Detecting local risk factors for residual malaria in northern Ghana using Bayesian model averaging
Abstract Background There is a need for comprehensive evaluations of the underlying local factors that contribute to residual malaria in sub-Saharan Africa. However, it is difficult to compare the wide array of demographic, socio-economic, and environmental variables associated with malaria transmis...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2018-09-01
|
Series: | Malaria Journal |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s12936-018-2491-2 |
_version_ | 1818241928069644288 |
---|---|
author | Justin Millar Paul Psychas Benjamin Abuaku Collins Ahorlu Punam Amratia Kwadwo Koram Samuel Oppong Denis Valle |
author_facet | Justin Millar Paul Psychas Benjamin Abuaku Collins Ahorlu Punam Amratia Kwadwo Koram Samuel Oppong Denis Valle |
author_sort | Justin Millar |
collection | DOAJ |
description | Abstract Background There is a need for comprehensive evaluations of the underlying local factors that contribute to residual malaria in sub-Saharan Africa. However, it is difficult to compare the wide array of demographic, socio-economic, and environmental variables associated with malaria transmission using standard statistical approaches while accounting for seasonal differences and nonlinear relationships. This article uses a Bayesian model averaging (BMA) approach for identifying and comparing potential risk and protective factors associated with residual malaria. Results The relative influence of a comprehensive set of demographic, socio-economic, environmental, and malaria intervention variables on malaria prevalence were modelled using BMA for variable selection. Data were collected in Bunkpurugu-Yunyoo, a rural district in northeast Ghana that experiences holoendemic seasonal malaria transmission, over six biannual surveys from 2010 to 2013. A total of 10,022 children between the ages 6 to 59 months were used in the analysis. Multiple models were developed to identify important risk and protective factors, accounting for seasonal patterns and nonlinear relationships. These models revealed pronounced nonlinear associations between malaria risk and distance from the nearest urban centre and health facility. Furthermore, the association between malaria risk and age and some ethnic groups was significantly different in the rainy and dry seasons. BMA outperformed other commonly used regression approaches in out-of-sample predictive ability using a season-to-season validation approach. Conclusions This modelling framework offers an alternative approach to disease risk factor analysis that generates interpretable models, can reveal complex, nonlinear relationships, incorporates uncertainty in model selection, and produces accurate predictions. Certain modelling applications, such as designing targeted local interventions, require more sophisticated statistical methods which are capable of handling a wide range of relevant data while maintaining interpretability and predictive performance, and directly characterize uncertainty. To this end, BMA represents a valuable tool for constructing more informative models for understanding risk factors for malaria, as well as other vector-borne and environmentally mediated diseases. |
first_indexed | 2024-12-12T13:37:07Z |
format | Article |
id | doaj.art-9f9997c6875a4ee4bbd55eabe9b528d9 |
institution | Directory Open Access Journal |
issn | 1475-2875 |
language | English |
last_indexed | 2024-12-12T13:37:07Z |
publishDate | 2018-09-01 |
publisher | BMC |
record_format | Article |
series | Malaria Journal |
spelling | doaj.art-9f9997c6875a4ee4bbd55eabe9b528d92022-12-22T00:22:55ZengBMCMalaria Journal1475-28752018-09-0117111410.1186/s12936-018-2491-2Detecting local risk factors for residual malaria in northern Ghana using Bayesian model averagingJustin Millar0Paul Psychas1Benjamin Abuaku2Collins Ahorlu3Punam Amratia4Kwadwo Koram5Samuel Oppong6Denis Valle7Emerging Pathogens Institute, University of FloridaEmerging Pathogens Institute, University of FloridaNoguchi Memorial Institute for Medical Research, College of Health Sciences, University of GhanaNoguchi Memorial Institute for Medical Research, College of Health Sciences, University of GhanaEmerging Pathogens Institute, University of FloridaNoguchi Memorial Institute for Medical Research, College of Health Sciences, University of GhanaNational Malaria Control Programme, Public Health Division, Ghana Health ServiceEmerging Pathogens