Chain-of-thought prompting enhances the abilities of large language models (LLMs) significantly. It not only makes these models more specific and context-aware but also impacts the wider field of artificial intelligence (AI). This approach broadens the usability of AI, increases its efficiency, and aligns it more closely with human thinking and decision-making processes. As we improve this method, it is set to become a key element in the future of AI, adding more purpose, precision, and ethical consideration to these technologies. In medicine, the chain-of-thought prompting is especially beneficial. Its capacity to handle complex information, its logical and sequential reasoning, and its suitability for ethically and context-sensitive situations make it an invaluable tool for healthcare professionals. Its role in enhancing medical care and research is expected to grow as we further develop and use this technique. Chain-of-thought prompting bridges the gap between AI’s traditionally obscure decision-making process and the clear, accountable standards required in healthcare. It does this by emulating a reasoning style familiar to medical professionals, fitting well into their existing practices and ethical codes. While solving AI transparency is a complex challenge, the chain-of-thought approach is a significant step toward making AI more comprehensible and trustworthy in medicine. This review focuses on understanding the workings of LLMs, particularly how chain-of-thought prompting can be adapted for nephrology’s unique requirements. It also aims to thoroughly examine the ethical aspects, clarity, and future possibilities, offering an in-depth view of the exciting convergence of these areas.

Patients with chronic kidney disease (CKD) necessitate specialized renal diets to prevent complications such as hyperkalemia and hyperphosphatemia. A comprehensive assessment of food components is pivotal, yet burdensome for healthcare providers. With evolving artificial intelligence (AI) technology, models such as ChatGPT, Bard AI, and Bing Chat can be instrumental in educating patients and assisting professionals. To gauge the efficacy of different AI models in discerning potassium and phosphorus content in foods, four AI models—ChatGPT 3.5, ChatGPT 4, Bard AI, and Bing Chat—were evaluated. A total of 240 food items, curated from the Mayo Clinic Renal Diet Handbook for CKD patients, were input into each model. These items were characterized by their potassium (149 items) and phosphorus (91 items) content. Each model was tasked to categorize the items into high or low potassium and high phosphorus content. The results were juxtaposed with the Mayo Clinic Renal Diet Handbook’s recommendations. The concordance between repeated sessions was also evaluated to assess model consistency. Among the models tested, ChatGPT 4 displayed superior performance in identifying potassium content, correctly classifying 81% of the foods. It accurately discerned 60% of low potassium and 99% of high potassium foods. In comparison, ChatGPT 3.5 exhibited a 66% accuracy rate. Bard AI and Bing Chat models had an accuracy rate of 79% and 81%, respectively. Regarding phosphorus content, Bard AI stood out with a flawless 100% accuracy rate. ChatGPT 3.5 and Bing Chat recognized 85% and 89% of the high phosphorus foods correctly, while ChatGPT 4 registered a 77% accuracy rate. Emerging AI models manifest a diverse range of accuracy in discerning potassium and phosphorus content in foods suitable for CKD patients. ChatGPT 4, in particular, showed a marked improvement over its predecessor, especially in detecting potassium content. The Bard AI model exhibited exceptional precision for phosphorus identification. This study underscores the potential of AI models as efficient tools in renal dietary planning, though refinements are warranted for optimal utility.

Background: ChatGPT is a novel tool that allows people to engage in conversations with an advanced machine learning model. ChatGPT's performance in the US Medical Licensing Examination is comparable with a successful candidate's performance. However, its performance in the nephrology field remains undetermined. This study assessed ChatGPT's capabilities in answering nephrology test questions. Methods: Questions sourced from Nephrology Self-Assessment Program and Kidney Self-Assessment Program were used, each with multiple-choice single-answer questions. Questions containing visual elements were excluded. Each question bank was run twice using GPT-3.5 and GPT-4. Total accuracy rate, defined as the percentage of correct answers obtained by ChatGPT in either the first or second run, and the total concordance, defined as the percentage of identical answers provided by ChatGPT during both runs, regardless of their correctness, were used to assess its performance. Results: A comprehensive assessment was conducted on a set of 975 questions, comprising 508 questions from Nephrology Self-Assessment Program and 467 from Kidney Self-Assessment Program. GPT-3.5 resulted in a total accuracy rate of 51%. Notably, the employment of Nephrology Self-Assessment Program yielded a higher accuracy rate compared with Kidney Self-Assessment Program (58% versus 44%; P < 0.001). The total concordance rate across all questions was 78%, with correct answers exhibiting a higher concordance rate (84%) compared with incorrect answers (73%) (P < 0.001). When examining various nephrology subfields, the total accuracy rates were relatively lower in electrolyte and acid-base disorder, glomerular disease, and kidney-related bone and stone disorders. The total accuracy rate of GPT-4's response was 74%, higher than GPT-3.5 (P < 0.001) but remained below the passing threshold and average scores of nephrology examinees (77%). Conclusions: ChatGPT exhibited limitations regarding accuracy and repeatability when addressing nephrology-related questions. Variations in performance were evident across various subfields.

Literature reviews are valuable for summarizing and evaluating the available evidence in various medical fields, including nephrology. However, identifying and exploring the potential sources requires focus and time devoted to literature searching for clinicians and researchers. ChatGPT is a novel artificial intelligence (AI) large language model (LLM) renowned for its exceptional ability to generate human-like responses across various tasks. However, whether ChatGPT can effectively assist medical professionals in identifying relevant literature is unclear. Therefore, this study aimed to assess the effectiveness of ChatGPT in identifying references to literature reviews in nephrology. We keyed the prompt “Please provide the references in Vancouver style and their links in recent literature on… name of the topic” into ChatGPT-3.5 (03/23 Version). We selected all the results provided by ChatGPT and assessed them for existence, relevance, and author/link correctness. We recorded each resource’s citations, authors, title, journal name, publication year, digital object identifier (DOI), and link. The relevance and correctness of each resource were verified by searching on Google Scholar. Of the total 610 references in the nephrology literature, only 378 (62%) of the references provided by ChatGPT existed, while 31% were fabricated, and 7% of citations were incomplete references. Notably, only 122 (20%) of references were authentic. Additionally, 256 (68%) of the links in the references were found to be incorrect, and the DOI was inaccurate in 206 (54%) of the references. Moreover, among those with a link provided, the link was correct in only 20% of cases, and 3% of the references were irrelevant. Notably, an analysis of specific topics in electrolyte, hemodialysis, and kidney stones found that >60% of the references were inaccurate or misleading, with less reliable authorship and links provided by ChatGPT. Based on our findings, the use of ChatGPT as a sole resource for identifying references to literature reviews in nephrology is not recommended. Future studies could explore ways to improve AI language models’ performance in identifying relevant nephrology literature.

Accurate information regarding oxalate levels in foods is essential for managing patients with hyperoxaluria, oxalate nephropathy, or those susceptible to calcium oxalate stones. This study aimed to assess the reliability of chatbots in categorizing foods based on their oxalate content. We assessed the accuracy of ChatGPT-3.5, ChatGPT-4, Bard AI, and Bing Chat to classify dietary oxalate content per serving into low (8 mg) oxalate content categories. A total of 539 food items were processed through each chatbot. The accuracy was compared between chatbots and stratified by dietary oxalate content categories. Bard AI had the highest accuracy of 84%, followed by Bing (60%), GPT-4 (52%), and GPT-3.5 (49%) (p < 0.001). There was a significant pairwise difference between chatbots, except between GPT-4 and GPT-3.5 (p = 0.30). The accuracy of all the chatbots decreased with a higher degree of dietary oxalate content categories but Bard remained having the highest accuracy, regardless of dietary oxalate content categories. There was considerable variation in the accuracy of AI chatbots for classifying dietary oxalate content. Bard AI consistently showed the highest accuracy, followed by Bing Chat, GPT-4, and GPT-3.5. These results underline the potential of AI in dietary management for at-risk patient groups and the need for enhancements in chatbot algorithms for clinical accuracy.