A machine learning algorithm to predict a culprit lesion after out of hospital cardiac arrest

BackgroundWe aimed to develop a machine learning algorithm to predict the presence of a culprit lesion in patients with out-of-hospital cardiac arrest (OHCA). MethodsWe used the King's Out-of-Hospital Cardiac Arrest Registry, a retrospective cohort of 398 patients admitted to King's College Hospital between May 2012 and December 2017. The primary outcome was the presence of a culprit coronary artery lesion, for which a gradient boosting model was optimized to predict. The algorithm was then validated in two independent European cohorts comprising 568 patients. ResultsA culprit lesion was observed in 209/309 (67.4%) patients receiving early coronary angiography in the development, and 199/293 (67.9%) in the Ljubljana and 102/132 (61.1%) in the Bristol validation cohorts, respectively. The algorithm, which is presented as a web application, incorporates nine variables including age, a localizing feature on electrocardiogram (ECG) (>= 2 mm of ST change in contiguous leads), regional wall motion abnormality, history of vascular disease and initial shockable rhythm. This model had an area under the curve (AUC) of 0.89 in the development and 0.83/0.81 in the validation cohorts with good calibration and outperforms the current gold standard-ECG alone (AUC: 0.69/0.67/0/67). ConclusionsA novel simple machine learning-derived algorithm can be applied to patients with OHCA, to predict a culprit coronary artery disease lesion with high accuracy.

Automated summary

A machine learning algorithm was developed to predict the presence of a culprit lesion in patients with out-of-hospital cardiac arrest. The algorithm incorporates nine variables and was validated using data from the King's Out-of-Hospital Cardiac Arrest Registry. The results showed that the algorithm has high accuracy in predicting culprit coronary artery disease lesions and outperforms the current standard electrocardiogram.