Institute, University of FloridaAbstract Background There is a need for comprehensive evaluations of the underlying local factors that contribute to residual malaria in sub-Saharan Africa. However, it is difficult to compare the wide array of demographic, socio-economic, and environmental variables associated with malaria transmission using standard statistical approaches while accounting for seasonal differences and nonlinear relationships. This article uses a Bayesian model averaging (BMA) approach for identifying and comparing potential risk and protective factors associated with residual malaria. Results The relative influence of a comprehensive set of demographic, socio-economic, environmental, and malaria intervention variables on malaria prevalence were modelled using BMA for variable selection. Data were collected in Bunkpurugu-Yunyoo, a rural district in northeast Ghana that experiences holoendemic seasonal malaria transmission, over six biannual surveys from 2010 to 2013. A total of 10,022 children between the ages 6 to 59 months were used in the analysis. Multiple models were developed to identify important risk and protective factors, accounting for seasonal patterns and nonlinear relationships. These models revealed pronounced nonlinear associations between malaria risk and distance from the nearest urban centre and health facility. Furthermore, the association between malaria risk and age and some ethnic groups was significantly different in the rainy and dry seasons. BMA outperformed other commonly used regression approaches in out-of-sample predictive ability using a season-to-season validation approach. Conclusions This modelling framework offers an alternative approach to disease risk factor analysis that generates interpretable models, can reveal complex, nonlinear relationships, incorporates uncertainty in model selection, and produces accurate predictions. Certain modelling applications, such as designing targeted local interventions, require more sophisticated statistical methods which are capable of handling a wide range of relevant data while maintaining interpretability and predictive performance, and directly characterize uncertainty. To this end, BMA represents a valuable tool for constructing more informative models for understanding risk factors for malaria, as well as other vector-borne and environmentally mediated diseases.http://link.springer.com/article/10.1186/s12936-018-2491-2Risk factorsBayesian model averagingNonlinear patternsStatistical methods |
spellingShingle | Justin Millar Paul Psychas Benjamin Abuaku Collins Ahorlu Punam Amratia Kwadwo Koram Samuel Oppong Denis Valle Detecting local risk factors for residual malaria in northern Ghana using Bayesian model averaging Malaria Journal Risk factors Bayesian model averaging Nonlinear patterns Statistical methods |
title | Detecting local risk factors for residual malaria in northern Ghana using Bayesian model averaging |
title_full | Detecting local risk factors for residual malaria in northern Ghana using Bayesian model averaging |
title_fullStr | Detecting local risk factors for residual malaria in northern Ghana using Bayesian model averaging |
title_full_unstemmed | Detecting local risk factors for residual malaria in northern Ghana using Bayesian model averaging |
title_short | Detecting local risk factors for residual malaria in northern Ghana using Bayesian model averaging |
title_sort | detecting local risk factors for residual malaria in northern ghana using bayesian model averaging |
topic | Risk factors Bayesian model averaging Nonlinear patterns Statistical methods |
url | http://link.springer.com/article/10.1186/s12936-018-2491-2 |
work_keys_str_mv | AT justinmillar detectinglocalriskfactorsforresidualmalariainnorthernghanausingbayesianmodelaveraging AT paulpsychas detectinglocalriskfactorsforresidualmalariainnorthernghanausingbayesianmodelaveraging AT benjaminabuaku detectinglocalriskfactorsforresidualmalariainnorthernghanausingbayesianmodelaveraging AT collinsahorlu detectinglocalriskfactorsforresidualmalariainnorthernghanausingbayesianmodelaveraging AT punamamratia detectinglocalriskfactorsforresidualmalariainnorthernghanausingbayesianmodelaveraging AT kwadwokoram detectinglocalriskfactorsforresidualmalariainnorthernghanausingbayesianmodelaveraging AT samueloppong detectinglocalriskfactorsforresidualmalariainnorthernghanausingbayesianmodelaveraging AT denisvalle detectinglocalriskfactorsforresidualmalariainnorthernghanausingbayesianmodelaveraging |