse–related chatter. The annotation strategies used for improving interannotator agreement (IAA), a detailed annotation guideline, and machine learning experiments that illustrate the utility of the annotated corpus are also described. MethodsWe employed an iterative annotation strategy, with interannotator discussions held and updates made to the annotation guidelines at each iteration to improve IAA for the manual annotation task. Using the grounded theory approach, we first characterized tweets into fine-grained categories and then grouped them into 4 broad classes—abuse or misuse, personal consumption, mention, and unrelated. After the completion of manual annotations, we experimented with several machine learning algorithms to illustrate the utility of the corpus and generate baseline performance metrics for automatic classification on these data. ResultsOur final annotated set consisted of 16,443 tweets mentioning at least 20 abuse-prone medications including opioids, benzodiazepines, atypical antipsychotics, central nervous system stimulants, and gamma-aminobutyric acid analogs. Our final overall IAA was 0.86 (Cohen kappa), which represents high agreement. The manual annotation process revealed the variety of ways in which prescription medication misuse or abuse is discussed on Twitter, including expressions indicating coingestion, nonmedical use, nonstandard route of intake, and consumption above the prescribed doses. Among machine learning classifiers, support vector machines obtained the highest automatic classification accuracy of 73.00% (95% CI 71.4-74.5) over the test set (n=3271). ConclusionsOur manual analysis and annotations of a large number of tweets have revealed types of information posted on Twitter about a set of abuse-prone prescription medications and their distributions. In the interests of reproducible and community-driven research, we have made our detailed annotation guidelines and the training data for the classification experiments publicly available, and the test data will be used in future shared tasks.

Free-text information represents a valuable resource for epidemiological surveillance. Its unstructured nature, however, presents significant challenges in the extraction of meaningful information. This study presents a deep learning model for classifying otitis using pediatric medical records. We analyzed the Pedianet database, which includes data from January 2004 to August 2017. The model categorizes narratives from clinical record diagnoses into six types: no otitis, non-media otitis, non-acute otitis media (OM), acute OM (AOM), AOM with perforation, and recurrent AOM. Utilizing deep learning architectures, including an ensemble model, this study addressed the challenges associated with the manual classification of extensive narrative data. The performance of the model was evaluated according to a gold standard classification made by three expert clinicians. The ensemble model achieved values of 97.03, 93.97, 96.59, and 95.48 for balanced precision, balanced recall, accuracy, and balanced F1 measure, respectively. These results underscore the efficacy of using automated systems for medical diagnoses, especially in pediatric care. Our findings demonstrate the potential of deep learning in interpreting complex medical records, enhancing epidemiological surveillance and research. This approach offers significant improvements in handling large-scale medical data, ensuring accuracy and minimizing human error. The methodology is adaptable to other medical contexts, promising a new horizon in healthcare analytics. [ABSTRACT FROM AUTHOR]

Background: Despite the fact that medication is taken during more than 90% of pregnancies, the fetal risk for most medications is unknown, and the majority of medications have no data regarding safety in pregnancy. Objective: Using ß-blockers as a proof-of-concept, the primary objective of this study was to assess the utility of Twitter data for a cohort study design--in particular, whether we could identify (1) Twitter users who have posted tweets reporting that they took medication during pregnancy and (2) their associated pregnancy outcomes. Methods: We searched for mentions of ß-blockers in 2.75 billion tweets posted by 415,690 users who announced their pregnancy on Twitter. We manually reviewed the matching tweets to first determine if the user actually took the ß-blocker mentioned in the tweet. Then, to help determine if the ß-blocker was taken during pregnancy, we used the time stamp of the tweet reporting intake and drew upon an automated natural language processing (NLP) tool that estimates the date of the user's prenatal time period. For users who posted tweets indicating that they took or may have taken the ß-blocker during pregnancy, we drew upon additional NLP tools to help identify tweets that report their pregnancy outcomes. Adverse pregnancy outcomes included miscarriage, stillbirth, birth defects, preterm birth (<37 weeks gestation), low birth weight (<5 pounds and 8 ounces at delivery), and neonatal intensive care unit (NICU) admission. Normal pregnancy outcomes included gestational age =37 weeks and birth weight =5 pounds and 8 ounces. Results: We retrieved 5114 tweets, posted by 2339 users, that mention a ß-blocker, and manually identified 2332 (45.6%) tweets, posted by 1195 (51.1%) of the users, that self-report taking the ß-blocker. We were able to estimate the date of the prenatal time period for 356 pregnancies among 334 (27.9%) of these 1195 users. Among these 356 pregnancies, we identified 257 (72.2%) during which the ß-blocker was or may have been taken. We manually verified an adverse pregnancy outcome--preterm birth, NICU admission, low birth weight, birth defects, or miscarriage--for 38 (14.8%) of these 257 pregnancies. We manually verified a gestational age =37 weeks for 198 (90.4%) and a birth weight =5 pounds and 8 ounces for 50 (22.8%) of the 219 pregnancies for which we did not identify an adverse pregnancy outcome. Conclusions: Our ability to detect pregnancy outcomes for Twitter users who posted tweets reporting that they took or may have taken a ß-blocker during pregnancy suggests that Twitter can be a complementary resource for cohort studies of drug safety in pregnancy. [ABSTRACT FROM AUTHOR]