Adrian Siu

Background: Surveillance following cancer surgery with curative intent serves the purpose of permitting early detection of recurrent disease in addition to monitoring and management of post‐resection functional sequelae. Although recommendations exist for most primary cancers, in the context of radical or re‐operative surgery such as pelvic exenteration (PE), whether these strategies are appropriate is unclear. The purpose of this review was to evaluate the oncological and functional follow‐up strategies after PE. Methods: A comprehensive literature search was conducted across PubMed, Embase, Medline, and Cochrane databases for studies published between January 2000 and December 2024. Eligible studies reported long‐term oncological and/or functional follow‐up after PE. Studies including other surgical procedures, short‐term (< 12 month) follow‐up, non‐English articles, and case reports were excluded. Data extracted included follow‐up length, frequency, and investigation type. Risk of bias was assessed using the AGREE‐II and ROBINS‐I tools. Results: Forty‐two studies were included, comprising 39 cohort studies and three non‐original articles. Oncological follow‐up, described in 28 studies, frequently included clinic visits every 3–4 months for the first 2–3 years, transitioning to annual reviews after 5 years. Modalities such as tumour markers, CT and MRI imaging, and colonoscopies varied widely. Functional follow‐up was addressed in 19 studies, utilising validated instruments including the EORTC QLQ‐C30 and SF‐36. Most studies lacked standardisation, and no single article comprehensively addressed both oncological and functional aspects. Conclusion: Current follow‐up practices after PE exhibit significant heterogeneity, highlighting the need for standardised protocols. Future research should focus on appropriately sized prospective cohort studies and randomised trials to develop evidence‐based guidelines tailored to the unique needs of this high‐risk patient population.

Aim: Artificial intelligence (AI) chatbots such as Chat Generative Pretrained Transformer‐4 (ChatGPT‐4) have made significant strides in generating human‐like responses. Trained on an extensive corpus of medical literature, ChatGPT‐4 has the potential to augment patient education materials. These chatbots may be beneficial to populations considering a diagnosis of colorectal cancer (CRC). However, the accuracy and quality of patient education materials are crucial for informed decision‐making. Given workforce demands impacting holistic care, AI chatbots can bridge gaps in CRC information, reaching wider demographics and crossing language barriers. However, rigorous evaluation is essential to ensure accuracy, quality and readability. Therefore, this study aims to evaluate the efficacy, quality and readability of answers generated by ChatGPT‐4 on CRC, utilizing patient‐style question prompts.Method: To evaluate ChatGPT‐4, eight CRC‐related questions were derived using peer‐reviewed literature and Google Trends. Eight colorectal surgeons evaluated AI responses for accuracy, safety, appropriateness, actionability and effectiveness. Quality was assessed using validated tools: the Patient Education Materials Assessment Tool (PEMAT‐AI), modified DISCERN (DISCERN‐AI) and Global Quality Score (GQS). A number of readability assessments were measured including Flesch Reading Ease (FRE) and the Gunning Fog Index (GFI).Results: The responses were generally accurate (median 4.00), safe (4.25), appropriate (4.00), actionable (4.00) and effective (4.00). Quality assessments rated PEMAT‐AI as ‘very good’ (71.43), DISCERN‐AI as ‘fair’ (12.00) and GQS as ‘high’ (4.00). Readability scores indicated difficulty (FRE 47.00, GFI 12.40), suggesting a higher educational level was required.Conclusion: This study concludes that ChatGPT‐4 is capable of providing safe but nonspecific medical information, suggesting its potential as a patient education aid. However, enhancements in readability through contextual prompting and fine‐tuning techniques are required before considering implementation into clinical practice.

Objective Approximately 30% of Australians reside in rural communities, where accessing healthcare facilities can be challenging due to considerable distance. This can result in disparities in healthcare equity, subsequently increasing risk of adverse health outcomes, delayed diagnosis, and diminished quality of life. These geographical constraints may be exacerbated in advanced cancers for which treatment is available only at selected centres with appropriate expertise. The aim of this study was therefore to explore the impact of patient residence on experience and healthcare utilisation following cytoreductive surgery (CRS) and hyperthermic intraperitoneal chemotherapy (HIPEC). Methods A retrospective study examined consecutive CRS and HIPEC patients at Royal Prince Alfred hospital from 2017 to 2022. Patients were stratified as metropolitan and regional based on their postcode. Demographics, experiential, and healthcare utilisation data were collected at multiple time points. Statistical analysis included chi-squared and T-tests. Results Of the 317 participants, 228 (72%) were from metropolitan and 89 (28%) from regional areas. Regional patients tended to rate their hospital experience as ‘very good’ (P = 0.016). Metropolitan patients were more compliant with surgical follow-up (P < 0.001). No other differences were observed in patient characteristics, experience or healthcare utilisation. Conclusions The geographical location of patients undergoing CRS and HIPEC for peritoneal malignancies at a major tertiary referral centre did not significantly influence their experience or healthcare utilisation outcomes. Future studies should evaluate long-term healthcare service utilisation or the ramifications of reduced follow-up on recurrence and survival, which will contribute to a deeper understanding of resource allocation in metropolitan and regional Australia, and illuminate its impact on clinical outcomes.

