Early death after cancer surgery is higher in low-income and middle-income countries (LMICs) compared with in high-income countries, yet the impact of facility characteristics on early postoperative outcomes is unknown. The aim of this study was to examine the association between hospital infrastructure, resource availability, and processes on early outcomes after cancer surgery worldwide. A multimethods analysis was performed as part of the GlobalSurg 3 study—a multicentre, international, prospective cohort study of patients who had surgery for breast, colorectal, or gastric cancer. The primary outcomes were 30-day mortality and 30-day major complication rates. Potentially beneficial hospital facilities were identified by variable selection to select those associated with 30-day mortality. Adjusted outcomes were determined using generalised estimating equations to account for patient characteristics and country-income group, with population stratification by hospital. Between April 1, 2018, and April 23, 2019, facility-level data were collected for 9685 patients across 238 hospitals in 66 countries (91 hospitals in 20 high-income countries; 57 hospitals in 19 upper-middle-income countries; and 90 hospitals in 27 low-income to lower-middle-income countries). The availability of five hospital facilities was inversely associated with mortality: ultrasound, CT scanner, critical care unit, opioid analgesia, and oncologist. After adjustment for case-mix and country income group, hospitals with three or fewer of these facilities (62 hospitals, 1294 patients) had higher mortality compared with those with four or five (adjusted odds ratio [OR] 3·85 [95% CI 2·58–5·75]; p<0·0001), with excess mortality predominantly explained by a limited capacity to rescue following the development of major complications (63·0% vs 82·7%; OR 0·35 [0·23–0·53]; p<0·0001). Across LMICs, improvements in hospital facilities would prevent one to three deaths for every 100 patients undergoing surgery for cancer. Hospitals with higher levels of infrastructure and resources have better outcomes after cancer surgery, independent of country income. Without urgent strengthening of hospital infrastructure and resources, the reductions in cancer-associated mortality associated with improved access will not be realised. National Institute for Health and Care Research.

The rapid advancement of large language models (LLMs) has generated significant enthusiasm within healthcare, especially in supporting clinical decision-making and patient management. However, inherent limitations including hallucinations, outdated clinical context, and unreliable references pose serious concerns for their clinical utility. Retrieval-Augmented Generation (RAG) models address these limitations by integrating validated, curated medical literature directly into AI workflows, significantly enhancing the accuracy, relevance, and transparency of generated outputs. This viewpoint discusses how RAG frameworks can specifically benefit plastic and reconstructive surgery by providing contextually accurate, evidence-based, and clinically grounded support for decision-making. Potential clinical applications include clinical decision support, efficient evidence synthesis, customizable patient education, informed consent materials, multilingual capabilities, and structured surgical documentation. By querying specialized databases that incorporate contemporary guidelines and literature, RAG models can markedly reduce inaccuracies and increase the reliability of AI-generated responses. However, the implementation of RAG technology demands rigorous database curation, regular updating with guidelines from surgical societies, and ongoing validation to maintain clinical relevance. Addressing challenges related to data privacy, governance, ethical considerations, and user training remains critical for successful clinical adoption. In conclusion, RAG models represent a significant advancement in overcoming traditional LLM limitations, promoting transparency and clinical accuracy with great potential for plastic surgery. Plastic surgeons and researchers are encouraged to explore and integrate these innovative generative AI frameworks to enhance patient care, surgical outcomes, communication, documentation quality, and education.

Artificial intelligence (AI) technologies are rapidly transforming the field of plastic surgery, offering new opportunities for improving patient outcomes through enhanced diagnostic capabilities, personalized treatment planning, and outcome prediction. However, the integration of these technologies into clinical practice requires navigation of complex regulatory frameworks established by the US Food and Drug Administration. This review outlines the current FDA regulatory pathways relevant to AI applications in plastic surgery, including the 510(k), De Novo, and Premarket Approval processes. We discuss the FDA’s Digital Health Center of Excellence, established in 2020, which serves as a central resource for developers of AI-based medical devices. The unique challenges of regulating adaptive AI technologies in plastic surgery are examined, with particular focus on the FDA’s “total product lifecycle” approach and real-world performance monitoring requirements. We highlight the importance of Good Machine Learning Practices and the collaborative framework developed by FDA, National Institute of Standards and Technology, and international regulatory bodies. For plastic surgeons and researchers developing AI tools, we provide practical recommendations, including early FDA engagement, emphasis on algorithm transparency and explainability, and strategies for addressing bias in training datasets. By understanding and effectively navigating these regulatory requirements, plastic surgeons can successfully develop and implement safe, effective AI technologies that advance patient care while maintaining compliance with evolving FDA standards.

