Predicting the hotspots of age-adjusted mortality rates of lower respiratory infection across the continental United States: Integration of GIS, spatial statistics and machine learning algorithms.
Ontology highlight
ABSTRACT:
SUBMITTER: Mollalo A
PROVIDER: S-EPMC7442929 | biostudies-literature | 2020 Oct
REPOSITORIES: biostudies-literature
Publications
Predicting the hotspots of age-adjusted mortality rates of lower respiratory infection across the continental United States: Integration of GIS, spatial statistics and machine learning algorithms.
Mollalo Abolfazl A Vahedi Behrooz B Bhattarai Shreejana S Hopkins Laura C LC Banik Swagata S Vahedi Behzad B
International journal of medical informatics 20200822
<h4>Objective</h4>Although lower respiratory infections (LRI) are among the leading causes of mortality in the US, their association with underlying factors and geographic variation have not been adequately examined.<h4>Methods</h4>In this study, explanatory variables (n = 46) including climatic, topographic, socio-economic, and demographic factors were compiled at the county level across the continentalUS.Machine learning algorithms - logistic regression (LR), random forest (RF), gradient boost ...[more]
Similar Datasets
Project description:Despite the usefulness of artificial neural networks (ANNs) in the study of various complex problems, ANNs have not been applied for modeling the geographic distribution of tuberculosis (TB) in the US. Likewise, ecological level researches on TB incidence rate at the national level are inadequate for epidemiologic inferences. We collected 278 exploratory variables including environmental and a broad range of socio-economic features for modeling the disease across the continental US. The spatial pattern of the disease distribution was statistically evaluated using the global Moran's I, Getis⁻Ord General G, and local Gi* statistics. Next, we investigated the applicability of multilayer perceptron (MLP) ANN for predicting the disease incidence. To avoid overfitting, L1 regularization was used before developing the models. Predictive performance of the MLP was compared with linear regression for test dataset using root mean square error, mean absolute error, and correlations between model output and ground truth. Results of clustering analysis showed that there is a significant spatial clustering of smoothed TB incidence rate (p < 0.05) and the hotspots were mainly located in the southern and southeastern parts of the country. Among the developed models, single hidden layer MLP had the best test accuracy. Sensitivity analysis of the MLP model showed that immigrant population (proportion), underserved segments of the population, and minimum temperature were among the factors with the strongest contributions. The findings of this study can provide useful insight to health authorities on prioritizing resource allocation to risk-prone areas.
| S-EPMC6338935 | biostudies-literature
Project description:MotivationThe detection of genomic regions unusually rich in a given pattern is an important undertaking in the analysis of next-generation sequencing data. Recent studies of chromosomal translocations in activated B lymphocytes have identified regions that are frequently translocated to c-myc oncogene. A quantitative method for the identification of translocation hotspots was crucial to this study. Here we improve this analysis by using a simple probabilistic model and the framework provided by scan statistics to define the number and location of translocation breakpoint hotspots. A key feature of our method is that it provides a global chromosome-wide nominal control level to clustering, as opposed to previous methods based on local criteria. While being motivated by a specific application, the detection of unusual clusters is a widespread problem in bioinformatics. We expect our method to be useful in the analysis of data from other experimental approaches such as of ChIP-seq and 4C-seq.ResultsThe analysis of translocations from B lymphocytes with the method described here reveals the presence of longer hotspots when compared with those defined previously. Further, we show that the hotspot size changes substantially in the absence of DNA repair protein 53BP1. When 53BP1 deficiency is combined with overexpression of activation-induced cytidine deaminase, the hotspot length increases even further. These changes are not detected by previous methods that use local significance criteria for clustering. Our method is also able to identify several exclusive translocation hotspots located in genes of known tumor supressors.Availability and implementationThe detection of translocation hotspots is done with hot_scan, a program implemented in R and Perl. Source code and documentation are freely available for download at https://github.com/itojal/hot_scan.
| S-EPMC4155254 | biostudies-literature
Project description:Prediction of the COVID-19 incidence rate is a matter of global importance, particularly in the United States. As of 4 June 2020, more than 1.8 million confirmed cases and over 108 thousand deaths have been reported in this country. Few studies have examined nationwide modeling of COVID-19 incidence in the United States particularly using machine-learning algorithms. Thus, we collected and prepared a database of 57 candidate explanatory variables to examine the performance of multilayer perceptron (MLP) neural network in predicting the cumulative COVID-19 incidence rates across the continental United States. Our results indicated that a single-hidden-layer MLP could explain almost 65% of the correlation with ground truth for the holdout samples. Sensitivity analysis conducted on this model showed that the age-adjusted mortality rates of ischemic heart disease, pancreatic cancer, and leukemia, together with two socioeconomic and environmental factors (median household income and total precipitation), are among the most substantial factors for predicting COVID-19 incidence rates. Moreover, results of the logistic regression model indicated that these variables could explain the presence/absence of the hotspots of disease incidence that were identified by Getis-Ord Gi* (p < 0.05) in a geographic information system environment. The findings may provide useful insights for public health decision makers regarding the influence of potential risk factors associated with the COVID-19 incidence at the county level.