Background: Artificial intelligence (AI) chatbots, such as ChatGPT, have made significant progress. These chatbots, particularly popular among health care professionals and patients, are transforming patient education and disease experience with personalized information. Accurate, timely patient education is crucial for informed decision-making, especially regarding prostate-specific antigen screening and treatment options. However, the accuracy and reliability of AI chatbots’ medical information must be rigorously evaluated. Studies testing ChatGPT’s knowledge of prostate cancer are emerging, but there is a need for ongoing evaluation to ensure the quality and safety of information provided to patients. Objective: This study aims to evaluate the quality, accuracy, and readability of ChatGPT-4’s responses to common prostate cancer questions posed by patients. Methods: Overall, 8 questions were formulated with an inductive approach based on information topics in peer-reviewed literature and Google Trends data. Adapted versions of the Patient Education Materials Assessment Tool for AI (PEMAT-AI), Global Quality Score, and DISCERN-AI tools were used by 4 independent reviewers to assess the quality of the AI responses. The 8 AI outputs were judged by 7 expert urologists, using an assessment framework developed to assess accuracy, safety, appropriateness, actionability, and effectiveness. The AI responses’ readability was assessed using established algorithms (Flesch Reading Ease score, Gunning Fog Index, Flesch-Kincaid Grade Level, The Coleman-Liau Index, and Simple Measure of Gobbledygook [SMOG] Index). A brief tool (Reference Assessment AI [REF-AI]) was developed to analyze the references provided by AI outputs, assessing for reference hallucination, relevance, and quality of references. Results: The PEMAT-AI understandability score was very good (mean 79.44%, SD 10.44%), the DISCERN-AI rating was scored as “good” quality (mean 13.88, SD 0.93), and the Global Quality Score was high (mean 4.46/5, SD 0.50). Natural Language Assessment Tool for AI had pooled mean accuracy of 3.96 (SD 0.91), safety of 4.32 (SD 0.86), appropriateness of 4.45 (SD 0.81), actionability of 4.05 (SD 1.15), and effectiveness of 4.09 (SD 0.98). The readability algorithm consensus was “difficult to read” (Flesch Reading Ease score mean 45.97, SD 8.69; Gunning Fog Index mean 14.55, SD 4.79), averaging an 11th-grade reading level, equivalent to 15- to 17-year-olds (Flesch-Kincaid Grade Level mean 12.12, SD 4.34; The Coleman-Liau Index mean 12.75, SD 1.98; SMOG Index mean 11.06, SD 3.20). REF-AI identified 2 reference hallucinations, while the majority (28/30, 93%) of references appropriately supplemented the text. Most references (26/30, 86%) were from reputable government organizations, while a handful were direct citations from scientific literature. Conclusions: Our analysis found that ChatGPT-4 provides generally good responses to common prostate cancer queries, making it a potentially valuable tool for patient education in prostate cancer care. Objective quality assessment tools indicated that the natural language processing outputs were generally reliable and appropriate, but there is room for improvement.

Background: Rural Australians typically encounter disparities in healthcare access leading to adverse health outcomes, delayed diagnosis and reduced quality of life (QoL) parameters. These disparities may be exacerbated in advanced malignancies, where treatment is only available at highly specialised centres with appropriate multidisciplinary expertise. Thus, this study aims to determine the association between patient residence on oncological, surgical and QoL outcomes following cytoreductive surgery (CRS) and hyperthermic intra-peritoneal chemotherapy (HIPEC). Methods: A retrospective analysis was conducted on consecutive patients undergoing CRS and HIPEC at Royal Prince Alfred Hospital from January 2017 to March 2022. On the basis of their postcode of residence, patients were stratified into metropolitan and regional groups. Data encompassing demographics, oncological, surgical and QoL outcomes were compared. Statistical analysis included chi-square test, t-tests and Kaplan–Meier survival curves. Results: Among the 317 patients, 228 (72%) were categorised as metropolitan and 89 (28%) as regional. Metropolitan patients presented higher rates of recurrence (61.8% versus 40.0%, p = 0.014) and shorter overall mean survival [3.8 years (95% CI: 3.44–4.09) versus 4.2 years (95% CI: 3.76–4.63), p = 0.019] compared with regional patients. No other statistically significant differences were observed in oncological, surgical and QoL outcomes. Conclusions: Most oncological, surgical and QoL parameters did not differ by geographical location of patients undergoing CRS and HIPEC for peritoneal malignancies at a high-volume quaternary referral centre. Observed differences in recurrence and survival may be attributed to the selective nature of surgical referrals and variable follow-up patterns. Future research should focus on characterising referral pathways and its influence on post-operative outcomes.

