Prefiltered component-based greedy (PreCoG) scan method

The spatial distribution of disease cases can provide important insights into disease spread and its potential risk factors. Identifying disease clusters correctly can help us discover new risk factors and inform interventions to control and prevent the spread of disease as quickly as possible. In this study, we propose a novel scan method, the Prefiltered Component-based Greedy (PreCoG) scan method, which efficiently and accurately detects irregularly shaped clusters using a prefiltered component-based algorithm. The PreCoG scan method's flexibility allows it to perform well in detecting both regularly and irregularly-shaped clusters. Additionally, it is fast to apply while providing high power, sensitivity, and positive predictive value for the detected clusters compared to other scan methods. To confirm the effectiveness of the PreCoG method, we compare its performance to many other scan methods. Additionally, we have implemented this method in the smerc R package to make it publicly available to other researchers. Our proposed PreCoG scan method presents a unique and innovative process for detecting disease clusters and can improve the accuracy of disease surveillance systems.

Performance of a negative binomial-GLM in spatial scan statistic: a case study of low-birth weights in Pakistan

Spatial cluster analyses of health events are useful for enabling targeted interventions. Spatial scan statistic is the stateof- the-art method for this kind of analysis and the Poisson Generalized Linear Model (GLM) approach to the spatial scan statistic can be used for count data for spatial cluster detection with covariate adjustment. However, its use for modelling is limited due to data over-dispersion. A Generalized Linear Mixed Model (GLMM) has recently been proposed for modelling this kind of over-dispersion by incorporating random effects to model area-specific intrinsic variation not explained by other covariates in the model. However, these random effects may exhibit a geographical correlation, which may lead to a potential spatial cluster being undetected. To handle the over-dispersion in the count data, this study aimed to evaluate the performance of a negative binomial- GLM in spatial scan statistic on real-world data of low birth weights in Khyber-Pakhtunkhwa Province, Pakistan, 2019. The results were compared with the Poisson-GLM and GLMM, showing that the negative binomial-GLM is an ideal choice for spatial scan statistic in the presence of over-dispersed data. With a covariate (maternal anaemia) adjustment, the negative binomial-GLMbased spatial scan statistic detected one significant cluster covering Dir lower district. Without the covariate adjustment, it detected two clusters, each covering one district. The district of Peshawar was seen as the most likely cluster and Battagram as the secondary cluster. However, none of the clusters were detected by GLMM spatial scan statistic, which might be due to the spatial correlation of the random effects in GLMM.

A Shared-Frailty Spatial Scan Statistic Model for Time-to-Event Data

Spatial scan statistics are well-known methods widely used to detect spatial clusters of events. Furthermore, several spatial scan statistics models have been applied to the spatial analysis of time-to-event data. However, these models do not take account of potential correlations between the observations of individuals within the same spatial unit or potential spatial dependence between spatial units. To overcome this problem, we have developed a scan statistic based on a Cox model with shared frailty and that takes account of the spatial dependence between spatial units. In simulation studies, we found that (i) conventional models of spatial scan statistics for time-to-event data fail to maintain the type I error in the presence of a correlation between the observations of individuals within the same spatial unit and (ii) our model performed well in the presence of such correlation and spatial dependence. We have applied our method to epidemiological data and the detection of spatial clusters of mortality in patients with end-stage renal disease in northern France.

