Association between exposure to airborne pollutants and COVID-19 in Los Angeles, United States with ensemble-based dynamic emission model

Identifying interactions among air pollutant emissions on diabetes prevalence in Northeast China using a complex network

BACKGROUND

Low air quality related to ambient air pollution is the largest environmental risk to health worldwide. Interactions between air pollution emissions may affect associations between air pollution exposure and chronic diseases. Therefore, this study aimed to quantify interactions among air pollution emissions and assess their effects on the association between air pollution and diabetes.

METHODS

After constructing long-term emission networks for six air pollutants based on data collected from routine monitoring stations in Northeast China, a mutual information network was used to quantify interactions among air pollution emissions. Multiple linear regression analysis was then used to explore the influence of emission interactions on the association between air pollution exposure and the prevalence of diabetes based on data reported from the Northeast Natural Cohort Study in China.

RESULTS

Complex network analysis detected three major emission sources in Northeast China located in Shenyang and Changchun. The effects of particulate matter (PM2.5 and PM10) and ground-level ozone (O3) emissions were limited to certain communities but could spread to other communities through emissions in Inner Mongolia. Emissions of sulfur dioxide (SO2), nitrogen dioxide (NO2), and carbon monoxide (CO) significantly influenced other communities. These results indicated that air pollutants in different geographic areas can interact directly or indirectly. Adjusting for interactions between emissions changed associations between air pollution emissions and diabetes prevalence, especially for PM2.5, NO2, and CO.

CONCLUSIONS

Complex network analysis is suitable for quantifying interactions among air pollution emissions and suggests that the effects of PM2.5 and NO2 emissions on health outcomes may have been overestimated in previous population studies while those of CO may have been underestimated. Further studies examining associations between air pollution and chronic diseases should consider controlling for the effects of interactions among pollution emissions.

A comprehensive review of the development of land use regression approaches for modeling spatiotemporal variations of ambient air pollution: A perspective from 2011 to 2023

Land use regression (LUR) models are widely used in epidemiological and environmental studies to estimate humans' exposure to air pollution within urban areas. However, the early models, developed using linear regressions and data from fixed monitoring stations and passive sampling, were primarily designed to model traditional and criteria air pollutants and had limitations in capturing high-resolution spatiotemporal variations of air pollution. Over the past decade, there has been a notable development of multi-source observations from low-cost monitors, mobile monitoring, and satellites, in conjunction with the integration of advanced statistical methods and spatially and temporally dynamic predictors, which have facilitated significant expansion and advancement of LUR approaches. This paper reviews and synthesizes the recent advances in LUR approaches from the perspectives of the changes in air quality data acquisition, novel predictor variables, advances in model-developing approaches, improvements in validation methods, model transferability, and modeling software as reported in 155 LUR studies published between 2011 and 2023. We demonstrate that these developments have enabled LUR models to be developed for larger study areas and encompass a wider range of criteria and unregulated air pollutants. LUR models in the conventional spatial structure have been complemented by more complex spatiotemporal structures. Compared with linear models, advanced statistical methods yield better predictions when handling data with complex relationships and interactions. Finally, this study explores new developments, identifies potential pathways for further breakthroughs in LUR methodologies, and proposes future research directions. In this context, LUR approaches have the potential to make a significant contribution to future efforts to model the patterns of long- and short-term exposure of urban populations to air pollution.

Environmental, meteorological and pandemic restriction-related variables affecting SARS-CoV-2 cases

Three years have passed since the outbreak of Coronavirus Disease 2019 (COVID-19) brought the world to standstill. In most countries, the restrictions have ended, and the immunity of the population has increased; however, the possibility of new dangerous variants emerging remains. Therefore, it is crucial to develop tools to study and forecast the dynamics of future pandemics. In this study, a generalized additive model (GAM) was developed to evaluate the impact of meteorological and environmental variables, along with pandemic-related restrictions, on the incidence of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in Córdoba, Argentina. The results revealed that mean temperature and vegetation cover were the most significant predictors affecting SARS-CoV-2 cases, followed by government restriction phases, days of the week, and hours of sunlight. Although fine particulate matter (PM2.5) and NO2 were less related, they improved the model's predictive power, and a 1-day lag enhanced accuracy metrics. The models exhibited strong adjusted coefficients of determination (R2adj) but did not perform as well in terms of root-mean-square error (RMSE). This suggests that the number of cases may not be the primary variable for controlling the spread of the disease. Furthermore, the increase in positive cases related to policy interventions may indicate the presence of lockdown fatigue. This study highlights the potential of data science as a management tool for identifying crucial variables that influence epidemiological patterns and can be monitored to prevent an overload in the healthcare system.

