Extensive phenotype data and machine learning in prediction of mortality in acute coronary syndrome - the MADDEC study.

Ann Med 2019 Mar 27;51(2):156-163. Epub 2019 Apr 27.

a Faculty of Medicine and Health Technology , Tampere University , Tampere , Finland.

Investigation of the clinical potential of extensive phenotype data and machine learning (ML) in the prediction of mortality in acute coronary syndrome (ACS). The value of ML and extensive clinical data was analyzed in a retrospective registry study of 9066 consecutive ACS patients (January 2007 to October 2017). Main outcome was six-month mortality. Prediction models were developed using two ML methods, logistic regression and extreme gradient boosting (xgboost). The models were fitted in training set of patients treated in 2007-2014 and 2017 (81%,  = 7344) and validated in a separate validation set of patients treated in 2015-2016 with full GRACE score data available for comparison of model accuracy (19%,  = 1722). Overall, six-month mortality was 7.3% ( = 660). Several variables were found to be significantly associated with six-month mortality by both ML methods. The xgboost scored the best performance: AUC 0.890 (0.864-0.916). The AUC values for logistic regression and GRACE score were 0.867(0.837-0.897) and 0.822 (0.785-0.859), respectively. The AUC value of xgboost was better when compared to logistic regression ( = .012) and GRACE score ( < .00001). The use of extensive phenotype data and novel machine learning improves prediction of mortality in ACS over traditional GRACE score. KEY MESSAGES The collection of extensive cardiovascular phenotype data from electronic health records as well as from data recorded by physicians can be used highly effectively in prediction of mortality after acute coronary syndrome. Supervised machine learning methods such as logistic regression and extreme gradient boosting using extensive phenotype data significantly outperform conventional risk assessment by the current golden standard GRACE score. Integration of electronic health records and the use of supervised machine learning methods can be easily applied in a single centre level to model the risk of mortality.

Download full-text PDF

Source
http://dx.doi.org/10.1080/07853890.2019.1596302DOI Listing
March 2019
1 Read

Publication Analysis

Top Keywords

logistic regression
12
six-month mortality
12
grace score
12
acute coronary
8
mortality acute
8
patients treated
8
set patients
8
learning prediction
8
coronary syndrome
8
prediction mortality
8
machine learning
8
data machine
8
phenotype data
8
extensive phenotype
8
mortality
5
fitted training
4
training set
4
81%  = 7344
4
2017 81%
4
models fitted
4

References

(Supplied by CrossRef)
Article in Eur Heart J
Motwani M et al.
Eur Heart J 2017

Similar Publications