Seki T, et al. - Researchers analyzed cohort data from a prospective multi-center cohort study for out-of-hospital cardiac arrest (OHCA) patients transported by an ambulance in the Kanto area of Japan between January 2012 and March 2013 (SOS-KANTO 2012 study) to build a prognostication model for OHCA with presumed cardiac etiology using an advanced machine learning technique. Of 16,452 patients, they obtained data for OHCA patients aged ≥18 years with presumed cardiac etiology and divided the patients into two groups (training set: n = 5718, between January 1, 2012 and December 12, 2012; test set: n = 1608, between January 1, 2013 and March 31, 2013). They observed 421 variables during prehospital and emergency department settings; of these, they used 35 prehospital variables, or 35 prehospital and 18 in-hospital variables, for outcome prediction of 1-year survival using a random forest method. In validation using the test set, they obtained the area under the receiver operating characteristics curve values of 0.943 and 0.958 using prognostication models trained with 35 variables, or 53 variables for 1-year survival, respectively. These findings suggest the favorable predictive value of the advanced machine learning technique for 1-year survival of OHCA with presumed cardiac etiology. The clinical utility of the models is supported for detecting patients who could have been potentially saved.