Environmental Factors Influencing the Dynamics and Evolution of COVID-19: A Systematic Review on the Study of Short-Term Ozone Exposure

The potential influence of environmental factors, particularly air pollutants such as ozone (O3), on the dynamics and progression of COVID-19 remains a significant concern. This study aimed to systematically review and analyze the current body of literature to assess the impact of short-term ozone exposure on COVID-19 transmission dynamics and disease evolution. A rigorous systematic review was conducted in March 2023, covering studies from January 2020 to January 2023 found in PubMed, Web of Science, and Scopus. We followed the PRISMA guidelines and PROSPERO criteria, focusing exclusively on the effects of short-term ozone exposure on COVID-19. The literature search was restricted to English-language journal articles, with the inclusion and exclusion criteria strictly adhered to. Out of 4674 identified studies, 18 fulfilled the inclusion criteria, conducted across eight countries. The findings showed a varied association between short-term ozone exposure and COVID-19 incidence, severity, and mortality. Some studies reported a higher association between ozone exposure and incidence in institutional settings (OR: 1.06, 95% CI: 1.00-1.13) compared to the general population (OR: 1.00, 95% CI: 0.98-1.03). The present research identified a positive association between ozone exposure and both total and active COVID-19 cases as well as related deaths (coefficient for cases: 0.214; for recoveries: 0.216; for active cases: 0.467; for deaths: 0.215). Other studies also found positive associations between ozone levels and COVID-19 cases and deaths, while fewer reports identified a negative association between ozone exposure and COVID-19 incidence (coefficient: -0.187) and mortality (coefficient: -0.215). Conversely, some studies found no significant association between ozone exposure and COVID-19, suggesting a complex and potentially region-specific relationship. The relationship between short-term ozone exposure and COVID-19 dynamics is complex and multifaceted, indicating both positive and negative associations. These variations are possibly due to demographic and regional factors. Further research is necessary to bridge current knowledge gaps, especially considering the potential influence of short-term O3 exposure on COVID-19 outcomes and the broader implications on public health policy and preventive strategies during pandemics.

Severe Acute Respiratory Syndrome and Particulate Matter Exposure: A Systematic Review

BACKGROUND

Particulate matter (PM) exposure is responsible for seven million deaths annually and has been implicated in the pathogenesis of respiratory infections such as severe acute respiratory syndrome (SARS). Understanding modifiable risk factors of high mortality, resource burdensome C19 and exposure risks such as PM is key to mitigating their devastating effects. This systematic review focuses on the literature available, identifying the spatial and temporal variation in the role of quantified PM exposure in SARS disease outcome and planning our future experimental studies.

METHODS

The systematic review utilized keywords adhered to the PRISMA guidelines. We included original human research studies in English.

RESULTS

Initial search yielded N = 906, application of eligibility criteria yielded N = 46. Upon analysis of risk of bias N = 41 demonstrated high risk. Studies found a positive association between elevated PM2.5, PM10 and SARS-related outcomes. A geographic and temporal variation in both PM and C19's role was observed.

CONCLUSION

C19 is a high mortality and resource intensive disease which devastated the globe. PM exposure is also a global health crisis. Our systematic review focuses on the intersection of this impactful disease-exposure dyad and understanding the role of PM is important in the development of interventions to prevent future spread of viral infections.

Temporal Characteristics of Ozone (O3) in the Representative City of the Yangtze River Delta: Explanatory Factors and Sensitivity Analysis

