Vascular access performance determines the adequacy, safety, and cost of hemodialysis. Stenosis, thrombosis, cannulation difficulty, infection, and access-related cardiac stress remain major sources of morbidity. This narrative review examines artificial intelligence and sensing technologies for vascular access care, based on PubMed and ClinicalTrials.gov searches through 22 August 2026 with citation chaining. Existing reviews have examined artificial intelligence in dialysis broadly or prediction models in isolation. In this review, the vascular access itself is kept as the unit of analysis, and the evidence is followed across four connected stages: systemic risk stratification; prediction of maturation, dysfunction, and complications from clinical, ultrasound, and multimodal data; longitudinal monitoring with optical, acoustic, vibration, thermal, and pressure sensors; and procedural support with robotics and visualization technologies. Reported discrimination is high in retrospective, recording-level analyses, reaching areas under the curve of 0.99 and sample-level accuracy of 100%, but falls to approximately 0.71 in longitudinal designs that predict future events in the same patients; patient-level external validation and calibration are also rarely reported. No approach has yet been demonstrated to reduce thrombosis, prolong patency, avoid interventions, or lower cost relative to standard care in prospective multicenter studies. Deployment is further constrained by power budgets, duty cycling, and transmission bandwidth in wearable devices. Technical feasibility should not be read as clinical utility.

Background: Timely vascular access creation in end-stage kidney disease is critical for optimizing patient outcomes. While early nephrology referral (⩾90 days pre-dialysis) improves access patency and survival, late referral is associated with worse outcomes. Healthcare system structure and demographics may impact vascular access strategies. This study compared late-referral hemodialysis patients from two high-volume hospitals in different healthcare systems, focusing on vascular access and survival. Methods: This retrospective, two-center study included 463 late-referral hemodialysis patients (mean age 60.4 ± 15.8 years; 63.3% male) initiating dialysis with a tunneled CVC between January 2020 and May 2024 at King’s College Hospital, London ( n = 249) and Policlinico A. Gemelli, Rome ( n = 214). Primary outcome: all-cause mortality. Secondary outcomes: AVF creation, primary and secondary AVF patency, and CRBSI. Results: AVF recipients had significantly lower mortality than non-AVF patients ( p = 0.002), and a lower bacteremia rate ( p = 0.05) across both Italy and UK cohorts ( p = 0.005 and p = 0.0005, respectively). Time to AVF creation was significantly associated with mortality (OR 1.003; 95% CI 1.000–1.006; p = 0.02). AVF creation was achieved in 42.1% ( n = 195), with primary patency rate of 62.7% at 6 months. Ethnicity ( p = 0.01) and age ( p = 0.0004) influenced AVF type selection. Among non-AVF patients, 26% declined surgery despite eligibility, showing reduced survival ( p = 0.03). CRBSIs occurred in 16% of patients, mostly Gram-positive (70.3%). Relapse rate was higher with CVC removal/replacement than guidewire exchange (19.4% vs 0%; p = 0.01). Conclusions: Early AVF creation in late-referral hemodialysis patients improves survival and reduces CRBSI risk. Reducing CVC requirement, especially in AVF-eligible patients, is a key strategy to improve outcomes.

Background: Catheter-related bloodstream infections (CRBSIs) are the main complications associated with the use of permanent central venous catheters (CVCs). However, standardized management protocols for infected tunneled CVCs remain heterogeneous. We present an innovative stylet-protected guidewire-exchange technique designed to minimize contamination and preserve vascular access sites. Methods: We performed a retrospective, observational, single-center study of infected tunneled CVC replacement at the Nephrology Unit of Policlinico A. Gemelli Foundation (Rome) from January 2019 to June 2024. Follow-up ranged from 1 to 4 years. The primary endpoint was infection-free survival, defined as time to relapse (recurrent CRBSI with the same pathogen) or reinfection (a different pathogen). Results: A total of 99 CVC exchanges were performed in 99 patients (M 50.5%, F 49.5%; median age: 72 years, IQR 62–78.5). To assess the safety of the technique, guidewire cultures were obtained, confirming persistence of the initial CRBSI pathogen. Despite positive guidewire cultures, relapse by the same pathogen occurred in only 2% of cases: one Pseudomonas aeruginosa (at 3 months) and one Staphylococcus aureus (at 8 months). Reinfection with different pathogens occurred in 11.1% of cases (11 patients) after a median of 283 days (IQR 121–642). All catheters maintained extracorporeal blood flow ⩾250 mL/min, ensuring adequate dialysis. Conclusions: This stylet-protected guidewire-exchange demonstrated excellent infection-free survival, including infections caused by high-risk pathogens such as Staphylococcus aureus . These results support guidewire exchange as a safe, effective and reproducible method for replacing infected tunneled CVCs in hemodialysis patients.