A machine learning approach for predicting urine output after fluid administration.

BACKGROUND AND OBJECTIVE: To develop a machine learning model to predict urine output (UO) in sepsis patients after fluid resuscitation. METHODS: We identified sepsis patients in the Multiparameter Intelligent Monitoring in Intensive Care-III v1.4 database according to the Sepsis-3 criteria. We focused on two outcomes: whether the UO decreased after fluid administration and whether oliguria (defined as UO less than the threshold of 0.5 mL/kg/h) developed. A gradient tree-based machine learning model implemented with an eXtreme Gradient Boosting algorithm was used to integrate relevant physiological parameters for predicting the aforementioned outcomes. A confusion matrix was computed. RESULTS: A total of 232,929 events in 19,275 patients were included. Using decreased UO as the outcome measure, the optimal model achieved an area under the curve (AUC) of 0.86; for predicting oliguria, most models achieved an AUC greater than 0.86, and the highest sensitivity was 92.2% when the model was applied to patients with baseline oliguria. CONCLUSIONS: Machine learning could help clinicians evaluate fluid status in sepsis patients after fluid administration, thus preventing fluid overload-related complications.

Automation of the kidney function prediction and classification through ultrasound-based kidney imaging using deep learning.

Prediction of kidney function and chronic kidney disease (CKD) through kidney ultrasound imaging has long been considered desirable in clinical practice because of its safety, convenience, and affordability. However, this highly desirable approach is beyond the capability of human vision. We developed a deep learning approach for automatically determining the estimated glomerular filtration rate (eGFR) and CKD status. We exploited the transfer learning technique, integrating the powerful ResNet model pretrained on an ImageNet dataset in our neural network architecture, to predict kidney function based on 4,505 kidney ultrasound images labeled using eGFRs derived from serum creatinine concentrations. To further extract the information from ultrasound images, we leveraged kidney length annotations to remove the peripheral region of the kidneys and applied various data augmentation schemes to produce additional data with variations. Bootstrap aggregation was also applied to avoid overfitting and improve the model's generalization. Moreover, the kidney function features obtained by our deep neural network were used to identify the CKD status defined by an eGFR of <60 ml/min/1.73 m2. A Pearson correlation coefficient of 0.741 indicated the strong relationship between artificial intelligence (AI)- and creatinine-based GFR estimations. Overall CKD status classification accuracy of our model was 85.6% -higher than that of experienced nephrologists (60.3%-80.1%). Our model is the first fundamental step toward realizing the potential of transforming kidney ultrasound imaging into an effective, real-time, distant screening tool. AI-GFR estimation offers the possibility of noninvasive assessment of kidney function, a key goal of AI-powered functional automation in clinical practice.