دورية أكاديمية
Analysing the impact of comorbid conditions and media coverage on online symptom search data: a novel AI-based approach for COVID-19 tracking.
| العنوان: | Analysing the impact of comorbid conditions and media coverage on online symptom search data: a novel AI-based approach for COVID-19 tracking. |
|---|---|
| المؤلفون: | Lyu S; School of Computer Science, Monash University, Melbourne, Australia., Adegboye O; Menzies School of Health Research, Darwin, Charles Darwin University, NT, Australia., Adhinugraha KM; School of Computing and Information Technology, La Trobe University, Melbourne, Australia., Emeto TI; Australian Institute of Tropical Health and Medicine, James Cook University, Townsville, QLD, Australia., Taniar D; School of Computer Science, Monash University, Melbourne, Australia. |
| المصدر: | Infectious diseases (London, England) [Infect Dis (Lond)] 2024 May; Vol. 56 (5), pp. 348-358. Date of Electronic Publication: 2024 Feb 02. |
| نوع المنشور: | Journal Article |
| اللغة: | English |
| بيانات الدورية: | Publisher: Informa Healthcare Country of Publication: England NLM ID: 101650235 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 2374-4243 (Electronic) Linking ISSN: 23744243 NLM ISO Abbreviation: Infect Dis (Lond) Subsets: MEDLINE |
| أسماء مطبوعة: | Original Publication: London, England : Informa Healthcare, [2015]- |
| مواضيع طبية MeSH: | COVID-19*/epidemiology, Humans ; SARS-CoV-2 ; Disease Outbreaks ; Artificial Intelligence |
| مستخلص: | Background: Web search data have proven to bea valuable early indicator of COVID-19 outbreaks. However, the influence of co-morbid conditions with similar symptoms and the effect of media coverage on symptom-related searches are often overlooked, leading to potential inaccuracies in COVID-19 simulations. Method: This study introduces a machine learning-based approach to estimate the magnitude of the impact of media coverage and comorbid conditions with similar symptoms on online symptom searches, based on two scenarios with quantile levels 10-90 and 25-75. An incremental batch learning RNN-LSTM model was then developed for the COVID-19 simulation in Australia and New Zealand, allowing the model to dynamically simulate different infection rates and transmissibility of SARS-CoV-2 variants. Result: The COVID-19 infected person-directed symptom searches were found to account for only a small proportion of the total search volume (on average 33.68% in Australia vs. 36.89% in New Zealand) compared to searches influenced by media coverage and comorbid conditions (on average 44.88% in Australia vs. 50.94% in New Zealand). The proposed method, which incorporates estimated symptom component ratios into the RNN-LSTM embedding model, significantly improved COVID-19 simulation performance. Conclusion: Media coverage and comorbid conditions with similar symptoms dominate the total number of online symptom searches, suggesting that direct use of online symptom search data in COVID-19 simulations may overestimate COVID-19 infections. Our approach provides new insights into the accurate estimation of COVID-19 infections using online symptom searches, thereby assisting governments in developing complementary methods for public health surveillance. |
| فهرسة مساهمة: | Keywords: COVID-19; Infectious diseases; deep learning; digital health; infection control; social media |
| SCR Organism: | SARS-CoV-2 variants |
| تواريخ الأحداث: | Date Created: 20240202 Date Completed: 20240403 Latest Revision: 20240403 |
| رمز التحديث: | 20240403 |
| DOI: | 10.1080/23744235.2024.2311281 |
| PMID: | 38305899 |
| قاعدة البيانات: | MEDLINE |
PDF full text from Publisher | تدمد: | 2374-4243 |
|---|---|
| DOI: | 10.1080/23744235.2024.2311281 |