Spatial non-parametric Bayesian clustered coefficients.

In the field of population health research, understanding the similarities between geographical areas and quantifying their shared effects on health outcomes is crucial. In this paper, we synthesise a number of existing methods to create a new approach that specifically addresses this goal. The approach is called a Bayesian spatial Dirichlet process clustered heterogeneous regression model. This non-parametric framework allows for inference on the number of clusters and the clustering configurations, while simultaneously estimating the parameters for each cluster. We demonstrate the efficacy of the proposed algorithm using simulated data and further apply it to analyse influential factors affecting children's health development domains in Queensland. The study provides valuable insights into the contributions of regional similarities in education and demographics to health outcomes, aiding targeted interventions and policy design.

Where are the vulnerable children? Identification and comparison of clusters of young children with health and developmental vulnerabilities across Queensland.

This study aimed to better understand the vulnerability of children in their first year of school, aged between 5 years 5 months and 6 years 6 months, based on five health and development domains. Identification of subgroups of children within these domains can lead to more targeted policies to reduce these vulnerabilities. The focus of this study was to determine clusters of geographical regions with high and low proportions of vulnerable children in Queensland, Australia. This was achieved by carrying out a K-means analysis on data from the Australian Early Development Census and the Australian Bureau of Statistics. The clusters were then compared with respect to their geographic locations and risk factor profiles. The results are made publicly available via an interactive dashboard application developed in R Shiny.

Towards development of functional climate-driven early warning systems for climate-sensitive infectious diseases: Statistical models and recommendations.

Climate, weather and environmental change have significantly influenced patterns of infectious disease transmission, necessitating the development of early warning systems to anticipate potential impacts and respond in a timely and effective way. Statistical modelling plays a pivotal role in understanding the intricate relationships between climatic factors and infectious disease transmission. For example, time series regression modelling and spatial cluster analysis have been employed to identify risk factors and predict spatial and temporal patterns of infectious diseases. Recently advanced spatio-temporal models and machine learning offer an increasingly robust framework for modelling uncertainty, which is essential in climate-driven disease surveillance due to the dynamic and multifaceted nature of the data. Moreover, Artificial Intelligence (AI) techniques, including deep learning and neural networks, excel in capturing intricate patterns and hidden relationships within climate and environmental data sets. Web-based data has emerged as a powerful complement to other datasets encompassing climate variables and disease occurrences. However, given the complexity and non-linearity of climate-disease interactions, advanced techniques are required to integrate and analyse these diverse data to obtain more accurate predictions of impending outbreaks, epidemics or pandemics. This article presents an overview of an approach to creating climate-driven early warning systems with a focus on statistical model suitability and selection, along with recommendations for utilizing spatio-temporal and machine learning techniques. By addressing the limitations and embracing the recommendations for future research, we could enhance preparedness and response strategies, ultimately contributing to the safeguarding of public health in the face of evolving climate challenges.

Impacts of heatwaves on type 2 diabetes mortality in China: a comparative analysis between coastal and inland cities.

The impacts of extreme temperatures on diabetes have been explored in previous studies. However, it is unknown whether the impacts of heatwaves appear variations between inland and coastal regions. This study aims to quantify the associations between heat exposure and type 2 diabetes mellitus (T2DM) deaths in two cities with different climate features in Shandong Province, China. We used a case-crossover design by quasi-Poisson generalized additive regression with a distributed lag model with lag 2 weeks, controlling for relative humidity, the concentration of air pollution particles with a diameter of 2.5 µm or less (PM2.5), and seasonality. The wet- bulb temperature (Tw) was used to measure the heat stress of the heatwaves. A significant association between heatwaves and T2DM deaths was only found in the coastal city (Qingdao) at the lag of 2 weeks at the lowest Tw = 14℃ (relative risk (RR) = 1.49, 95% confidence interval (CI): 1.11-2.02; women: RR = 1.51, 95% CI: 1.02-2.24; elderly: RR = 1.50, 95% CI: 1.08-2.09). The lag-specific effects were significant associated with Tw at lag of 1 week at the lowest Tw = 14℃ (RR = 1.14, 95% CI: 1.03-1.26; women: RR = 1.15, 95% CI: 1.01-1.31; elderly: RR = 1.15, 95% CI: 1.03-1.28). However, no significant association was found in Jian city. The research suggested that Tw was significantly associated with T2DM mortality in the coastal city during heatwaves on T2DM mortality. Future strategies should be implemented with considering socio-environmental contexts in regions.