Assessing and attenuating the impact of selection bias on spatial cluster detection studies

Spatial cluster analyses are commonly used in epidemiologic studies of case-control data to detect whether certain areas in a study region have an excess of disease risk. Case-control studies are susceptible to potential biases including selection bias, which can result from non-participation of eligible subjects in the study. However, there has been no systematic evaluation of the effects of non-participation on the findings of spatial cluster analyses. In this paper, we perform a simulation study assessing the effect of non-participation on spatial cluster analysis using the local spatial scan statistic under a variety of scenarios that vary the location and rates of study non-participation and the presence and intensity of a zone of elevated risk for disease for simulated case-control studies. We find that geographic areas of lower participation among controls than cases can greatly inflate false-positive rates for identification of artificial spatial clusters. Additionally, we find that even modest non-participation outside of a true zone of elevated risk can decrease spatial power to identify the true zone. We propose a spatial algorithm to correct for potentially spatially structured non-participation that compares the spatial distributions of the observed sample and underlying population. We demonstrate its ability to markedly decrease false positive rates in the absence of elevated risk and resist decreasing spatial sensitivity to detect true zones of elevated risk. We apply our method to a case-control study of non-Hodgkin lymphoma. Our findings suggest that greater attention should be paid to the potential effects of non-participation in spatial cluster studies.

A simulation study for geographic cluster detection analysis on population-based health survey data using spatial scan statistics

Background

In public health and epidemiology, spatial scan statistics can be used to identify spatial cluster patterns of health-related outcomes from population-based health survey data. Although it is appropriate to consider the complex sample design and sampling weight when analyzing complex sample survey data, the observed survey responses without these considerations are often used in many studies related to spatial cluster detection.

Methods

We conducted a simulation study to investigate which data type from complex survey data is more suitable for use by comparing the spatial cluster detection results of three approaches: (1) individual-level data, (2) weighted individual-level data, and (3) aggregated data.

Results

The results of the spatial cluster detection varied depending on the data type. To compare the performance of spatial cluster detection, sensitivity and positive predictive value (PPV) were evaluated over 100 iterations. The average sensitivity was high for all three approaches, but the average PPV was higher when using aggregated data than when using individual-level data with or without sampling weights.

Conclusions

Through the simulation study, we found that use of aggregate-level data is more appropriate than other types of data, when searching for spatial clusters using spatial scan statistics on population-based health survey data.

Detecting Spatial Clusters of Coronavirus Infection Across London During the Second Wave

The identification of seriously infected areas across a city, region, or country can inform policies and assist in resources allocation. Concentration of coronavirus infection can be identified through applying cluster detection methods to coronavirus cases over space. To enhance the identification of seriously infected areas by relevant studies, this study focused on coronavirus infection by small area across a city during the second wave. Specifically, we firstly explored spatiotemporal patterns of new coronavirus cases. Subsequently, we detected spatial clusters of new coronavirus cases by small area. Empirically, we used the London-wide small-area coronavirus infection data aggregately collected. Methodologically, we applied a fast Bayesian model-based detection method newly developed to new coronavirus cases by small area. As empirical evidence on the association of socioeconomic factors and coronavirus spread have been found, spatial patterns of coronavirus infection are arguably associated with socioeconomic and built environmental characteristics. Therefore, we further investigated the socioeconomic and built environmental characteristics of the clusters detected. As a result, the most significant clusters of new cases during the second wave are likely to occur around the airports. And, lower income or lower healthcare accessibility is associated with concentration of coronavirus infection across London.

Simultaneous spatial smoothing and outlier detection using penalized regression, with application to childhood obesity surveillance from electronic health records

Electronic health records (EHRs) have become a platform for data-driven granular-level surveillance in recent years. In this paper, we make use of EHRs for early prevention of childhood obesity. The proposed method simultaneously provides smooth disease mapping and outlier information for obesity prevalence that are useful for raising public awareness and facilitating targeted intervention. More precisely, we consider a penalized multilevel generalized linear model. We decompose regional contribution into smooth and sparse signals, which are automatically identified by a combination of fusion and sparse penalties imposed on the likelihood function. In addition, we weigh the proposed likelihood to account for the missingness and potential nonrepresentativeness arising from the EHR data. We develop a novel alternating minimization algorithm, which is computationally efficient, easy to implement, and guarantees convergence. Simulation studies demonstrate superior performance of the proposed method. Finally, we apply our method to the University of Wisconsin Population Health Information Exchange database.

