Background: Acute kidney injury (AKI) is a major complication of acute myocardial infarction(AMI), which can significantly increase mortality. This study is to analyze the related risk factors and establish a prediction score of acute kidney injury in order to take early measurement for prevention. Methods: The medical records of 6014 hospitalized patients with AMI in Beijing Anzhen Hospital from January 2010 to December 2016 were retrospectively analyzed. These patients were randomly assigned into two cohorts: one was for the derivation of prediction score (n = 4252) and another for validation (n = 1762). The criterion for AKI was defined as an increase in serum creatinine of >= 0.3 mg/dL or >= 50% from baseline within 48 h. On the basis of odds ratio obtained from multivariate logistic regression analysis, a prediction score of acute kidney injury after AMI was built up. Results: In this prediction score, risk score 1 point included hypertension history, heart rate > 100 bpm on admission, peak serum troponin I >= 100 g/L, and time from admission to coronary reperfusion > 120 min; risks score 2 points included Killip classification >= class 3 on admission; and maximum dosage of intravenous furosemide >= 60 mg/d; risks score 3 points only included shock during hospitalization. In addition, when baseline estimated glomerular filtration rate (eGFR) was less than 90 ml/min.1.73 m(2), every 10 ml/min.1.73 m(2) reduction of eGFR increased risk score 1 point. Youden index showed that the best cut-off value for prediction of AKI was 3 points with a sensitivity of 71.1% and specificity 74.2%. The datasets of derivation and validation both displayed adequate discrimination (an area under the ROC curve, 0.79 and 0.81, respectively) and satisfactory calibration (Hosmer-Lemeshow statistic test, P = 0.63 and P = 0.60, respectively). Conclusions: In conclusion, a prediction score for AKI secondary to AMI in Chinese patients was established, which may help to prevent AKI early.