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). 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.

Acute coronary syndrome risk prediction based on gradient boosted tree feature selection and recursive feature elimination: A dataset-specific modeling study

“…; coronary vascular disease variables (bifurcation site, chronic total occlusion (CTO), angulation of diseased vessels, calcification of diseased vessels, type of diseased vessels, and location of diseased vessels). Among them, e' wave velocity, history of renal insufficiency, left ventricular mass index, and apolipoprotein A are variables that we did not find in the data sets of other literature [13,14], but actually have some influence on ACS. Renal insufficiency will activate the renin-angiotensin system (RAAS) and sympathetic nervous system, aggravate cardiac insufficiency, and affect long-term prognosis and survival.…”

“…Among them, e’ wave velocity, history of renal insufficiency, left ventricular mass index, and apolipoprotein A are variables that we did not find in the data sets of other literature [ 13 , 14 ], but actually have some influence on ACS. Renal insufficiency will activate the renin-angiotensin system (RAAS) and sympathetic nervous system, aggravate cardiac insufficiency, and affect long-term prognosis and survival.…”

“…In recent years, machine learning has performed well for ACS prediction [11], and can significantly improve the performance. Various machine learning modeling methods, including Naive Bayes, Random Forest, Gradient Boosting, Logistic Regression, and Support Vector Machines, have been employed in numerous studies for the diagnosis and risk assessment of ACS [12][13][14]. Machine learning can also mine potential risk factors for disease.…”