Establishing AKI Warning System in Peking Union Medical College Hospital from a Machine Learning Approach: A Single-center Research Protocol

Abstract

Background and Objective In-hospital acute kidney injury (AKI) has significant negative impact over patient outcome and length of hospital stay. The use of electronic medical record (EMR) early warning to identify and intervene AKI in a timely manner is of great significance to reduce the severity of AKI and improve the prognosis of patients. At present, AKI-related research based on the EMR system mainly uses traditional statistical methods for retrospective analysis, mainly for inpatients in single-disciplinary wards, and there is still a lack of AKI risk early warning models based on artificial intelligence technology in large-scale multi-disciplinary wards with time-sensitive information and further prospective research. This study aims to develop a multiple-ward AKI prediction model tailored for general hospitals in China based on machine-learning algorithm and big data acquired by EMR system. Methods This single-center study consists of both a retrospective observational study and a prospective study. All hospitalized adult patients admitted in Peking Union Medical College Hospital (PUMCH) between 2016 and 2020 were included in the retrospective study. Logistic regression, naive Bayes, random forest, support vector machine and gradient boosting and recurrent neural network based on demographics, clinical feature, vital signs, imaging, lab results and charts will be used for modeling, which aims to predict AKI 24-48h in advance and will be internally validated. The prospective study intends to include all adult inpatients in PUMCH for 12 consecutive months. Among them, all adult hospitalized patients within 6 months before the AKI early warning system is launched would be the control group, and all adult hospitalized patients within 6 months after the AKI early warning system is launched would be the intervention group. In the intervention group, the AKI early warning system would be embedded in the EMR, and all patients hospitalized for more than 24 hours would be assessed for AKI risk in the next 48 hours in real time every 6 hours, and early intervention would be carried out for high-risk patients. The control group did not have the abovementioned AKI high-risk and alarm prompts, and no corresponding intervention measures. The incidence of with AKI and AKI grade 3, AKI remission rate, end-stage renal disease progression rate, mortality during hospitalization, length of stay, hospitalization expenses and other indicators would be compared between the two groups. Expected results An estimated number of 127000 in-hospital patients will be included in the retrospective study, among which 14605 patients suffered from AKI. The prediction model is expected to predict AKI 24-48 hours in advance and the aim for area under receiver operating characteristics curve would be>0.80. In the prospective study, 34,748 inpatients will be enrolled, including 17 374 in both the intervention group and the control group. The duration time of renal replacement therapy and length of hospital stay in the intervention group would be shorter than those in the control group (P<0.05), the proportion of renal replacement therapy, the incidence of AKI and AKI 3, the rate of progression of end-stage renal disease, the mortality rate during hospitalization, and the hospitalization cost would be lower than those in the control group (P<0.05), and the AKI remission rate would be higher than that in the control group (P<0.05). Expected conclusion EMR-based multi-ward AKI prediction model would predict AKI risk 24-48h in advance, lowering AKI incidence and severity, improving clinical outcomes.