Ozone (O₃) has attracted considerable attention due to its harmful effects on the ecosystem and human health. The Yangtze River Delta (YRD), China in particular has experienced severe O₃ pollution in recent years. Here, we conducted a long-term observation of O₃ in YRD to reveal its characteristics. The O₃ concentration in autumn was the highest at 72.76 ppb due to photochemical contribution and local convection patterns, with its lowest value of 2.40 ppb in winter. O₃ exhibited strong diurnal variations, showing the highest values in the early afternoon (15:00-16:00) and the minimum in 07:00-08:00, specifically, peroxyacetyl nitrate (PAN) showed similar variations to O₃ but PAN peak usually occurred 1 h earlier than that of O₃ due to PAN photolysis. A generalized additive model indicated that the key factors to O₃ formation were NO₂, PAN, and temperature. It was found that a certain temperature rise promoted O₃ formation, whereas temperatures above 27 °C inhibited O₃ formation. An observation-based model showed O₃ formation was VOCs-limited in spring and winter, was NO_x-limited in summer, and even controlled by both VOCs and NO_x in autumn. Thus, prevention and control strategies for O₃ in the YRD are strongly recommended to be variable for each season based on various formation mechanisms.

The impact of air pollution on COVID-19 incidence, severity, and mortality: A systematic review of studies in Europe and North America

BACKGROUND

Air pollution is speculated to increase the risks of COVID-19 spread, severity, and mortality.

OBJECTIVES

We systematically reviewed studies investigating the relationship between air pollution and COVID-19 cases, non-fatal severity, and mortality in North America and Europe.

METHODS

We searched PubMed, Web of Science, and Scopus for studies investigating the effects of harmful pollutants, including particulate matter with diameter ≤2.5 or 10 μm (PM_2.5 or PM₁₀), ozone (O₃), nitrogen dioxide (NO₂), sulfur dioxide (SO₂) and carbon monoxide (CO), on COVID-19 cases, severity, and deaths in Europe and North America through to June 19, 2021. Articles were included if they quantitatively measured the relationship between exposure to air pollution and COVID-19 health outcomes.

RESULTS

From 2,482 articles screened, we included 116 studies reporting 355 separate pollutant-COVID-19 estimates. Approximately half of all evaluations on incidence were positive and significant associations (52.7%); for mortality the corresponding figure was similar (48.1%), while for non-fatal severity this figure was lower (41.2%). Longer-term exposure to pollutants appeared more likely to be positively associated with COVID-19 incidence (63.8%). PM_2.5, PM₁₀, O₃, NO₂, and CO were most strongly positively associated with COVID-19 incidence, while PM_2.5 and NO₂ with COVID-19 deaths. All studies were observational and most exhibited high risk of confounding and outcome measurement bias.

DISCUSSION

Air pollution may be associated with worse COVID-19 outcomes. Future research is needed to better test the air pollution-COVID-19 hypothesis, particularly using more robust study designs and COVID-19 measures that are less prone to measurement error and by considering co-pollutant interactions.

Effect of ambient air pollution and meteorological factors on the potential transmission of COVID-19 in Turkey

There is a need to improve the understanding of air quality parameters and meteorological conditions on the transmission of SARS-CoV-2 in different regions of the world. In this preliminary study, we explore the relationship between short-term air quality (nitrogen dioxide (NO₂), sulfur dioxide (SO₂), ozone (O₃), and particulate matter (PM_2.5, PM₁₀)) exposure, temperature, humidity, and wind speed on SARS-CoV-2 transmission in 41 cities of Turkey with reported weekly cases from February 8 to April 2, 2021. Both linear and non-linear relationships were explored. The nonlinear association between weekly confirmed cases and short-term exposure to predictor factors was investigated using a generalized additive model (GAM). The preliminary results indicate that there was a significant association between humidity and weekly confirmed COVID-19 cases. The cooler temperatures had a positive correlation with the occurrence of new confirmed cases. The low PM_2.5 concentrations had a negative correlation with the number of new cases, while reducing SO₂ concentrations may help decrease the number of new cases. This is the first study investigating the relationship between measured air pollutants, meteorological factors, and the number of weekly confirmed COVID-19 cases across Turkey. There are several limitations of the presented study, however, the preliminary results show that there is a need to understand the impacts of regional air quality parameters and meteorological factors on the transmission of the virus.