BACKGROUND Artificial intelligence (AI) chatbots, such as ChatGPT, have made significant progress. These chatbots, particularly popular among health care professionals and patients, are transforming patient education and disease experience with personalized information. Accurate, timely patient education is crucial for informed decision-making, especially regarding prostate-specific antigen screening and treatment options. However, the accuracy and reliability of AI chatbots’ medical information must be rigorously evaluated. Studies testing ChatGPT’s knowledge of prostate cancer are emerging, but there is a need for ongoing evaluation to ensure the quality and safety of information provided to patients. OBJECTIVE This study aims to evaluate the quality, accuracy, and readability of ChatGPT-4’s responses to common prostate cancer questions posed by patients. METHODS Overall, 8 questions were formulated with an inductive approach based on information topics in peer-reviewed literature and Google Trends data. Adapted versions of the Patient Education Materials Assessment Tool for AI (PEMAT-AI), Global Quality Score, and DISCERN-AI tools were used by 4 independent reviewers to assess the quality of the AI responses. The 8 AI outputs were judged by 7 expert urologists, using an assessment framework developed to assess accuracy, safety, appropriateness, actionability, and effectiveness. The AI responses’ readability was assessed using established algorithms (Flesch Reading Ease score, Gunning Fog Index, Flesch-Kincaid Grade Level, The Coleman-Liau Index, and Simple Measure of Gobbledygook [SMOG] Index). A brief tool (Reference Assessment AI [REF-AI]) was developed to analyze the references provided by AI outputs, assessing for reference hallucination, relevance, and quality of references. RESULTS The PEMAT-AI understandability score was very good (mean 79.44%, SD 10.44%), the DISCERN-AI rating was scored as “good” quality (mean 13.88, SD 0.93), and the Global Quality Score was high (mean 4.46/5, SD 0.50). Natural Language Assessment Tool for AI had pooled mean accuracy of 3.96 (SD 0.91), safety of 4.32 (SD 0.86), appropriateness of 4.45 (SD 0.81), actionability of 4.05 (SD 1.15), and effectiveness of 4.09 (SD 0.98). The readability algorithm consensus was “difficult to read” (Flesch Reading Ease score mean 45.97, SD 8.69; Gunning Fog Index mean 14.55, SD 4.79), averaging an 11th-grade reading level, equivalent to 15- to 17-year-olds (Flesch-Kincaid Grade Level mean 12.12, SD 4.34; The Coleman-Liau Index mean 12.75, SD 1.98; SMOG Index mean 11.06, SD 3.20). REF-AI identified 2 reference hallucinations, while the majority (28/30, 93%) of references appropriately supplemented the text. Most references (26/30, 86%) were from reputable government organizations, while a handful were direct citations from scientific literature. CONCLUSIONS Our analysis found that ChatGPT-4 provides generally good responses to common prostate cancer queries, making it a potentially valuable tool for patient education in prostate cancer care. Objective quality assessment tools indicated that the natural language processing outputs were generally reliable and appropriate, but there is room for improvement.

Background: Appendicitis is a common surgical condition that requires urgent medical attention. Recent advancements in artificial intelligence and large language processing, such as ChatGPT, have demonstrated potential in supporting healthcare management and scientific research. This study aims to evaluate the accuracy and comprehensiveness of ChatGPT's knowledge on appendicitis management.Methods: Six questions related to appendicitis management were created by experienced RACS qualified general surgeons to assess ChatGPT's ability to provide accurate information. The criteria of ChatGPT answers' accuracy were compared with current healthcare guidelines for appendicitis and subjective evaluation by two RACS qualified General Surgeons. Additionally, ChatGPT was then asked to provide five high level evidence references to support its responses.Results: ChatGPT provided clinically relevant information on appendicitis management, however, was inconsistent in doing so and often provided superficial information. Further to this, ChatGPT encountered difficulties in generating relevant references, with some being either non‐existent or incorrect.Conclusion: ChatGPT has the potential to provide timely and comprehensible medical information on appendicitis management to laypersons. However, its issue of inaccuracy in information and production of non‐existent or erroneous references presents a challenge for researchers and clinicians who may inadvertently employ such information in their research or healthcare. Therefore, clinicians should exercise caution when using ChatGPT for these purposes.