Clustered spatio-temporal varying coefficient regression model

In regression analysis for spatio-temporal data, identifying clusters of spatial units over time in a regression coefficient could provide insight into the unique relationship between a response and covariates in certain subdomains of space and time windows relative to the background in other parts of the spatial domain and the time period of interest. In this article, we propose a varying coefficient regression method for spatial data repeatedly sampled over time, with heterogeneity in regression coefficients across both space and over time. In particular, we extend a varying coefficient regression model for spatial-only data to spatio-temporal data with flexible temporal patterns. We consider the detection of a potential cylindrical cluster of regression coefficients based on testing whether the regression coefficient is the same or not over the entire spatial domain for each time point. For multiple clusters, we develop a sequential identification approach. We assess the power and identification of known clusters via a simulation study. Our proposed methodology is illustrated by the analysis of a cancer mortality dataset in the Southeast of the U.S.

Discovering Spatio-Temporal Clusters of Road Collisions Using the Method of Fast Bayesian Model-Based Cluster Detection

Public availability of geo-coded or geo-referenced road collisions (crashes) makes it possible to perform geovisualisation and spatio-temporal analysis of road collisions across a city. This study aims to detect spatio-temporal clusters of road collisions across Greater London between 2010 and 2014. We implemented a fast Bayesian model-based cluster detection method with no covariates and after adjusting for potential covariates respectively. As empirical evidence on the association of street connectivity measures and the occurrence of road collisions had been found, we selected street connectivity measures as the potential covariates in our cluster detection. Results of the most significant cluster and the second most significant cluster during five consecutive years are located around the central areas. Moreover, after adjusting the covariates, the most significant cluster moves from the central areas of London to its peripheral areas, while the second most significant cluster remains unchanged. Additionally, one potential covariate used in this study, length-based road density, exhibits a positive association with the number of road collisions; meanwhile count-based intersection density displays a negative association. Although the covariates (i.e., road density and intersection density) exhibit potential impact on the clusters of road collisions, they are unlikely to contribute to the majority of clusters. Furthermore, the method of fast Bayesian model-based cluster detection is developed to discover spatio-temporal clusters of serious injury collisions. Most of the areas at risk of serious injury collisions overlay those at risk of road collisions. Although not being identified as areas at risk of road collisions, some districts, e.g., City of London, are regarded as areas at risk of serious injury collisions.

Syndromic surveillance using ambulance transfer data in Tokyo, Japan

Bioterrorism attacks become more probable when important high-profile international or political events are held, such as G7 summit meetings or mass gathering events including Olympic and Paralympic games and FIFA World Cup tournaments. Outbreaks of infectious disease and widespread incidents of food poisoning are also public health concerns at such times. In Japan, the Tokyo Metropolitan Government operates Ambulance Transfer Syndromic Surveillance (ATSS), which can help monitor such incidents. The present study presents and assesses the ATSS framework. During the study period of October 2017 through November 2018, we monitored 33 areas for symptoms of 9 categories: vomiting/nausea, dizziness, palpitation, unconsciousness, breathing disorder, fever, spasm/paralysis, collapse/weakness, and bloody emesis/nasal hemorrhage. Among all symptoms, we found 9929 low-level aberrations, 2537 medium-level aberrations, and 577 high-level aberrations, with respective frequencies of 9.2%, 2.3%, and 0.5%. Of those, Tokyo Metropolitan Institute of Public Health reported the information to Tokyo Metropolitan Government 28 times during the period. Of the 28 identified clusters, Tokyo Metropolitan Government judged the necessity for investigating 7. All of those were investigated at hospitals by the jurisdictional public health center. Because ATSS covers almost the entire Tokyo metropolitan area, with about 13.8 million residents, it is definitely the largest syndromic surveillance in the world.

