RESUMEN
OBJECTIVE: Peripheral arterial disease (PAD) has been associated with suboptimal treatment, high mortality, and high amputation rates. It is unclear how the COVID-19 (coronavirus disease 2019) pandemic affected this development in a long term context. METHODS: This was a register based, retrospective, nationwide cohort study including patients hospitalised with PAD as a main or secondary diagnosis and amputation surgery between 2012 - 2021 in Germany. Primary endpoints were population wide major and minor amputation rates, in hospital mortality, and in hospital mortality rates. Secondary endpoints were same admission revascularisations and in hospital mortality in case of complications, i.e., failure to rescue (FTR). Pre-pandemic and pandemic trends, focusing on lockdown periods, were analysed. RESULTS: A total of 365 926 patient records with PAD and amputation surgery were analysed. Median patient age was 75 years and 28.8% were female. Overall population wide amputation and in hospital mortality rates (monthly decrease -0.002/100 000, p < .001, and -0.001/100 000, p < .001, respectively) and in hospital mortality rate (8.0% for 2012 - 2014 vs. 6.5% for 2020 - 2021; p < .001) declined between 2012 and 2020. Concurrently, same admission revascularisations increased (41.0% for 2012 - 2014 vs. 47.0% for 2020 - 2021; p < .001), while FTR decreased in a subset of complications (acute ischaemia, major bleeding, compartment syndrome, and mesenterial ischaemia). In the first pandemic lockdown, there was a temporary trend change to higher major amputations rates (0.02/100 000; p < .001) and higher in hospital mortality rates (+0.007/100 000; p < .001), which changed to a decrease as of the second lockdown (-0.03/100 000, p = .034, and -0.010/100 000, p < .001, respectively) in an interrupted time series analysis. There was no statistically significant change in observed amputation rates during lockdowns, while observed in hospital mortality rates decreased by 12.0% in the first lockdown (0.22/100 000 vs. 0.25/100 000; p = .005) compared with reference periods of the two previous years. CONCLUSION: Between 2012 and 2021, pre-pandemic trends toward decreasing population wide overall amputation rates, fewer major amputations, more amputation related revascularisation procedures, and lower in hospital mortality were maintained despite a temporary trend to increased major amputations and in hospital mortality during the first COVID-19-related lockdown in Germany.
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.