Background: The growing interest in artificial intelligence (AI) has spurred an increase in the availability of Large Language Models (LLMs) in surgical education. These LLMs hold the potential to augment medical curricula for future healthcare professionals, facilitating engagement in remote learning experiences, and assisting in personalised student feedback. Objectives: To evaluate the ability of LLMs to assist junior doctors in providing advice for common ward-based surgical scenarios with increasing complexity. Methods: Utilising an instrumental case study approach, this study explored the potential of LLMs by comparing the responses of the ChatGPT-4, BingAI and BARD. LLMs were prompted by 3 common ward-based surgical scenarios and tasked with assisting junior doctors in clinical decision-making. The outputs were assessed by a panel of two senior surgeons with extensive experience in AI and education, qualitatively utilising a Likert scale on their accuracy, safety, and effectiveness to determine their viability as a synergistic tool in surgical education. A quantitative assessment of their reliability and readability was conducted using the DISCERN score and a set of reading scores, including the Flesch Reading Ease Score, Flesch-Kincaid Grade Level, and Coleman-Liau index. Results: BARD proved superior in readability, with Flesch Reading Ease Score 50.13 (± 5.00), Flesch-Kincaid Grade Level 9.33 (± 0.76), and Coleman-Liau index 11.67 (± 0.58). ChatGPT-4 outperformed BARD and BingAI, with the highest DISCERN score of 71.7 (± 2.52). Using a Likert scale-based framework, the surgical expert panel further affirmed that the advice provided by the ChatGPT-4 was suitable and safe for first-year interns and residents. A t-test showed statistical significance in reliability among all three AIs (P < 0.05) and readability only between the ChatGPT-4 and BARD. This study underscores the potential for LLM integration in surgical education, particularly ChatGPT, in the provision of reliable and accurate information. Conclusions: This study highlighted the potential of LLM, specifically ChatGPT-4, as a valuable educational resource for junior doctors. The findings are limited by the potential of non-generalizability of the use of junior doctors' simulated scenarios. Future work should aim to optimise learning experiences and better support surgical trainees. Particular attention should be paid to addressing the longitudinal impact of LLMs, refining AI models, validating AI content, and exploring technological amalgamations for improved outcomes.

Background: Peritoneal malignancies are challenging cancers to manage. While cytoreductive surgery and hyperthermic intraperitoneal chemotherapy (CRS and HIPEC), may offer a cure, it is a radical procedure associated with significant morbidity. Pre‐emptive identification of deconditioned patients for optimization may mitigate surgical risk. However, the difficulty lies in identifying a cost‐effective predictive tool. Recently, there has been interest in sarcopenia, which may occur due to malignancy. The purpose of this study was to assess the utility of sarcopenia at predicting post‐operative outcomes.Methods: A quaternary‐centre retrospective study of CRS and HIPEC patients (2017–2020), were conducted to determine the association between pre‐operative sarcopenia on oncological (peritoneal carcinomatosis index (PCI)) and surgical outcomes (complications). Sarcopenia from lumbar CT‐images were measured using Slice‐o‐matic™. Statistical differences were analysed using Mann–Whitney U and Chi‐squared test.Results: Cohort analysis (n = 94) found 40% had sarcopenia, majority were female (53.2%), and average age of 55 years. The major pathologies was colorectal cancer (n = 39, 41.5%), appendix adenocarcinoma (n = 21, 22.3%), and pseudomyxoma peritonei (PMP) (n = 19, 20.2%). Sarcopenia was associated with decreased weight, 72.7 versus 82.2 kg (P = 0.014) and shorter survival, 1.4 versus 2.1 years (95% CI, 1.09–3.05, P = 0.032). Median PCI (excluding PMP) was 11 (6–18) and median PCI (only PMP) was 25 (11–32). Post‐operatively, sarcopenia patients experienced more complications (72.5% vs. 64.8%, P = 0.001).Conclusion: Pre‐emptive identification of sarcopenia may be a useful prognostic indicator and predictor of post‐operative outcomes in CRS and HIPEC. For oncological patients, sarcopenia may be an indicator of patients requiring targeted pre‐operative rehabilitation, or advanced disease requiring further treatment.