| S-EPMC7344609 | biostudies-literature
Project description:Multisample U-statistics encompass a wide class of test statistics that allow the comparison of 2 or more distributions. U-statistics are especially powerful because they can be applied to both numeric and nonnumeric data, eg, ordinal and categorical data where a pairwise similarity or distance-like measure between categories is available. However, when comparing the distribution of a variable across 2 or more groups, observed differences may be due to confounding covariates. For example, in a case-control study, the distribution of exposure in cases may differ from that in controls entirely because of variables that are related to both exposure and case status and are distributed differently among case and control participants. We propose to use individually reweighted data (ie, using the stratification score for retrospective data or the propensity score for prospective data) to construct adjusted U-statistics that can test the equality of distributions across 2 (or more) groups in the presence of confounding covariates. Asymptotic normality of our adjusted U-statistics is established and a closed form expression of their asymptotic variance is presented. The utility of our approach is demonstrated through simulation studies, as well as in an analysis of data from a case-control study conducted among African-Americans, comparing whether the similarity in haplotypes (ie, sets of adjacent genetic loci inherited from the same parent) occurring in a case and a control participant differs from the similarity in haplotypes occurring in 2 control participants.
| S-EPMC6322553 | biostudies-literature
Project description:Less than 25% of the volume of the juvenile continental crust preserved today is older than 3?Ga, there are no known rocks older than approximately 4?Ga, and yet a number of recent models of continental growth suggest that at least 60-80% of the present volume of the continental crust had been generated by 3?Ga. Such models require that large volumes of pre-3?Ga crust were destroyed and replaced by younger crust since the late Archaean. To address this issue, we evaluate the influence on the rock record of changing the rates of generation and destruction of the continental crust at different times in Earth's history. We adopted a box model approach in a numerical model constrained by the estimated volumes of continental crust at 3?Ga and the present day, and by the distribution of crust formation ages in the present-day crust. The data generated by the model suggest that new continental crust was generated continuously, but with a marked decrease in the net growth rate at approximately 3?Ga resulting in a temporary reduction in the volume of continental crust at that time. Destruction rates increased dramatically around 3 billion years ago, which may be linked to the widespread development of subduction zones. The volume of continental crust may have exceeded its present value by the mid/late Proterozoic. In this model, about 2.6-2.3 times of the present volume of continental crust has been generated since Earth's formation, and approximately 1.6-1.3 times of this volume has been destroyed and recycled back into the mantle.This article is part of a discussion meeting issue 'Earth dynamics and the development of plate tectonics'.
| S-EPMC6189557 | biostudies-literature
Project description:Amphibians with missing, misshapen, and extra limbs have garnered public and scientific attention for two decades, yet the extent of the phenomenon remains poorly understood. Despite progress in identifying the causes of abnormalities in some regions, a lack of knowledge about their broader spatial distribution and temporal dynamics has hindered efforts to understand their implications for amphibian population declines and environmental quality. To address this data gap, we conducted a nationwide, 10-year assessment of 62,947 amphibians on U.S. National Wildlife Refuges. Analysis of a core dataset of 48,081 individuals revealed that consistent with expected background frequencies, an average of 2% were abnormal, but abnormalities exhibited marked spatial variation with a maximum prevalence of 40%. Variance partitioning analysis demonstrated that factors associated with space (rather than species or year sampled) captured 97% of the variation in abnormalities, and the amount of partitioned variance decreased with increasing spatial scale (from site to refuge to region). Consistent with this, abnormalities occurred in local to regional hotspots, clustering at scales of tens to hundreds of kilometers. We detected such hotspot clusters of high-abnormality sites in the Mississippi River Valley, California, and Alaska. Abnormality frequency was more variable within than outside of hotspot clusters. This is consistent with dynamic phenomena such as disturbance or natural enemies (pathogens or predators), whereas similarity of abnormality frequencies at scales of tens to hundreds of kilometers suggests involvement of factors that are spatially consistent at a regional scale. Our characterization of the spatial and temporal variation inherent in continent-wide amphibian abnormalities demonstrates the disproportionate contribution of local factors in predicting hotspots, and the episodic nature of their occurrence.
