Spatio-temporal modeling of COVID-19 prevalence and mortality using artificial neural network algorithms

Validation study for assessing COVID-19 pneumonia treatments

This study investigates the effectiveness of Azvudine and nirmatrelvir-ritonavir (Paxlovid) in treating COVID-19 pneumonia through an analysis of real-world clinical data. We retrospectively collected data from COVID-19 patients hospitalized at the Second Xiangya Hospital of Central South University between December 21, 2022, and January 18, 2023. Using kernel density estimation, box-and-whisker plots, and Schoenfeld residual plots, we evaluated the transition of patients to negative status and assessed factors such as age, disease severity, and treatment effects. The findings revealed that both Azvudine and Paxlovid significantly reduced recovery times, with Azvudine showing notable benefits for patients aged 50-80. Our analysis indicated that these drugs improved lung CT values and reduced disease severity in moderate cases. The Cox model demonstrated robustness in predicting outcomes, and a nomogram was developed for individualized recovery probability assessment. These results provide important insights into optimizing COVID-19 treatment and the potential of predictive models in clinical decision-making.

Prolonged exposure to air pollution and risk of acute kidney injury and related mortality: a prospective cohort study based on hospitalized AKI cases and general population controls from the UK Biobank

BACKGROUND

Previous investigations identified a connection between air pollution and kidney diseases. Nevertheless, there is a lack of comprehensive evidence on the long-term risks posed by air pollution with respect to acute kidney injury (AKI) and AKI-related death.

METHODS

This prospective cohort analysis included 414,885 UK Biobank (UKB) participants who did not exhibit AKI at the study's outset. AKI was defined based on ICD-10 codes recorded for hospitalized patients. Cox proportional hazards models were used to assess the association between prolonged exposure to air pollutants (particulate matter with diameters of 2.5 micrometers or less (PM2.5), between 2.5 and 10 micrometers (PM2.5-10), and 10 micrometers or less (PM10), along with nitrogen dioxide (NO2) and nitrogen oxides (NOx)) and the risk of AKI and AKI-related death, adjusting for potential confounders including sex, age, ethnicity, education, income, lifestyle factors, and relevant clinical covariates. Restricted cubic splines were applied to evaluate non-linear dose-response relationships, and stratified analyses were performed to explore potential effect modification across subgroups.

RESULTS

Over an average follow-up duration of 11.7 years, 14,983 cases of AKI and 326 cases of AKI-related death were diagnosed. Quartile analysis showed individuals exposed to higher levels of these air pollutants had a significantly higher risk of developing AKI and AKI-related death compared to those in the lowest quartile (all P < 0.05). The RCS curves depicting the relationship between PM2.5, PM2.5-10, PM10, NO2, NOx, and the risk of AKI showed a significant departure from linearity (P for non-linearity < 0.05), while the relationships between PM2.5, NO2, NOx, and the risk of AKI-related death did not exhibit a significant departure from linearity (P for non-linearity > 0.05). Sensitivity analyses confirmed the robustness of our findings.

CONCLUSION

Our study reveals a direct association between prolonged air pollution exposure and elevated risks of both AKI and AKI-related death. These findings offer scientific validation for the adoption of environmental and public health measures directed towards the reduction of air pollution. Such initiatives could potentially ease the impact associated with AKI and AKI-related death.

Towards Improved XAI-Based Epidemiological Research into the Next Potential Pandemic

By applying AI techniques to a variety of pandemic-relevant data, artificial intelligence (AI) has substantially supported the control of the spread of the SARS-CoV-2 virus. Along with this, epidemiological machine learning studies of SARS-CoV-2 have been frequently published. While these models can be perceived as precise and policy-relevant to guide governments towards optimal containment policies, their black box nature can hamper building trust and relying confidently on the prescriptions proposed. This paper focuses on interpretable AI-based epidemiological models in the context of the recent SARS-CoV-2 pandemic. We systematically review existing studies, which jointly incorporate AI, SARS-CoV-2 epidemiology, and explainable AI approaches (XAI). First, we propose a conceptual framework by synthesizing the main methodological features of the existing AI pipelines of SARS-CoV-2. Upon the proposed conceptual framework and by analyzing the selected epidemiological studies, we reflect on current research gaps in epidemiological AI toolboxes and how to fill these gaps to generate enhanced policy support in the next potential pandemic.