Epidemiological features of seasonal influenza transmission among 11 climate zones in Chinese Mainland.

BACKGROUND: Previous studies provided some evidence of meteorological factors influence seasonal influenza transmission patterns varying across regions and latitudes. However, research on seasonal influenza activities based on climate zones are still in lack. This study aims to utilize the ecological-based Köppen Geiger climate zones classification system to compare the spatial and temporal epidemiological characteristics of seasonal influenza in Chinese Mainland and assess the feasibility of developing an early warning system. METHODS: Weekly influenza cases number from 2014 to 2019 at the county and city level were sourced from China National Notifiable Infectious Disease Report Information System. Epidemic temporal indices, time series seasonality decomposition, spatial modelling theories including Moran's I and local indicators of spatial association were applied to identify the spatial and temporal patterns of influenza transmission. RESULTS: All climate zones had peaks in Winter-Spring season. Arid, desert, cold (BWk) showed up the first peak. Only Tropical, savannah (Aw) and Temperate, dry winter with hot summer (Cwa) zones had unique summer peak. Temperate, no dry season and hot summer (Cfa) zone had highest average incidence rate (IR) at 1.047/100,000. The Global Moran's I showed that average IR had significant clustered trend (z = 53.69, P < 0.001), with local Moran's I identified high-high cluster in Cfa and Cwa. IR differed among three age groups between climate zones (0-14 years old: F = 26.80, P < 0.001; 15-64 years old: F = 25.04, P < 0.001; Above 65 years old: F = 5.27, P < 0.001). Age group 0-14 years had highest average IR in Cwa and Cfa (IR = 6.23 and 6.21) with unique dual peaks in winter and spring season showed by seasonality decomposition. CONCLUSIONS: Seasonal influenza exhibited distinct spatial and temporal patterns in different climate zones. Seasonal influenza primarily emerged in BWk, subsequently in Cfa and Cwa. Cfa, Cwa and BSk pose high risk for seasonal influenza epidemics. The research finds will provide scientific evidence for developing seasonal influenza early warning system based on climate zones.

Mapping the prevalence of cancer risk factors at the small area level in Australia.

BACKGROUND: Cancer is a significant health issue globally and it is well known that cancer risk varies geographically. However in many countries there are no small area-level data on cancer risk factors with high resolution and complete reach, which hinders the development of targeted prevention strategies. METHODS: Using Australia as a case study, the 2017-2018 National Health Survey was used to generate prevalence estimates for 2221 small areas across Australia for eight cancer risk factor measures covering smoking, alcohol, physical activity, diet and weight. Utilising a recently developed Bayesian two-stage small area estimation methodology, the model incorporated survey-only covariates, spatial smoothing and hierarchical modelling techniques, along with a vast array of small area-level auxiliary data, including census, remoteness, and socioeconomic data. The models borrowed strength from previously published cancer risk estimates provided by the Social Health Atlases of Australia. Estimates were internally and externally validated. RESULTS: We illustrated that in 2017-2018 health behaviours across Australia exhibited more spatial disparities than previously realised by improving the reach and resolution of formerly published cancer risk factors. The derived estimates revealed higher prevalence of unhealthy behaviours in more remote areas, and areas of lower socioeconomic status; a trend that aligned well with previous work. CONCLUSIONS: Our study addresses the gaps in small area level cancer risk factor estimates in Australia. The new estimates provide improved spatial resolution and reach and will enable more targeted cancer prevention strategies at the small area level. Furthermore, by including the results in the next release of the Australian Cancer Atlas, which currently provides small area level estimates of cancer incidence and relative survival, this work will help to provide a more comprehensive picture of cancer in Australia by supporting policy makers, researchers, and the general public in understanding the spatial distribution of cancer risk factors. The methodology applied in this work is generalisable to other small area estimation applications and has been shown to perform well when the survey data are sparse.

