Background
The Madrid Acute Kidney Injury Prediction Score (MAKIPS) is a recently described tool able to do an automatic calculation of the risk of hospital-acquired AKI (HA-AKI) from electronic clinical records and could easily be implemented in clinical practice but, to date, it has not been externally validated. The objective of our study was to perform an external validation of the MAKIPS score in a hospital with different characteristics and case-mix.
Methods
External validation cohort study of the MAKIPS score, performed on patients hospitalized at a single tertiary hospital between April 2018 and September 2019. Performance was assessed by discrimination using area under the receiver operating characteristic curves (AUCROC) and calibration plots.
Results
HA-AKI in the external validation cohort was 5.3%. When compared to the MAKIPS cohort, the validation cohort showed a higher prevalence of men, diabetes, hypertension, cardiovascular disease, cerebrovascular disease, anaemia, congestive heart failure, chronic pulmonary disease, connective tissue diseases and renal disease, whereas, the prevalences of peptic ulcer disease, liver disease, malignancy, metastatic solid tumours and AIDS were significantly lower. In the validation cohort, the MAKIPS score showed an AUC of 0.798 (95% CI 0.788 -0.809). Calibration plots showed that at probability rates below 0.19, the score tended to overestimate, and at probability rates between 0.22 and 0.67, rates the score tended to underestimate the risk of HA-AKI.
Conclusions
The MAKIPS score can be a useful tool, easily obtainable from electronic records, to predict HA-AKI in hospitals with different case-mix characteristics.