Optimizing the maximum reported cluster size in the spatial scan statistic for survival data

Lee, Sujee; Moon, Jisu; Jung, Inkyung

doi:10.1186/s12942-021-00286-w

Cited by 7 publications

(9 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The spatial scan statistic is a useful and widely used tool for detecting spatial or space–time clusters in disease surveillance. The software SaTScan, available for free, enhances this method’s ease-of-access for researchers [ 45 ]. We used SaTScan to accurately locate the spatial clustering areas of diabetes and to explore if diabetes had clustering characteristics in space and time.…”

Section: Discussionmentioning

confidence: 99%

Spatiotemporal Analysis and Risk Assessment Model Research of Diabetes among People over 45 Years Old in China

Wang

Dong

Yang

2022

IJERPH

View full text Add to dashboard Cite

Diabetes, which is a chronic disease with a high prevalence in people over 45 years old in China, is a public health issue of global concern. In order to explore the spatiotemporal patterns of diabetes among people over 45 years old in China, to find out diabetes risk factors, and to assess its risk, we used spatial autocorrelation, spatiotemporal cluster analysis, binary logistic regression, and a random forest model in this study. The results of the spatial autocorrelation analysis and the spatiotemporal clustering analysis showed that diabetes patients are mainly clustered near the Beijing–Tianjin–Hebei region, and that the prevalence of diabetes clusters is waning. Age, hypertension, dyslipidemia, and smoking history were all diabetes risk factors (p < 0.05), but the spatial heterogeneity of these factors was weak. Compared with the binary logistic regression model, the random forest model showed better accuracy in assessing diabetes risk. According to the assessment risk map generated by the random forest model, the northeast region and the Beijing–Tianjin–Hebei region are high-risk areas for diabetes.

show abstract

Section: Discussionmentioning

confidence: 99%

Spatiotemporal Analysis and Risk Assessment Model Research of Diabetes among People over 45 Years Old in China

Wang

Dong

Yang

2022

IJERPH

View full text Add to dashboard Cite

show abstract

“…If the window size is too large, a high false positive rate may occur. Similarly, a high false negative rate may occur if the window size is too small [26] .Therefore, this study determines the window radius by using the Gini index function to compare the size of the Gini index under different scan circle radii [25,27,28] . The scan radius corresponding to the largest Gini index value is selected as the optimum scan window radius, where the cluster aggregation intensity is relatively stable and the clustering is more obvious, and the overlapping phenomenon of the aggregation area can be effectively avoided.…”

Section: Space-time Scanmentioning

confidence: 99%

The state of the incidence and mortality of hepatitis B in China from 2004 to 2021: A spatiotemporal characteristics and trend analysis

Zhang

Cai

et al. 2023

Preprint

View full text Add to dashboard Cite

Objective: To describe the spatiotemporal characteristics and trend of incidence and mortality of hepatitis B in China from 2004 to 2021 and to identify its possible hotspots and potential high-risk areas for the disease. Methods: Time trends in hepatitis B incidence and mortality were analyzed using Joinpoint regression models, and annual percentage change (APC) and average annual percentage change (AAPC) were calculated stratified by age. The spatial autocorrelation analysis of GeoDa and the space-time scanning analysis of SaTScan software were used to identify potential changes and regional differences in the spatial and temporal distribution of hepatitis B humans in China during the study period. Results: From 2004 to 2021, the number of hepatitis B cases in China increased from 916,396 in 2004 to 976,233 in 2021 (AAPC=0.31%, P=0.665), and the number of deaths decreased from 783 in 2004 to 413 in 2021 (AAPC=-3.23%, P =0.076). There was an increasing trend of standardized incidence of hepatitis B in the age group over 30 years. The High-High cluster areas of incidence rate of hepatitis B in China from 2004 to 2012 were mainly concentrated in the northwest,and in the southeast from 2017 to 2021 were concentrated, while the High-Low cluster areas of mortality rate of hepatitis B were mainly concentrated in Beijing and Shanghai from 2004 to 2019.The results of space–time cluster analysis for incidence rate of hepatitis B in China from 2004 to 2018 included one primary clustering area and two secondary clustering areas. The primary clustering area was located in the west of China, including Tibet, Qinghai, Xinjiang and Gansu, and the high-risk time frame was from January 2006 to December 2012 (RR = 2.78, LLR = 300786.49, P < 0.001). The results of space–time cluster analysis for mortality rate of hepatitis B in China from 2004 to 2018 included one primary clustering area and two secondary clustering areas. The primary clustering area was located in Beijing of China, and the high-risk time frame was from January 2007 to December 2013 (RR = 12.14, LLR = 1120.197907, P < 0.001). Conclusion: The overall trend incidence and mortality of hepatitis B in China has decreased over the 18-year period, but the number of hepatitis B incidences is on the rise. The spatial distribution of hepatitis B incidence rate in each region of the country had spatial positive correlation.Hepatitis B incidence and mortality rates vary widely in China with different epidemiologic trends affecting different locations and revealing different spatial changing patterns.

show abstract

“…The maximum scanning window size (MSWS) was set to use a time aggregation of 147 days for commercial permits, 1406 days for demolition permits, 1555 days for residential permits, and 1248 days for roof repair permits, and scanned for both high and low rates. As noted by Han et al (2016) and expanded upon by Lee et al (2021), the default maximum spatial cluster size (MSCS) may lead to overly large clusters and obscure smaller significant ones. However, the correction for this, the Gini index, can be selected only when employing a Bernoulli or Poisson model.…”

Section: Spatiotemporal Analysis Using Satscan™mentioning

confidence: 99%

Space-Time Clustering with the Space-Time Permutation Model in SaTScan™ Applied to Building Permit Data Following the 2011 Joplin, Missouri Tornado

Stimers

Lenagala

Haddock

et al. 2022

Int J Disaster Risk Sci

View full text Add to dashboard Cite

Community recovery from a major natural hazard-related disaster can be a long process, and rebuilding likely does not occur uniformly across space and time. Spatial and temporal clustering may be evident in certain data types that can be used to frame the progress of recovery following a disaster. Publically available building permit data from the city of Joplin, Missouri, were gathered for four permit types, including residential, commercial, roof repair, and demolition. The data were used to (1) compare the observed versus expected frequency (chi-square) of permit issuance before and after the EF5 2011 tornado; (2), determine if significant space-time clusters of permits existed using the SaTScan™ cluster analysis program (version 9.7); and (3) fit any emergent cluster data to the widely-cited Kates 10-year recovery model. All permit types showed significant increases in issuance for at least 5 years following the event, and one (residential) showed significance for nine of the 10 years. The cluster analysis revealed a total of 16 significant clusters across the 2011 damage area. The results of fitting the significant cluster data to the Kates model revealed that those data closely followed the model, with some variation in the residential permit data path.

show abstract

Optimizing the maximum reported cluster size in the spatial scan statistic for survival data

Cited by 7 publications

References 26 publications

Spatiotemporal Analysis and Risk Assessment Model Research of Diabetes among People over 45 Years Old in China

Spatiotemporal Analysis and Risk Assessment Model Research of Diabetes among People over 45 Years Old in China

The state of the incidence and mortality of hepatitis B in China from 2004 to 2021: A spatiotemporal characteristics and trend analysis

Space-Time Clustering with the Space-Time Permutation Model in SaTScan™ Applied to Building Permit Data Following the 2011 Joplin, Missouri Tornado

Contact Info

Product

Resources

About