Cats requiring MV for elapid snake envenomation have a favorable outcome and require a relatively short period of MV. Complications encountered are unlikely to influence outcome.
ObjectiveTo determine whether patterns of trauma changed following the start of local lockdowns due to COVID-19.DesignMulti-institutional retrospective study assessing patients presenting within 2 years prior to local lockdown due to COVID-19 and 1 year following lockdown inclusive.SettingTwo university teaching hospitals and one private referral center in Australia.AnimalsDogs and cats with a presenting complaint of known or suspected trauma.InterventionsPatient signalment, date of presentation, trauma type, treatment interventions and patient outcome (survival to discharge, cardiopulmonary arrest, or euthanasia) were recorded in a web-based data capture system (REDCap).Measurements and Main ResultsThree thousand one hundred eighty-nine patients (682 cats and 2,507 dogs) were included in the study. Overall trauma prevalence was 2.9% with pre-lockdown prevalence of 2.8% and post-lockdown prevalence of 3.1% (p < 0.001). Cats had higher rates of blunt trauma while penetrating trauma was more prevalent in dogs (p < 0.001). Juvenile patients were also more likely to have blunt trauma when compared to adult patients (p < 0.001). Patient age and sex characteristics did not differ when comparing the 2 time periods. Compared to pre-lockdown, blunt and penetrating trauma patterns changed post-lockdown in dogs and cats (p < 0.001 for both). Interventions were performed more frequently (p = 0.039) in the post-lockdown with surgical procedures having a significant increase (p = 0.015). Survival rates increased post-lockdown for both species (p < 0.001) with financially driven euthanasia being less common than in pre-lockdown for dogs (p = 0.02).ConclusionsTrauma patterns changed for cats and dogs in the post-lockdown period. Compared to pre-lockdown, trauma prevalence was higher with a decrease in mortality rate. No increase in juvenile patients was identified post-lockdown. A decrease in financially driven euthanasia and an increase in interventions suggest no negative financial effect from COVID-19 lockdown on trauma patient care in Australia.
108 Background: Classification of disease response is an essential task in cancer research and needs to be done at scale. Automating this process can improve efficiency in the generation of real-world evidence, potentially leading to better patient outcomes. We aim to develop and evaluate Natural Language Processing (NLP) models for this task. Methods: Using 6203 computed tomography (CT) and 1358 magnetic resonance imaging (MRI) reports from 587 patients with lung cancer of all stages seen at the National Cancer Centre Singapore (NCCS), we trained four NLP models (BioBERT, RadBERT-RoBERTA, BioClinicalBERT, GatorTron) to classify the reports into one of four categories: no evidence of disease, stable disease, partial response or disease progression. Model output was compared against human-curated ground truth and performance was evaluated by accuracy. Results: Of the 4 models, GatorTron performed the best (accuracy = 97.1%), followed by RadBERT-RoBERTA (accuracy = 96.2%), BioBERT (accuracy = 94.2%), with BioClinicalBERT being last (accuracy = 90.4%). NLP Model runtimes for the dataset were relatively short, with BioBERT and BioClinicalBERT taking 3 minutes per epoch, RadBERT-RoBERTA taking 6 minutes per epoch, and GatorTron taking 10 minutes per epoch on a single central processing unit (CPU). Conclusions: We have demonstrated the effectiveness of NLP models for classifying disease responses in radiology reports of lung cancer patients. This has the potential to help derive progression-free survival for real-world evidence generation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.