The influence of socioeconomic and environmental determinants on acute myocardial infarction (AMI) mortality from the spatial epidemiological perspective

Plenty of epidemiological approaches have been explored to detect the effects of environmental and socioeconomic factors on acute myocardial infarction (AMI) mortality. Whereas, identifying the influence of potential affecting factors on AMI mortality based on a spatial epidemiological perspective was strongly desired. Moreover, the interaction effects of two potential factors on the diseases were always neglected previously. Here, the Geodetector and geographically & temporally weighted regression model (GTWR) combined with multi-source spatiotemporal datasets were introduced to quantitatively determine the relationship between AMI mortality and potential influencing factors across Xi'an during 2014-2016. Besides, Moran's I was adopted to diagnose the spatial autocorrelation of AMI mortality. Some findings were achieved. The number of AMI mortality cases increased from 5075 in 2014 to 6774 in 2016. Air pollutants, meteorological factors, economic status, and topography factors exhibited a significant effect on AMI mortality. The AMI mortality demonstrated an obvious spatial autocorrelation feature during 2014-2016. POP and PE represented the most obvious impact on AMI mortality, respectively. Moreover, the interaction of any two factors was larger than that of the single factor on AMI mortality, and the factors with the strongest interaction vary according to lag groups and ages. The effects of factors on AMI mortality were POP (- 628.925) > PE (140.102) > RD (79.145) > O₃ (- 58.438) > E_NH₃ (42.370) for male, and POP (- 751.206) > RD (132.935) > E_NH₃ (58.758) > PE (- 45.434) > O₃ (- 21.256) for female, respectively. This work reminds the local government to continuously control air pollution, strengthen urban planning, and improve the health care of the rural areas for alleviating AMI mortality. Meanwhile, the scheme of the current study supplies a scientific reference for examining the effects of potential impact factors on related diseases using the spatial epidemiological perspective.

Elucidating the role of environmental management of forests, air quality, solid waste and wastewater on the dissemination of SARS-CoV-2

The increasing frequency of zoonotic diseases is amongst several catastrophic repercussions of inadequate environmental management. Emergence, prevalence, and lethality of zoonotic diseases is intrinsically linked to environmental management which are currently at a destructive level globally. The effects of these links are complicated and interdependent, creating an urgent need of elucidating the role of environmental mismanagement to improve our resilience to future pandemics. This review focused on the pertinent role of forests, outdoor air, indoor air, solid waste and wastewater management in COVID-19 dissemination to analyze the opportunities prevailing to control infectious diseases considering relevant data from previous disease outbreaks. Global forest management is currently detrimental and hotspots of forest fragmentation have demonstrated to result in zoonotic disease emergences. Deforestation is reported to increase susceptibility to COVID-19 due to wildfire induced pollution and loss of forest ecosystem services. Detection of SARS-CoV-2 like viruses in multiple animal species also point to the impacts of biodiversity loss and forest fragmentation in relation to COVID-19. Available literature on air quality and COVID-19 have provided insights into the potential of air pollutants acting as plausible virus carrier and aggravating immune responses and expression of ACE2 receptors. SARS-CoV-2 is detected in outdoor air, indoor air, solid waste, wastewater and shown to prevail on solid surfaces and aerosols for prolonged hours. Furthermore, lack of protection measures and safe disposal options in waste management are evoking concerns especially in underdeveloped countries due to high infectivity of SARS-CoV-2. Inadequate legal framework and non-adherence to environmental regulations were observed to aggravate the postulated risks and vulnerability to future waves of pandemics. Our understanding underlines the urgent need to reinforce the fragile status of global environmental management systems through the development of strict legislative frameworks and enforcement by providing institutional, financial and technical supports.

The role of outdoor and indoor air quality in the spread of SARS-CoV-2: Overview and recommendations by the research group on COVID-19 and particulate matter (RESCOP commission)

There are important questions surrounding the potential contribution of outdoor and indoor air quality in the transmission of SARS-CoV-2 and perpetuation of COVID-19 epidemic waves. Environmental health may be a critical component of COVID-19 prevention. The public health community and health agencies should consider the evolving evidence in their recommendations and statements, and work to issue occupational guidelines. Evidence coming from the current epidemiological and experimental research is expected to add knowledge about virus diffusion, COVID-19 severity in most polluted areas, inter-personal distance requirements and need for wearing face masks in indoor or outdoor environments. The COVID-19 pandemic has highlighted the need for maintaining particulate matter concentrations at low levels for multiple health-related reasons, which may also include the spread of SARS-CoV-2. Indoor environments represent even a more crucial challenge to cope with, as it is easier for the SARS-COV2 to spread, remain vital and infect other subjects in closed spaces in the presence of already infected asymptomatic or mildly symptomatic people. The potential merits of preventive measures, such as CO₂ monitoring associated with natural or controlled mechanical ventilation and air purification, for schools, indoor public places (restaurants, offices, hotels, museums, theatres/cinemas etc.) and transportations need to be carefully considered. Hospital settings and nursing/retirement homes as well as emergency rooms, infectious diseases divisions and ambulances represent higher risk indoor environments and may require additional monitoring and specific decontamination strategies based on mechanical ventilation or air purification.

