Supporting elimination of lymphatic filariasis in Samoa by predicting locations of residual infection using machine learning and geostatistics

Abstract The global elimination of lymphatic filariasis (LF) is a major focus of the World Health Organization. One key challenge is locating residual infections that can perpetuate the transmission cycle. We show how a targeted sampling strategy using predictions from a geospatial model, combining...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Helen J. Mayfield, Hugh Sturrock, Benjamin F. Arnold, Ricardo Andrade-Pacheco, Therese Kearns, Patricia Graves, Take Naseri, Robert Thomsen, Katherine Gass, Colleen L. Lau
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2020
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/cb04387885e54caa9663c31ec57feff6
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:cb04387885e54caa9663c31ec57feff6
record_format	dspace
spelling	oai:doaj.org-article:cb04387885e54caa9663c31ec57feff62021-12-02T15:09:32ZSupporting elimination of lymphatic filariasis in Samoa by predicting locations of residual infection using machine learning and geostatistics10.1038/s41598-020-77519-82045-2322https://doaj.org/article/cb04387885e54caa9663c31ec57feff62020-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-77519-8https://doaj.org/toc/2045-2322Abstract The global elimination of lymphatic filariasis (LF) is a major focus of the World Health Organization. One key challenge is locating residual infections that can perpetuate the transmission cycle. We show how a targeted sampling strategy using predictions from a geospatial model, combining random forests and geostatistics, can improve the sampling efficiency for identifying locations with high infection prevalence. Predictions were made based on the household locations of infected persons identified from previous surveys, and environmental variables relevant to mosquito density. Results show that targeting sampling using model predictions would have allowed 52% of infections to be identified by sampling just 17.7% of households. The odds ratio for identifying an infected individual in a household at a predicted high risk compared to a predicted low risk location was 10.2 (95% CI 4.2–22.8). This study provides evidence that a ‘one size fits all’ approach is unlikely to yield optimal results when making programmatic decisions based on model predictions. Instead, model assumptions and definitions should be tailored to each situation based on the objective of the surveillance program. When predictions are used in the context of the program objectives, they can result in a dramatic improvement in the efficiency of locating infected individuals.Helen J. MayfieldHugh SturrockBenjamin F. ArnoldRicardo Andrade-PachecoTherese KearnsPatricia GravesTake NaseriRobert ThomsenKatherine GassColleen L. LauNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 10, Iss 1, Pp 1-11 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Helen J. Mayfield Hugh Sturrock Benjamin F. Arnold Ricardo Andrade-Pacheco Therese Kearns Patricia Graves Take Naseri Robert Thomsen Katherine Gass Colleen L. Lau Supporting elimination of lymphatic filariasis in Samoa by predicting locations of residual infection using machine learning and geostatistics
description	Abstract The global elimination of lymphatic filariasis (LF) is a major focus of the World Health Organization. One key challenge is locating residual infections that can perpetuate the transmission cycle. We show how a targeted sampling strategy using predictions from a geospatial model, combining random forests and geostatistics, can improve the sampling efficiency for identifying locations with high infection prevalence. Predictions were made based on the household locations of infected persons identified from previous surveys, and environmental variables relevant to mosquito density. Results show that targeting sampling using model predictions would have allowed 52% of infections to be identified by sampling just 17.7% of households. The odds ratio for identifying an infected individual in a household at a predicted high risk compared to a predicted low risk location was 10.2 (95% CI 4.2–22.8). This study provides evidence that a ‘one size fits all’ approach is unlikely to yield optimal results when making programmatic decisions based on model predictions. Instead, model assumptions and definitions should be tailored to each situation based on the objective of the surveillance program. When predictions are used in the context of the program objectives, they can result in a dramatic improvement in the efficiency of locating infected individuals.
format	article
author	Helen J. Mayfield Hugh Sturrock Benjamin F. Arnold Ricardo Andrade-Pacheco Therese Kearns Patricia Graves Take Naseri Robert Thomsen Katherine Gass Colleen L. Lau
author_facet	Helen J. Mayfield Hugh Sturrock Benjamin F. Arnold Ricardo Andrade-Pacheco Therese Kearns Patricia Graves Take Naseri Robert Thomsen Katherine Gass Colleen L. Lau
author_sort	Helen J. Mayfield
title	Supporting elimination of lymphatic filariasis in Samoa by predicting locations of residual infection using machine learning and geostatistics
title_short	Supporting elimination of lymphatic filariasis in Samoa by predicting locations of residual infection using machine learning and geostatistics
title_full	Supporting elimination of lymphatic filariasis in Samoa by predicting locations of residual infection using machine learning and geostatistics
title_fullStr	Supporting elimination of lymphatic filariasis in Samoa by predicting locations of residual infection using machine learning and geostatistics
title_full_unstemmed	Supporting elimination of lymphatic filariasis in Samoa by predicting locations of residual infection using machine learning and geostatistics
title_sort	supporting elimination of lymphatic filariasis in samoa by predicting locations of residual infection using machine learning and geostatistics
publisher	Nature Portfolio
publishDate	2020
url	https://doaj.org/article/cb04387885e54caa9663c31ec57feff6
work_keys_str_mv	AT helenjmayfield supportingeliminationoflymphaticfilariasisinsamoabypredictinglocationsofresidualinfectionusingmachinelearningandgeostatistics AT hughsturrock supportingeliminationoflymphaticfilariasisinsamoabypredictinglocationsofresidualinfectionusingmachinelearningandgeostatistics AT benjaminfarnold supportingeliminationoflymphaticfilariasisinsamoabypredictinglocationsofresidualinfectionusingmachinelearningandgeostatistics AT ricardoandradepacheco supportingeliminationoflymphaticfilariasisinsamoabypredictinglocationsofresidualinfectionusingmachinelearningandgeostatistics AT theresekearns supportingeliminationoflymphaticfilariasisinsamoabypredictinglocationsofresidualinfectionusingmachinelearningandgeostatistics AT patriciagraves supportingeliminationoflymphaticfilariasisinsamoabypredictinglocationsofresidualinfectionusingmachinelearningandgeostatistics AT takenaseri supportingeliminationoflymphaticfilariasisinsamoabypredictinglocationsofresidualinfectionusingmachinelearningandgeostatistics AT robertthomsen supportingeliminationoflymphaticfilariasisinsamoabypredictinglocationsofresidualinfectionusingmachinelearningandgeostatistics AT katherinegass supportingeliminationoflymphaticfilariasisinsamoabypredictinglocationsofresidualinfectionusingmachinelearningandgeostatistics AT colleenllau supportingeliminationoflymphaticfilariasisinsamoabypredictinglocationsofresidualinfectionusingmachinelearningandgeostatistics
_version_	1718387839698206720

Supporting elimination of lymphatic filariasis in Samoa by predicting locations of residual infection using machine learning and geostatistics

Ejemplares similares