Mohs micrographic surgery (MMS) is considered the gold standard for difficult‐to‐treat malignant skin tumors, whose incidence is on the rise. Currently, there are no agreed upon classifiers to predict complex MMS procedures. Such classifiers could enable better patient scheduling, reduce staff burnout and improve patient education. Our goal was to create an accessible and interpretable classifier(s) that would predict complex MMS procedures. A retrospective study applying machine learning models to a dataset of 8644 MMS procedures to predict complex wound reconstruction and number of MMS procedure stages. Each procedure record contained preoperative data on patient demographics, estimated clinical tumor size prior to surgery (mean diameter), tumor characteristics and tumor location, and postoperative procedure outcomes included the wound reconstruction technique and the number of MMS stages performed in order to achieve tumor‐free margins. For the number of stages complexity classification model, the area under the receiver operating characteristic curve (AUROC) was 0.79 (good performance), with model accuracy of 77%, sensitivity of 71%, specificity of 77%, positive prediction value (PPV) of 14% and negative prediction value (NPV) of 98%. The results for the wound reconstruction complexity classification model were 0.84 for the AUROC (excellent performance), with model accuracy of 75%, sensitivity of 72%, specificity of 76%, PPV of 39% and NPV of 93%. The ML models we created predict the complexity of the components that comprise the MMS procedure. Using the accessible and interpretable tool we provide online, clinicians can improve the management and well‐being of their patients. Study limitation is that models are based on data generated from a single surgeon.

Background: It has been demonstrated that luteal phase support (LPS) is crucial in filling the gap between the disappearance of exogenously administered hCG for ovulation triggering and the initiation of secretion of endogenous hCG from the implanting conceptus. LPS has a pivotal role of in establishing and maintaining in vitro fertilization (IVF) pregnancies. Over the last decade, a plethora of studies bringing new information on many aspects of LPS have been published. Due to lack of consent between researchers and a dearth of robust evidence-based guidelines, we wanted to make the leap from the bench to the bedside, what are the common LPS practices in fresh IVF cycles compared to current evidence and guidelines? How has expert opinion changed over 10 years in light of recent literature? Methods: Over a decade (2009–2019), we conducted 4 web-based surveys on a large IVF-specialist website on common LPS practices and controversies. The self-report, multiple-choice surveys quantified results by annual IVF cycles. Results: On average, 303 IVF units responded to each survey, representing, on average, 231,000 annual IVF cycles. Most respondents in 2019 initiated LPS on the day of, or the day after egg collection (48.7 % and 36.3 %, respectively). In 2018, 72 % of respondents administered LPS for 8–10 gestational weeks, while in 2019, 65 % continued LPS until 10–12 weeks. Vaginal progesterone is the predominant delivery route; its utilization rose from 64 % of cycles in 2009 to 74.1 % in 2019. Oral P use has remained negligible; a slight increase to 2.9 % in 2019 likely reflects dydrogesterone’s introduction into practice. E2 and GnRH agonists are rarely used for LPS, as is hCG alone, limited by its associated risk of ovarian hyperstimulation syndrome (OHSS). Conclusions: Our Assisted reproductive technology (ART)-community survey series gave us insights into physician views on using progesterone for LPS. Despite extensive research and numerous publications, evidence quality and recommendation levels are surprisingly low for most topics. Clinical guidelines use mostly low-quality evidence. There is no single accepted LPS protocol. Our study highlights the gaps between science and practice and the need for further LPS research, with an emphasis on treatment individualization.