SARS-CoV-2 and other airborne respiratory viruses in outdoor aerosols in three Swiss cities before and during the first wave of the COVID-19 pandemic

Caused by the SARS-CoV-2 virus, Coronavirus disease 2019 (COVID-19) has been affecting the world since the end of 2019. While virus-laden particles have been commonly detected and studied in the aerosol samples from indoor healthcare settings, studies are scarce on air surveillance of the virus in outdoor non-healthcare environments, including the correlations between SARS-CoV-2 and other respiratory viruses, between viruses and environmental factors, and between viruses and human behavior changes due to the public health measures against COVID-19. Therefore, in this study, we collected airborne particulate matter (PM) samples from November 2019 to April 2020 in Bern, Lugano, and Zurich. Among 14 detected viruses, influenza A, HCoV-NL63, HCoV-HKU1, and HCoV-229E were abundant in air. SARS-CoV-2 and enterovirus were moderately common, while the remaining viruses occurred only in low concentrations. SARS-CoV-2 was detected in PM₁₀ (PM below 10 µm) samples of Bern and Zurich, and PM_2.5 (PM below 2.5 µm) samples of Bern which exhibited a concentration positively correlated with the local COVID-19 case number. The concentration was also correlated with the concentration of enterovirus which raised the concern of coinfection. The estimated COVID-19 infection risks of an hour exposure at these two sites were generally low but still cannot be neglected. Our study demonstrated the potential functionality of outdoor air surveillance of airborne respiratory viruses, especially at transportation hubs and traffic arteries.

Impact of Short-Term Air Pollution on Respiratory Infections: A Time-Series Analysis of COVID-19 Cases in California during the 2020 Wildfire Season

The 2020 California wildfire season coincided with the peak of the COVID-19 pandemic affecting many counties in California, with impacts on air quality. We quantitatively analyzed the short-term effect of air pollution on COVID-19 transmission using county-level data collected during the 2020 wildfire season. Using time-series methodology, we assessed the relationship between short-term exposure to particulate matter (PM2.5), carbon monoxide (CO), nitrogen dioxide (NO2), and Air Quality Index (AQI) on confirmed cases of COVID-19 across 20 counties impacted by wildfires. Our findings indicate that PM2.5, CO, and AQI are positively associated with confirmed COVID-19 cases. This suggests that increased air pollution could worsen the situation of a health crisis such as the COVID-19 pandemic. Health policymakers should make tailored policies to cope with situations that may increase the level of air pollution, especially during a wildfire season.

Ecological studies of COVID-19 and air pollution: How useful are they?

Background:

Results from ecological studies have suggested that air pollution increases the risk of developing and dying from COVID-19. Drawing causal inferences from the measures of association reported in ecological studies is fraught with challenges given biases arising from an outcome whose ascertainment is incomplete, varies by region, time, and across sociodemographic characteristics, and cannot account for clustering or within-area heterogeneity. Through a series of analyses, we illustrate the dangers of using ecological studies to assess whether ambient air pollution increases the risk of dying from, or transmitting, COVID-19.

Methods:

We performed an ecological analysis in the continental United States using county-level ambient concentrations of fine particulate matter (PM_2.5) between 2000 and 2016 and cumulative COVID-19 mortality counts through June 2020, December 2020, and April 2021. To show that spurious associations can be obtained in ecological data, we modeled the association between PM_2.5 and the prevalence of human immunodeficiency virus (HIV). We fitted negative binomial models, with a logarithmic offset for county-specific population, to these data. Natural cubic splines were used to describe the shape of the exposure-response curves.

Results:

Our analyses revealed that the shape of the exposure-response curve between PM_2.5 and COVID-19 changed substantially over time. Analyses of COVID-19 mortality through June 30, 2021, suggested a positive linear relationship. In contrast, an inverse pattern was observed using county-level concentrations of PM_2.5 and the prevalence of HIV.

