The COVID-19 pandemic swept across the world rapidly, infecting millions of people. An efficient tool that can accurately recognize important clinical concepts of COVID-19 from free text in electronic health records (EHRs) will be valuable to accelerate COVID-19 clinical research. To this end, this study aims at adapting the existing CLAMP natural language processing tool to quickly build COVID-19 SignSym, which can extract COVID-19 signs/symptoms and their 8 attributes (body location, severity, temporal expression, subject, condition, uncertainty, negation, and course) from clinical text. The extracted information is also mapped to standard concepts in the Observational Medical Outcomes Partnership common data model. A hybrid approach of combining deep learning-based models, curated lexicons, and pattern-based rules was applied to quickly build the COVID-19 SignSym from CLAMP, with optimized performance. Our extensive evaluation using 3 external sites with clinical notes of COVID-19 patients, as well as the online medical dialogues of COVID-19, shows COVID-19 SignSym can achieve high performance across data sources. The workflow used for this study can be generalized to other use cases, where existing clinical natural language processing tools need to be customized for specific information needs within a short time. COVID-19 SignSym is freely accessible to the research community as a downloadable package (https://clamp.uth.edu/covid/nlp.php) and has been used by 16 healthcare organizations to support clinical research of COVID-19.

Objective Automated analysis of vaccine postmarketing surveillance narrative reports is important to understand the progression of rare but severe vaccine adverse events (AEs). This study implemented and evaluated state-of-the-art deep learning algorithms for named entity recognition to extract nervous system disorder-related events from vaccine safety reports. Materials and Methods We collected Guillain-Barré syndrome (GBS) related influenza vaccine safety reports from the Vaccine Adverse Event Reporting System (VAERS) from 1990 to 2016. VAERS reports were selected and manually annotated with major entities related to nervous system disorders, including, investigation, nervous_AE, other_AE, procedure, social_circumstance, and temporal_expression. A variety of conventional machine learning and deep learning algorithms were then evaluated for the extraction of the above entities. We further pretrained domain-specific BERT (Bidirectional Encoder Representations from Transformers) using VAERS reports (VAERS BERT) and compared its performance with existing models. Results and Conclusions Ninety-one VAERS reports were annotated, resulting in 2512 entities. The corpus was made publicly available to promote community efforts on vaccine AEs identification. Deep learning-based methods (eg, bi-long short-term memory and BERT models) outperformed conventional machine learning-based methods (ie, conditional random fields with extensive features). The BioBERT large model achieved the highest exact match F-1 scores on nervous_AE, procedure, social_circumstance, and temporal_expression; while VAERS BERT large models achieved the highest exact match F-1 scores on investigation and other_AE. An ensemble of these 2 models achieved the highest exact match microaveraged F-1 score at 0.6802 and the second highest lenient match microaveraged F-1 score at 0.8078 among peer models.

Karn Wijarnpreecha and Fang Li shared co-first authorship.

Gene flow is widely thought to homogenize spatially separate populations, eroding effects of divergent selection. The resulting theory of 'migration-selection balance' is predicated on a common assumption that all genotypes are equally prone to dispersal. If instead certain genotypes are disproportionately likely to disperse, then migration can actually promote population divergence. For example, previous work has shown that threespine stickleback (Gasterosteus aculeatus) differ in their propensity to move up- or downstream ('rheotactic response'), which may facilitate genetic divergence between adjoining lake and stream populations of stickleback. Here, we demonstrate that intraspecific variation in a sensory system (superficial neuromast lines) contributes to this variation in swimming behaviour in stickleback. First, we show that intact neuromasts are necessary for a typical rheotactic response. Next, we showed that there is heritable variation in the number of neuromasts and that stickleback with more neuromasts are more likely to move downstream. Variation in pectoral fin shape contributes to additional variation in rheotactic response. These results illustrate how within-population quantitative variation in sensory and locomotor traits can influence dispersal behaviour, thereby biasing dispersal between habitats and favouring population divergence.

(1) Background: Several studies showed a sustained temperature of 47 °C or 50 °C for one minute resulted in vascular stasis and bone resorption with only limited bone regrowth over a 3–4-week healing period. The purpose of the present study was to evaluate the temperature changes (ΔΤ) that occur during the preparation of dental implant osteotomies using MIS® straight drills versus Densah® burs in a clockwise (cutting) drilling protocol. (2) Methods: Two hundred (240) osteotomies of two different systems’ drills were prepared at 6 mm depth at 800, 1000, and 1200 revolutions per minute (RPM), in fresh, unembalmed tibiae, obtained by a female cadaver. ΔΤ was calculated by subtracting the baseline temperature on the tibial surface, from the maximum temperature-inside the osteotomy (ΔT = Tmax − Tbase). The variables were evaluated both for their individual and for their synergistic effect on ΔΤ with the use of one-, two-, three- and four-way interactions; (3) Results: An independent and a three-way interaction (drill design, drill width, and RPM) was found in all three RPM for the Densah® burs and at 1000 RPM for the MIS® straight drills. As Densah® burs diameter increased, ΔΤ decreased. The aforementioned pattern was seen only at 1000 RPM for the MIS® straight drills. The usage of drills 20 times more than the implant manufacturers’ recommendation did not significantly affect the ΔΤ. A stereoscopic examination of the specimens confirmed the findings. (4) Conclusions: The independent and synergistic effect of drills’ diameter, design and RPM had a significant effect on ΔΤ in human tibiae, which never exceeded the critical threshold of 47 °C.