Search

Abstract Current research in nephrology is increasingly focused on elucidating the complexity inherent in tightly interwoven molecular systems and their correlation with pathology and related therapeutics, including dialysis and renal transplantation. Rapid advances in the omics sciences, medical device sensorization, and networked digital medical devices have made such research increasingly data centered. Data-centric science requires the support of computationally powerful and sophisticated tools able to handle the overflow of novel biomarkers and therapeutic targets. This is a context in which artificial intelligence (AI) and, more specifically, machine learning (ML) can provide a clear analytical advantage, given the rapid advances in their ability to harness multimodal data, from genomic information to signal, image and even heterogeneous electronic health records (EHR). However, paradoxically, only a small fraction of ML-based medical decision support systems undergo validation and demonstrate clinical usefulness. To effectively translate all this new knowledge into clinical practice, the development of clinically compliant support systems based on interpretable and explainable ML-based methods and clear analytical strategies for personalized medicine are imperative. Intelligent nephrology, that is, the design and development of AI-based strategies for a data-centric approach to nephrology, is just taking its first steps and is by no means yet close to its coming of age. These first steps are not even homogeneously taken, as a digital divide in access to technology has become evident between developed and developing countries, also affecting underrepresented minorities. With all this in mind, this editorial aim to provide a selective overview of the current use of AI technologies in nephrology and heralds the “Artificial Intelligence in Nephrology” special issue launched by BMC Nephrology.

Abstract Background Chronic kidney disease (CKD) is associated with endothelial dysfunctions thus prompting links between microcirculation (MC), inflammation and major cardiovascular risk factors. Purpose of the study We have previously reported that siRNA-silencing of CD40 (siCD40) reduced atherosclerosis (ATH) progression. Here, we have deepened on the effects of the siCD40 treatment by evaluating retrospectively, in stored kidneys from the siCD40 treated ApoE−/− mice, the renal microcirculation (measured as the density of peritubular capillaries), macrophage infiltration and NF-κB activation. Methods Kidneys were isolated after 16 weeks of treatment with the anti-CD40 siRNA (siCD40), with a scrambled control siRNA (siSC) or with PBS (Veh. group). Renal endothelium, infiltrating macrophages and activated NF-κB in endothelium were identified by immunohistochemistry, while the density of stained peritubular capillaries was quantified by image analysis. Results ATH was associated with a reduction in renal MC, an effect reversed by the anti-CD40 siRNA treatment (3.8 ± 2.7% in siCD40; vs. 1.8 ± 0.1% in siSC; or 1.9 ± 1.6% in Veh.; p