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...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2021-09-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-021-97643-3 |
| _version_ | 1818422118326468608 |
|---|---|
| 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 |
| collection | DOAJ |
| 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. |
| first_indexed | 2024-12-14T13:21:10Z |
| format | Article |
| id | doaj.art-4932909e049644539ef7902709d72dbc |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-14T13:21:10Z |
| publishDate | 2021-09-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-4932909e049644539ef7902709d72dbc2022-12-21T22:59:55ZengNature PortfolioScientific Reports2045-23222021-09-0111111010.1038/s41598-021-97643-3Machine learning risk prediction model for acute coronary syndrome and death from use of non-steroidal anti-inflammatory drugs in administrative dataJuan Lu0Ling Wang1Mohammed Bennamoun2Isaac Ward3Senjian An4Ferdous Sohel5Benjamin J. W. Chow6Girish Dwivedi7Frank M. Sanfilippo8Medical School, The University of Western AustraliaSchool of Population and Global Health, The University of Western AustraliaDepartment of Computer Science and Software Engineering, The University of Western AustraliaSchool of Population and Global Health, The University of Western AustraliaSchool of Electrical Engineering, Computing and Mathematical Sciences, Curtin UniversityDepartment of Computer Science and Software Engineering, The University of Western AustraliaDivision of Cardiology, University of Ottawa Faculty of Medicine and University of Ottawa Heart InstituteMedical School, The University of Western AustraliaSchool of Population and Global Health, The University of Western AustraliaAbstract 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.https://doi.org/10.1038/s41598-021-97643-3 |
| spellingShingle | 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 Scientific Reports |
| title | 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_short | 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 |
| url | https://doi.org/10.1038/s41598-021-97643-3 |
| 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 |