Disease mapping: Geographic differences in population rates of interventional treatment for prostate cancer in Australia.

BACKGROUND: Treatment decisions for men diagnosed with prostate cancer depend on a range of clinical and patient characteristics such as disease stage, age, general health, risk of side effects and access. Associations between treatment patterns and area-level factors such as remoteness and socioeconomic disadvantage have been observed in many countries. OBJECTIVE: To model spatial differences in interventional treatment rates for prostate cancer at high spatial resolution to inform policy and decision-making. METHODS: Hospital separations data for interventional treatments for prostate cancer (radical prostatectomy, low dose rate and high dose rate brachytherapy) for men aged 40 years and over were modelled using spatial models, generalised linear mixed models, maximised excess events tests and k-means statistical clustering. RESULTS: Geographic differences in population rates of interventional treatments were found (p<0.001). Separation rates for radical prostatectomy were lower in remote areas (12.2 per 10 000 person-years compared with 15.0-15.9 in regional and major city areas). Rates for all treatments decreased with increasing socioeconomic disadvantage (radical prostatectomy 19.1 /10 000 person-years in the most advantaged areas compared with 12.9 in the most disadvantaged areas). Three groups of similar areas were identified: those with higher rates of radical prostatectomy, those with higher rates of low dose brachytherapy, and those with low interventional treatment rates but higher rates of excess deaths. The most disadvantaged areas and remote areas tended to be in the latter group. CONCLUSIONS: The geographic differences in treatment rates may partly reflect differences in patients' physical and financial access to treatments. Treatment rates also depend on diagnosis rates and thus reflect variation in investigation rates for prostate cancer and presentation of disease. Spatial variation in interventional treatments may aid identification of areas of under-treatment or over-treatment.

clusterBMA: Bayesian model averaging for clustering.

Various methods have been developed to combine inference across multiple sets of results for unsupervised clustering, within the ensemble clustering literature. The approach of reporting results from one 'best' model out of several candidate clustering models generally ignores the uncertainty that arises from model selection, and results in inferences that are sensitive to the particular model and parameters chosen. Bayesian model averaging (BMA) is a popular approach for combining results across multiple models that offers some attractive benefits in this setting, including probabilistic interpretation of the combined cluster structure and quantification of model-based uncertainty. In this work we introduce clusterBMA, a method that enables weighted model averaging across results from multiple unsupervised clustering algorithms. We use clustering internal validation criteria to develop an approximation of the posterior model probability, used for weighting the results from each model. From a combined posterior similarity matrix representing a weighted average of the clustering solutions across models, we apply symmetric simplex matrix factorisation to calculate final probabilistic cluster allocations. In addition to outperforming other ensemble clustering methods on simulated data, clusterBMA offers unique features including probabilistic allocation to averaged clusters, combining allocation probabilities from 'hard' and 'soft' clustering algorithms, and measuring model-based uncertainty in averaged cluster allocation. This method is implemented in an accompanying R package of the same name. We use simulated datasets to explore the ability of the proposed technique to identify robust integrated clusters with varying levels of separation between subgroups, and with varying numbers of clusters between models. Benchmarking accuracy against four other ensemble methods previously demonstrated to be highly effective in the literature, clusterBMA matches or exceeds the performance of competing approaches under various conditions of dimensionality and cluster separation. clusterBMA substantially outperformed other ensemble methods for high dimensional simulated data with low cluster separation, with 1.16 to 7.12 times better performance as measured by the Adjusted Rand Index. We also explore the performance of this approach through a case study that aims to identify probabilistic clusters of individuals based on electroencephalography (EEG) data. In applied settings for clustering individuals based on health data, the features of probabilistic allocation and measurement of model-based uncertainty in averaged clusters are useful for clinical relevance and statistical communication.