A Bayesian spatio-temporal model of COVID-19 spread in England

Exploring the spatio-temporal variations of COVID-19 transmission and its potential determinants could provide a deeper understanding of the dynamics of disease spread. This study aimed to investigate the spatio-temporal spread of COVID-19 infections in England, and examine its associations with socioeconomic, demographic and environmental risk factors. We obtained weekly reported COVID-19 cases from 7 March 2020 to 26 March 2022 at Middle Layer Super Output Area (MSOA) level in mainland England from publicly available datasets. With these data, we conducted an ecological study to predict the COVID-19 infection risk and identify its associations with socioeconomic, demographic and environmental risk factors using a Bayesian hierarchical spatio-temporal model. The Bayesian model outperformed the ordinary least squares model and geographically weighted regression model in terms of prediction accuracy. The spread of COVID-19 infections over space and time was heterogeneous. Hotspots of infection risk exhibited inconsistent clustering patterns over time. Risk factors found to be positively associated with COVID-19 infection risk were: annual household income [relative risk (RR) = 1.0008, 95% Credible Interval (CI) 1.0005-1.0012], unemployment rate [RR = 1.0027, 95% CI 1.0024-1.0030], population density on the log scale [RR = 1.0146, 95% CI 1.0129-1.0164], percentage of Caribbean population [RR = 1.0022, 95% CI 1.0009-1.0036], percentage of adults aged 45-64 years old [RR = 1.0031, 95% CI 1.0024-1.0039], and particulate matter ( PM 2.5 ) concentrations [RR = 1.0126, 95% CI 1.0083-1.0167]. The study highlights the importance of considering socioeconomic, demographic, and environmental factors in analysing the spatio-temporal variations of COVID-19 infections in England. The findings could assist policymakers in developing tailored public health interventions at a localised level.

Optimizing spatio-temporal correlation structures for modeling food security in Africa: a simulation-based investigation

This study investigates the impact of spatio- temporal correlation using four spatio-temporal models: Spatio-Temporal Poisson Linear Trend Model (SPLTM), Poisson Temporal Model (TMS), Spatio-Temporal Poisson Anova Model (SPAM), and Spatio-Temporal Poisson Separable Model (STSM) concerning food security and nutrition in Africa. Evaluating model goodness of fit using the Watanabe Akaike Information Criterion (WAIC) and assessing bias through root mean square error and mean absolute error values revealed a consistent monotonic pattern. SPLTM consistently demonstrates a propensity for overestimating food security, while TMS exhibits a diverse bias profile, shifting between overestimation and underestimation based on varying correlation settings. SPAM emerges as a beacon of reliability, showcasing minimal bias and WAIC across diverse scenarios, while STSM consistently underestimates food security, particularly in regions marked by low to moderate spatio-temporal correlation. SPAM consistently outperforms other models, making it a top choice for modeling food security and nutrition dynamics in Africa. This research highlights the impact of spatial and temporal correlations on food security and nutrition patterns and provides guidance for model selection and refinement. Researchers are encouraged to meticulously evaluate the biases and goodness of fit characteristics of models, ensuring their alignment with the specific attributes of their data and research goals. This knowledge empowers researchers to select models that offer reliability and consistency, enhancing the applicability of their findings.

Identifying childhood malaria hotspots and risk factors in a Nigerian city using geostatistical modelling approach

Malaria ranks high among prevalent and ravaging infectious diseases in sub-Saharan Africa (SSA). The negative impacts, disease burden, and risk are higher among children and pregnant women as part of the most vulnerable groups to malaria in Nigeria. However, the burden of malaria is not even in space and time. This study explores the spatial variability of malaria prevalence among children under five years (U5) in medium-sized rapidly growing city of Akure, Nigeria using model-based geostatistical modeling (MBG) technique to predict U5 malaria burden at a 100 × 100 m grid, while the parameter estimation was done using Monte Carlo maximum likelihood method. The non-spatial logistic regression model shows that U5 malaria prevalence is significantly influenced by the usage of insecticide-treated nets-ITNs, window protection, and water source. Furthermore, the MBG model shows predicted U5 malaria prevalence in Akure is greater than 35% at certain locations while we were able to ascertain places with U5 prevalence > 10% (i.e. hotspots) using exceedance probability modelling which is a vital tool for policy development. The map provides place-based evidence on the spatial variation of U5 malaria in Akure, and direction on where intensified interventions are crucial for the reduction of U5 malaria burden and improvement of urban health in Akure, Nigeria.

