Leveraging deep-learning and unconventional data for real-time surveillance, forecasting, and early warning of respiratory pathogens outbreak

Artificial Intelligence in Medicine, Год журнала: 2025, Номер 161, С. 103076 - 103076

Опубликована: Фев. 1, 2025

Язык: Английский

---

Leveraging Responsible, Explainable, and Local Artificial Intelligence Solutions for Clinical Public Health in the Global South

Healthcare, Год журнала: 2023, Номер 11(4), С. 457 - 457

Опубликована: Фев. 4, 2023

In the present paper, we will explore how artificial intelligence (AI) and big data analytics (BDA) can help address clinical public global health needs in Global South, leveraging capitalizing on our experience with “Africa-Canada Artificial Intelligence Data Innovation Consortium” (ACADIC) Project focusing ethical regulatory challenges had to face. “Clinical health” be defined as an interdisciplinary field, at intersection of medicine health, whilst “clinical is practice a special focus issue management resource-limited settings contexts, including South. As such, represent vital approaches, instrumental (i) applying community/population perspective well lens (ii) identifying both individual levels, (iii) systematically addressing determinants social structural ones, (iv) reaching goals population’s well-being, especially socially vulnerable, underserved communities, (v) better coordinating integrating delivery healthcare provisions, (vi) strengthening promotion, protection, equity, (vii) closing gender inequality other (ethnic socio-economic) disparities gaps. Clinical are called respond more pressing contemporary society, for which AI BDA unlock new options perspectives. aftermath still ongoing COVID-19 pandemic, future trend field devoted building healthy, resilient able face several arising from globally networked hyper-risks, ageing, multimorbidity, chronic disease accumulation, climate change.

Язык: Английский

---

Regional analysis of economic resilience pre and post COVID-19 pandemic in Indonesia

R-Economy, Год журнала: 2025, Номер 11(1), С. 94 - 109

Опубликована: Янв. 1, 2025

Relevance. Similar to other countries, Indonesia's economy was significantly impacted by the COVID-19 pandemic, especially at district and city levels. As second-largest contributor GDP, East Java faced noticeable economic downturns. Industry, region's main sector, played a key role in these challenges, making it essential evaluate all sectors from regional perspective navigate this turbulence effectively. Research objective. This study investigates economy's sectoral competitiveness Java, with particular focus on 17 categorized Statistic Indonesia (Badan Pusat Statistik-BPS) before after COVID-19. Data methods. The relies data Badan Statistik (BPS). dataset includes GDP information for 11 regions, namely 7 districts 4 cities, 2018 2022, covering pre- post-pandemic periods. Methodologically, employed Location Quotient (LQ) analysis Mix Share Analysis. LQ used assess concentration comparative advantage of Java's regions. Shift-Share analyses were applied identify competitive industries specific regions their advantages. Results. findings show positive growth most except two regencies that saw decline. emphasizes need strengthen resilience village level using Village Fund national budget. Conclusions. Regional stakeholders, central government interventions, continued development leading are mitigating effects According theory, collaboration between businesses is crucial enhancing increasing number sectors.

Язык: Английский

---

Accurate total consumer price index forecasting with data augmentation, multivariate features, and sentiment analysis: A case study in Korea

PLoS ONE, Год журнала: 2025, Номер 20(5), С. e0321530 - e0321530

Опубликована: Май 13, 2025

The Consumer Price Index (CPI) is a key economic indicator used by policymakers worldwide to monitor inflation and guide monetary policy decisions. In Korea, the CPI significantly impacts decisions on interest rates, fiscal frameworks, Bank of Korea’s strategies for stability. Given its importance, accurately forecasting Total crucial informed decision-making. Achieving accurate estimation, however, presents several challenges. First, Korean calculated as weighted sum 462 items grouped into 12 categories goods services. This heterogeneity makes it difficult account all variations in consumer behavior price dynamics. Second, monthly frequency data results relatively sparse time series, limiting performance analysis. Furthermore, external factors such changes pandemics add further volatility CPI. To address these challenges, we propose novel framework consisting four components: (1) hybrid Convolutional Neural Network-Long Short-Term Memory mechanism designed capture complex patterns data, enhancing estimation accuracy; (2) multivariate inputs that incorporate component indices alongside auxiliary variables richer contextual information; (3) augmentation through linear interpolation convert daily optimizing highly parametrized deep learning models; (4) sentiment index derived from CPI-related news articles, providing insights influencing fluctuations. Experimental demonstrate proposed model outperforms existing approaches prediction, evidenced lower RMSE values. improved accuracy has potential support development more timely effective policies.

Язык: Английский

---

A fairness assessment of mobility-based COVID-19 case prediction models

PLoS ONE, Год журнала: 2023, Номер 18(10), С. e0292090 - e0292090

Опубликована: Окт. 18, 2023

In light of the outbreak COVID-19, analyzing and measuring human mobility has become increasingly important. A wide range studies have explored spatiotemporal trends over time, examined associations with other variables, evaluated non-pharmacologic interventions (NPIs), predicted or simulated COVID-19 spread using data. Despite benefits publicly available data, a key question remains unanswered: are models data performing equitably across demographic groups? We hypothesize that bias in used to train predictive might lead unfairly less accurate predictions for certain groups. To test our hypothesis, we applied two mobility-based COVID infection prediction at county level United States SafeGraph correlated model performance sociodemographic traits. Findings revealed there is systematic models' toward characteristics. Specifically, tend favor large, highly educated, wealthy, young, urban counties. currently by many tends capture information about older, poorer, educated people from rural regions, which turn negatively impacts accuracy these areas. Ultimately, this study points need improved collection sampling approaches allow an representation patterns

