Dataset Information

A machine learning-driven spatio-temporal vulnerability appraisal based on socio-economic data for COVID-19 impact prevention in the U.S. counties.

ABSTRACT: A mature and hybrid machine-learning model is verified by mature empirical analysis to measure county-level COVID-19 vulnerability and track the impact of the imposition of pandemic control policies in the U.S. A total of 30 county-level social, economic, and medical variables and a timeline of the imposed policies constitutes a COVID-19 database. A hybrid feature-selection model composed of four machine-learning algorithms is developed to emphasize the regional impact of community features on the case fatality rate (CFR). A COVID-19 vulnerability index (COVULin) is proposed to measure the county's vulnerability, the effects of model's parameters on mortality, and the efficiency of control policies. The results showed that the dense counties in which minority groups represent more than 45% of the population and those with poverty rates greater than 24% were the most vulnerable counties during the first and the last pandemic peaks, respectively. Highly-correlated CFR and COVULin scores indicated a close agreement between the model outcomes and COVID-19 impacts. Counties with higher poverty and uninsured rates were the most resistant to government intervention. It is anticipated that the proposed model can play an essential role in identifying vulnerable communities and help reduce damages during long-term alike disasters.

SUBMITTER: Moosazadeh M

PROVIDER: S-EPMC9167466 | biostudies-literature | 2022 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A machine learning-driven spatio-temporal vulnerability appraisal based on socio-economic data for COVID-19 impact prevention in the U.S. counties.

Moosazadeh Mohammad M Ifaei Pouya P Tayerani Charmchi Amir Saman AS Asadi Somayeh S Yoo ChangKyoo C

Sustainable cities and society 20220605

A mature and hybrid machine-learning model is verified by mature empirical analysis to measure county-level COVID-19 vulnerability and track the impact of the imposition of pandemic control policies in the U.S. A total of 30 county-level social, economic, and medical variables and a timeline of the imposed policies constitutes a COVID-19 database. A hybrid feature-selection model composed of four machine-learning algorithms is developed to emphasize the regional impact of community features on t ...[more]

PMID: 35692599

Similar Datasets

Project description:BackgroundHemorrhagic fever with renal syndrome (HFRS) occurs widely in Northeastern China, but the mechanism and interactions of meteorological and socio-economic factors on the transmission of HFRS are still largely unknown.ObjectiveWe explored the effects of socioeconomic-environmental factors on the spatio-temporal variation of HFRS incidence from 2001 to 2019 in Northeastern China. Specifically, the relative importance and contribution rates (CR) of determinants of HFRS were identified by boosted regression tree and variance partitioning analysis, respectively. Structural equation models (SEMs) were used to explain the roles of climatic and socio-economic factors in the transmission of HFRS. And a negative binomial regression was used to identify the risk effect between monthly meteorological variables and HFRS with 0-6 months lags in Northeastern China.ResultsOver the past decades, the high-risk areas of HFRS were mainly concentrated in the northern and eastern areas of Northeastern China. Additionally, HFRS mainly presented a decreasing trend from 2001 to 2019 in most areas of Northeastern China, but slightly increased in the cities of Daqing, Songyuan, Baicheng, and Tonghua. The temporal dynamics of the incidence of HFRS were primarily explained by the variations in population density (CR = 27.30%), climate (CR = 13.30%), and economic condition(CR = 1.90%). The spatial variations of HFRS were medicated by the climate (CR = 16.95%) and population density (CR = 9.45%) and medical health care (CR = 2.25%). The SEM models indicated that humid and warm climates were conducive to the incidence and increase of HFRS, but the improvement in education and an increase in population density reduced the transmission of HFRS.ConclusionClimate and population density appeared to mediate the spatio-temporal variation of HFRS in Northeastern China. These findings may provide valuable empirical evidence for the management of HFRS in endemic areas.

Project description:BackgroundDespite the successful efforts in controlling malaria in Vietnam, the disease remains a significant health concern, particularly in Central Vietnam. This study aimed to assess correlations between environmental, climatic, and socio-economic factors in the district with malaria cases.MethodsThe study was conducted in 15 provinces in Central Vietnam from January 2018 to December 2022. Monthly malaria cases were obtained from the Institute of Malariology, Parasitology, and Entomology Quy Nhon, Vietnam. Environmental, climatic, and socio-economic data were retrieved using a Google Earth Engine script. A multivariable Zero-inflated Poisson regression was undertaken using a Bayesian framework with spatial and spatiotemporal random effects with a conditional autoregressive prior structure. The posterior random effects were estimated using Bayesian Markov Chain Monte Carlo simulation with Gibbs sampling.ResultsThere was a total of 5,985 Plasmodium falciparum and 2,623 Plasmodium vivax cases during the study period. Plasmodium falciparum risk increased by five times (95% credible interval [CrI] 4.37, 6.74) for each 1-unit increase of normalized difference vegetation index (NDVI) without lag and by 8% (95% CrI 7%, 9%) for every 1ºC increase in maximum temperature (TMAX) at a 6-month lag. While a decrease in risk of 1% (95% CrI 0%, 1%) for a 1 mm increase in precipitation with a 6-month lag was observed. A 1-unit increase in NDVI at a 1-month lag was associated with a four-fold increase (95% CrI 2.95, 4.90) in risk of P. vivax. In addition, the risk increased by 6% (95% CrI 5%, 7%) and 3% (95% CrI 1%, 5%) for each 1ºC increase in land surface temperature during daytime with a 6-month lag and TMAX at a 4-month lag, respectively. Spatial analysis showed a higher mean malaria risk of both species in the Central Highlands and southeast parts of Central Vietnam and a lower risk in the northern and north-western areas.ConclusionIdentification of environmental, climatic, and socio-economic risk factors and spatial malaria clusters are crucial for designing adaptive strategies to maximize the impact of limited public health resources toward eliminating malaria in Vietnam.