Assessing the spatial structure of the association between attendance at preschool and children's developmental vulnerabilities in Queensland, Australia.

Demographic and educational factors are essential, influential factors of early childhood development. This study aimed to investigate spatial patterns in the association between attendance at preschool and children's developmental vulnerabilities in one or more domain(s) in their first year of full-time school at a small area level in Queensland, Australia. This was achieved by applying geographically weighted regression (GWR) followed by K-means clustering of the regression coefficients. Three distinct geographical clusters were found in Queensland using the GWR coefficients. The first cluster covered more than half of the state of Queensland, including the Greater Brisbane region, and displays a strong negative association between developmental vulnerabilities and attendance at preschool. That is, areas with high proportions of preschool attendance tended to have lower proportions of children with at least one developmental vulnerability in the first year of full-time school. Clusters two and three were characterized by stronger negative associations between developmental vulnerabilities, English as the mother language, and geographic remoteness, respectively. This research provides evidence of the need for collaboration between health and education sectors in specific regions of Queensland to update current service provision policies and to ensure holistic and appropriate care is available to support children with developmental vulnerabilities.

Impact of environmental factors on diabetes mortality: A comparison between inland and coastal areas.

BACKGROUND: Diabetes mortality varies between coastal and inland areas in Shandong Province, China. However, evidence about the reasons for this disparity is limited. We assume that distinct environmental conditions may contribute to the disparities in diabetes mortality patterns between coastal and inland areas. METHOD: Qingdao and Jinan were selected as typical coastal and inland cities in Shandong Province, respectively, with similar socioeconomic but different environmental characteristics. Data on diabetes deaths and environmental factors (i.e., temperature, relative humidity and air pollution particles with a diameter of 2.5 µm or less (PM2.5)) were collected from 2013 to 2020. Spatial kriging methods were used to estimate the aggregated diabetes mortality at the city level. A distributed lag non-linear model (DLNM) was used to quantify the possible cumulative and non-cumulative associations between environmental factors and diabetes mortality by age, sex and location. RESULTS: In the coastal city (Qingdao), the maximum cumulative relative risks (RRs) of temperature and PM2.5 associated with diabetes deaths were 2.54 (95 % confidence interval (CI): 1.25-5.15), and 1.17 (95 % CI: 1.01-1.37) respectively, at lag 1 week. In the inland city (Jinan), only temperature exhibited significant cumulative associations with diabetes deaths (RR = 1.54, 95 % CI: 1.07-2.23 at 29 °C). Lower relative humidity (22 %-45 %) had a lag-specific association with diabetes deaths in inland areas at lag 3 weeks (RR = 1.33, 95 % CI: 1.03-1.70 at 22 %). CONCLUSION: Despite the lower PM2.5 concentrations in the coastal location, diabetes mortality exhibited stronger links to environmental variables in the coastal city than in the inland city. These findings suggest that the control of air pollution could decrease the mortality burden of diabetes, even in the region with relatively good air quality. Additionally, the spatial estimation method is recommended to identify associations between environmental factors and diseases in studies with limited data.

Geographical and spatial variations in bowel cancer screening participation, Australia, 2015-2020.

BACKGROUND: Participation in bowel cancer screening programs remains poor in many countries. Knowledge of geographical variation in participation rates may help design targeted interventions to improve uptake. This study describes small-area and broad geographical patterns in bowel screening participation in Australia between 2015-2020. METHODS: Publicly available population-level participation data for Australia's National Bowel Cancer Screening Program (NBCSP) were modelled using generalized linear models to quantify screening patterns by remoteness and area-level disadvantage. Bayesian spatial models were used to obtain smoothed estimates of participation across 2,247 small areas during 2019-2020 compared to the national average, and during 2015-2016 and 2017-2018 for comparison. Spatial heterogeneity was assessed using the maximized excess events test. RESULTS: Overall, screening participation rates was around 44% over the three time-periods. Participation was consistently lower in remote or disadvantaged areas, although heterogeneity was evident within these broad categories. There was strong evidence of spatial differences in participation over all three periods, with little change in patterns between time periods. If the spatial variation was reduced (so low participation areas were increased to the 80th centile), an extra 250,000 screens (4% of total) would have been conducted during 2019-2020. CONCLUSIONS: Despite having a well-structured evidence-based government funded national bowel cancer screening program, the substantial spatial variation in participation rates highlights the importance of accounting for the unique characteristics of specific geographical regions and their inhabitants. Identifying the reasons for geographical disparities could inform interventions to achieve more equitable access and a higher overall bowel screening uptake.

