Citations

Background Prior authorization (PA) is a major source of administrative burden, treatment delay, and clinician burnout. Artificial intelligence (AI), particularly large language models (LLMs), is increasingly used to assist with clinical documentation, yet its reliability for payer-facing administrative tasks remains uncertain. Objective To evaluate the quality of PA letters drafted by ChatGPT-5 for commonly used medications requiring PA in nephrology. Quality was evaluated based on correctness and strength of clinical reasoning. Methods We created a single standardized prompt and applied it across 29 nephrology scenarios to generate PA letters. Each PA letter was reviewed against four criteria: 1) absence of false statements or hallucinations, 2) correctness of ICD-10 coding, 3) presence and validity of citations, and 4) clinical reasoning, rated on a 4-point Likert scale (illogical, weak, adequate and strong). FDA drug labels, KDIGO guidelines and related randomized controlled trials were used as reference standards. Results Out of 29 letters, one letter (3.5%) contained false statements mentioning an irrelevant clinical trial. The ICD-10 diagnosis code was correct in 23 letters (79.3%), most errors were related to chronic kidney disease (CKD) staging or internal diagnostic inconsistencies. 27 letters (93.1%) cited valid references, with one letter citing an incorrect trial and another one citing a correct KDIGO guideline with inaccessible link. Twenty-six letters (89.7%) demonstrated strong clinical reasoning, supported by guideline-oriented or FDA label–aligned justification. The remaining 3 letters were rated as adequate reasoning. The main areas for improvement involved citing relevant references and emphasizing special considerations, for example Risk Evaluation and Mitigation Strategy (REMS) compliance for eculizumab. Conclusions ChatGPT-5 can generate clinically coherent PA drafts for nephrology medications, but limitations in coding precision and citation reliability persist. With appropriate oversight, AI-assisted documentation may reduce administrative burden while maintaining safety and accuracy.

ABSTRACT Background Cognitive impairment (CI) is a critical complication in peritoneal dialysis (PD) patients, associated with decreased quality of life and increased hospitalization. Despite its significant impact, the prevalence, risk factors, and consequences of CI in PD patients are not well understood. We aimed to determine the prevalence, risk factors, and outcomes of CI in PD patients. Methods We performed systematic reviews in OVID Medline, Embase, and Cochrane databases until February 2024 to identify cross-sectional and cohort studies on prevalence of CI (identified by cognitive assessment scales) in PD patients. The Newcastle–Ottawa Scale was used to assess risk of bias. A pooled meta-analysis of CI prevalence in PD and a subgroup analysis comparing the risk of CI between PD and non-PD settings were performed using a random-effects model. Results A total of 19 studies were identified, involving 2882 PD patients. The pooled prevalence of CI in PD patients was 47.7% (95%CI: 35.8–59.9%). CI in patients undergoing PD appears to be associated with older age, female gender, lower levels of education, and is linked to higher rates of hospitalization and peritonitis, compared to those without CI. However, it is not associated with increased mortality. Compared to hemodialysis, PD showed a trend toward a lower risk of CI (OR 0.64, 95%CI 0.39–1.03; P = .068). Conclusion CI is highly prevalent and associated with several adverse clinical outcomes in PD patients. These findings could contribute to facilitate the development of screening and early intervention strategies to reduce the burden of disease in this population.

Background: Despite the prevalence and incidence of kidney stones progressively increasing worldwide, public awareness of this condition remains unclear. Understanding trends of awareness can assist healthcare professionals and policymakers in planning and implementing targeted health interventions. This study investigated online search interest in “kidney stone” by analyzing Google Trends, focusing on stationarity of the trends and predicting future trends. Methods: We performed time series analysis on worldwide Google monthly search data from January 2004 to November 2023. The Augmented Dickey–Fuller (ADF) test was used to assess the stationarity of the data, with a p-value below 0.05 indicating stationarity. Time series forecasting was performed using the autoregressive integrated moving average to predict future trends. Results: The highest search interest for “kidney stone” (score 100) was in August 2022, while the lowest was in December 2007 (score 36). As of November 2023, search interest remained high, at 92. The ADF test was significant (p = 0.023), confirming data stationarity. The time series forecasting projected continued high public interest, likely reflecting ongoing concern and awareness. Notably, diverse regions such as Iran, the Philippines, Ecuador, the United States, and Nepal showed significant interest, suggesting widespread awareness of nephrolithiasis. Conclusion: This study highlighted that “kidney stone” is a consistently relevant health issue globally. The increase and stationarity of search trends, the forecasted sustained interest, and diverse regional interest emphasize the need for collaborative research and educational initiatives. This study’s analysis serves as a valuable tool for shaping future healthcare policies and research directions in addressing nephrolithiasis related health challenges.

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 (<5 mg), moderate (5–8 mg), and high (>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.

Background and Objectives: Literature reviews are foundational to understanding medical evidence. With AI tools like ChatGPT, Bing Chat and Bard AI emerging as potential aids in this domain, this study aimed to individually assess their citation accuracy within Nephrology, comparing their performance in providing precise. Materials and Methods: We generated the prompt to solicit 20 references in Vancouver style in each 12 Nephrology topics, using ChatGPT, Bing Chat and Bard. We verified the existence and accuracy of the provided references using PubMed, Google Scholar, and Web of Science. We categorized the validity of the references from the AI chatbot into (1) incomplete, (2) fabricated, (3) inaccurate, and (4) accurate. Results: A total of 199 (83%), 158 (66%) and 112 (47%) unique references were provided from ChatGPT, Bing Chat and Bard, respectively. ChatGPT provided 76 (38%) accurate, 82 (41%) inaccurate, 32 (16%) fabricated and 9 (5%) incomplete references. Bing Chat provided 47 (30%) accurate, 77 (49%) inaccurate, 21 (13%) fabricated and 13 (8%) incomplete references. In contrast, Bard provided 3 (3%) accurate, 26 (23%) inaccurate, 71 (63%) fabricated and 12 (11%) incomplete references. The most common error type across platforms was incorrect DOIs. Conclusions: In the field of medicine, the necessity for faultless adherence to research integrity is highlighted, asserting that even small errors cannot be tolerated. The outcomes of this investigation draw attention to inconsistent citation accuracy across the different AI tools evaluated. Despite some promising results, the discrepancies identified call for a cautious and rigorous vetting of AI-sourced references in medicine. Such chatbots, before becoming standard tools, need substantial refinements to assure unwavering precision in their outputs.

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.