Artificial Intelligence Evidence-Based Current Status and Potential for Lower Limb Vascular Management

Humans use tools: From handcrafted tools to artificial intelligence

Human evolution is instrument based. Humans created tools >2 million years ago to aid them in hunting, gathering, and defense, allowing them to build shelters and farms and transport goods and people over great distances. Written records preserved our knowledge and experiences for future generations. Instruments have greatly influenced surgery. Knives and needles were used by ancient surgeons, whereas lasers, endoscopes, and robotics are used today. Artificial intelligence (AI) is the future of surgical instruments, increasing precision through self-evaluation, but development remains in the early stages. Vascular surgery research and practice has used AI-powered systems that can track patient progress and identify vascular disease risk using deep learning and pattern recognition, as well as improved radiological interpretation of vascular imaging and medicine. Using insights and data-driven recommendations, AI-powered decision support systems could help surgeons in enhancing patient outcomes by providing guidance to navigate complex anatomy and identify anomalies. Robots can assist surgeons in performing risky, complex operations with optimal outcomes. Human expertise and AI will revolutionize surgery, enhancing its safety, precision, and efficacy. Surgical applications of AI raise numerous questions and debates. Data must be representative of all populations, data management must protect the privacy of patients and physicians, and the AI decision-making process must be clarified to produce validated models that can be used ethically. Vascular surgeons' judgment and experience should not be automated. Instead, AI should contribute to the efficiency and effectiveness of vascular surgeons. Human clinicians must interpret AI-generated data, use clinical judgment, and build empathy, compassion, and shared decision-making to sustain doctor-patient relationships. From simple tools to complex modern technologies, the history of tools reveals human creativity. Our environment has been altered by technology, ensuring our survival and growth. AI is still a half-told tale that will inspire and amaze us for years to come.

Artificial intelligence-assisted dermatology diagnosis: From unimodal to multimodal

Artificial Intelligence (AI) is progressively permeating medicine, notably in the realm of assisted diagnosis. However, the traditional unimodal AI models, reliant on large volumes of accurately labeled data and single data type usage, prove insufficient to assist dermatological diagnosis. Augmenting these models with text data from patient narratives, laboratory reports, and image data from skin lesions, dermoscopy, and pathologies could significantly enhance their diagnostic capacity. Large-scale pre-training multimodal models offer a promising solution, exploiting the burgeoning reservoir of clinical data and amalgamating various data types. This paper delves into unimodal models' methodologies, applications, and shortcomings while exploring how multimodal models can enhance accuracy and reliability. Furthermore, integrating cutting-edge technologies like federated learning and multi-party privacy computing with AI can substantially mitigate patient privacy concerns in dermatological datasets and further fosters a move towards high-precision self-diagnosis. Diagnostic systems underpinned by large-scale pre-training multimodal models can facilitate dermatology physicians in formulating effective diagnostic and treatment strategies and herald a transformative era in healthcare.

Computer Science meets Vascular Surgery: Keeping a pulse on artificial intelligence

Artificial intelligence (AI)-based technologies have garnered interest across a range of disciplines in the past several years, with an even more recent interest in various health care fields, including Vascular Surgery. AI offers a unique ability to analyze health data more quickly and efficiently than could be done by humans alone and can be used for clinical applications such as diagnosis, risk stratification, and follow-up, as well as patient-used applications to improve both patient and provider experiences, mitigate health care disparities, and individualize treatment. As with all novel technologies, AI is not without its risks and carries with it unique ethical considerations that will need to be addressed before its broad integration into health care systems. AI has the potential to revolutionize the way care is provided to patients, including those requiring vascular care.

Diffusion-Weighted Imaging Prior to Percutaneous Sclerotherapy of Venous Malformations—Proof of Concept Study for Prediction of Clinical Outcome

Prediction of response to percutaneous sclerotherapy in patients with venous malformations (VM) is currently not possible with baseline clinical or imaging characteristics. This prospective single-center study aimed to predict treatment outcome of percutaneous sclerotherapy as measured by quality of life (QoL) by using radiomic analysis of diffusion-weighted (dw) magnetic resonance imaging (MRI) before and after first percutaneous sclerotherapy. In all patients (n = 16) pre-interventional (PRE-) and delta (DELTA-) radiomic features (RF) were extracted from dw-MRI before and after first percutaneous sclerotherapy with ethanol gel or polidocanol foam, while QoL was assessed using the Toronto Extremity Salvage Score (TESS) and the 36-Item Short Form Survey (SF-36) health questionnaire. For selecting features that allow differentiation of clinical response, a stepwise dimension reduction was performed. Logistic regression models were fitted and selected PRE-/DELTA-RF were tested for their predictive value. QoL improved significantly after percutaneous sclerotherapy. While no common baseline patient characteristics were able to predict response to percutaneous sclerotherapy, the radiomics signature of VMs (independent PRE/DELTA-RF) revealed high potential for the prediction of clinical response after percutaneous sclerotherapy. This proof-of-concept study provides first evidence on the potential predictive value of (delta) radiomic analysis from diffusion-weighted MRI for Quality-of-Life outcome after percutaneous sclerotherapy in patients with venous malformations.