Conclusions:

Our analyses indicated that ecological analyses are prone to showing spurious relationships between ambient air pollution and mortality from COVID-19 as well as the prevalence of HIV. We discuss the many potential biases inherent in any ecological-based analysis of air pollution and COVID-19.

Positive association between outdoor air pollution and the incidence and severity of COVID-19. A review of the recent scientific evidences

In June 2020, we published a review focused on assessing the influence of various air pollutants on the transmission of SARS-CoV-2, and the severity of COVID-19 in patients infected by the coronavirus. The results of most of those reviewed studies suggested that chronic exposure to certain air pollutants might lead to more severe and lethal forms of COVID-19, as well as delays/complications in the recovery of the patients. Since then, a notable number of studies on this topic have been published, including also various reviews. Given the importance of this issue, we have updated the information published since our previous review. Taking together the previous results and those of most investigations now reviewed, we have concluded that there is a significant association between chronic exposure to various outdoor air pollutants: PM_2.5, PM₁₀, O₃, NO₂, SO₂ and CO, and the incidence/risk of COVID-19 cases, as well as the severity/mortality of the disease. Unfortunately, studies on the potential influence of other important air pollutants such as VOCs, dioxins and furans, or metals, are not available in the scientific literature. In relation to the influence of outdoor air pollutants on the transmission of SARS-CoV-2, although the scientific evidence is much more limited, some studies point to PM_2.5 and PM₁₀ as potential airborne transmitters of the virus. Anyhow, it is clear that environmental air pollution plays an important negative role in COVID-19, increasing its incidence and mortality.

PM2.5 as a major predictor of COVID-19 basic reproduction number in the USA

Many studies have proposed a relationship between COVID-19 transmissibility and ambient pollution levels. However, a major limitation in establishing such associations is to adequately account for complex disease dynamics, influenced by e.g. significant differences in control measures and testing policies. Another difficulty is appropriately controlling the effects of other potentially important factors, due to both their mutual correlations and a limited dataset. To overcome these difficulties, we will here use the basic reproduction number (R₀) that we estimate for USA states using non-linear dynamics methods. To account for a large number of predictors (many of which are mutually strongly correlated), combined with a limited dataset, we employ machine-learning methods. Specifically, to reduce dimensionality without complicating the variable interpretation, we employ Principal Component Analysis on subsets of mutually related (and correlated) predictors. Methods that allow feature (predictor) selection, and ranking their importance, are then used, including both linear regressions with regularization and feature selection (Lasso and Elastic Net) and non-parametric methods based on ensembles of weak-learners (Random Forest and Gradient Boost). Through these substantially different approaches, we robustly obtain that PM_2.5 is a major predictor of R₀ in USA states, with corrections from factors such as other pollutants, prosperity measures, population density, chronic disease levels, and possibly racial composition. As a rough magnitude estimate, we obtain that a relative change in R₀, with variations in pollution levels observed in the USA, is typically ~30%, which further underscores the importance of pollution in COVID-19 transmissibility.

The application of artificial intelligence and data integration in COVID-19 studies: a scoping review

Objective

To summarize how artificial intelligence (AI) is being applied in COVID-19 research and determine whether these AI applications integrated heterogenous data from different sources for modeling.

Materials and Methods

We searched 2 major COVID-19 literature databases, the National Institutes of Health’s LitCovid and the World Health Organization’s COVID-19 database on March 9, 2021. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guideline, 2 reviewers independently reviewed all the articles in 2 rounds of screening.

Results

In the 794 studies included in the final qualitative analysis, we identified 7 key COVID-19 research areas in which AI was applied, including disease forecasting, medical imaging-based diagnosis and prognosis, early detection and prognosis (non-imaging), drug repurposing and early drug discovery, social media data analysis, genomic, transcriptomic, and proteomic data analysis, and other COVID-19 research topics. We also found that there was a lack of heterogenous data integration in these AI applications.

Discussion

Risk factors relevant to COVID-19 outcomes exist in heterogeneous data sources, including electronic health records, surveillance systems, sociodemographic datasets, and many more. However, most AI applications in COVID-19 research adopted a single-sourced approach that could omit important risk factors and thus lead to biased algorithms. Integrating heterogeneous data for modeling will help realize the full potential of AI algorithms, improve precision, and reduce bias.

Conclusion

There is a lack of data integration in the AI applications in COVID-19 research and a need for a multilevel AI framework that supports the analysis of heterogeneous data from different sources.