Enhanced Artificial Intelligence Strategies in Renal Oncology: Iterative Optimization and Comparative Analysis of GPT 3.5 Versus 4.0.

BACKGROUND: The rise of artificial intelligence (AI) in medicine has revealed the potential of ChatGPT as a pivotal tool in medical diagnosis and treatment. This study assesses the efficacy of ChatGPT versions 3.5 and 4.0 in addressing renal cell carcinoma (RCC) clinical inquiries. Notably, fine-tuning and iterative optimization of the model corrected ChatGPT's limitations in this area. METHODS: In our study, 80 RCC-related clinical questions from urology experts were posed three times to both ChatGPT 3.5 and ChatGPT 4.0, seeking binary (yes/no) responses. We then statistically analyzed the answers. Finally, we fine-tuned the GPT-3.5 Turbo model using these questions, and assessed its training outcomes. RESULTS: We found that the average accuracy rates of answers provided by ChatGPT versions 3.5 and 4.0 were 67.08% and 77.50%, respectively. ChatGPT 4.0 outperformed ChatGPT 3.5, with a higher accuracy rate in responses (p < 0.05). By counting the number of correct responses to the 80 questions, we then found that although ChatGPT 4.0 performed better (p < 0.05), both versions were subject to instability in answering. Finally, by fine-tuning the GPT-3.5 Turbo model, we found that the correct rate of responses to these questions could be stabilized at 93.75%. Iterative optimization of the model can result in 100% response accuracy. CONCLUSION: We compared ChatGPT versions 3.5 and 4.0 in addressing clinical RCC questions, identifying their limitations. By applying the GPT-3.5 Turbo fine-tuned model iterative training method, we enhanced AI strategies in renal oncology. This approach is set to enhance ChatGPT's database and clinical guidance capabilities, optimizing AI in this field.

Comparison of Perioperative Outcomes and Complications of Laparoscopic and Robotic Nephroureterectomy Approaches in Patients with Upper-Tract Urothelial Carcinoma.

BACKGROUND: For medical institutions without robotic equipment, it remains uncertain whether laparoscopic radical nephroureterectomy (LNU) can achieve results similar to those of robotic surgery for the treatment of upper tract urothelial carcinoma (UTUC). This meta-analysis aimed to compare the efficacy and safety of robot-assisted radical nephroureterectomy (RANU) with that of LNU using a large sample size of patients. METHODS: A systematic meta-analysis was performed using data (available to May 2022) acquired from multiple scientific databases. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) and Assessing the Methodological Quality of Systematic Reviews (AMSTAR) guidelines, according to the protocols registered with PROSPERO (CRD42021264046), were followed to perform this cumulative analysis. RESULTS: Nine high-quality studies were included in this analysis, considering factors such as operative time (OT), estimated blood loss (EBL), length of hospital stay (LOS), positive surgical margins (PSM), and complications. Statistical indicators revealed no significant differences between the RANU and LNU groups in terms of OT (weighted mean difference [WMD] 29.41, 95% confidence interval [CI] -1.10 to 59.92; p = 0.22), EBL (WMD -55.30, 95% CI -171.14 to 60.54; p = 0.13), LOS (WMD -0.39, 95% CI -1.03 to 0.25; p = 0.12), PSM (odds ratio [OR] 1.22, 95% CI 0.44-3.36; p = 0.17], or complications (OR 0.91, 95% CI 0.49-1.69; p = 0.13). CONCLUSION: The meta-analysis showed that the perioperative and safety indicators of both RANU and LNU were similar and both showed favorable outcomes in UTUC treatment. However, some uncertainties remain in the implementation and selection of lymph nodes for dissection.

Amplifying Chinese physicians' emphasis on patients' psychological states beyond urologic diagnoses with ChatGPT-A multi-center cross-sectional study.

BACKGROUND: Artificial intelligence (AI) technologies, particularly large language models (LLMs), have been widely employed by the medical community. In addressing the intricacies of urology, ChatGPT offers a novel possibility to aid in clinical decision-making. This study aimed to investigate the decision-making ability of LLMs in solving complex urology-related problems and assess its effectiveness in providing psychological support to patients with urological disorders. MATERIALS AND METHODS: This study evaluated the clinical and psychological support capabilities of ChatGPT 3.5 and 4.0 in the field of urology. A total of 69 clinical and 30 psychological questions were posed to the AI models, and their responses were evaluated by both urologists and psychologists. As a control, clinicians from Chinese medical institutions provided responses under closed-book conditions. Statistical analyses were conducted separately for each subgroup. RESULTS: In multiple-choice tests covering diverse urological topics, ChatGPT 4.0, performed comparably to the physician group, with no significant overall score difference. Subgroup analyses revealed variable performance, based on disease type and physician experience, with ChatGPT 4.0 generally outperforming ChatGPT 3.5 and exhibiting competitive results against physicians. When assessing the psychological support capabilities of AI, it is evident that ChatGPT4.0 outperforms ChatGPT3.5 across all urology-related psychological problems. CONCLUSIONS: The performance of LLMs in dealing with standardized clinical problems and providing psychological support has certain advantages over clinicians. AI stands out as a promising tool for potential clinical aid.

Prognostic nutritional index before surgical treatment may serve as a prognostic biomarker for patients with upper tract urothelial carcinoma: A systematic review and meta-analysis.

Objective: This meta-analysis aims to assess whether the prognostic nutritional index (PNI) score before treatment can be an independent biomarker of the prognosis of patients with upper tract urothelial carcinoma (UTUC). Materials and methods: We systematically search PubMed, Embase, Scopus database, and Cochrane Library, and the search time is up to April 2021. Use STATA 16.0 software for data processing and statistical analysis. Results: Six studies, including seven cohorts, were eventually included in our meta-analysis. The meta-analysis results showed that low PNI scores are associated with worse OS (HR: 1.92; 95% CI 1.60 to 2.30; P < 0.01), DFS/RFS/PFS (HR: 1.57; 95% CI 1.33 to 1.85; P < 0.01), and CSS/DSS (HR: 1.79; 95% CI 1.49 to 2.16; P < 0.01), which supported the PNI score as an independent prognostic biomarker for survival outcomes. The subgroup analysis and Begg's test showed that the results were stable. Conclusion: Based on current evidence, this meta-analysis proves that the PNI score of UTUC patients before treatment is an independent prognostic biomarker. It performs well on OS, DFS/RFS/PFS, and CSS/DSS. This conclusion needs to be verified by a prospective cohort study with larger sample size and a more rigorous design. Systematic review registration: [https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42022338503], identifier [CRD42022338503].