Machine learning risk prediction model for acute coronary syndrome and death from use of non-steroidal anti-inflammatory drugs in administrative data

Abstract Our aim was to investigate the usefulness of machine learning approaches on linked administrative health data at the population level in predicting older patients’ one-year risk of acute coronary syndrome and death following the use of non-steroidal anti-inflammatory drugs (NSAIDs). Patient...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Juan Lu, Ling Wang, Mohammed Bennamoun, Isaac Ward, Senjian An, Ferdous Sohel, Benjamin J. W. Chow, Girish Dwivedi, Frank M. Sanfilippo
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/4932909e049644539ef7902709d72dbc
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:4932909e049644539ef7902709d72dbc
record_format dspace
spelling oai:doaj.org-article:4932909e049644539ef7902709d72dbc2021-12-02T18:02:31ZMachine learning risk prediction model for acute coronary syndrome and death from use of non-steroidal anti-inflammatory drugs in administrative data10.1038/s41598-021-97643-32045-2322https://doaj.org/article/4932909e049644539ef7902709d72dbc2021-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-97643-3https://doaj.org/toc/2045-2322Abstract Our aim was to investigate the usefulness of machine learning approaches on linked administrative health data at the population level in predicting older patients’ one-year risk of acute coronary syndrome and death following the use of non-steroidal anti-inflammatory drugs (NSAIDs). Patients from a Western Australian cardiovascular population who were supplied with NSAIDs between 1 Jan 2003 and 31 Dec 2004 were identified from Pharmaceutical Benefits Scheme data. Comorbidities from linked hospital admissions data and medication history were inputs. Admissions for acute coronary syndrome or death within one year from the first supply date were outputs. Machine learning classification methods were used to build models to predict ACS and death. Model performance was measured by the area under the receiver operating characteristic curve (AUC-ROC), sensitivity and specificity. There were 68,889 patients in the NSAIDs cohort with mean age 76 years and 54% were female. 1882 patients were admitted for acute coronary syndrome and 5405 patients died within one year after their first supply of NSAIDs. The multi-layer neural network, gradient boosting machine and support vector machine were applied to build various classification models. The gradient boosting machine achieved the best performance with an average AUC-ROC of 0.72 predicting ACS and 0.84 predicting death. Machine learning models applied to linked administrative data can potentially improve adverse outcome risk prediction. Further investigation of additional data and approaches are required to improve the performance for adverse outcome risk prediction.Juan LuLing WangMohammed BennamounIsaac WardSenjian AnFerdous SohelBenjamin J. W. ChowGirish DwivediFrank M. SanfilippoNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Juan Lu
Ling Wang
Mohammed Bennamoun
Isaac Ward
Senjian An
Ferdous Sohel
Benjamin J. W. Chow
Girish Dwivedi
Frank M. Sanfilippo
Machine learning risk prediction model for acute coronary syndrome and death from use of non-steroidal anti-inflammatory drugs in administrative data
description Abstract Our aim was to investigate the usefulness of machine learning approaches on linked administrative health data at the population level in predicting older patients’ one-year risk of acute coronary syndrome and death following the use of non-steroidal anti-inflammatory drugs (NSAIDs). Patients from a Western Australian cardiovascular population who were supplied with NSAIDs between 1 Jan 2003 and 31 Dec 2004 were identified from Pharmaceutical Benefits Scheme data. Comorbidities from linked hospital admissions data and medication history were inputs. Admissions for acute coronary syndrome or death within one year from the first supply date were outputs. Machine learning classification methods were used to build models to predict ACS and death. Model performance was measured by the area under the receiver operating characteristic curve (AUC-ROC), sensitivity and specificity. There were 68,889 patients in the NSAIDs cohort with mean age 76 years and 54% were female. 1882 patients were admitted for acute coronary syndrome and 5405 patients died within one year after their first supply of NSAIDs. The multi-layer neural network, gradient boosting machine and support vector machine were applied to build various classification models. The gradient boosting machine achieved the best performance with an average AUC-ROC of 0.72 predicting ACS and 0.84 predicting death. Machine learning models applied to linked administrative data can potentially improve adverse outcome risk prediction. Further investigation of additional data and approaches are required to improve the performance for adverse outcome risk prediction.
format article
author Juan Lu
Ling Wang
Mohammed Bennamoun
Isaac Ward
Senjian An
Ferdous Sohel
Benjamin J. W. Chow
Girish Dwivedi
Frank M. Sanfilippo
author_facet Juan Lu
Ling Wang
Mohammed Bennamoun
Isaac Ward
Senjian An
Ferdous Sohel
Benjamin J. W. Chow
Girish Dwivedi
Frank M. Sanfilippo
author_sort Juan Lu
title Machine learning risk prediction model for acute coronary syndrome and death from use of non-steroidal anti-inflammatory drugs in administrative data
title_short Machine learning risk prediction model for acute coronary syndrome and death from use of non-steroidal anti-inflammatory drugs in administrative data
title_full Machine learning risk prediction model for acute coronary syndrome and death from use of non-steroidal anti-inflammatory drugs in administrative data
title_fullStr Machine learning risk prediction model for acute coronary syndrome and death from use of non-steroidal anti-inflammatory drugs in administrative data
title_full_unstemmed Machine learning risk prediction model for acute coronary syndrome and death from use of non-steroidal anti-inflammatory drugs in administrative data
title_sort machine learning risk prediction model for acute coronary syndrome and death from use of non-steroidal anti-inflammatory drugs in administrative data
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/4932909e049644539ef7902709d72dbc
work_keys_str_mv AT juanlu machinelearningriskpredictionmodelforacutecoronarysyndromeanddeathfromuseofnonsteroidalantiinflammatorydrugsinadministrativedata
AT lingwang machinelearningriskpredictionmodelforacutecoronarysyndromeanddeathfromuseofnonsteroidalantiinflammatorydrugsinadministrativedata
AT mohammedbennamoun machinelearningriskpredictionmodelforacutecoronarysyndromeanddeathfromuseofnonsteroidalantiinflammatorydrugsinadministrativedata
AT isaacward machinelearningriskpredictionmodelforacutecoronarysyndromeanddeathfromuseofnonsteroidalantiinflammatorydrugsinadministrativedata
AT senjianan machinelearningriskpredictionmodelforacutecoronarysyndromeanddeathfromuseofnonsteroidalantiinflammatorydrugsinadministrativedata
AT ferdoussohel machinelearningriskpredictionmodelforacutecoronarysyndromeanddeathfromuseofnonsteroidalantiinflammatorydrugsinadministrativedata
AT benjaminjwchow machinelearningriskpredictionmodelforacutecoronarysyndromeanddeathfromuseofnonsteroidalantiinflammatorydrugsinadministrativedata
AT girishdwivedi machinelearningriskpredictionmodelforacutecoronarysyndromeanddeathfromuseofnonsteroidalantiinflammatorydrugsinadministrativedata
AT frankmsanfilippo machinelearningriskpredictionmodelforacutecoronarysyndromeanddeathfromuseofnonsteroidalantiinflammatorydrugsinadministrativedata
_version_ 1718378864785227776