The use of Natural Language Processing (NLP) has attracted increased interest in healthcare with various potential applications including identification and extraction of health information, development of chatbots and virtual assistants. The aim of this comprehensive literature review was to provide an overview of NLP applications in vascular surgery, identify current limitations, and discuss future perspectives in the field. The MEDLINE database was searched on April 2023. The database was searched using a combination of keywords to identify studies reporting the use of NLP and chatbots in three main vascular diseases. Keywords used included Natural Language Processing, chatbot, chatGPT, aortic disease, carotid, peripheral artery disease, vascular, and vascular surgery. Given the heterogeneity of study design, techniques, and aims, a comprehensive literature review was performed to provide an overview of NLP applications in vascular surgery. By enabling identification and extraction of information on patients with vascular diseases, such technology could help to analyse data from healthcare information systems to provide feedback on current practice and help in optimising patient care. In addition, chatbots and NLP driven techniques have the potential to be used as virtual assistants for both health professionals and patients. While Artificial Intelligence and NLP technology could be used to enhance care for patients with vascular diseases, many challenges remain including the need to define guidelines and clear consensus on how to evaluate and validate these innovations before their implementation into clinical practice.

Purpose: The performance of self-expanding interwoven nitinol stent (Supera) in femoropopliteal interventions has been proven through trials with short lesions and with relatively low proportion of occlusions. There is limited evidence of Supera stent in long lesions. The aim of this study was to assess the clinical safety and efficiency of the Supera stent in the treatment of long femoropopliteal lesions (Trans-Atlantic Inter-Society Consensus [TASC] C/D) in patients with symptomatic peripheral arterial disease (PAD). Methods: The STELLA SUPERA (STEnting Long de L’Artère fémorale superficielle par le stent métallique Supera) is a prospective, 2-center, single-arm study. Patients with symptomatic (Rutherford stages 2–6) de novo and TASC C/D lesions of the femoropopliteal segment were treated with Supera stent. The primary endpoint was the primary sustained clinical improvement at 12 months. Follow-up included clinical examination, duplex scan, and biplane X-ray up to 24 months. Results: Between December 2016 and October 2018, 48 symptomatic patients with 49 femoropopliteal lesions (TASC D = 32, 65%) were treated. The mean lesion length was 234 ± 123 mm, and 78% were total occlusion. The mean stented lesion length was 273 ± 127 mm. At 12 and 24 months, the primary sustained clinical improvement rate was 87.2% and 79.7%, respectively. The Rutherford category assessment was significantly improved at 24 months compared with baseline (p=0.02). At 24 months, the primary patency and freedom from target lesion revascularization (TLR) rates were 77.9% and 86.9%, respectively. The ankle-brachial pressure index increased from 0.62 ± 0.15 at baseline to 0.93 ± 0.15 at 24 months (p<0.0001). There were no stent fractures at 24 months. Conclusion: The use of Supera stent in long lesions (TASC C/D) is a safe and effective endovascular alternative. These results reinforce the need for randomized clinical trials to assess the value of interwoven stents for long femoropopliteal lesions.

Mean Gradient (MG) elevation can be detected immediately after transcatheter aortic valve implantation (TAVI) or secondarily during follow-up. Comparisons and interactions between these two parameters and their impact on outcomes have not previously been investigated. This study aimed to identify incidence, influence on prognosis, and parameters associated with immediate high post-procedural mean transvalvular gradient (PPMG) and delayed mean gradient increase (6 to 12 months after TAVI, DMGI) in the FRANCE 2 (French Aortic National CoreValve and Edwards 2) registry. The registry includes all consecutive symptomatic patients with severe aortic stenosis who have undergone TAVI. Three groups were analyzed: (1) PPMG < 20 mmHg without DMGI > 10 mmHg (control); (2) PPMG < 20 mmHg with DMGI > 10 mmHg (Group 1); and (3) PPMG ≥ 20 mmHg (Group 2). From January 2010 to January 2012, 4201 consecutive patients were prospectively enrolled in the registry. Controls comprised 2078 patients. In Group 1(n = 131 patients), DMGI exceeded 10 mmHg in 5.6%, and was not associated with greater 4-years mortality than in controls (32.6% vs. 40.1%, p = 0.27). In Group 2 (n = 144 patients), PPMG was at least 20 mmHg in 6.1% and was associated with higher 4-year mortality (48.7% versus 40.1%, p = 0.005). A total of two-thirds of the patients with PPMG ≥ 20 mmHg had MG < 20 mmHg at 1 year, with mortality similar to the controls (39.2% vs. 40.1%, p = 0.73). Patients with PPMG > 20 mmHg 1 year post-TAVI had higher 4-years mortality than the general population of the registry, unlike patients with MG normalization.

Large language models and artificial intelligence (AI) based chatbots have brought new insights in healthcare, but they also raise major concerns. Their applications in vascular surgery have scarcely been investigated to date. This international survey aimed to evaluate the perceptions and feedback from vascular surgeons on the use of AI chatbots in vascular surgery. This international open e-survey comprised 50 items that covered participant characteristics, their perceptions on the use of AI chatbots in vascular surgery, and their user experience. The study was designed in accordance with the Checklist for reporting Results of Internet E-Surveys and was critically reviewed and approved by international members of the European Vascular Research Collaborative (EVRC) prior to distribution. Participation was open to self reported health professionals specialised (or specialising) in vascular surgery, including residents or fellows. Of the 342 individuals who visited the survey page, 318 (93%) agreed to participate; 262 (82.4%) finished the survey and were included in the analysis. Most were consultants or attending physicians (64.1%), most declared not having any training or education related to AI in healthcare (221; 84.4%), and 198 (75.6%) rated their knowledge about the abilities of AI chatbots between average to very poor. Interestingly, 95 participants (36.3%) found that AI chatbots were very useful or somewhat useful in clinical practice at this stage and 229 (87.4%) agreed that they should be systematically validated prior to being used. Eighty participants (30.5%) had specifically tested it for questions related to clinical practice and 59 (73.8%) of them experienced issues or limitations. This international survey provides an overview of perceptions of AI chatbots by vascular surgeons and highlights the need to improve knowledge and training of health professionals to better evaluate, define, and implement their use in vascular surgery.