Background The aim of this study was to compare the ability to predict 30‐day in‐hospital mortality of lactate versus the modified Rapid Emergency Medicine Score (mREMS) versus the arithmetic sum of the mREMS plus the numerical value of lactate (mREMS‐L). Methods A prospective, multicentric, emergency department delivery, pragmatic study was conducted. To determine the predictive capacity of the scales, lactate was measured and the mREMS and mREMS‐L were calculated in adult patients (aged>18 years) transferred with high priority by ambulance to the emergency department in five hospitals of Castilla y Leon between 1 January 2020 and 31 December 2021. The area under the receiver operating characteristic (ROC) curve of each of the scales was calculated in terms of mortality for 30 days. Results A total of 5371 participants were included, and the in‐hospital mortality rate at 30 days was of 11.4% (615 cases). The best cut‐off point determined in the mREMS was 7.0 points (sensitivity of 67% and specificity of 84%), and for lactate, the cut‐off point was 1.4 mmol/L (sensitivity of 88% and specificity of 67%). Finally, the combined mREMS‐L showed a cut‐off point of 7.9 (sensitivity of 83% and a specificity of 83%). The area under the ROC curve of the mREMS, lactate and mREMS‐L for 30‐day mortality was 0.851, 0.853, and 0.903, respectively (p < 0.001 in all cases). Conclusions The new score generated, mREMS‐L, obtained better statistical results than its components (mREMS and lactate) separately.