Multiple-cluster detection test for purely temporal disease clustering: Integration of scan statistics and generalized linear models

The spatial scan statistic is commonly used to detect spatial and/or temporal disease clusters in epidemiological studies. Although multiple clusters in the study space can be thus identified, current theoretical developments are mainly based on detecting a ‘single’ cluster. The standard scan statistic procedure enables the detection of multiple clusters, recursively identifying additional ‘secondary’ clusters. However, their p-values are calculated one at a time, as if each cluster is a primary one. Therefore, a new procedure that can accurately evaluate multiple clusters as a whole is needed. The present study focuses on purely temporal cases and then proposes a new test procedure that evaluates the p-value for multiple clusters, combining generalized linear models with an information criterion approach. This framework encompasses the conventional, currently widely used detection procedure as a special case. An application study adopting the new framework is presented, analysing the Japanese daily incidence of out-of-hospital cardiac arrest cases. The analysis reveals that the number of the incident increases around New Year’s Day in Japan. Further, simulation studies undertaken confirm that the proposed method possesses a consistency property that tends to select the correct number of clusters when the truth is known.

p-value approximations for spatial scan statistics using extreme value distributions

Spatial scan statistics are widely applied to identify spatial clusters in geographic disease surveillance. To evaluate the statistical significance of detected clusters, Monte Carlo hypothesis testing is often used because the null distribution of spatial scan statistics is not known. A drawback of the method is that we have to increase the number of replications to obtain accurate p-values. Gumbel-based p-value approximations for spatial scan statistics have recently been proposed and evaluated for Poisson and Bernoulli models. In this study, we examine the use of a generalized extreme value distribution to approximate the null distribution of spatial scan statistics as well as the Gumbel distribution. Through simulation, p-value approximations using extreme value distributions for spatial scan statistics are assessed for multinomial and ordinal models in addition to Poisson and Bernoulli models.

Spatial scan statistics with overdispersion

The spatial scan statistic has been widely used in spatial disease surveillance and spatial cluster detection for more than a decade. However, overdispersion often presents in real-world data, causing not only violation of the Poisson assumption but also excessive type I errors or false alarms. In order to account for overdispersion, we extend the Poisson-based spatial scan test to a quasi-Poisson-based test. The simulation shows that the proposed method can substantially reduce type I error probabilities in the presence of overdispersion. In a case study of infant mortality in Jiangxi, China, both tests detect a cluster; however, a secondary cluster is identified by only the Poisson-based test. It is recommended that a cluster detected by the Poisson-based scan test should be interpreted with caution when it is not confirmed by the quasi-Poisson-based test.

A spatial scan statistic for multinomial data

As a geographical cluster detection analysis tool, the spatial scan statistic has been developed for different types of data such as Bernoulli, Poisson, ordinal, exponential and normal. Another interesting data type is multinomial. For example, one may want to find clusters where the disease-type distribution is statistically significantly different from the rest of the study region when there are different types of disease. In this paper, we propose a spatial scan statistic for such data, which is useful for geographical cluster detection analysis for categorical data without any intrinsic order information. The proposed method is applied to meningitis data consisting of five different disease categories to identify areas with distinct disease-type patterns in two counties in the U.K. The performance of the method is evaluated through a simulation study.

Statistical methods for the geographical analysis of rare diseases

In this chapter we provide a summary of different methods for the detection of disease clusters. First of all, we give a summary of methods for computing estimates of the relative risk. These estimates provide smoothed values of the relative risks that can account for its spatial variation. Some methods for assessing spatial autocorrelation and general clustering are also discussed to test for significant spatial variation of the risk. In order to find the actual location of the clusters, scan methods are introduced. The spatial scan statistic is discussed as well as its extension by means of Generalised Linear Models that allows for the inclusion of covariates and cluster effects. In this context, zero-inflated models are introduced to account for the high number of zeros that appear when studying rare diseases. Finally, two applications of these methods are shown using data of Systemic Lupus Erythematosus in Spain and brain cancer in Navarre (Spain).