The effect of the urban exposome on COVID-19 health outcomes: A systematic review and meta-analysis

BACKGROUND

The global severity of SARS-CoV-2 illness has been associated with various urban characteristics, including exposure to ambient air pollutants. This systematic review and meta-analysis aims to synthesize findings from ecological and non-ecological studies to investigate the impact of multiple urban-related features on a variety of COVID-19 health outcomes.

METHODS

On December 5, 2022, PubMed was searched to identify all types of observational studies that examined one or more urban exposome characteristics in relation to various COVID-19 health outcomes such as infection severity, the need for hospitalization, ICU admission, COVID pneumonia, and mortality.

RESULTS

A total of 38 non-ecological and 241 ecological studies were included in this review. Non-ecological studies highlighted the significant effects of population density, urbanization, and exposure to ambient air pollutants, particularly PM2.5. The meta-analyses revealed that a 1 μg/m3 increase in PM2.5 was associated with a higher likelihood of COVID-19 hospitalization (pooled OR 1.08 (95% CI:1.02-1.14)) and death (pooled OR 1.06 (95% CI:1.03-1.09)). Ecological studies, in addition to confirming the findings of non-ecological studies, also indicated that higher exposure to nitrogen dioxide (NO2), ozone (O3), sulphur dioxide (SO2), and carbon monoxide (CO), as well as lower ambient temperature, humidity, ultraviolet (UV) radiation, and less green and blue space exposure, were associated with increased COVID-19 morbidity and mortality.

CONCLUSION

This systematic review has identified several key vulnerability features related to urban areas in the context of the recent COVID-19 pandemic. The findings underscore the importance of improving policies related to urban exposures and implementing measures to protect individuals from these harmful environmental stressors.

Spatiotemporal observations of host-pathogen interactions in mucosa during SARS-CoV-2 infection indicate a protective role of ILC2s

IMPORTANCE

Our study revealed the spatial interaction between humanized ACE2 and pseudovirus expressing Spike, emphasizing the role of type 2 innate lymphoid cells during the initial phase of viral infection. These findings provide a foundation for the development of mucosal vaccines and other treatment approaches for both pre- and post-infection management of coronavirus disease 2019.

Is there a relationship between internet access and COVID-19 mortality? Evidence from Nigeria based on a spatial analysis

With over 6.5 million deaths due to COVID-19, it has become an issue of global health concern. Early findings have identified several social determinants of deaths from COVID-19. However, very few studies have been done on the relationship between internet access and COVID-19 mortality in the context of developing countries. Using geospatial methods, this study examines the relationship between internet access and COVID-19 mortality disparity in Nigeria. In contrast to the widely reported relationship in the literature that internet access lowers the risk of COVID-19 mortality, the current study finds that geographical locations with the highest internet access are the hotspots of COVID-19 mortality in Nigeria, especially some parts of southwest Nigeria. In addition, findings show that population density and unemployment are risk factors of COVID-19 mortality. The study recommends educating the population on the use of online health information and the need to adhere strictly to non-pharmaceutical and vaccination interventions to reduce the number of deaths caused by the virus.

Changes in symptoms and characteristics of COVID-19 patients across different variants: two years study using neural network analysis

BACKGROUND

Considering the fact that COVID-19 has undergone various changes over time, its symptoms have also varied. The aim of this study is to describe and compare the changes in personal characteristics, symptoms, and underlying conditions of individuals infected with different strains of COVID-19.

