Adverse event detection by integrating twitter data and VAERS

Information systems for vaccine safety surveillance

Immunization implementation in the community relies upon post-licensure vaccine safety surveillance to maintain safe vaccination programs and to detect rare AEFI not observed in clinical trials. The increasing availability of electronic health-care related data and correspondence from both health-related providers and internet-based media has revolutionized health-care information. Many and varied forms of health information related to adverse event following immunization (AEFI) are potentially suitable for vaccine safety surveillance. The utilization of these media ranges from more efficient use of electronic spontaneous reporting, automated solicited surveillance methods, screening various electronic health record types, and the utilization of natural language processing techniques to scan enormous amounts of internet-based data for AEFI mentions. Each of these surveillance types have advantages and disadvantages and are often complementary to each other. Most are "hypothesis generating," detecting potential safety signals, where some, such as vaccine safety datalinking, may also serve as "hypothesis testing" to help verify and investigate those potential signals.

COVID-19 vaccine design using reverse and structural vaccinology, ontology-based literature mining and machine learning

Rational vaccine design, especially vaccine antigen identification and optimization, is critical to successful and efficient vaccine development against various infectious diseases including coronavirus disease 2019 (COVID-19). In general, computational vaccine design includes three major stages: (i) identification and annotation of experimentally verified gold standard protective antigens through literature mining, (ii) rational vaccine design using reverse vaccinology (RV) and structural vaccinology (SV) and (iii) post-licensure vaccine success and adverse event surveillance and its usage for vaccine design. Protegen is a database of experimentally verified protective antigens, which can be used as gold standard data for rational vaccine design. RV predicts protective antigen targets primarily from genome sequence analysis. SV refines antigens through structural engineering. Recently, RV and SV approaches, with the support of various machine learning methods, have been applied to COVID-19 vaccine design. The analysis of post-licensure vaccine adverse event report data also provides valuable results in terms of vaccine safety and how vaccines should be used or paused. Ontology standardizes and incorporates heterogeneous data and knowledge in a human- and computer-interpretable manner, further supporting machine learning and vaccine design. Future directions on rational vaccine design are discussed.

Mild Adverse Events of Sputnik V Vaccine in Russia: Social Media Content Analysis of Telegram via Deep Learning

Background

There is a limited amount of data on the safety profile of the COVID-19 vector vaccine Gam-COVID-Vac (Sputnik V). Previous infodemiology studies showed that social media discourse could be analyzed to assess the most concerning adverse events (AE) caused by drugs.

Objective

We aimed to investigate mild AEs of Sputnik V based on a participatory trial conducted on Telegram in the Russian language. We compared AEs extracted from Telegram with other limited databases on Sputnik V and other COVID-19 vaccines. We explored symptom co-occurrence patterns and determined how counts of administered doses, age, gender, and sequence of shots could confound the reporting of AEs.

Methods

We collected a unique dataset consisting of 11,515 self-reported Sputnik V vaccine AEs posted on the Telegram group, and we utilized natural language processing methods to extract AEs. Specifically, we performed multilabel classifications using the deep neural language model Bidirectional Encoder Representations from Transformers (BERT) “DeepPavlov,” which was pretrained on a Russian language corpus and applied to the Telegram messages. The resulting area under the curve score was 0.991. We chose symptom classes that represented the following AEs: fever, pain, chills, fatigue, nausea/vomiting, headache, insomnia, lymph node enlargement, erythema, pruritus, swelling, and diarrhea.

Results

Telegram users complained mostly about pain (5461/11,515, 47.43%), fever (5363/11,515, 46.57%), fatigue (3862/11,515, 33.54%), and headache (2855/11,515, 24.79%). Women reported more AEs than men (1.2-fold, P<.001). In addition, there were more AEs from the first dose than from the second dose (1.1-fold, P<.001), and the number of AEs decreased with age (β=.05 per year, P<.001). The results also showed that Sputnik V AEs were more similar to other vector vaccines (132 units) than with messenger RNA vaccines (241 units) according to the average Euclidean distance between the vectors of AE frequencies. Elderly Telegram users reported significantly more (5.6-fold on average) systemic AEs than their peers, according to the results of the phase 3 clinical trials published in The Lancet. However, the AEs reported in Telegram posts were consistent (Pearson correlation r=0.94, P=.02) with those reported in the Argentinian postmarketing AE registry.

Conclusions

After the Sputnik V vaccination, Russian Telegram users reported mostly pain, fever, and fatigue. The Sputnik V AE profile was comparable with other vector COVID-19 vaccines. Discussion on social media could provide meaningful information about the AE profile of novel vaccines.

Analysis of Population Differences in Digital Conversations About Cancer Clinical Trials: Advanced Data Mining and Extraction Study

Background

Racial and ethnic diversity in clinical trials for cancer treatment is essential for the development of treatments that are effective for all patients and for identifying potential differences in toxicity between different demographics. Mining of social media discussions about clinical trials has been used previously to identify patient barriers to enrollment in clinical trials; however, a comprehensive breakdown of sentiments and barriers by various racial and ethnic groups is lacking.

Objective

The aim of this study is to use an innovative methodology to analyze web-based conversations about cancer clinical trials and to identify and compare conversation topics, barriers, and sentiments between different racial and ethnic populations.

Methods

We analyzed 372,283 web-based conversations about cancer clinical trials, of which 179,339 (48.17%) of the discussions had identifiable race information about the individual posting the conversations. Using sophisticated machine learning software and analyses, we were able to identify key sentiments and feelings, topics of interest, and barriers to clinical trials across racial groups. The stage of treatment could also be identified in many of the discussions, allowing for a unique insight into how the sentiments and challenges of patients change throughout the treatment process for each racial group.

