Ensemble of deep learning language models to support the creation of living systematic reviews for the COVID-19 literature.

BACKGROUND: The COVID-19 pandemic has led to an unprecedented amount of scientific publications, growing at a pace never seen before. Multiple living systematic reviews have been developed to assist professionals with up-to-date and trustworthy health information, but it is increasingly challenging for systematic reviewers to keep up with the evidence in electronic databases. We aimed to investigate deep learning-based machine learning algorithms to classify COVID-19-related publications to help scale up the epidemiological curation process. METHODS: In this retrospective study, five different pre-trained deep learning-based language models were fine-tuned on a dataset of 6365 publications manually classified into two classes, three subclasses, and 22 sub-subclasses relevant for epidemiological triage purposes. In a k-fold cross-validation setting, each standalone model was assessed on a classification task and compared against an ensemble, which takes the standalone model predictions as input and uses different strategies to infer the optimal article class. A ranking task was also considered, in which the model outputs a ranked list of sub-subclasses associated with the article. RESULTS: The ensemble model significantly outperformed the standalone classifiers, achieving a F1-score of 89.2 at the class level of the classification task. The difference between the standalone and ensemble models increases at the sub-subclass level, where the ensemble reaches a micro F1-score of 70% against 67% for the best-performing standalone model. For the ranking task, the ensemble obtained the highest recall@3, with a performance of 89%. Using an unanimity voting rule, the ensemble can provide predictions with higher confidence on a subset of the data, achieving detection of original papers with a F1-score up to 97% on a subset of 80% of the collection instead of 93% on the whole dataset. CONCLUSION: This study shows the potential of using deep learning language models to perform triage of COVID-19 references efficiently and support epidemiological curation and review. The ensemble consistently and significantly outperforms any standalone model. Fine-tuning the voting strategy thresholds is an interesting alternative to annotate a subset with higher predictive confidence.

Teledentistry in pediatric dentistry: review and presentation of a clinical case.

OBJECTIVES Teledentistry is a telematics approach validated in the literature that allows the remote diagnosis and management of various oral health problems, avoiding direct face-to-face contact with the patient. This study aims to present a review of the scientific literature to analyze in which fields of pediatric dentistry teledentistry has found application and with what results;in addition, a case of unconventional oral candidiasis in a child, diagnosed and managed through the use of teledentistry during the SARS-CoV-2 pandemic in April 2020, is presented. MATERIALS AND METHODS The literature search was performed through PubMed (using keyword and MeSH terms), Scopus and Embase databases, evaluating observational, interventional, case reports and case series studies, published in English between 1999 and 2021 and conducted in children. The clinical case presented was diagnosed and managed through photographs that the pediatric dentist received from the patient's mother via a multi-platform messaging application. Through the same application, the mother was able to provide informed consent to take care of the patient remotely, after acceptance of possible critical issues regarding teledentistry, and receive a prescription for home treatment of oral candidiasis. RESULTS After exclusion of duplicates and articles that did not meet the inclusion criteria, 14 studies were selected. Teledentistry was applied in four different areas: oral health promotion, with 2 studies examining smartphone applications to improve home oral hygiene, diagnosis/follow-up/treatment in orthodontics with 4 studies, caries and other hard and soft tissue diseases of the oral cavity with 7 studies, and finally dental traumatology with a single study. With regard to the promotion of oral health, two applications for the improvement of home oral hygiene were examined. They showed promise for motivation and education. In orthodontics, the studies evaluated in this review reported that teledentistry is useful and valuable for follow-up and orthodontic consultations that can be obtained quickly;doubts remain regarding expense, intervention time and operator compensation. In addition, remotely supervised interceptive treatment appears to reduce the severity of malocclusions. About caries and other hard and soft tissue diseases of the oral cavity, results indicate that teledentistry can reduce waiting lists and the need for face-to-face examinations. Teledentistry is considered valid, efficient and potentially cost-effective for screening and follow-up of caries, being comparable to traditional clinical examination. Teledentistry has proven to be comparable to clinical examination for the diagnosis of dental trauma. CONCLUSIONS The data collected allow us to conclude that teledentistry, thanks to advances in technology, can be a useful means for pediatric dentists to improve the oral health of young patients and to provide better access to oral health services by effectively replacing face-to-face dentistry in various situations. The presented clinical case confirms the conclusions obtained from the literature search. CLINICAL SIGNIFICANCE Teledentistry can replace face-to-face visits in several areas of pediatric dentistry and ensuring safe care during any future pandemics.Copyright © 2023 EDRA SpA. Tutti i diritti riservati.

Risk and Protective Factors in the COVID-19 Pandemic: A Rapid Evidence Map.

Background: Given the worldwide spread of the 2019 Novel Coronavirus (COVID-19), there is an urgent need to identify risk and protective factors and expose areas of insufficient understanding. Emerging tools, such as the Rapid Evidence Map (rEM), are being developed to systematically characterize large collections of scientific literature. We sought to generate an rEM of risk and protective factors to comprehensively inform areas that impact COVID-19 outcomes for different sub-populations in order to better protect the public. Methods: We developed a protocol that includes a study goal, study questions, a PECO statement, and a process for screening literature by combining semi-automated machine learning with the expertise of our review team. We applied this protocol to reports within the COVID-19 Open Research Dataset (CORD-19) that were published in early 2020. SWIFT-Active Screener was used to prioritize records according to pre-defined inclusion criteria. Relevant studies were categorized by risk and protective status; susceptibility category (Behavioral, Physiological, Demographic, and Environmental); and affected sub-populations. Using tagged studies, we created an rEM for COVID-19 susceptibility that reveals: (1) current lines of evidence; (2) knowledge gaps; and (3) areas that may benefit from systematic review. Results: We imported 4,330 titles and abstracts from CORD-19. After screening 3,521 of these to achieve 99% estimated recall, 217 relevant studies were identified. Most included studies concerned the impact of underlying comorbidities (Physiological); age and gender (Demographic); and social factors (Environmental) on COVID-19 outcomes. Among the relevant studies, older males with comorbidities were commonly reported to have the poorest outcomes. We noted a paucity of COVID-19 studies among children and susceptible sub-groups, including pregnant women, racial minorities, refugees/migrants, and healthcare workers, with few studies examining protective factors. Conclusion: Using rEM analysis, we synthesized the recent body of evidence related to COVID-19 risk and protective factors. The results provide a comprehensive tool for rapidly elucidating COVID-19 susceptibility patterns and identifying resource-rich/resource-poor areas of research that may benefit from future investigation as the pandemic evolves.