Cargando…
Empirical Mode Decomposition and k-Nearest Embedding Vectors for Timely Analyses of Antibiotic Resistance Trends
BACKGROUND: 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 avai...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2013
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3636283/ https://www.ncbi.nlm.nih.gov/pubmed/23637796 http://dx.doi.org/10.1371/journal.pone.0061180 |
_version_ | 1782267308608061440 |
---|---|
author | Teodoro, Douglas Lovis, Christian |
author_facet | Teodoro, Douglas Lovis, Christian |
author_sort | Teodoro, Douglas |
collection | PubMed |
description | BACKGROUND: 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. OBJECTIVE: 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. METHODS: 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. RESULTS: 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. CONCLUSION: 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 | Online Article Text |
id | pubmed-3636283 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2013 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-36362832013-05-01 Empirical Mode Decomposition and k-Nearest Embedding Vectors for Timely Analyses of Antibiotic Resistance Trends Teodoro, Douglas Lovis, Christian PLoS One Research Article BACKGROUND: 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. OBJECTIVE: 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. METHODS: 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. RESULTS: 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. CONCLUSION: 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. Public Library of Science 2013-04-25 /pmc/articles/PMC3636283/ /pubmed/23637796 http://dx.doi.org/10.1371/journal.pone.0061180 Text en © 2013 Teodoro, Lovis http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are properly credited. |
spellingShingle | Research Article Teodoro, Douglas Lovis, Christian Empirical Mode Decomposition and k-Nearest Embedding Vectors for Timely Analyses of Antibiotic Resistance Trends |
title | 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_short | 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 |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3636283/ https://www.ncbi.nlm.nih.gov/pubmed/23637796 http://dx.doi.org/10.1371/journal.pone.0061180 |
work_keys_str_mv | AT teodorodouglas empiricalmodedecompositionandknearestembeddingvectorsfortimelyanalysesofantibioticresistancetrends AT lovischristian empiricalmodedecompositionandknearestembeddingvectorsfortimelyanalysesofantibioticresistancetrends |