Results

We observed that only 4.01% (372,283/9,284,284) of cancer-related discussions referenced clinical trials. Within these discussions, topics of interest and identified clinical trial barriers discussed by all racial and ethnic groups throughout the treatment process included health care professional interactions, cost of care, fear, anxiety and lack of awareness, risks, treatment experiences, and the clinical trial enrollment process. Health care professional interactions, cost of care, and enrollment processes were notably discussed more frequently in minority populations. Other minor variations in the frequency of discussion topics between ethnic and racial groups throughout the treatment process were identified.

Conclusions

This study demonstrates the power of digital search technology in health care research. The results are also valuable for identifying the ideal content and timing for the delivery of clinical trial information and resources for different racial and ethnic groups.

A scoping review of the use of Twitter for public health research

Public health practitioners and researchers have used traditional medical databases to study and understand public health for a long time. Recently, social media data, particularly Twitter, has seen some use for public health purposes. Every large technological development in history has had an impact on the behaviour of society. The advent of the internet and social media is no different. Social media creates public streams of communication, and scientists are starting to understand that such data can provide some level of access into the people's opinions and situations. As such, this paper aims to review and synthesize the literature on Twitter applications for public health, highlighting current research and products in practice. A scoping review methodology was employed and four leading health, computer science and cross-disciplinary databases were searched. A total of 755 articles were retreived, 92 of which met the criteria for review. From the reviewed literature, six domains for the application of Twitter to public health were identified: (i) Surveillance; (ii) Event Detection; (iii) Pharmacovigilance; (iv) Forecasting; (v) Disease Tracking; and (vi) Geographic Identification. From our review, we were able to obtain a clear picture of the use of Twitter for public health. We gained insights into interesting observations such as how the popularity of different domains changed with time, the diseases and conditions studied and the different approaches to understanding each disease, which algorithms and techniques were popular with each domain, and more.

An ensemble of neural models for nested adverse drug events and medication extraction with subwords

OBJECTIVE

This article describes an ensembling system to automatically extract adverse drug events and drug related entities from clinical narratives, which was developed for the 2018 n2c2 Shared Task Track 2.

MATERIALS AND METHODS

We designed a neural model to tackle both nested (entities embedded in other entities) and polysemous entities (entities annotated with multiple semantic types) based on MIMIC III discharge summaries. To better represent rare and unknown words in entities, we further tokenized the MIMIC III data set by splitting the words into finer-grained subwords. We finally combined all the models to boost the performance. Additionally, we implemented a featured-based conditional random field model and created an ensemble to combine its predictions with those of the neural model.

RESULTS

Our method achieved 92.78% lenient micro F1-score, with 95.99% lenient precision, and 89.79% lenient recall, respectively. Experimental results showed that combining the predictions of either multiple models, or of a single model with different settings can improve performance.

DISCUSSION

Analysis of the development set showed that our neural models can detect more informative text regions than feature-based conditional random field models. Furthermore, most entity types significantly benefit from subword representation, which also allows us to extract sparse entities, especially nested entities.

CONCLUSION

The overall results have demonstrated that the ensemble method can accurately recognize entities, including nested and polysemous entities. Additionally, our method can recognize sparse entities by reconsidering the clinical narratives at a finer-grained subword level, rather than at the word level.

A systematic review on integration mechanisms in human and animal health surveillance systems with a view to addressing global health security threats

BACKGROUND

Health surveillance is an important element of disease prevention, control, and management. During the past two decades, there have been several initiatives to integrate health surveillance systems using various mechanisms ranging from the integration of data sources to changing organizational structures and responses. The need for integration is caused by an increasing demand for joint data collection, use and preparedness for emerging infectious diseases.

OBJECTIVE

To review the integration mechanisms in human and animal health surveillance systems and identify their contributions in strengthening surveillance systems attributes.

METHOD

The review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analysis Protocols (PRISMA-P) 2015 checklist. Peer-reviewed articles were searched from PubMed, HINARI, Web of Science, Science Direct and advanced Google search engines. The review included articles published in English from 1900 to 2018. The study selection considered all articles that used quantitative, qualitative or mixed research methods. Eligible articles were assessed independently for quality by two authors using the QualSyst Tool and relevant information including year of publication, field, continent, addressed attributes and integration mechanism were extracted.

RESULTS

A total of 102 publications were identified and categorized into four pre-set integration mechanisms: interoperability (35), convergent integration (27), semantic consistency (21) and interconnectivity (19). Most integration mechanisms focused on sensitivity (44.1%), timeliness (41.2%), data quality (23.5%) and acceptability (17.6%) of the surveillance systems. Generally, the majority of the surveillance system integrations were centered on addressing infectious diseases and all hazards. The sensitivity of the integrated systems reported in these studies ranged from 63.9 to 100% (median = 79.6%, n = 16) and the rate of data quality improvement ranged from 73 to 95.4% (median = 87%, n = 4). The integrated systems were also shown improve timeliness where the recorded changes were reported to be ranging from 10 to 91% (median = 67.3%, n = 8).

CONCLUSION

Interoperability and semantic consistency are the common integration mechanisms in human and animal health surveillance systems. Surveillance system integration is a relatively new concept but has already been shown to enhance surveillance performance. More studies are needed to gain information on further surveillance attributes.

A 2018 workshop: vaccine and drug ontology studies (VDOS 2018)

This Editorial first introduces the background of the vaccine and drug relations and how biomedical terminologies and ontologies have been used to support their studies. The history of the seven workshops, initially named VDOSME, and then named VDOS, is also summarized and introduced. Then the 7th International Workshop on Vaccine and Drug Ontology Studies (VDOS 2018), held on August 10th, 2018, Corvallis, Oregon, USA, is introduced in detail. These VDOS workshops have greatly supported the development, applications, and discussion of vaccine- and drug-related terminology and drug studies.