ChatGPT and generative AI in urology and surgery-A narrative review.

Introduction: ChatGPT (generative pre-trained transformer [GPT]), developed by OpenAI, is a type of generative artificial intelligence (AI) that has been widely utilised since its public release. It orchestrates an advanced conversational intelligence, producing sophisticated responses to questions. ChatGPT has been successfully demonstrated across several applications in healthcare, including patient management, academic research and clinical trials. We aim to evaluate the different ways ChatGPT has been utilised in urology and more broadly in surgery. Methods: We conducted a literature search of the PubMed and Embase electronic databases for the purpose of writing a narrative review and identified relevant articles on ChatGPT in surgery from the years 2000 to 2023. A PRISMA flow chart was created to highlight the article selection process. The search terms 'ChatGPT' and 'surgery' were intentionally kept broad given the nascency of the field. Studies unrelated to these terms were excluded. Duplicates were removed. Results: Multiple papers have been published about novel uses of ChatGPT in surgery, ranging from assisting in administrative tasks including answering frequently asked questions, surgical consent, writing operation reports, discharge summaries, grants, journal article drafts, reviewing journal articles and medical education. AI and machine learning has also been extensively researched in surgery with respect to patient diagnosis and predicting outcomes. There are also several limitations with the software including artificial hallucination, bias, out-of-date information and patient confidentiality. Conclusion: The potential of ChatGPT and related generative AI models are vast, heralding the beginning of a new era where AI may eventually become integrated seamlessly into surgical practice. Concerns with this new technology must not be disregarded in the urge to hasten progression, and potential risks impacting patients' interests must be considered. Appropriate regulation and governance of this technology will be key to optimising the benefits and addressing the intricate challenges of healthcare delivery and equity.

Imaging in Renal Cell Carcinoma Detection.

INTRODUCTION: Imaging in renal cell carcinoma (RCC) is a constantly evolving landscape. The incidence of RCC has been rising over the years with the improvement in image quality and sensitivity in imaging modalities resulting in "incidentalomas" being detected. We aim to explore the latest advances in imaging for RCC. METHODS: A literature search was conducted using Medline and Google Scholar, up to May 2024. For each subsection of the manuscript, a separate search was performed using a combination of the following key terms "renal cell carcinoma", "renal mass", "ultrasound", "computed tomography", "magnetic resonance imaging", "18F-Fluorodeoxyglucose PET/CT", "prostate-specific membrane antigen PET/CT", "technetium-99m sestamibi SPECT/CT", "carbonic anhydrase IX", "girentuximab", and "radiomics". Studies that were not in English were excluded. The reference lists of selected manuscripts were checked manually for eligible articles. RESULTS: The main imaging modalities for RCC currently are ultrasound, computed tomography (CT) and magnetic resonance imaging (MRI). Contrast-enhanced US (CEUS) has emerged as an alternative to CT or MRI for the characterisation of renal masses. Furthermore, there has been significant research in molecular imaging in recent years, including FDG PET, PSMA PET/CT, 99mTc-Sestamibi, and anti-carbonic anhydrase IX monoclonal antibodies/peptides. Radiomics and the use of AI in radiology is a growing area of interest. CONCLUSIONS: There will be significant change in the field of imaging in RCC as molecular imaging becomes increasingly popular, which reflects a shift in management to a more conservative approach, especially for small renal masses (SRMs). There is the hope that the improvement in imaging will result in less unnecessary invasive surgeries or biopsies being performed for benign or indolent renal lesions.

Analysis of potential clinical management issues in unreported mortality data from an Australian health service.

BACKGROUND: We have previously reported incomplete data submission to the Victorian Audit of Surgical Mortality (VASM) by a large health service. We have further examined the source health service clinical data to assess whether any clinical management issues (CMI) occurred and should have been reported. METHODS: The previous study identified 46 deaths that should have been reported to VASM. The hospital records of these patients were further analysed. Data recorded included the patient's age, gender, admission type and clinical course. Any potential clinical management issues were recorded and classified using the VASM definitions (area of consideration or concern, adverse event). RESULTS: Median age of the deceased patients was 72 (range 17-94), with 17 (37%) being female. Patients were under the care of nine different specialties with general surgery being the most common (18/46). Only four (8.7%) of the cases were electively admitted. 17 (37%) patients had at least one CMI with 10 (21.7%) classified as adverse events. Most deaths were not considered preventable. CONCLUSION: The proportion of CMI in the unreported deaths was consistent with the previously reported VASM data, however current findings show a high percentage of adverse events. The underreporting may be due to inexperienced medical staff or coders, poor quality notes or confusion about what should be reported. These findings reinforce the importance of data collection and reporting at the health service level, and a number of important lessons and opportunities to improve patient safety have been lost.