It is very important to ensure reliable performance of deep learning model for future dataset for healthcare. This is more pronounced in the case of patient generated health data such as patient reported symptoms, which are not collected in a controlled environment. Since there has been a big difference in influenza incidence since the COVID-19 pandemic, we evaluated whether the deep learning model can maintain sufficiently robust performance against these changes. We have collected 226,655 episodes from 110,893 users since June 2020 and tested the influenza screening model, our model showed 87.02% sensitivity and 0.8670 of AUROC. The results of COVID-19 pandemic are comparable to that of before COVID-19 pandemic.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.3233/SHTI220533 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
This article provides an overview of vitamin C for preventing and treating respiratory infections. Studies in a wide variety of animals have shown vitamin C to be protective against infections. In controlled trials in the general human population, >1 g/day vitamin C did not prevent common colds.
View Article and Find Full Text PDFBlastic Plasmacytoid Dendritic Cell Neoplasm, a Very Rare Hematological Malignancy With Initial Cutaneous Involvement: A Case Report.
Acta Dermatovenerol Croat
November 2024
Prof. Miloš Nikolić, MD, PhD, University of Belgrade, School of Medicine,, Belgrade, Serbia;
Blastic plasmacytoid dendritic cell neoplasm (BPDCN) is a very rare and aggressive hematologic malignancy, arising from plasmacytoid dendritic cells (pDCs). BPDCN frequently has, at least initially, exclusively cutaneous presentation. We present a 45-year-old woman with a 3-month history of rapidly evolving violaceous patches, infiltrated plaques, and bruise-like tumefactions, disseminated on her face and upper trunk.
View Article and Find Full Text PDFBridging the health information gap among undergraduate university students: The role of academic libraries.
Health Info Libr J
January 2025
Sam Jonah Library, University of Cape Coast, Cape Coast, Ghana.
Background: Although university students are young and seem generally healthy, they do have health information needs that affect their academic work. Some university healthcare services and academic libraries collaborated during the COVID-19 pandemic to provide health information to students.
Aims/objectives: The study explored the health information gap among undergraduate students in universities in Ghana.
Psychiatric Epidemiology During the COVID-19 Pandemic.
Curr Epidemiol Rep
June 2024
Department of Epidemiology, Mailman School of Public Health, Columbia University, NY, NY.
Purpose Of Review: Our review critically examines research on trends in mental health among US adults following the COVID-19 pandemic's onset and makes recommendations for research on the topic.
Recent Findings: Studies comparing pre-pandemic nationally representative government surveys ("benchmark surveys") with pandemic-era non-benchmark surveys generally estimated 3-4-fold increases in the prevalence of adverse mental-health outcomes following the pandemic's onset. However, studies analyzing trends in repeated waves of a single survey, which may carry a lower risk of bias, generally estimated much smaller increases in adverse outcomes.
Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the etiological agent of the coronavirus disease 2019 (COVID-19) pandemic, remains endemic worldwide ∼5 years since the first documented case. Severe COVID-19 is widely considered to be caused by a dysregulated immune response to SARS-CoV-2 within the respiratory tract. Circulating levels of the chemokine CXCL10 are strongly positively associated with poor outcome; however, its precise role in pathogenesis and its suitability as a therapeutic target have remained undefined.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!