Understanding links between water-quality variables and nitrate concentration in freshwater streams using high frequency sensor data.

Real-time monitoring using in-situ sensors is becoming a common approach for measuring water-quality within watersheds. High-frequency measurements produce big datasets that present opportunities to conduct new analyses for improved understanding of water-quality dynamics and more effective management of rivers and streams. Of primary importance is enhancing knowledge of the relationships between nitrate, one of the most reactive forms of inorganic nitrogen in the aquatic environment, and other water-quality variables. We analysed high-frequency water-quality data from in-situ sensors deployed in three sites from different watersheds and climate zones within the National Ecological Observatory Network, USA. We used generalised additive mixed models to explain the nonlinear relationships at each site between nitrate concentration and conductivity, turbidity, dissolved oxygen, water temperature, and elevation. Temporal auto-correlation was modelled with an auto-regressive-moving-average (ARIMA) model and we examined the relative importance of the explanatory variables. Total deviance explained by the models was high for all sites (99%). Although variable importance and the smooth regression parameters differed among sites, the models explaining the most variation in nitrate contained the same explanatory variables. This study demonstrates that building a model for nitrate using the same set of explanatory water-quality variables is achievable, even for sites with vastly different environmental and climatic characteristics. Applying such models will assist managers to select cost-effective water-quality variables to monitor when the goals are to gain a spatial and temporal in-depth understanding of nitrate dynamics and adapt management plans accordingly.

A global perspective on the intrinsic dimensionality of COVID-19 data.

We develop a novel global perspective of the complexity of the relationships between three COVID-19 datasets, the standardised per-capita growth rate of COVID-19 cases and deaths, and the Oxford Coronavirus Government Response Tracker COVID-19 Stringency Index (CSI) which is a measure describing a country's stringency of lockdown policies. We use a state-of-the-art heterogeneous intrinsic dimension estimator implemented as a Bayesian mixture model, called Hidalgo. Our findings suggest that these highly popular COVID-19 statistics may project onto two low-dimensional manifolds without significant information loss, suggesting that COVID-19 data dynamics are generated from a latent mechanism characterised by a few important variables. The low dimensionality imply a strong dependency among the standardised growth rates of cases and deaths per capita and the CSI for countries over 2020-2021. Importantly, we identify spatial autocorrelation in the intrinsic dimension distribution worldwide. The results show how high-income countries are more prone to lie on low-dimensional manifolds, likely arising from aging populations, comorbidities, and increased per capita mortality burden from COVID-19. Finally, the temporal stratification of the dataset allows the examination of the intrinsic dimension at a more granular level throughout the pandemic.

SMOTE-CD: SMOTE for compositional data.

Compositional data are a special kind of data, represented as a proportion carrying relative information. Although this type of data is widely spread, no solution exists to deal with the cases where the classes are not well balanced. After describing compositional data imbalance, this paper proposes an adaptation of the original Synthetic Minority Oversampling TEchnique (SMOTE) to deal with compositional data imbalance. The new approach, called SMOTE for Compositional Data (SMOTE-CD), generates synthetic examples by computing a linear combination of selected existing data points, using compositional data operations. The performance of the SMOTE-CD is tested with three different regressors (Gradient Boosting tree, Neural Networks, Dirichlet regressor) applied to two real datasets and to synthetic generated data, and the performance is evaluated using accuracy, cross-entropy, F1-score, R2 score and RMSE. The results show improvements across all metrics, but the impact of oversampling on performance varies depending on the model and the data. In some cases, oversampling may lead to a decrease in performance for the majority class. However, for the real data, the best performance across all models is achieved when oversampling is used. Notably, the F1-score is consistently increased with oversampling. Unlike the original technique, the performance is not improved when combining oversampling of the minority classes and undersampling of the majority class. The Python package smote-cd implements the method and is available online.

Predicting Carcass Weight of Grass-Fed Beef Cattle before Slaughter Using Statistical Modelling.

Gaining insights into the utilization of farm-level data for decision-making within the beef industry is vital for improving production and profitability. In this study, we present a statistical model to predict the carcass weight (CW) of grass-fed beef cattle at different stages before slaughter using historical cattle data. Models were developed using two approaches: boosted regression trees and multiple linear regression. A sample of 2995 grass-fed beef cattle from 3 major properties in Northern Australia was used in the modeling. Four timespans prior to the slaughter, i.e., 1 month, 3 months, 9-10 months, and at weaning, were considered in the predictive modelling. Seven predictors, i.e., weaning weight, weight gain since weaning to each stage before slaughter, time since weaning to each stage before slaughter, breed, sex, weaning season (wet and dry), and property, were used as the potential predictors of the CW. To assess the predictive performance in each scenario, a test set which was not used to train the models was utilized. The results showed that the CW of the cattle was strongly associated with the animal's body weight at each stage before slaughter. The results showed that the CW can be predicted with a mean absolute percentage error (MAPE) of 4% (~12-16 kg) at three months before slaughter. The predictive error increased gradually when moving away from the slaughter date, e.g., the prediction error at weaning was ~8% (~20-25 kg). The overall predictive performances of the two statistical approaches was approximately similar, and neither of the models substantially outperformed each other. Predicting the CW in advance of slaughter may allow farmers to adequately prepare for forthcoming needs at the farm level, such as changing husbandry practices, control inventory, and estimate price return, thus allowing them to maximize the profitability of the industry.

Being Bayesian in the 2020s: opportunities and challenges in the practice of modern applied Bayesian statistics.

Building on a strong foundation of philosophy, theory, methods and computation over the past three decades, Bayesian approaches are now an integral part of the toolkit for most statisticians and data scientists. Whether they are dedicated Bayesians or opportunistic users, applied professionals can now reap many of the benefits afforded by the Bayesian paradigm. In this paper, we touch on six modern opportunities and challenges in applied Bayesian statistics: intelligent data collection, new data sources, federated analysis, inference for implicit models, model transfer and purposeful software products. This article is part of the theme issue 'Bayesian inference: challenges, perspectives, and prospects'.

Geographical and spatial disparities in the incidence and survival of rare cancers in Australia.

Rare cancers collectively account for around a quarter of cancer diagnoses and deaths. However, epidemiological studies are sparse. We describe spatial and geographical patterns in incidence and survival of rare cancers across Australia using a population-based cancer registry cohort of rare cancer cases diagnosed among Australians aged at least 15 years, 2007 to 2016. Rare cancers were defined using site- and histology-based categories from the European RARECARE study, as individual cancer types having crude annual incidence rates of less than 6/100 000. Incidence and survival patterns were modelled with generalised linear and Bayesian spatial Leroux models. Spatial heterogeneity was tested using the maximised excess events test. Rare cancers (n = 268 070) collectively comprised 22% of all invasive cancer diagnoses and accounted for 27% of all cancer-related deaths in Australia, 2007 to 2016 with an overall 5-year relative survival of around 53%. Males and those living in more remote or more disadvantaged areas had higher incidence but lower survival. There was substantial evidence for spatial variation in both incidence and survival for rare cancers between small geographical areas across Australia, with similar patterns so that those areas with higher incidence tended to have lower survival. Rare cancers are a substantial health burden in Australia. Our study has highlighted the need to better understand the higher burden of these cancers in rural and disadvantaged regions where the logistical challenges in their diagnosis, treatment and support are magnified.