METHODS

This descriptive-analytical study was conducted on 46,747 patients who underwent PCR testing during a two-year period from February 22, 2020 to February 23, 2022, in South Khorasan province, Iran. Patient characteristics and symptoms were extracted based on self-report and the information system. The data were analyzed using logistic regression and artificial neural network approaches. The R software was used for analysis and a significance level of 0.05 was considered for the tests.

RESULTS

Among the 46,747 cases analyzed, 23,239 (49.7%) were male, and the mean age was 51.48 ± 21.41 years. There was a significant difference in symptoms among different variants of the disease (p < 0.001). The factors with a significant positive association were myalgia (OR: 2.04; 95% CI, 1.76 - 2.36), cough (OR: 1.93; 95% CI, 1.68-2.22), and taste or smell disorder (OR: 2.62; 95% CI, 2.1 - 3.28). Additionally, aging was found to increase the likelihood of testing positive across the six periods.

CONCLUSION

We found that older age, myalgia, cough and taste/smell disorder are better factors compared to dyspnea or high body temperature, for identifying a COVID-19 patient. As the disease evolved, chills and diarrhea, demonstrated prognostic strength as in Omicron.

Uncovering COVID-19 infection determinants in Portugal: towards an evidence-based spatial susceptibility index to support epidemiological containment policies

BACKGROUND

COVID-19 caused the largest pandemic of the twenty-first century forcing the adoption of containment policies all over the world. Many studies on COVID-19 health determinants have been conducted, mainly using multivariate methods and geographic information systems (GIS), but few attempted to demonstrate how knowing social, economic, mobility, behavioural, and other spatial determinants and their effects can help to contain the disease. For example, in mainland Portugal, non-pharmacological interventions (NPI) were primarily dependent on epidemiological indicators and ignored the spatial variation of susceptibility to infection.

METHODS

We present a data-driven GIS-multicriteria analysis to derive a spatial-based susceptibility index to COVID-19 infection in Portugal. The cumulative incidence over 14 days was used in a stepwise multiple linear regression as the target variable along potential determinants at the municipal scale. To infer the existence of thresholds in the relationships between determinants and incidence the most relevant factors were examined using a bivariate Bayesian change point analysis. The susceptibility index was mapped based on these thresholds using a weighted linear combination.

RESULTS

Regression results support that COVID-19 spread in mainland Portugal had strong associations with factors related to socio-territorial specificities, namely sociodemographic, economic and mobility. Change point analysis revealed evidence of nonlinearity, and the susceptibility classes reflect spatial dependency. The spatial index of susceptibility to infection explains with accuracy previous and posterior infections. Assessing the NPI levels in relation to the susceptibility map points towards a disagreement between the severity of restrictions and the actual propensity for transmission, highlighting the need for more tailored interventions.

CONCLUSIONS

This article argues that NPI to contain COVID-19 spread should consider the spatial variation of the susceptibility to infection. The findings highlight the importance of customising interventions to specific geographical contexts due to the uneven distribution of COVID-19 infection determinants. The methodology has the potential for replication at other geographical scales and regions to better understand the role of health determinants in explaining spatiotemporal patterns of diseases and promoting evidence-based public health policies.

A Novel Multi-Objective Binary Chimp Optimization Algorithm for Optimal Feature Selection: Application of Deep-Learning-Based Approaches for SAR Image Classification

Removing redundant features and improving classifier performance necessitates the use of meta-heuristic and deep learning (DL) algorithms in feature selection and classification problems. With the maturity of DL tools, many data-driven polarimetric synthetic aperture radar (POLSAR) representation models have been suggested, most of which are based on deep convolutional neural networks (DCNNs). In this paper, we propose a hybrid approach of a new multi-objective binary chimp optimization algorithm (MOBChOA) and DCNN for optimal feature selection. We implemented the proposed method to classify POLSAR images from San Francisco, USA. To do so, we first performed the necessary preprocessing, including speckle reduction, radiometric calibration, and feature extraction. After that, we implemented the proposed MOBChOA for optimal feature selection. Finally, we trained the fully connected DCNN to classify the pixels into specific land-cover labels. We evaluated the performance of the proposed MOBChOA-DCNN in comparison with nine competitive methods. Our experimental results with the POLSAR image datasets show that the proposed architecture had a great performance for different important optimization parameters. The proposed MOBChOA-DCNN provided fewer features (27) and the highest overall accuracy. The overall accuracy values of MOBChOA-DCNN on the training and validation datasets were 96.89% and 96.13%, respectively, which were the best results. The overall accuracy of SVM was 89.30%, which was the worst result. The results of the proposed MOBChOA on two real-world benchmark problems were also better than the results with the other methods. Furthermore, it was shown that the MOBChOA-DCNN performed better than methods from previous studies.

