Renal Diseases

SMART DIALYSIS - Scaling Machine Learning and Artificial Intelligence AlgoRithms to OpTimize the Performance and Delivery of Acute DIALYSIS. Hypothesis: Can the investigators develop and implement Machine Learning and Artificial Intelligence Algorithms into Clinical Information Systems to Optimize the Prescription, Delivery, and Performance of Acute Dialysis? Objective(s): 1. Identify variables surrounding identified Key Performance Indicators that may be used by Machine Learning and Artificial Intelligence algorithms to optimize the prescription and performance of acute dialysis. 2. Develop Machine Learning and Artificial Intelligence algorithms to help guide the prescription and delivery of acute dialysis in the development of Clinical Decision Support tools and Best Practice Advisories and create a ML/AI Augmented SMART DIALYSIS Digital Dashboard. 3. Implement and evaluate the performance of the developed Machine Learning and Artificial Intelligence algorithms on patient-centered and health economic outcomes. 4. Validate and benchmark the performance of the evaluated Machine Learning and Artificial Intelligence algorithms across multiple jurisdictions.

This is a single-center observational study aimed at setting up and testing new ultrasound vascular imaging protocols, conducted exclusively for research purposes. The study will perform US examinations in 60 subjects. The subjects enrolled in the study will be examined the first time and will then provide consent to be examined again in the future if needed. The primary aim of this study is to set-up and test new advanced US protocol for the arm and cerebral blood vessels The secondary objectives will be: * Define ranges of normality/reference values of US-based parameters to be compared with pathological values. * Evaluate the repeatability and reproducibility of the acquired US measurements. * Evaluate the correlation between age and the acquired US measurements. * Evaluate the correlation between gender and the acquired US measurements.

The project aims to study the impact of SGLT2i therapy on clinical and biochemical aspects. in elderly. The project will combine different types of data, such as clinical and biological information, and will use advanced Bayesian statistical methods to understand the relationship between risk factors and patient outcomes following treatment with SGLT2 inhibitors.