Prediction of long-term hospitalisation and all-cause mortality in patients with chronic heart failure on Dutch claims data: a machine learning approach
Abstract Background Accurately predicting which patients with chronic heart failure (CHF) are particularly vulnerable for adverse outcomes is of crucial importance to support clinical decision making. The goal of the current study was to examine the predictive value on long term heart failure (HF) h...
Guardado en:
Autores principales: | , , , , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
BMC
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/1bbfe8e8bf964465bb8bff38db791fe9 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:1bbfe8e8bf964465bb8bff38db791fe9 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:1bbfe8e8bf964465bb8bff38db791fe92021-11-08T10:59:22ZPrediction of long-term hospitalisation and all-cause mortality in patients with chronic heart failure on Dutch claims data: a machine learning approach10.1186/s12911-021-01657-w1472-6947https://doaj.org/article/1bbfe8e8bf964465bb8bff38db791fe92021-11-01T00:00:00Zhttps://doi.org/10.1186/s12911-021-01657-whttps://doaj.org/toc/1472-6947Abstract Background Accurately predicting which patients with chronic heart failure (CHF) are particularly vulnerable for adverse outcomes is of crucial importance to support clinical decision making. The goal of the current study was to examine the predictive value on long term heart failure (HF) hospitalisation and all-cause mortality in CHF patients, by exploring and exploiting machine learning (ML) and traditional statistical techniques on a Dutch health insurance claims database. Methods Our study population consisted of 25,776 patients with a CHF diagnosis code between 2012 and 2014 and one year and three years follow-up HF hospitalisation (1446 and 3220 patients respectively) and all-cause mortality (2434 and 7882 patients respectively) were measured from 2015 to 2018. The area under the receiver operating characteristic (ROC) curve (AUC) was calculated after modelling the data using Logistic Regression, Random Forest, Elastic Net regression and Neural Networks. Results AUC rates ranged from 0.710 to 0.732 for 1-year HF hospitalisation, 0.705–0.733 for 3-years HF hospitalisation, 0.765–0.787 for 1-year mortality and 0.764–0.791 for 3-years mortality. Elastic Net performed best for all endpoints. Differences between techniques were small and only statistically significant between Elastic Net and Logistic Regression compared with Random Forest for 3-years HF hospitalisation. Conclusion In this study based on a health insurance claims database we found clear predictive value for predicting long-term HF hospitalisation and mortality of CHF patients by using ML techniques compared to traditional statistics.Onno P. van der GaliënRené C. HoekstraMuhammed T. GürgözeOlivier C. ManintveldMark R. van den BuntCor J. VeenmanEric BoersmaBMCarticleHeart failureHealth insurance claimsPrognosisOutcomesMachine learningComputer applications to medicine. Medical informaticsR858-859.7ENBMC Medical Informatics and Decision Making, Vol 21, Iss 1, Pp 1-13 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Heart failure Health insurance claims Prognosis Outcomes Machine learning Computer applications to medicine. Medical informatics R858-859.7 |
spellingShingle |
Heart failure Health insurance claims Prognosis Outcomes Machine learning Computer applications to medicine. Medical informatics R858-859.7 Onno P. van der Galiën René C. Hoekstra Muhammed T. Gürgöze Olivier C. Manintveld Mark R. van den Bunt Cor J. Veenman Eric Boersma Prediction of long-term hospitalisation and all-cause mortality in patients with chronic heart failure on Dutch claims data: a machine learning approach |
description |
Abstract Background Accurately predicting which patients with chronic heart failure (CHF) are particularly vulnerable for adverse outcomes is of crucial importance to support clinical decision making. The goal of the current study was to examine the predictive value on long term heart failure (HF) hospitalisation and all-cause mortality in CHF patients, by exploring and exploiting machine learning (ML) and traditional statistical techniques on a Dutch health insurance claims database. Methods Our study population consisted of 25,776 patients with a CHF diagnosis code between 2012 and 2014 and one year and three years follow-up HF hospitalisation (1446 and 3220 patients respectively) and all-cause mortality (2434 and 7882 patients respectively) were measured from 2015 to 2018. The area under the receiver operating characteristic (ROC) curve (AUC) was calculated after modelling the data using Logistic Regression, Random Forest, Elastic Net regression and Neural Networks. Results AUC rates ranged from 0.710 to 0.732 for 1-year HF hospitalisation, 0.705–0.733 for 3-years HF hospitalisation, 0.765–0.787 for 1-year mortality and 0.764–0.791 for 3-years mortality. Elastic Net performed best for all endpoints. Differences between techniques were small and only statistically significant between Elastic Net and Logistic Regression compared with Random Forest for 3-years HF hospitalisation. Conclusion In this study based on a health insurance claims database we found clear predictive value for predicting long-term HF hospitalisation and mortality of CHF patients by using ML techniques compared to traditional statistics. |
format |
article |
author |
Onno P. van der Galiën René C. Hoekstra Muhammed T. Gürgöze Olivier C. Manintveld Mark R. van den Bunt Cor J. Veenman Eric Boersma |
author_facet |
Onno P. van der Galiën René C. Hoekstra Muhammed T. Gürgöze Olivier C. Manintveld Mark R. van den Bunt Cor J. Veenman Eric Boersma |
author_sort |
Onno P. van der Galiën |
title |
Prediction of long-term hospitalisation and all-cause mortality in patients with chronic heart failure on Dutch claims data: a machine learning approach |
title_short |
Prediction of long-term hospitalisation and all-cause mortality in patients with chronic heart failure on Dutch claims data: a machine learning approach |
title_full |
Prediction of long-term hospitalisation and all-cause mortality in patients with chronic heart failure on Dutch claims data: a machine learning approach |
title_fullStr |
Prediction of long-term hospitalisation and all-cause mortality in patients with chronic heart failure on Dutch claims data: a machine learning approach |
title_full_unstemmed |
Prediction of long-term hospitalisation and all-cause mortality in patients with chronic heart failure on Dutch claims data: a machine learning approach |
title_sort |
prediction of long-term hospitalisation and all-cause mortality in patients with chronic heart failure on dutch claims data: a machine learning approach |
publisher |
BMC |
publishDate |
2021 |
url |
https://doaj.org/article/1bbfe8e8bf964465bb8bff38db791fe9 |
work_keys_str_mv |
AT onnopvandergalien predictionoflongtermhospitalisationandallcausemortalityinpatientswithchronicheartfailureondutchclaimsdataamachinelearningapproach AT renechoekstra predictionoflongtermhospitalisationandallcausemortalityinpatientswithchronicheartfailureondutchclaimsdataamachinelearningapproach AT muhammedtgurgoze predictionoflongtermhospitalisationandallcausemortalityinpatientswithchronicheartfailureondutchclaimsdataamachinelearningapproach AT oliviercmanintveld predictionoflongtermhospitalisationandallcausemortalityinpatientswithchronicheartfailureondutchclaimsdataamachinelearningapproach AT markrvandenbunt predictionoflongtermhospitalisationandallcausemortalityinpatientswithchronicheartfailureondutchclaimsdataamachinelearningapproach AT corjveenman predictionoflongtermhospitalisationandallcausemortalityinpatientswithchronicheartfailureondutchclaimsdataamachinelearningapproach AT ericboersma predictionoflongtermhospitalisationandallcausemortalityinpatientswithchronicheartfailureondutchclaimsdataamachinelearningapproach |
_version_ |
1718442403815227392 |