Exploration of the COVID-19 pandemic at the neighborhood level in an intra-urban setting

The COVID-19 pandemic represents a worldwide threat to health. Since its onset in 2019, the pandemic has proceeded in different phases, which have been shaped by a complex set of influencing factors, including public health and social measures, the emergence of new virus variants, and seasonality. Understanding the development of COVID-19 incidence and its spatiotemporal patterns at a neighborhood level is crucial for local health authorities to identify high-risk areas and develop tailored mitigation strategies. However, analyses at the neighborhood level are scarce and mostly limited to specific phases of the pandemic. The aim of this study was to explore the development of COVID-19 incidence and spatiotemporal patterns of incidence at a neighborhood scale in an intra-urban setting over several pandemic phases (March 2020-December 2021). We used reported COVID-19 case data from the health department of the district Berlin-Neukölln, Germany, additional socio-demographic data, and text documents and materials on implemented public health and social measures. We examined incidence over time in the context of the measures and other influencing factors, with a particular focus on age groups. We used incidence maps and spatial scan statistics to reveal changing spatiotemporal patterns. Our results show that several factors may have influenced the development of COVID-19 incidence. In particular, the far-reaching measures for contact reduction showed a substantial impact on incidence in Neukölln. We observed several age group-specific effects: school closures had an effect on incidence in the younger population (< 18 years), whereas the start of the vaccination campaign had an impact primarily on incidence among the elderly (> 65  years). The spatial analysis revealed that high-risk areas were heterogeneously distributed across the district. The location of high-risk areas also changed across the pandemic phases. In this study, existing intra-urban studies were supplemented by our investigation of the course of the pandemic and the underlying processes at a small scale over a long period of time. Our findings provide new insights for public health authorities, community planners, and policymakers about the spatiotemporal development of the COVID-19 pandemic at the neighborhood level. These insights are crucial for guiding decision-makers in implementing mitigation strategies.

Spatial-Temporal Event Analysis as a Prospective Approach for Signalling Emerging Food Fraud-Related Anomalies in Supply Chains

One of the pillars on which food traceability systems are based is the unique identification and recording of products and batches along the supply chain. Patterns of these identification codes in time and place may provide useful information on emerging food frauds. The scanning of codes on food packaging by users results in interesting spatial-temporal datasets. The analysis of these data using artificial intelligence could advance current food fraud detection approaches. Spatial-temporal patterns of the scanned codes could reveal emerging anomalies in supply chains as a result of food fraud in the chain. These patterns have not been studied yet, but in other areas, such as biology, medicine, credit card fraud, etc., parallel approaches have been developed, and are discussed in this paper. This paper projects these approaches for transfer and implementation in food supply chains in view of future applications for early warning of emerging food frauds.

What have we learned about socioeconomic inequalities in the spread of COVID-19? A systematic review

This article aims to provide a better understanding of the associations between groups of socioeconomic variables and confirmed cases of COVID-19. The focus is on cross-continental differences of reported positive, negative, unclear, or no associations. A systematic review of the literature is conducted on the Web of Science and SCOPUS databases. Our search identifies 314 eligible studies published on or before 31 December 2021. We detect nine groups of frequently used socioeconomic variables and results are presented by region of the world (Africa, Asia, Europe, Middle East, North American and South America). The review expands to describe the most used statistical and modelling techniques as well as inclusion of additional dimensions such as demographic, healthcare weather and mobility. Meanwhile findings agree on the generalized positive impact of population density, per capita GDP and urban areas on transmission of infections, contradictory results have been found concerning to educational level and income.