| S-EPMC3832516 | biostudies-literature
Project description:Continental aquatic species richness hotspots are unevenly distributed across the planet. In present-day Europe, only two centers of biodiversity exist (Lake Ohrid on the Balkans and the Caspian Sea). During the Neogene, a wide variety of hotspots developed in a series of long-lived lakes. The mechanisms underlying the presence of richness hotspots in different geological periods have not been properly examined thus far. Based on Miocene to Recent gastropod distributions, we show that the existence and evolution of such hotspots in inland-water systems are tightly linked to the geodynamic history of the European continent. Both past and present hotspots are related to the formation and persistence of long-lived lake systems in geological basins or to isolation of existing inland basins and embayments from the marine realm. The faunal evolution within hotspots highly depends on warm climates and surface area. During the Quaternary icehouse climate and extensive glaciations, limnic biodiversity sustained a severe decline across the continent and most former hotspots disappeared. The Recent gastropod distribution is mainly a geologically young pattern formed after the Last Glacial Maximum (19 ky) and subsequent formation of postglacial lakes. The major hotspots today are related to long-lived lakes in preglacially formed, permanently subsiding geological basins.
| S-EPMC4577204 | biostudies-literature
Project description:BackgroundIn 2002, the WHO declared interpersonal violence to be a leading public health problem. Previous research demonstrates that urban spaces with a high incidence of violent trauma (hotspots) correlate with features of built environment and social determinants. However, there are few studies that analyse injury data across the axes of both space and time to characterise injury-environment relationships. This paper describes a spatiotemporal analysis of violent injuries in Vancouver, Canada, from 2001 to 2008.MethodsUsing geographic information systems, 575 violent trauma incidents were mapped and analysed using kernel density estimation to identify hotspot locations. Patterns between space, time, victim age and sex and mechanism of injury were investigated with an exploratory approach.ResultsSeveral patterns in space and time were identified and described, corresponding to distinct neighbourhood characteristics. Violent trauma hotspots were most prevalent in Vancouver's nightclub district on Friday and Saturday nights, with higher rates in the most socioeconomically deprived neighbourhoods. Victim sex, age and mechanism of injury also formed strong patterns. Three neighbourhood profiles are presented using the dual axis of space/time to describe the hotspot environments.ConclusionsThis work posits the value of exploratory spatial data analysis using geographic information systems in trauma epidemiology studies and further suggests that using both space and time concurrently to understand urban environmental correlates of injury provides a more granular or higher resolution picture of risk. We discuss implications for injury prevention and control, focusing on education, regulation, the built environment and injury surveillance.
| S-EPMC3931990 | biostudies-literature
Project description:As more human genomic data become available, fine-scale recombination rate variation can be inferred on a genome-wide scale. Current statistical methods to infer recombination rates that can be applied to moderate, or large, genomic regions are limited to approximated likelihoods. Here, we develop a Bayesian full-likelihood method using Markov Chain Monte Carlo (MCMC) to estimate background recombination rates and hotspots. The probability model is inspired by the observed patterns of recombination at several genomic regions analyzed in sperm-typing studies. Posterior probabilities and Bayes factors of recombination hotspots along chromosomes are inferred. For moderate-size genomic regions (e.g., with <100 SNPs), the full-likelihood method is used. Larger regions are split into subintervals (typically each having between 20 and 50 markers). The likelihood is approximated based on the genealogies for each subinterval. The background recombination rates, hotspots, and parameters are evaluated by using a parallel computing approach and assuming shared parameters across the subintervals. Simulation analyses show that our method can accurately estimate the variation in recombination rates across genomic regions. In particular, clusters of hotspots can be distinguished even though weaker hotspots are present. The method is applied to SNP data from the HLA region, the MS32, and chromosome 19.
| S-EPMC2669376 | biostudies-literature
Project description:MotivationGene therapy with retroviral vectors can induce adverse effects when those vectors integrate in sensitive genomic regions. Retroviral vectors are preferred that target sensitive regions less frequently, motivating the search for localized clusters of integration sites and comparison of the clusters formed by integration of different vectors. Scan statistics allow the discovery of spatial differences in clustering and calculation of false discovery rates providing statistical methods for comparing retroviral vectors.ResultsA scan statistic for comparing two vectors using multiple window widths is proposed with software to detect clustering differentials and compute false discovery rates. Application to several sets of experimentally determined HIV integration sites demonstrates the software. Simulated datasets of various sizes and signal strengths are used to determine the power to discover clusters and evaluate a convenient lower bound. This provides a toolkit for planning evaluations of new gene therapy vectors.Availability and implementationThe geneRxCluster R package containing a simple tutorial and usage hints is available from http://www.bioconductor.org.
| S-EPMC4029028 | biostudies-literature