Readmissions following deep inferior epigastric perforator (DIEP) flap breast reconstruction represent a significant healthcare burden, yet current risk prediction methods lack precision in identifying high-risk patients. We developed a machine learning model to predict 30-day readmission risk using a large national surgical quality database. This retrospective analysis examined 13,312 DIEP flap procedures from the American College of Surgeons National Surgical Quality Improvement Program database (2016-2022). A stacked machine learning model was developed incorporating patient demographics, comorbidities, operative characteristics, and laboratory values. Model performance was assessed using accuracy, precision, recall, and F1 score. The overall readmission rate was 5.42% (723 patients). The stacked model achieved 88% accuracy and 79% recall for readmission prediction with an area under the receiver operating characteristic curve of 0.8921 (95% CI: 0.853-0.927) on the test set. Key predictors included days from operation until superficial incisional surgical site infection complications, operative time, body mass index, and preoperative albumin. This stacked machine learning approach demonstrates strong predictive capability for post-DIEP flap readmissions, with high sensitivity for identifying at-risk patients. The model's performance suggests clinical utility in preoperative risk stratification and resource allocation. Implementation could enable targeted intervention strategies to potentially reduce readmission rates in high-risk populations.

Hand surgery decision-making requires integration of complex anatomical understanding, diverse patient-specific factors, and nuanced operative techniques. While artificial intelligence (AI), large language models (LLMs), and retrieval-augmented generation (RAG) models have advanced significantly in various fields, no AI-driven clinical decision support systems currently exist for hand surgery. A novel retrieval-enhanced AI large language model specifically tailored for hand surgery was developed, capable of effectively utilizing peer-reviewed published hand surgery literature for clinical decision support in real-time at point of care. An AI clinical decision support system was developed integrating all available open-access 4510 peer-reviewed hand surgery publications from 2000 to 2024 identified through hand surgery-relevant keywords. Documents were processed using a hierarchical pipeline based on the RAPTOR methodology, which breaks down large texts into smaller segments to enhance accurate retrieval. The system was evaluated using 15 standardized clinical queries assessed using automated computational metrics for correctness and semantic similarity to source documents. The AI system demonstrated consistent performance with an average G-Eval correctness score of 0.79, SEM with an average similarity score of 0.75 (range: 0.54-0.86) and average maximum similarity score of 0.80 (range: 0.56-0.91), predominantly at moderate confidence levels. Generated recommendations were contextually appropriate and reliably linked to relevant hand surgery literature, providing accurate and clinically meaningful guidance. The AI system, HandRAG, incorporating RAG and LLM approach offers potential benefits for evidence-based clinical decision support and education in hand surgery.

Background: The advent of general-purpose large language models (LLMs) like ChatGPT (OpenAI, San Francisco, CA) has revolutionized natural language processing, but their applicability in specialized medical fields, like plastic surgery, remains limited because of a lack of domain-specific knowledge. Objectives: This study aims to develop and evaluate PlasticSurgeryGPT, a dedicated LLM fine-tuned on plastic surgery literature, to enhance performance in clinical decision support, surgical education, and research within the field. Methods: A comprehensive dataset of 25,389 plastic surgery research abstracts published between January 1, 2010, and January 1, 2024, was retrieved from PubMed. The abstracts underwent rigorous preprocessing, including text cleaning and tokenization. The authors of this study fine-tuned the pretrained GPT-2 model on this dataset using the PyTorch and HuggingFace frameworks. The performance of PlasticSurgeryGPT was evaluated against the default GPT-2 model using BLEU, METEOR, and ROUGE-1 metrics. Results: Using the fine-tuned model, named PlasticSurgeryGPT, the authors demonstrated substantial improvements over the generic GPT-2 model in capturing the semantic nuances of plastic surgery text. PlasticSurgeryGPT outperformed GPT-2 across BLEU, METEOR, and ROUGE-1 metrics, with scores of 0.135519, 0.583554, and 0.216813, respectively, compared with GPT-2's scores of 0.130179, 0.550498, and 0.215494. Conclusions: PlasticSurgeryGPT represents the first plastic surgery–specific LLM, demonstrating enhanced performance in generating relevant and accurate content compared with a general-purpose model. This work underscores the potential of domain-specific LLMs in improving clinical practice, surgical education, and research in plastic surgery. Future studies should focus on incorporating full-text articles, multimodal data, and larger models to further enhance performance and applicability.