… Although some of these risk models used machine learning, none of these models investigated
… Therefore, we aimed to develop a machine learning–based AKI prediction model that …

… This study represents the novel combination of machine learning predictive algorithms with
… compared different machine learning techniques for predicting AKI using more than 300 dif…

… Machine learning methods may provide advantages for AKI … The machine learning method
assessed in this study was that … The machine learning method assessed in this study was that …

… regression models while remaining stable and small for the machine learning models.
Changes in the rate of acute kidney injury were strongly linked to increasing overprediction, while …

… Acute kidney injury (AKI) is the most common and serious complication of sepsis, …
based on novel machine learning (ML) algorithms for AKI in critically ill patients with sepsis. …

… The number of studies applying machine learning (ML) to predict acute kidney injury (AKI)
has grown steadily over the past decade. We assess and critically appraise the state of the art …

… Machine learning performance to predict acute kidney injury is variable and depends on
the predictor variables included in the model as well as the type of algorithm deployed. …

… acute kidney injury within 24, 48, or 72 hours. We hypothesized that a machine-learning-…
could accurately estimate risk for postencounter acute kidney injury shortly after ED arrival. …

… hyperparameters for machine learning in this space. In the context of machine learning, a
“… The machine-learning algorithm itself can be considered a hyperparameter: should we use …

… We used the Logistic regression and machine learning extreme gradient boosting (XGBoost)
to build two models which can predict patients who will progress to AKI stage 3. …