Empirical mode decomposition and k-nearest embedding vectors for timely analyses of antibiotic resistance trends.

<h4>Background</h4>Antibiotic resistance is a major worldwide public health concern. In clinical settings, timely antibiotic resistance information is key for care providers as it allows appropriate targeted treatment or improved empirical treatment when the specific results of the patie...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Douglas Teodoro, Christian Lovis
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2013
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/fac3f268582248e684b27fe6ce42e444
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:fac3f268582248e684b27fe6ce42e444
record_format	dspace
spelling	oai:doaj.org-article:fac3f268582248e684b27fe6ce42e4442021-11-18T07:47:51ZEmpirical mode decomposition and k-nearest embedding vectors for timely analyses of antibiotic resistance trends.1932-620310.1371/journal.pone.0061180https://doaj.org/article/fac3f268582248e684b27fe6ce42e4442013-01-01T00:00:00Zhttps://www.ncbi.nlm.nih.gov/pmc/articles/pmid/23637796/?tool=EBIhttps://doaj.org/toc/1932-6203<h4>Background</h4>Antibiotic resistance is a major worldwide public health concern. In clinical settings, timely antibiotic resistance information is key for care providers as it allows appropriate targeted treatment or improved empirical treatment when the specific results of the patient are not yet available.<h4>Objective</h4>To improve antibiotic resistance trend analysis algorithms by building a novel, fully data-driven forecasting method from the combination of trend extraction and machine learning models for enhanced biosurveillance systems.<h4>Methods</h4>We investigate a robust model for extraction and forecasting of antibiotic resistance trends using a decade of microbiology data. Our method consists of breaking down the resistance time series into independent oscillatory components via the empirical mode decomposition technique. The resulting waveforms describing intrinsic resistance trends serve as the input for the forecasting algorithm. The algorithm applies the delay coordinate embedding theorem together with the k-nearest neighbor framework to project mappings from past events into the future dimension and estimate the resistance levels.<h4>Results</h4>The algorithms that decompose the resistance time series and filter out high frequency components showed statistically significant performance improvements in comparison with a benchmark random walk model. We present further qualitative use-cases of antibiotic resistance trend extraction, where empirical mode decomposition was applied to highlight the specificities of the resistance trends.<h4>Conclusion</h4>The decomposition of the raw signal was found not only to yield valuable insight into the resistance evolution, but also to produce novel models of resistance forecasters with boosted prediction performance, which could be utilized as a complementary method in the analysis of antibiotic resistance trends.Douglas TeodoroChristian LovisPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 8, Iss 4, p e61180 (2013)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Douglas Teodoro Christian Lovis Empirical mode decomposition and k-nearest embedding vectors for timely analyses of antibiotic resistance trends.
description	<h4>Background</h4>Antibiotic resistance is a major worldwide public health concern. In clinical settings, timely antibiotic resistance information is key for care providers as it allows appropriate targeted treatment or improved empirical treatment when the specific results of the patient are not yet available.<h4>Objective</h4>To improve antibiotic resistance trend analysis algorithms by building a novel, fully data-driven forecasting method from the combination of trend extraction and machine learning models for enhanced biosurveillance systems.<h4>Methods</h4>We investigate a robust model for extraction and forecasting of antibiotic resistance trends using a decade of microbiology data. Our method consists of breaking down the resistance time series into independent oscillatory components via the empirical mode decomposition technique. The resulting waveforms describing intrinsic resistance trends serve as the input for the forecasting algorithm. The algorithm applies the delay coordinate embedding theorem together with the k-nearest neighbor framework to project mappings from past events into the future dimension and estimate the resistance levels.<h4>Results</h4>The algorithms that decompose the resistance time series and filter out high frequency components showed statistically significant performance improvements in comparison with a benchmark random walk model. We present further qualitative use-cases of antibiotic resistance trend extraction, where empirical mode decomposition was applied to highlight the specificities of the resistance trends.<h4>Conclusion</h4>The decomposition of the raw signal was found not only to yield valuable insight into the resistance evolution, but also to produce novel models of resistance forecasters with boosted prediction performance, which could be utilized as a complementary method in the analysis of antibiotic resistance trends.
format	article
author	Douglas Teodoro Christian Lovis
author_facet	Douglas Teodoro Christian Lovis
author_sort	Douglas Teodoro
title	Empirical mode decomposition and k-nearest embedding vectors for timely analyses of antibiotic resistance trends.
title_short	Empirical mode decomposition and k-nearest embedding vectors for timely analyses of antibiotic resistance trends.
title_full	Empirical mode decomposition and k-nearest embedding vectors for timely analyses of antibiotic resistance trends.
title_fullStr	Empirical mode decomposition and k-nearest embedding vectors for timely analyses of antibiotic resistance trends.
title_full_unstemmed	Empirical mode decomposition and k-nearest embedding vectors for timely analyses of antibiotic resistance trends.
title_sort	empirical mode decomposition and k-nearest embedding vectors for timely analyses of antibiotic resistance trends.
publisher	Public Library of Science (PLoS)
publishDate	2013
url	https://doaj.org/article/fac3f268582248e684b27fe6ce42e444
work_keys_str_mv	AT douglasteodoro empiricalmodedecompositionandknearestembeddingvectorsfortimelyanalysesofantibioticresistancetrends AT christianlovis empiricalmodedecompositionandknearestembeddingvectorsfortimelyanalysesofantibioticresistancetrends
_version_	1718422950660538368

Empirical mode decomposition and k-nearest embedding vectors for timely analyses of antibiotic resistance trends.

Ejemplares similares