Multivariate Kalman filtering for spatio-temporal processes

An increasing interest in models for multivariate spatio-temporal processes has been noted in the last years. Some of these models are very flexible and can capture both marginal and cross spatial associations amongst the components of the multivariate process. In order to contribute to the statistical analysis of these models, this paper deals with the estimation and prediction of multivariate spatio-temporal processes by using multivariate state-space models. In this context, a multivariate spatio-temporal process is represented through the well-known Wold decomposition. Such an approach allows for an easy implementation of the Kalman filter to estimate linear temporal processes exhibiting both short and long range dependencies, together with a spatial correlation structure. We illustrate, through simulation experiments, that our method offers a good balance between statistical efficiency and computational complexity. Finally, we apply the method for the analysis of a bivariate dataset on average daily temperatures and maximum daily solar radiations from 21 meteorological stations located in a portion of south-central Chile.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00477-022-02266-3.

Comparative study of artificial neural network versus parametric method in COVID-19 data analysis

Since the previous two years, a new coronavirus (COVID-19) has found a major global problem. The speedy pathogen over the globe was followed by a shockingly large number of afflicted people and a gradual increase in the number of deaths. If the survival analysis of active individuals can be predicted, it will help to contain the epidemic significantly in any area. In medical diagnosis, prognosis and survival analysis, neural networks have been found to be as successful as general nonlinear models. In this study, a real application has been developed for estimating the COVID-19 mortality rates in Italy by using two different methods, artificial neural network modeling and maximum likelihood estimation. The predictions obtained from the multilayer artificial neural network model developed with 9 neurons in the hidden layer were compared with the numerical results. The maximum deviation calculated for the artificial neural network model was -0.14% and the R value was 0.99836. The study findings confirmed that the two different statistical models that were developed had high reliability.

A Novel Deep Supervised Learning-Based Approach for Intrusion Detection in IoT Systems

The Internet of Things (IoT) has become one of the most important concepts in various aspects of our modern life in recent years. However, the most critical challenge for the world-wide use of the IoT is to address its security issues. One of the most important tasks to address the security challenges in the IoT is to detect intrusion in the network. Although the machine/deep learning-based solutions have been repeatedly used to detect network intrusion through recent years, there is still considerable potential to improve the accuracy and performance of the classifier (intrusion detector). In this paper, we develop a novel training algorithm to better tune the parameters of the used deep architecture. To specifically do so, we first introduce a novel neighborhood search-based particle swarm optimization (NSBPSO) algorithm to improve the exploitation/exploration of the PSO algorithm. Next, we use the advantage of NSBPSO to optimally train the deep architecture as our network intrusion detector in order to obtain better accuracy and performance. For evaluating the performance of the proposed classifier, we use two network intrusion detection datasets named UNSW-NB15 and Bot-IoT to rate the accuracy and performance of the proposed classifier.

Numerical treatment on the new fractional-order SIDARTHE COVID-19 pandemic differential model via neural networks

In this study, modeling the COVID-19 pandemic via a novel fractional-order SIDARTHE (FO-SIDARTHE) differential system is presented. The purpose of this research seemed to be to show the consequences and relevance of the fractional-order (FO) COVID-19 SIDARTHE differential system, as well as FO required conditions underlying four control measures, called SI,  SD,  SA, and SR. The FO-SIDARTHE system incorporates eight phases of infection: susceptible (S), infected (I), diagnosed (D), ailing (A), recognized (R), threatening (T), healed (H), and extinct (E). Our objective of all these investigations is to use fractional derivatives to increase the accuracy of the SIDARTHE system. A FO-SIDARTHE system has yet to be disclosed, nor has it yet been treated using the strength of stochastic solvers. Stochastic solvers based on the Levenberg-Marquardt backpropagation methodology (L-MB) and neural networks (NNs), specifically L-MBNNs, are being used to analyze a FO-SIDARTHE problem. Three cases having varied values under the same fractional order are being presented to resolve the FO-SIDARTHE system. The statistics employed to provide numerical solutions toward the FO-SIDARTHE system are classified as obeys: 72% toward training, 18% in testing, and 10% for authorization. To establish the accuracy of such L-MBNNs utilizing Adams-Bashforth-Moulton, the numerical findings were compared with the reference solutions.