Project description:BackgroundThe disease burden caused by pulmonary tuberculosis (TB) in Sichuan province still persisted at a high level, and large spatial variances were presented across regional distribution disparities. The socio-economic factors were suspected to affect the population of TB notification, we aimed to describe TB case notification rate (CNR) and identify which factors influence TB epidemic are necessary for the prevention and control of the disease in Sichuan province.MethodsA retrospective cross-sectional study and an ecological spatial analysis was conducted to quantify the presence and location of spatial clusters of TB by the Moran's I index and examined these patterns with socio-economic risk factors by hierarchical Bayesian spatio-temporal model.ResultsA total of 630,009 pulmonary TB cases were notified from 2006 to 2015 in 181 counties of Sichuan province. The CNR decreased year by year since 2007, from 88.70 to 61.37 per 100,000 persons. The spatial heterogeneities of CNR were observed during the study periods. Global Moran's I index varied from 0.23 to 0.44 with all P-value < 0.001. The Bayesian spatio-temporal model with parametric spatio-temporal interactions was chosen as the best model according to the minimum of Deviance Information Criterion (DIC)(19,379.01), and in which the quadratic form of time was taken. The proportion of age group and education year were all associated with CNR after adjusting the spatial effect, temporal effect and spatio-temporal interactions. TB CNR increased by 10.2% [95% credible interval (CI): 6.7-13.7%] for every 1-standard-deviation increase in proportion of age group and decreased by 23% (95% CI: 13.7-32.7%) for every 1-standard-deviation increase in education year.ConclusionsThere were spatial clusters of TB notification rate in Sichuan province from 2006 to 2015, and heavy TB burden was mainly attributed to aging and low socioeconomic status including poor education. Thus, it is more important to pay more attention to the elderly population and improve socioeconomic status including promoting education level in Sichuan province to reduce the TB burden.

Project description:BackgroundTemperature, precipitation, relative humidity (RH), and Normalized Different Vegetation Index (NDVI), influence malaria transmission dynamics. However, an understanding of interactions between socioeconomic indicators, environmental factors and malaria incidence can help design interventions to alleviate the high burden of malaria infections on vulnerable populations. Our study thus aimed to investigate the socioeconomic and climatological factors influencing spatial and temporal variability of malaria infections in Mozambique.MethodsWe used monthly malaria cases from 2016 to 2018 at the district level. We developed an hierarchical spatial-temporal model in a Bayesian framework. Monthly malaria cases were assumed to follow a negative binomial distribution. We used integrated nested Laplace approximation (INLA) in R for Bayesian inference and distributed lag nonlinear modeling (DLNM) framework to explore exposure-response relationships between climate variables and risk of malaria infection in Mozambique, while adjusting for socioeconomic factors.ResultsA total of 19,948,295 malaria cases were reported between 2016 and 2018 in Mozambique. Malaria risk increased with higher monthly mean temperatures between 20 and 29°C, at mean temperature of 25°C, the risk of malaria was 3.45 times higher (RR 3.45 [95%CI: 2.37-5.03]). Malaria risk was greatest for NDVI above 0.22. The risk of malaria was 1.34 times higher (1.34 [1.01-1.79]) at monthly RH of 55%. Malaria risk reduced by 26.1%, for total monthly precipitation of 480 mm (0.739 [95%CI: 0.61-0.90]) at lag 2 months, while for lower total monthly precipitation of 10 mm, the risk of malaria was 1.87 times higher (1.87 [1.30-2.69]). After adjusting for climate variables, having lower level of education significantly increased malaria risk (1.034 [1.014-1.054]) and having electricity (0.979 [0.967-0.992]) and sharing toilet facilities (0.957 [0.924-0.991]) significantly reduced malaria risk.ConclusionOur current study identified lag patterns and association between climate variables and malaria incidence in Mozambique. Extremes in climate variables were associated with an increased risk of malaria transmission, peaks in transmission were varied. Our findings provide insights for designing early warning, prevention, and control strategies to minimize seasonal malaria surges and associated infections in Mozambique a region where Malaria causes substantial burden from illness and deaths.

Dataset Information

A machine learning-driven spatio-temporal vulnerability appraisal based on socio-economic data for COVID-19 impact prevention in the U.S. counties.

Publications

A machine learning-driven spatio-temporal vulnerability appraisal based on socio-economic data for COVID-19 impact prevention in the U.S. counties.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets