RESUMEN
AIM: The aim of this study was to investigate the potential of novel automated machine learning (AutoML) in vascular medicine by developing a discriminative artificial intelligence (AI) model for the classification of anatomical patterns of peripheral artery disease (PAD). MATERIAL AND METHODS: Random open-source angiograms of lower limbs were collected using a web-indexed search. An experienced researcher in vascular medicine labelled the angiograms according to the most applicable grade of femoropopliteal disease in the Global Limb Anatomic Staging System (GLASS). An AutoML model was trained using the Vertex AI (Google Cloud) platform to classify the angiograms according to the GLASS grade with a multi-label algorithm. Following deployment, we conducted a test using 25 random angiograms (five from each GLASS grade). Model tuning through incremental training by introducing new angiograms was executed to the limit of the allocated quota following the initial evaluation to determine its effect on the software's performance. RESULTS: We collected 323 angiograms to create the AutoML model. Among these, 80 angiograms were labelled as grade 0 of femoropopliteal disease in GLASS, 114 as grade 1, 34 as grade 2, 25 as grade 3 and 70 as grade 4. After 4.5 h of training, the AI model was deployed. The AI self-assessed average precision was 0.77 (0 is minimal and 1 is maximal). During the testing phase, the AI model successfully determined the GLASS grade in 100% of the cases. The agreement with the researcher was almost perfect with the number of observed agreements being 22 (88%), Kappa = 0.85 (95% CI 0.69-1.0). The best results were achieved in predicting GLASS grade 0 and grade 4 (initial precision: 0.76 and 0.84). However, the AI model exhibited poorer results in classifying GLASS grade 3 (initial precision: 0.2) compared to other grades. Disagreements between the AI and the researcher were associated with the low resolution of the test images. Incremental training expanded the initial dataset by 23% to a total of 417 images, which improved the model's average precision by 11% to 0.86. CONCLUSION: After a brief training period with a limited dataset, AutoML has demonstrated its potential in identifying and classifying the anatomical patterns of PAD, operating unhindered by the factors that can affect human analysts, such as fatigue or lack of experience. This technology bears the potential to revolutionize outcome prediction and standardize evidence-based revascularization strategies for patients with PAD, leveraging its adaptability and ability to continuously improve with additional data. The pursuit of further research in AutoML within the field of vascular medicine is both promising and warranted. However, it necessitates additional financial support to realize its full potential.
RESUMEN
OBJECTIVES: This study sought to report short- and long-term efficacy and safety outcomes of retrograde tibioperoneal access for endovascular treatment of chronic total occlusions (CTOs). BACKGROUND: Antegrade recanalization of peripheral CTO is associated with a high failure rate and retrograde puncture of tibioperoneal arteries has been adopted to overcome this limitation. METHODS: Within a retrospective single center cohort study, data of 554 infrainguinal occlusions were acquired in which a retrograde puncture of at least 1 infrapopliteal artery became necessary. Techniques used for access, retrograde lesion crossing, and antegrade treatment modalities were recorded. Next to short-term outcomes, long-term results through 4 years were described using survival analysis. RESULTS: The majority of patients (71.5%) had critical limb ischemia (CLI) and occlusion locations were the femoropopliteal segment (35.9%), infrapopliteal segment (42.6%), or both segments (21.5%). Retrograde access was most commonly performed via the proximal (28%) or distal (34%) anterior tibial artery. Retrograde access could be established in 98.6% and subsequent lesion crossing was successful in 95.1%. Complications due to distal puncture were rare (3.3%). At 1 year, freedom from target lesion revascularization and restenosis were 74.6 ± 3.7% and 67.5 ± 4.4% in claudicants and 62.2 ± 2.8% and 36.0 ± 4.4% in CLI patients, respectively. Late complications at the distal puncture site after a median follow-up time of 234 days comprised 1 stenosis, 7 occlusions, and 3 clinically nonrelevant arteriovenous fistula occurring only in CLI patients. CONCLUSIONS: Retrograde tibioperoneal access is a safe option for recanalization of complex CTOs after a failed antegrade approach. Complications at the puncture site were rare.
