Gregoire, James R.

Background The digital transformation in medical education is reshaping how clinical skills, such as point-of-care ultrasound (POCUS), are taught. In nephrology fellowship programs, POCUS is essential for enhancing diagnostic accuracy, guiding procedures, and optimizing patient management. To address these evolving demands, we developed an artificial intelligence (AI)-driven POCUS curriculum using a multiagent approach that integrates human expertise with advanced AI models, thereby elevating educational standards and better preparing fellows for contemporary clinical practice. Methods In April 2024, the Mayo Clinic Minnesota Nephrology Fellowship Program initiated a novel AI-assisted process to design a comprehensive POCUS curriculum. This process integrated multiple advanced AI models—including GPT-4.0, Claude 3.0 Opus, Gemini Advanced, and Meta AI with Llama 3—to generate initial drafts and iteratively refine content. A panel of blinded nephrology POCUS experts subsequently reviewed and modified the AI-generated material to ensure both clinical relevance and educational rigor. Results The curriculum underwent 12 iterative revisions, incorporating feedback from 29 communications across AI models. Key features of the final curriculum included expanded core topics, diversified teaching methods, enhanced assessment tools, and integration into inpatient and outpatient nephrology rotations. The curriculum emphasized quality assurance, POCUS limitations, and essential clinical applications, such as fistula/graft evaluation and software integration. Alignment with certification standards further strengthened its utility. AI models contributed significantly to the curriculum's foundational structure, while human experts provided critical clinical insights. Conclusion This curriculum, enhanced through a multiagent approach that combines AI and human collaboration, exemplifies the transformative potential of digital tools in nephrology education. The innovative framework seamlessly integrates advanced AI models with expert clinical insights, providing a scalable model for medical curriculum development that is responsive to evolving educational demands. The synergy between technological innovation and human expertise holds promising implications for advancing fellowship training. Future studies should evaluate its impact on clinical competencies and patient outcomes across diverse practice environments.

OBJECTIVE Determine if a longitudinal point-of-care ultrasonography (POCUS) elective for medical students is effective in improving POCUS knowledge. METHODS We share the format of our longitudinal POCUS elective for medical students. To evaluate the efficacy of our longitudinal elective, we compare the difference between pre-elective and post-elective scores on a POCUS test using a paired t-test with threshold of statistical significance of p ≤ .05. We also share the results of a post-elective survey evaluating the effectiveness and quality of the longitudinal POCUS elective. RESULTS Pretest mean score was 56.3% (σ = 13.6), while posttest mean score was 73.3% (σ = 9.4), with an average score improvement of 17.0% (95% CI 9.9-24.0%, p < .0001). All students strongly or moderately agreed that they would recommend the elective to future medical students, that they were more confident with their POCUS skills after completing the elective, that the time commitment of the elective was appropriate, and that they felt they had the time to fit the elective into their schedule as a medical school student. Most students (56.7%) strongly or moderately agreed that the knowledge gained from the POCUS elective had helped them in their clinical rotations. CONCLUSIONS Our longitudinal POCUS curriculum subjectively and objectively improves medical students’ POCUS knowledge while remaining accessible to students. We share our unique longitudinal POCUS elective curriculum, the format of which and its benefits are transferable to other medical schools. Through this, we hope to provide others with ideas on how they may implement a longitudinal POCUS elective.

Background This study investigated the efficacy of ChatGPT-3.5 and ChatGPT-4 in assessing drug safety for patients with kidney diseases, comparing their performance to Micromedex, a well-established drug information source. Despite the perception of non-prescription medications and supplements as safe, risks exist, especially for those with kidney issues. The study's goal was to evaluate ChatGPT's versions for their potential in clinical decision-making regarding kidney disease patients. Method The research involved analyzing 124 common non-prescription medications and supplements using ChatGPT-3.5 and ChatGPT-4 with queries about their safety for people with kidney disease. The AI responses were categorized as “generally safe,” “potentially harmful,” or “unknown toxicity.” Simultaneously, these medications and supplements were assessed in Micromedex using similar categories, allowing for a comparison of the concordance between the two resources. Results Micromedex identified 85 (68.5%) medications as generally safe, 35 (28.2%) as potentially harmful, and 4 (3.2%) of unknown toxicity. ChatGPT-3.5 identified 89 (71.8%) as generally safe, 11 (8.9%) as potentially harmful, and 24 (19.3%) of unknown toxicity. GPT-4 identified 82 (66.1%) as generally safe, 29 (23.4%) as potentially harmful, and 13 (10.5%) of unknown toxicity. The overall agreement between Micromedex and ChatGPT-3.5 was 64.5% and ChatGPT-4 demonstrated a higher agreement at 81.4%. Notably, ChatGPT-3.5's suboptimal performance was primarily influenced by a lower concordance rate among supplements, standing at 60.3%. This discrepancy could be attributed to the limited data on supplements within ChatGPT-3.5, with supplements constituting 80% of medications identified as unknown. Conclusion ChatGPT's capabilities in evaluating the safety of non-prescription drugs and supplements for kidney disease patients are modest compared to established drug information resources. Neither ChatGPT-3.5 nor ChatGPT-4 can be currently recommended as reliable drug information sources for this demographic. The results highlight the need for further improvements in the model's accuracy and reliability in the medical domain.