Severe acute kidney injury predicting model based on transcontinental databases: a single-centre prospective study

Abstract

ObjectivesThere are many studies of acute kidney injury (AKI) diagnosis models lack of external validation and prospective validation. We constructed the models using three databases to predict severe AKI within 48 hours in intensive care unit (ICU) patients.DesignA retrospective and prospective cohort study.SettingWe studied critically ill patients in our database (SHZJU-ICU) and two other public databases, the Medical Information Mart for Intensive Care (MIMIC) and AmsterdamUMC databases, including basic demographics, vital signs and laboratory results. We predicted the diagnosis of severe AKI in patients in the next 48 hours using machine-learning algorithms with the three databases. Then, we carried out real-time severe AKI prediction in the prospective validation study at our centre for 1 year.ParticipantsAll patients included in three databases with uniform exclusion criteria.Primary and secondary outcome measuresEffect evaluation index of prediction models.ResultsWe included 58 492 patients, and a total of 5257 (9.0%) patients met the definition of severe AKI. In the internal validation of the SHZJU-ICU and MIMIC databases, the best area under the receiver operating characteristic curve (AUROC) of the model was 0.86. The external validation results by AmsterdamUMC database were also satisfactory, with the best AUROC of 0.86. A total of 2532 patients were admitted to the centre for prospective validation; 358 positive results were predicted and 344 patients were diagnosed with severe AKI, with the best sensitivity of 0.72, the specificity of 0.80 and the AUROC of 0.84.ConclusionThe prediction model of severe AKI exhibits promises as a clinical application based on dynamic vital signs and laboratory results of multicentre databases with prospective and external validation.

Prediction of successful weaning from renal replacement therapy in critically ill patients based on machine learning

“…Study design and setting: This study is a retrospective single-center investigation that utilized data from the Comprehensive ICU Database of the Second Affiliated Hospital of the Medical College of Zhejiang University (SHZJU-ICU). This large academic teaching hospital, located in southeast China, encompasses four districts in Hangzhou [ 14 ], boasting a total of 3800 beds. The General ICU spans across three of these districts, comprising independent wards with capacities of 26, 40, and 10 beds.…”

“…While ML models have been successfully applied in AKI for early diagnosis, mortality prediction, recovery assessment, and RRT timing, yielding accuracies ranging from 81% to 97%, there is a relative lack of ML models designed specifically for RRT weaning [ 10–13 ]. Leveraging our center’s extensive database and an established prediction model for severe AKI [ 14 ], we conducted data mining, including demographics, continuous renal replacement therapy (CRRT) during time, time to get on and off the CRRT, and laboratory indicators, vital signs, medication records before and after critical time nodes to develop a predictive model for RRT discontinuation in patients with severe AKI.…”

Machine learning for acute kidney injury: Changing the traditional disease prediction mode

“…Deep learning is the process of learning the intrinsic laws and levels of the representation of sample data, and the information obtained from these learning processes can be of great help in the interpretation of data such as text, images and sound. As the complexity of graph models in deep learning leads to a dramatic increase in the time complexity of the algorithm, higher parallel programming skills and more and better hardware support are needed to ensure the real-time performance of the algorithm available databases, MIMIC-III, AmsterdamUMCdb and eICU (14)(15)(16)(17)(18)(19)(20)(21)(22)(23)(24)(25). The use of local databases is not common, and only information from the Mayo Clinic and SHZJU-ICU can be retrieved (21,26,27).…”

“…As the complexity of graph models in deep learning leads to a dramatic increase in the time complexity of the algorithm, higher parallel programming skills and more and better hardware support are needed to ensure the real-time performance of the algorithm available databases, MIMIC-III, AmsterdamUMCdb and eICU (14)(15)(16)(17)(18)(19)(20)(21)(22)(23)(24)(25). The use of local databases is not common, and only information from the Mayo Clinic and SHZJU-ICU can be retrieved (21,26,27). Public databases are highly integrated and easy to access, but it is inevitable that some of the missing information affects the authenticity of the data; for example, the variables with a large proportion of missing values in the MIMIC-III database include the lowest albumin level (74.1%), the highest bilirubin level (67.2%), the highest lactate level (55.8%), the highest C-reactive protein level (99.0%), the highest aspartate aminotransferase level (66.8%), the highest pH level (36.6%) and the lowest base excess level (64.8%) (14).…”

“…In addition, the differences in data extraction criteria settings or data preprocessing methods lead to a certain degree of incomparability among studies from the same database sources. Second, of the 14 studies we retrieved, only 3 studies conducted external validation of the model (20,21,26). While this is crucial for model generalization and relies on external validation for optimization of model hyperparameters, which is well understood by researchers, there are various constraints to external validation, including non-uniformity of case data formats across centers, self-protection of some medical structures for data security, or difficulty in matching predictions from other centers due to the complexity of the model.…”