Dataset Information

A GIS-Based Artificial Neural Network Model for Spatial Distribution of Tuberculosis across the Continental United States.

ABSTRACT: 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.

SUBMITTER: Mollalo A

PROVIDER: S-EPMC6338935 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Background: Pulmonary tuberculosis (PTB) is a chronic infectious disease and is the most common type of TB. Although the sputum smear test is a gold standard for diagnosing PTB, the method has numerous limitations, including low sensitivity, low specificity, and insufficient samples. Methods: The present study aimed to identify specific biomarkers of PTB and construct a model for diagnosing PTB by combining random forest (RF) and artificial neural network (ANN) algorithms. Two publicly available cohorts of TB, namely, the GSE83456 (training) and GSE42834 (validation) cohorts, were retrieved from the Gene Expression Omnibus (GEO) database. A total of 45 and 61 differentially expressed genes (DEGs) were identified between the PTB and control samples, respectively, by screening the GSE83456 cohort. An RF classifier was used for identifying specific biomarkers, following which an ANN-based classification model was constructed for identifying PTB samples. The accuracy of the ANN model was validated using the receiver operating characteristic (ROC) curve. The proportion of 22 types of immunocytes in the PTB samples was measured using the CIBERSORT algorithm, and the correlations between the immunocytes were determined. Results: Differential analysis revealed that 11 and 22 DEGs were upregulated and downregulated, respectively, and 11 biomarkers specific to PTB were identified by the RF classifier. The weights of these biomarkers were determined and an ANN-based classification model was subsequently constructed. The model exhibited outstanding performance, as revealed by the area under the curve (AUC), which was 1.000 for the training cohort. The AUC of the validation cohort was 0.946, which further confirmed the accuracy of the model. Conclusion: Altogether, the present study successfully identified specific genetic biomarkers of PTB and constructed a highly accurate model for the diagnosis of PTB based on blood samples. The model developed herein can serve as a reliable reference for the early detection of PTB and provide novel perspectives into the pathogenesis of PTB.

Project description:BACKGROUND: Since the mid 1990s populations of non-native apple snails (Ampullariidae) have been discovered with increasing frequency in the continental United States. Given the dramatic effects that introduced apple snails have had on both natural habitats and agricultural areas in Southeast Asia, their introduction to the mainland U.S. is cause for concern. We combine phylogenetic analyses of mtDNA sequences with examination of introduced populations and museum collections to clarify the identities, introduced distributions, geographical origins, and introduction histories of apple snails. RESULTS: Based on sampling to date, we conclude there are five species of non-native apple snails in the continental U.S. Most significantly, we recognize three species within what has been called the channeled apple snail: Pomacea canaliculata (California and Arizona), Pomacea insularum, (Florida, Texas, and Georgia) and Pomacea haustrum (Florida). The first established populations of P. haustrum were discovered in the late 1970s in Palm Beach County Florida, and have not spread appreciably in 30 years. In contrast, populations of P. insularum were established in Texas by 1989, in Florida by the mid to late 1990s, and in Georgia by 2005, and this species continues to spread rapidly. Most introduced P. insularum haplotypes are a close match to haplotypes from the Río Uruguay near Buenos Aires, indicating cold tolerance, with the potential to spread from Florida, Georgia, and Texas through Louisiana, Alabama, Mississippi, and South Carolina. Pomacea canaliculata populations were first discovered in California in 1997. Haplotypes of introduced P. canaliculata match native-range haplotypes from near Buenos Aires, Argentina, also indicating cold tolerance and the potential to establish farther north. CONCLUSION: The term "channeled apple snail" is descriptive of a morphology found in many apple snail species. It does not identify a single species or a monophyletic group. Clarifying species identifications permits a more accurate assessment of introduction histories and distributions, and provides a very different picture of the tempo and pattern of invasions than was inferred when the three species with channeled sutures were considered one. Matching introduced and native-range haplotypes suggests the potential for range expansion, with implications for native aquatic ecosystems and species, agriculture, and human health.

Project description:BackgroundNumerous studies have studied the association between daily average temperature (DAT) and daily COVID-19 confirmed cases, which show considerable heterogeneity, even opposite results, among different regions. Such heterogeneity suggests that characterizing the association on a large area scale would ignore the local variation, even obtain false results in some local regions. So, characterizing the spatial distribution of heterogeneous DAT-COVID-19 associations and exploring the causes plays an important role on making temperature-related region-specific intervention measures and early-warning systems.MethodsAiming to characterize the spatial distribution of associations between DAT and COVID-19 confirmed cases in the continental United States, we proposed a novel two-stage strategy. In the first stage, we used the common stratified distributed lag nonlinear model to obtain the rough state-specific associations. In the second stage, conditional autoregression was used to spatially smooth the rough estimations. Furtherly, based on the idea, two modified strategies were used to investigate the time-varying associations and the modification effects derived from the vaccination campaign.ResultsAround one-third of states exhibit no significant association between DAT and daily confirmed COVID-19 cases. Most of the remaining states present a low risk at low DAT and a high risk at high DAT, but several states present opposite associations. The average association curve presents a 'S' shape with positive association between -8 - 18 °C and keeping flat out of the range. An increased vaccination coverage rate will increase the risk when DAT < 12 °C, but slightly affect the risk when DAT > 12 °C.ConclusionA considerable spatial heterogeneity of DAT-COVID-19 associations exists in America and the average association curve presents a 'S' shape. The vaccination campaign significantly modifies the association when DAT is low, but only make a slight modification when DAT is high.

Dataset Information

A GIS-Based Artificial Neural Network Model for Spatial Distribution of Tuberculosis across the Continental United States.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets