Category Ranking

98%

Total Visits

921

Avg Visit Duration

2 minutes

Citations

20

Article Abstract

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.

Download full-text PDF

Source
http://dx.doi.org/10.1245/s10434-024-15107-0DOI Listing

Publication Analysis

Top Keywords

artificial intelligence
8
iterative optimization
8
chatgpt versions
8
chatgpt
7
enhanced artificial
4
intelligence strategies
4
strategies renal
4
renal oncology
4
oncology iterative
4
optimization comparative
4

Similar Publications

Toward Human-Centered Artificial Intelligence for Users' Digital Well-Being: Systematic Review, Synthesis, and Future Directions.

JMIR Hum Factors

September 2025

Seidenberg School of Computer Science and Information Systems, Pace University, New York City, NY, United States.

Background: As information and communication technologies and artificial intelligence (AI) become deeply integrated into daily life, the focus on users' digital well-being has grown across academic and industrial fields. However, fragmented perspectives and approaches to digital well-being in AI-powered systems hinder a holistic understanding, leaving researchers and practitioners struggling to design truly human-centered AI systems.

Objective: This paper aims to address the fragmentation by synthesizing diverse perspectives and approaches to digital well-being through a systematic literature review.

View Article and Find Full Text PDF

Parasitology of the twenty-first century: are we moving in the right direction?

J Med Microbiol

September 2025

Alberta Precision Laboratories Public Health Lab, Edmonton, Alberta, Canada.

For thousands of years, parasitic infections have represented a constant challenge to human health. Despite constant progress in science and medicine, the challenge has remained mostly unchanged over the years, partly due to the vast complexity of the host-parasite-environment relationships. Over the last century, our approaches to these challenges have evolved through considerable advances in science and technology, offering new and better solutions.

View Article and Find Full Text PDF

This review article, developed by the EASD Global Council, addresses the growing global challenges in diabetes research and care, highlighting the rising prevalence of diabetes, the increasing complexity of its management and the need for a coordinated international response. With regard to research, disparities in funding and infrastructure between high-income countries and low- and middle-income countries (LMICs) are discussed. The under-representation of LMIC populations in clinical trials, challenges in conducting large-scale research projects, and the ethical and legal complexities of artificial intelligence integration are also considered as specific issues.

View Article and Find Full Text PDF