Язык: Английский

---

Off-label drug use during the COVID-19 pandemic in Africa: topic modelling and sentiment analysis of ivermectin in South Africa and Nigeria as a case study

Journal of The Royal Society Interface, Год журнала: 2023, Номер 20(206)

Опубликована: Сен. 1, 2023

Although rejected by the World Health Organization, human and even veterinary formulation of ivermectin has widely been used for prevention treatment COVID-19. In this work we leverage Twitter to understand reasons drug use from supporters, their source information, emotions, gender demographics, location in Nigeria South Africa. Topic modelling is performed on a dataset gathered using keywords ‘ivermectin’ ‘ivm’. A model fine-tuned RoBERTa find stance tweets. Statistical analysis compare emotions. Most supporters either redistribute conspiracy theories posted influencers, or refer flawed studies confirming efficacy vitro . Three emotions have highest intensity, optimism, joy disgust. The number anti-ivermectin tweets significant positive correlation with vaccination rate. All provinces Africa most are pro-ivermectin higher disgust polarity. This makes effort public discussions regarding during COVID-19 pandemic help policy-makers rationale behind its popularity, inform more targeted policies discourage self-administration ivermectin. Moreover, it lesson future outbreaks.

Язык: Английский

---

Coronavirus Disease (COVID-19) Pandemic and Global Economic Circumstance

JOURNAL OF SOCIAL SCIENCE RESEARCH, Год журнала: 2023, Номер 19, С. 41 - 47

Опубликована: Март 16, 2023

This research investigates the influence of Coronavirus Disease (COVID-19) Pandemic event on evolution global economic circumstances, particularly among developed countries, including United States. The findings showed that COVID-19 has a widespread impact inflation expectations and individuals' lifestyles social life remarkably. These have consequences for actual activity, whereas careful monitoring may indicate anticipations un-anchoring dangers. According to these outcomes, providing comfortable situation finding right job managing in individual part by governments or any charge organizations workplaces is sincerely recommended. Additionally, taking care mental health treating suffering individuals must be considered.

Язык: Английский

---

Self-Harm Presentations to Hospital Trauma Centre Emergency Departments during the First Year of the COVID-19 Pandemic

Psychiatry Research, Год журнала: 2024, Номер 336, С. 115892 - 115892

Опубликована: Апрель 6, 2024

The COVID-19 pandemic raised concerns regarding increased suicide-related behaviours. We compared characteristics and counts of Emergency Department (ED) presentations for self-harm, an important outcome, during versus prior to the pandemic's first year. included patients presenting with self-harm ED two trauma centres in Toronto, Canada. Time series models intra-pandemic (March 2020-February 2021) presentation predictions from pre-pandemic data. proportion was between period preceding three years. A retrospective chart review eligible seen March 2019-February 2021 pre- vs. patient injury characteristics. While monthly were largely within expected ranges, total increased. Being widowed (OR=9.46; 95 %CI=1.10-81.08), employment/financial stressors (OR=1.65, %CI=1.06-2.58), job loss (OR=3.83; %CI=1.36-10.76), chest-stabbing (OR=2.50; %CI=1.16-5.39) associated presentations. Intra-pandemic also Intensive Care Unit (ICU) admission (OR=2.18, %CI=1.41-3.38). In summary, while number these did not increase early pandemic, their association variables indicating medically severe injury, economic stressors, being may inform future suicide prevention strategies.

Язык: Английский

---

Volatility of the COVID-19 vaccine hesitancy: sentiment analysis conducted in Brazil

Frontiers in Public Health, Год журнала: 2023, Номер 11

Опубликована: Июль 7, 2023

Background Vaccine hesitancy is a phenomenon that can interfere with the expansion of vaccination coverage and positioned as one top 10 global health threats. Previous studies have explored factors affect vaccine hesitancy, how it behaves in different locations, profile individuals which most present. However, few analyzed volatility hesitancy. Objective Identify manifested social media. Methods Twitter’s academic application programming interface was used to retrieve all tweets Brazilian Portuguese mentioning COVID-19 3 months (October 2020, June 2021, October 2021), retrieving 1,048,576 tweets. A sentiment analysis performed using Orange software lexicon Multilingual Portuguese. Results The feelings associated were volatile within 1 month, well throughout process, being resilient phenomenon. themes nurture change dynamically swiftly are often other topics also affecting society. Conclusion People manifest present arguments vary short period time, what demand government strategies mitigate effects be agile counteract expressed fear, by presenting scientific arguments.

Язык: Английский

---

Overcoming Crises of 2008 and 2020 by Developed and Developing Countries: Comparative Analysis

Bulletin of Kemerovo State University Series Political Sociological and Economic sciences, Год журнала: 2023, Номер 2023(3), С. 312 - 322

Опубликована: Окт. 17, 2023

Today the socio-economic development suffers from a high level of uncertainty and large number global changes. The purpose study is to compare how modern crises affected on economies developed developing countries assess economies’ weak points capabilities recover. authors analyzed dynamics countries’ real gross domestic ptoduct in 2001–2021 identified 2 most significant crisis periods. A comparative analysis inflation rates shows that during pandemic growth was more gradual than 2008; restrained countries. indicators 2007–2021 countries, G7 substantiates COVID-19 led less serious consequences for world economy economic 2008 due population business support programs, implementated by state institutions an unprecedented scale. According indicators, reaction restrained, recovery post-crisis period faster. However, primary reason this implementation rescue program article presents recommendations ensuring post-pandemic

Язык: Английский

---