Background: Breast reduction is a common procedure with growing rates in the United States of America, aimed at alleviating the physical and psychological burdens of macromastia. Despite high success rates, it carries a risk of complications, with incidence rates ranging from 6.2% to 43%. Objectives: The authors developed a machine learning model using gradient-boosting decision trees to predict severe breast reduction complications up to 30 days following surgery requiring inpatient care. Methods: This retrospective study included 322 cases of breast reduction surgery performed at the Tel Aviv Medical Center from 2017 to 2024. Model performance was evaluated using 5-fold cross-validation, and key metrics such as area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity were reported. An interpretability tool was also created to visualize complication risks based on clinical features. Results: Severe complications occurred in 7.4% of cases. Key predictive factors included specimen weight, SN-N distance, and liposuction volume. The model achieved an area under the receiver operating characteristic curve (AUC-ROC) of 0.83, with an accuracy of 0.93 and a negative predictive value (NPV) of 0.95. The interpretability tool clearly visualized complication risks, aiding preoperative counseling. Conclusions: This is the first study to use artificial intelligence (AI) to predict severe complications in breast reduction surgery. In this study, the AI model, with an AUC-ROC of 0.83 and NPV of 0.95, offers a reliable tool for surgical planning and patient education. Further validation across diverse populations is recommended to confirm its clinical utility. Level of Evidence: 4 (Risk):

AI is increasingly integrated into reproductive medicine, particularly in in vitro fertilization (IVF) and embryology. This study presents a comparative analysis of two global surveys conducted among IVF specialists and embryologists in 2022 (n=383) and 2025 (n=171) to assess the adoption, application, and perceptions of AI-based tools. In 2022, 24.8% of respondents used AI, primarily for embryo selection (86.3% of AI users), with strong interest in AI for sperm selection (87.5%) and embryo annotation (92.4%). By 2025, AI usage increased to 53.22% (regular or occasional use, n=91), with 21.64% (n=37) reporting regular use and 31.58% (n=54) reporting occasional use, with embryo selection remaining the dominant application (32.75%). Familiarity with AI increased notably, with 60.82% reporting at least moderate familiarity in 2025, compared to indirect evidence of lower familiarity in 2022. Key barriers to adoption included cost (38.01%) and lack of training (33.92%) in 2025, while ethical concerns and over-reliance on technology were significant risks (59.06% cited over-reliance). Both surveys highlighted optimism for AI’s potential, with 91.6% (n=351) in 2022 and 38.6% (n=66) in 2025 identifying embryo selection as a key benefit of AI. Additionally, 83.62% (n=143) of 2025 respondents were likely to invest in AI within 1–5 years, indicating strong interest in future adoption. These findings suggest a gradual increase in AI adoption, tempered by practical and ethical challenges, with implications for training, cost management, and ethical frameworks in reproductive medicine.

The global demand for cosmetic procedures is accelerating, with over 1.6 million aesthetic surgical procedures performed in the US in 2023. Concurrently, AI is transforming surgical practice through advanced analytics, predictive modeling, and computer vision. Cosmetic surgery, characterized by subjective outcomes and limited standardized metrics, presents a unique opportunity for AI integration to enhance precision, objectivity, and patient communication. Following PRISMA 2020 guidelines, we systematically searched MEDLINE/PubMed, Embase, and the Cochrane Library (January 2020−July 2025) for studies applying AI, machine learning, deep learning, computer vision, or large language models to cosmetic or aesthetic procedures. Eligible designs included randomized controlled trials, observational studies, diagnostic accuracy studies, feasibility studies, and prediction model development. Two reviewers independently screened titles/abstracts, assessed full texts, extracted data, and evaluated risk of bias using ROBINS-I for non-randomized studies. Of 3941 records, 38 met the inclusion criteria. AI applications spanned preoperative planning (predictive risk modeling, 3D outcome simulation), intraoperative guidance (augmented reality overlays), and postoperative monitoring (smartphone-based complication detection, objective aesthetic scoring). Benefits included improved patient–surgeon communication, enhanced risk stratification, and standardized outcome measurement. However, most studies were early-phase, with limited external validation, heterogeneous datasets, and inconsistent outcome metrics. Risk of bias was moderate to serious in most studies. AI in cosmetic surgery shows significant potential but remains in early clinical adoption. Progress requires multicenter validation, standardized datasets, explainable algorithms, and clear regulatory frameworks. Large language model—driven tools may accelerate development and integration, provided ethical, equitable, and patient-centered principles guide implementation.