Explainability of the COVID-19 epidemiological model with nonnegative tensor factorization.

The world is witnessing the devastating effects of the COVID-19 pandemic. Each country responded to contain the spread of the virus in the early stages through diverse response measures. Interpreting these responses and their patterns globally is essential to inform future responses to COVID-19 variants and future pandemics. A stochastic epidemiological model (SEM) is a well-established mathematical tool that helps to analyse the spread of infectious diseases through communities and the effects of various response measures. However, interpreting the outcome of these models is complex and often requires manual effort. In this paper, we propose a novel method to provide the explainability of an epidemiological model. We represent the output of SEM as a tensor model. We then apply nonnegative tensor factorization (NTF) to identify patterns of global response behaviours of countries and cluster the countries based on these patterns. We interpret the patterns and clusters to understand the global response behaviour of countries in the early stages of the pandemic. Our experimental results demonstrate the advantage of clustering using NTF and provide useful insights into the characteristics of country clusters.

Age- and Gender-Specific Differences in the Seasonal Distribution of Diabetes Mortality in Shandong, China: A Spatial Analysis.

Diabetes mortality in Shandong is higher than the national average in China. This study first explored diabetes mortality variation spatially at the county/district level among adults aged over 30 years in terms of age and gender, specifically by season. Daily diabetes mortality data were collected from 31 mortality surveillance points across Shandong Province in 2014. A geographic information system, spatial kriging interpolation and a spatial clustering method were used to examine the spatial patterns of diabetes mortality at the county/district level by season. Sensitivity analysis was conducted using diabetes mortality data from 10 mortality surveillance points from 2011 to 2020. As a result, the total diabetes mortality in eastern counties/districts was the highest (relative risk (RR) of cluster: 1.58, p = 0.00) across the whole province. For subgroups, women had higher mortality (16.84/100,000) than men (12.15/100,000), people aged over 75 years were the most vulnerable (93.91/100,000) and the highest-risk season was winter. However, the mortality differences between winter and summer were smaller in eastern and coastal regions than in other regions for all gender- and age-specific groups. The findings provide further evidence for early warning and precision preventative strategies for diabetes mortality in different regions of Shandong Province. Future research is required to identify the risk factors for diabetes and understand the differences in the social and environmental contexts.

Spatial statistical machine learning models to assess the relationship between development vulnerabilities and educational factors in children in Queensland, Australia.

BACKGROUND: The health and development of children during their first year of full time school is known to impact their social, emotional, and academic capabilities throughout and beyond early education. Physical health, motor development, social and emotional well-being, learning styles, language and communication, cognitive skills, and general knowledge are all considered to be important aspects of a child's health and development. It is important for many organisations and governmental agencies to continually improve their understanding of the factors which determine or influence development vulnerabilities among children. This article studies the relationships between development vulnerabilities and educational factors among children in Queensland, Australia. METHODS: Spatial statistical machine learning models are reviewed and compared in the context of a study of geographic variation in the association between development vulnerabilities and attendance at preschool among children in Queensland, Australia. A new spatial random forest (SRF) model is suggested that can explain more of the spatial variation in data than other approaches. RESULTS: In the case study, spatial models were shown to provide a better fit compared to models that ignored the spatial variation in the data. The SRF model was shown to be the only model which can explain all of the spatial variation in each of the development vulnerabilities considered in the case study. The spatial analysis revealed that the attendance at preschool factor has a strong influence on the physical health domain vulnerability and emotional maturity vulnerability among children in their first year of school. CONCLUSION: This study confirmed that it is important to take into account the spatial nature of data when fitting statistical machine learning models. A new spatial random forest model was introduced and was shown to explain more of the spatial variation and provide a better model fit in the case study of development vulnerabilities among children in Queensland. At small-area population level, increased attendance at preschool was strongly associated with reduced physical and emotional development vulnerabilities among children in their first year of school.