Natural language processing for clinical text in Spanish: The case of waiting lists in Chile

The waiting lists not covered by the Explicit Health Guarantee Plan for new specialty consultation in Chile increased due to the effects of the SARS-CoV-2 coronavirus (COVID-19) pandemic. This represents a problem derived from the delay in the resolution and prioritization of each case. This paper aims to describe the issue of the waiting lists in the Chilean health system and present an example of the application of Natural Language Processing (NLP). Specifically, a methodology for recognizing key information in medical narratives is described. Currently, we have a set of manually annotated medical referrals in the development of the Chilean Waiting List Corpus, with a fraction of 2,000 referrals in which the annotated medical entities were automatically normalized to the Unified Medical Language System concepts using the lexicon MedLexSp. The clinical NLP Group of the Center for Mathematical Modeling of the University of Chile, and other national NLP groups, are developing several tools and resources in medicine that can be transferred to the Chilean health system to support managing clinical text in Spanish. © 2022

Procesamiento de lenguaje natural para texto clínico en español: el caso de las listas de espera en Chile

The waiting lists not covered by the Explicit Health Guarantee Plan for new specialty consultation in Chile increased due to the effects of the SARS-CoV-2 coronavirus (COVID-19) pandemic. This represents a problem derived from the delay in the resolution and prioritization of each case. This paper aims to describe the issue of the waiting lists in the Chilean health system and present an example of the application of Natural Language Processing (NLP). Specifically, a methodology for recognizing key information in medical narratives is described. Currently, we have a set of manually annotated medical referrals in the development of the Chilean Waiting List Corpus, with a fraction of 2,000 referrals in which the annotated medical entities were automatically normalized to the Unified Medical Language System concepts using the lexicon MedLexSp. The clinical NLP Group of the Center for Mathematical Modeling of the University of Chile, and other national NLP groups, are developing several tools and resources in medicine that can be transferred to the Chilean health system to support managing clinical text in Spanish.

IMPLEMENTATION AND SHORT-TERM ADVERSE EVENTS OF ANTI-SARSCOV-2 VACCINES IN INFLAMMATORY BOWEL DISEASE PATIENTS: AN INTERNATIONAL WEB-BASED SURVEY

Introduction: Pivotal anti-SARS-CoV-2 vaccines clinical trials did not include patients with immune-mediated conditions such as inflammatory bowel disease (IBD). We aimed to describe the implementation of anti-SARS-CoV-2 vaccines among IBD patients, patients' concerns before vaccination and side-effect profile of the anti-SARS-CoV-2 vaccines using real-world data. Methods: An anonymous web-based self-completed survey was distributed in 36 European countries between June and July 2021. The results of patients' characteristics, concerns, vaccination status and side-effect profile were analysed using descriptive statistics and logistic regression. Results: Among the 3272 IBD patients completing the survey (0.1% of the IBD European population), 79.6% had received at least one dose of anti-SARS-CoV- 2 vaccine, and 71.7% had completed the vaccination process. Most of the patients (70.6%) were vaccinated with the Pfizer-BioNTech (BNT162b2) vaccine. Patients over 60 years old had a significantly higher rate of vaccination (OR 2.98, 95% CI 2.20-4.03, p<0.001). Patients' main concerns before vaccination were the possibility of having worse vaccine-related adverse events due to their IBD (24.6%), having an IBD flare after vaccination (21.1%) and reduced vaccine efficacy due to IBD or associated immunosuppression (17.6%). After the first dose of the vaccine, 72.4% had local symptoms at the injection site and 51.4% had systemic symptoms (5 patients had non-specified thrombosis). Adverse events were less frequent after the second dose of the vaccine and in older patients. When comparing with previous studies from the general population, the IBD patients answering the survey did not seem to have increased side effects (table 1). Only a minority of the patients were hospitalized (0.3%), needed a consultation (3.6%) or had to change IBD therapy (13.4%) after anti- SARS-CoV-2 vaccination. Conclusion: Although IBD patients raised concerns about the safety and efficacy of anti-SARS-CoV-2 vaccines, the implementation of vaccination in those responding to our survey was high and the adverse events were comparable to the general population, with minimal impact on their IBD. (Table Presented)

Regional Hotspots of Food Insufficiency During COVID-19: Evidence From the Household Pulse Survey

Objectives To examine regional differences in food insufficiency among households with children between Deep South states and the rest of the United States during the second year of the COVID-19 pandemic. Methods The U.S. Census Bureau's Household Pulse Survey is a massive, online, and rapid interagency effort to provide data on the social consequences of COVID-19. Here, data on food insufficiency among households with children, reported by household respondents (N = 232,016), were taken from phases 3.1 (4/15–7/5/2021) and 3.2 (7/21–10/11/2021). The main predictor was living in a Deep South state (Alabama, Georgia, Louisiana, Mississippi, South Carolina). Logistic regression models were run separately for each phase, adjusting for age, gender, race/ethnicity, marital status, household head educational attainment, number of children in the household, and household income-to-poverty ratio. Differences in these variables between the regions were also assessed. Survey weights included with Pulse were used in all analyses. Results The overall prevalence of food insufficiency among households with children was 12.2% in phase 3.1, with a higher prevalence in Deep South states (16.4%) compared to non-Deep South states (11.8%;p < .0001). Food insufficiency prevalence decreased in phase 3.2 to 10.3% for all households, but regional differences remained (Deep South = 13.9%, non-Deep South = 9.9%). Crude analysis showed that households with children in Deep South states had 46% and 63% higher odds of food insufficiency than non-Deep South states in phases 3.1 and 3.2, respectively. Factors associated with food insufficiency, including lower income and lower educational status, were more common in the Deep South, but after adjusting for these and other covariates, the odds of food insufficiency in Deep South states were still significantly greater (phase 3.1: OR = 1.19, 95%CI = 1.04–1.37;phase 3.2: OR = 1.30, 95%CI = 1.13–1.51). Conclusions Regional inequities in food insufficiency among households with children were present in the second year of the COVID-19 pandemic, with Deep South states suffering from higher rates. Factors associated with this problem were worse in the Deep South, but they did not fully explain differences between regions. Future studies should investigate the reasons for these inequities. Funding Sources Health Research Services Administration, DHHS.

Adapting to the Times: Examining Adaptive Instructional Strategies in Preferred and Non-preferred Class Types

Adaptive training can take place across multiple learning contexts, such as in-person or online class types, and in classroom or simulation environments [1]. Given the COVID-19 pandemic, institutes of higher education were forced to adapt and make instruction available both online and in-person;providing the opportunity to examine how adaptive learning strategies faired in different class types. When examining adaptive strategies across class types, of particular interest are individual learner characteristics and preferences, as students who typically would not take online classes found themselves taking classes in this medium [2]. We sought to evaluate the effectiveness of adaptive learning strategies across preferred and non-preferred class types. A significant interaction was found between instructional strategy presence and preferred class type, with students primarily attending classes in their preferred class type self-reporting significantly lower stress and workload levels than those who did not receive the adaptive instructional strategies. For students attending class primarily in their non-preferred learning environment, the opposite was true. Additionally, students in their preferred class types achieved higher exam scores. The methods, results, discussion and implications are discussed in the context of how to effectively conduct adaptive training. © 2021, Springer Nature Switzerland AG.

Clinical and immunological aspects of SARS-CoV-2 infection

Objective: To describe the molecular and cellular aspects of the immune response against SARS-CoV-2 and the clinical repercussions resulting from inefficient immune mechanisms. Introduction: The emergence of an atypical pneumonia in China in December 2019 led to a global confinement. The agent responsible for this new disease was named SARS-CoV-2 by the International Committee on Taxonomy of viruses, and the disease it produces was named COVID-19 by the WHO on February 11, 2020. Methodology: For this descriptive study we researched the databases of Pubmed, Science, Nature, The Lancet, The New England Journal of Medicine, medRxiv and Google Scholar;which descriptors used were: COVID-19, 2019-nCoV, SARS-CoV-2, lymphocytes, antibodies and immunity;including 130 studies in the review.