Cargando…

Feature selection and transformation by machine learning reduce variable numbers and improve prediction for heart failure readmission or death

BACKGROUND: The prediction of readmission or death after a hospital discharge for heart failure (HF) remains a major challenge. Modern healthcare systems, electronic health records, and machine learning (ML) techniques allow us to mine data to select the most significant variables (allowing for redu...

Descripción completa

Detalles Bibliográficos
Autores principales: Awan, Saqib E., Bennamoun, Mohammed, Sohel, Ferdous, Sanfilippo, Frank M., Chow, Benjamin J., Dwivedi, Girish
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6594617/
https://www.ncbi.nlm.nih.gov/pubmed/31242238
http://dx.doi.org/10.1371/journal.pone.0218760
_version_ 1783430265384730624
author Awan, Saqib E.
Bennamoun, Mohammed
Sohel, Ferdous
Sanfilippo, Frank M.
Chow, Benjamin J.
Dwivedi, Girish
author_facet Awan, Saqib E.
Bennamoun, Mohammed
Sohel, Ferdous
Sanfilippo, Frank M.
Chow, Benjamin J.
Dwivedi, Girish
author_sort Awan, Saqib E.
collection PubMed
description BACKGROUND: The prediction of readmission or death after a hospital discharge for heart failure (HF) remains a major challenge. Modern healthcare systems, electronic health records, and machine learning (ML) techniques allow us to mine data to select the most significant variables (allowing for reduction in the number of variables) without compromising the performance of models used for prediction of readmission and death. Moreover, ML methods based on transformation of variables may potentially further improve the performance. OBJECTIVE: To use ML techniques to determine the most relevant and also transform variables for the prediction of 30-day readmission or death in HF patients. METHODS: We identified all Western Australian patients aged 65 years and above admitted for HF between 2003–2008 in linked administrative data. We evaluated variables associated with HF readmission or death using standard statistical and ML based selection techniques. We also tested the new variables produced by transformation of the original variables. We developed multi-layer perceptron prediction models and compared their predictive performance using metrics such as Area Under the receiver operating characteristic Curve (AUC), sensitivity and specificity. RESULTS: Following hospital discharge, the proportion of 30-day readmissions or death was 23.7% in our cohort of 10,757 HF patients. The prediction model developed by us using a smaller set of variables (n = 8) had comparable performance (AUC 0.62) to the traditional model (n = 47, AUC 0.62). Transformation of the original 47 variables further improved (p<0.001) the performance of the predictive model (AUC 0.66). CONCLUSIONS: A small set of variables selected using ML matched the performance of the model that used the full set of 47 variables for predicting 30-day readmission or death in HF patients. Model performance can be further significantly improved by transforming the original variables using ML methods.
format Online
Article
Text
id pubmed-6594617
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-65946172019-07-05 Feature selection and transformation by machine learning reduce variable numbers and improve prediction for heart failure readmission or death Awan, Saqib E. Bennamoun, Mohammed Sohel, Ferdous Sanfilippo, Frank M. Chow, Benjamin J. Dwivedi, Girish PLoS One Research Article BACKGROUND: The prediction of readmission or death after a hospital discharge for heart failure (HF) remains a major challenge. Modern healthcare systems, electronic health records, and machine learning (ML) techniques allow us to mine data to select the most significant variables (allowing for reduction in the number of variables) without compromising the performance of models used for prediction of readmission and death. Moreover, ML methods based on transformation of variables may potentially further improve the performance. OBJECTIVE: To use ML techniques to determine the most relevant and also transform variables for the prediction of 30-day readmission or death in HF patients. METHODS: We identified all Western Australian patients aged 65 years and above admitted for HF between 2003–2008 in linked administrative data. We evaluated variables associated with HF readmission or death using standard statistical and ML based selection techniques. We also tested the new variables produced by transformation of the original variables. We developed multi-layer perceptron prediction models and compared their predictive performance using metrics such as Area Under the receiver operating characteristic Curve (AUC), sensitivity and specificity. RESULTS: Following hospital discharge, the proportion of 30-day readmissions or death was 23.7% in our cohort of 10,757 HF patients. The prediction model developed by us using a smaller set of variables (n = 8) had comparable performance (AUC 0.62) to the traditional model (n = 47, AUC 0.62). Transformation of the original 47 variables further improved (p<0.001) the performance of the predictive model (AUC 0.66). CONCLUSIONS: A small set of variables selected using ML matched the performance of the model that used the full set of 47 variables for predicting 30-day readmission or death in HF patients. Model performance can be further significantly improved by transforming the original variables using ML methods. Public Library of Science 2019-06-26 /pmc/articles/PMC6594617/ /pubmed/31242238 http://dx.doi.org/10.1371/journal.pone.0218760 Text en © 2019 Awan et al http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Awan, Saqib E.
Bennamoun, Mohammed
Sohel, Ferdous
Sanfilippo, Frank M.
Chow, Benjamin J.
Dwivedi, Girish
Feature selection and transformation by machine learning reduce variable numbers and improve prediction for heart failure readmission or death
title Feature selection and transformation by machine learning reduce variable numbers and improve prediction for heart failure readmission or death
title_full Feature selection and transformation by machine learning reduce variable numbers and improve prediction for heart failure readmission or death
title_fullStr Feature selection and transformation by machine learning reduce variable numbers and improve prediction for heart failure readmission or death
title_full_unstemmed Feature selection and transformation by machine learning reduce variable numbers and improve prediction for heart failure readmission or death
title_short Feature selection and transformation by machine learning reduce variable numbers and improve prediction for heart failure readmission or death
title_sort feature selection and transformation by machine learning reduce variable numbers and improve prediction for heart failure readmission or death
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6594617/
https://www.ncbi.nlm.nih.gov/pubmed/31242238
http://dx.doi.org/10.1371/journal.pone.0218760
work_keys_str_mv AT awansaqibe featureselectionandtransformationbymachinelearningreducevariablenumbersandimprovepredictionforheartfailurereadmissionordeath
AT bennamounmohammed featureselectionandtransformationbymachinelearningreducevariablenumbersandimprovepredictionforheartfailurereadmissionordeath
AT sohelferdous featureselectionandtransformationbymachinelearningreducevariablenumbersandimprovepredictionforheartfailurereadmissionordeath
AT sanfilippofrankm featureselectionandtransformationbymachinelearningreducevariablenumbersandimprovepredictionforheartfailurereadmissionordeath
AT chowbenjaminj featureselectionandtransformationbymachinelearningreducevariablenumbersandimprovepredictionforheartfailurereadmissionordeath
AT dwivedigirish featureselectionandtransformationbymachinelearningreducevariablenumbersandimprovepredictionforheartfailurereadmissionordeath