DClusterm: Model-Based Detection of Disease Clusters

Virgilio Gomez-Rubio, Paula Moraga, John Molitor, Barry Rowlingson

Research output: Contribution to journalArticle

Abstract

The detection of regions with unusually high risk plays an important role in disease mapping and the analysis of public health data. In particular, the detection of groups of areas (i.e., clusters) where the risk is significantly high is often conducted by public health authorities. Many methods have been proposed for the detection of these disease clusters, most of them based on moving windows, such as Kulldorff's spatial scan statistic. Here we describe a model-based approach for the detection of disease clusters implemented in the DClusterm package. Our model-based approach is based on representing a large number of possible clusters by dummy variables and then fitting many generalized linear models to the data where these covariates are included one at a time. Cluster detection is done by performing a variable or model selection among all fitted models using different criteria. Because of our model-based approach, cluster detection can be performed using different types of likelihoods and latent effects. We cover the detection of spatial and spatiotemporal clusters, as well as how to account for covariates, zero-inflated datasets and overdispersion in the data.
Original languageEnglish
Number of pages26
JournalJournal of Statistical Software
Volume90
Issue number14
DOIs
Publication statusPublished - 22 Aug 2019

Cite this

DClusterm: Model-Based Detection of Disease Clusters. / Gomez-Rubio, Virgilio; Moraga, Paula; Molitor, John; Rowlingson, Barry.

In: Journal of Statistical Software, Vol. 90, No. 14, 22.08.2019.

Research output: Contribution to journalArticle

Gomez-Rubio, Virgilio ; Moraga, Paula ; Molitor, John ; Rowlingson, Barry. / DClusterm: Model-Based Detection of Disease Clusters. In: Journal of Statistical Software. 2019 ; Vol. 90, No. 14.
@article{502294842bb84b48a28fb6aa72a5afe9,
title = "DClusterm: Model-Based Detection of Disease Clusters",
abstract = "The detection of regions with unusually high risk plays an important role in disease mapping and the analysis of public health data. In particular, the detection of groups of areas (i.e., clusters) where the risk is significantly high is often conducted by public health authorities. Many methods have been proposed for the detection of these disease clusters, most of them based on moving windows, such as Kulldorff's spatial scan statistic. Here we describe a model-based approach for the detection of disease clusters implemented in the DClusterm package. Our model-based approach is based on representing a large number of possible clusters by dummy variables and then fitting many generalized linear models to the data where these covariates are included one at a time. Cluster detection is done by performing a variable or model selection among all fitted models using different criteria. Because of our model-based approach, cluster detection can be performed using different types of likelihoods and latent effects. We cover the detection of spatial and spatiotemporal clusters, as well as how to account for covariates, zero-inflated datasets and overdispersion in the data.",
author = "Virgilio Gomez-Rubio and Paula Moraga and John Molitor and Barry Rowlingson",
year = "2019",
month = "8",
day = "22",
doi = "10.18637/jss.v090.i14",
language = "English",
volume = "90",
journal = "Journal of Statistical Software",
issn = "1548-7660",
publisher = "University of California at Los Angeles",
number = "14",

}

TY - JOUR

T1 - DClusterm: Model-Based Detection of Disease Clusters

AU - Gomez-Rubio, Virgilio

AU - Moraga, Paula

AU - Molitor, John

AU - Rowlingson, Barry

PY - 2019/8/22

Y1 - 2019/8/22

N2 - The detection of regions with unusually high risk plays an important role in disease mapping and the analysis of public health data. In particular, the detection of groups of areas (i.e., clusters) where the risk is significantly high is often conducted by public health authorities. Many methods have been proposed for the detection of these disease clusters, most of them based on moving windows, such as Kulldorff's spatial scan statistic. Here we describe a model-based approach for the detection of disease clusters implemented in the DClusterm package. Our model-based approach is based on representing a large number of possible clusters by dummy variables and then fitting many generalized linear models to the data where these covariates are included one at a time. Cluster detection is done by performing a variable or model selection among all fitted models using different criteria. Because of our model-based approach, cluster detection can be performed using different types of likelihoods and latent effects. We cover the detection of spatial and spatiotemporal clusters, as well as how to account for covariates, zero-inflated datasets and overdispersion in the data.

AB - The detection of regions with unusually high risk plays an important role in disease mapping and the analysis of public health data. In particular, the detection of groups of areas (i.e., clusters) where the risk is significantly high is often conducted by public health authorities. Many methods have been proposed for the detection of these disease clusters, most of them based on moving windows, such as Kulldorff's spatial scan statistic. Here we describe a model-based approach for the detection of disease clusters implemented in the DClusterm package. Our model-based approach is based on representing a large number of possible clusters by dummy variables and then fitting many generalized linear models to the data where these covariates are included one at a time. Cluster detection is done by performing a variable or model selection among all fitted models using different criteria. Because of our model-based approach, cluster detection can be performed using different types of likelihoods and latent effects. We cover the detection of spatial and spatiotemporal clusters, as well as how to account for covariates, zero-inflated datasets and overdispersion in the data.

U2 - 10.18637/jss.v090.i14

DO - 10.18637/jss.v090.i14

M3 - Article

VL - 90

JO - Journal of Statistical Software

JF - Journal of Statistical Software

SN - 1548-7660

IS - 14

ER -