The Arteriovenous Access Stage (AVAS) classification simplifies information about suitability of vessels for vascular access (VA). It's been previously validated in a clinical study. Here, AVAS performance was tested against multiple ultrasound mapping measurements using machine learning. A prospective multicentre international study (NCT04796558) with patient recruitment from March 2021-July 2024. Demographics, risk factors, vessels parameters, types of predicted and created VA (pVA, cVA) were collected. We modelled pVA and cVA using the Random Forest algorithm. Model performance was estimated and compared using Bayesian generalized linear models. ROC AUC with 95% credible intervals was the performance metric. 1151 patients were included. ROC AUC for pVA prediction by AVAS was 0.79 (0.77;0.82) and by mapping was 0.85 (0.83;0.88). ROC AUC for cVA prediction by AVAS was 0.71 (0.69;0.74) and by mapping was 0.8 (0.78;0.83). Using AVAS with other parameters increased the ROC AUC to 0.87 for pVA (0.84;0.89) and 0.82 (0.79;0.84) for cVA. Using mapping with other parameters increased the ROC AUC to 0.88 for pVA (0.86;0.91) and 0.85 (0.83;0.88) for cVA. Multiple mapping measurements showed higher performance at VA prediction than AVAS. However, AVAS is simpler and quicker, so may be preferable for routine clinical practice.

• MeSH
• arteriovenózní zkrat MeSH
• Bayesova věta MeSH
• lidé středního věku MeSH
• lidé MeSH
• prospektivní studie MeSH
• ROC křivka MeSH
• senioři MeSH
• strojové učení * MeSH
• ultrasonografie * metody   MeSH
• Check Tag
• lidé středního věku MeSH
• lidé MeSH
• mužské pohlaví MeSH
• senioři MeSH
• ženské pohlaví MeSH
• Publikační typ
• časopisecké články MeSH
• multicentrická studie MeSH
• práce podpořená grantem MeSH
• srovnávací studie MeSH

BACKGROUND: The arteriovenous access stage (AVAS) classification provides evaluation of upper extremity vessels for vascular access (VA) suitability. It divides patients into classes within three main groups: suitable for native fistula (AVAS1) or prosthetic graft (AVAS2), and patients not suitable for conventional native or prosthetic VA (AVAS3). We validated this system on a prospective dataset. METHODS: A prospective, international observational study (NCT04796558) involved 11 centres from 8 countries. Patient recruitment was from March 2021 to January 2024. Demographic data, risk factors, vessels parameters, VA types, AVAS class and early VA failure were collected. Percentage agreement was used to assess predictive ability of AVAS (comparison of AVAS and created VA) and consistency of AVAS assessment between evaluators. Pearson's Chi-squared test was used for comparison of early failure rate of conventional (predicted by AVAS) and unconventional (not predicted by AVAS) VA. RESULTS: From 1034 enrolled patients, 935 had arteriovenous fistula or graft, 99 patients did not undergo VA creation due opting for alternative renal replacement therapies, experiencing health complications, death or non-compliance. AVAS1 had 91.2%, AVAS2 7.2% and AVAS3 1.6% of patients. Agreement between evaluators was 89%. The most frequently created VAs were radial-cephalic (46%) and brachial-cephalic (27%) fistulae. The accuracy of AVAS versus created access was 79%. In comparison, VA predicted by clinicians versus created access was 62.1%. Inaccuracy of AVAS prediction was more common with higher AVAS classes, and the most common reason for inaccuracy was creation of distal VA despite less favourable anatomy (17%). Patients with unconventional VA had higher early failure rate than patients with conventional VA (20% vs 9.3%, respectively, P = .002). CONCLUSION: AVAS is effective in predicting VA creation, but overall accuracy is reduced at higher AVAS classes when the complexity of decision-making increases and proximal vessels require preservation. When AVAS was followed by clinicians, early failure was significantly decreased.

• Publikační typ
• časopisecké články MeSH