Publications by authors named "N Punjani"
To explore the frequency and predictive factors of erectile dysfunction diagnosis after colorectal cancer surgery. The Surveillance, Epidemiology, and End Results-Medicare database was used to identify a national sample of men undergoing surgery for colorectal cancer from 2004 to 2015. Men aged > 65 years with any index surgery within 1 year of diagnosis of colorectal cancer were included.
View Article and Find Full Text PDFArticle Synopsis
- Large language model (LLM) chatbots, like ChatGPT and Bard, can provide information about benign prostatic hyperplasia surgery, with their response quality improving significantly when prompted with specific criteria.
- A study evaluated the information quality and readability of these chatbots, finding that unprompted answers were rated moderately, but prompting improved the quality substantially.
- Overall, while the chatbots were generally accurate and complete in responding to simulated patient queries, the readability of their responses was poor, indicating a need for improvement in patient education materials.*
Objective: To assess the research output of urology residents at top programs and investigate the correlation between medical school research productivity (MRP), research during residency (RRP), and pursuit of academic practice. Further, to characterize trends in MRP before and after the transition to pass/fail scoring of USMLE Step 1.
Methods: Our team previously reported on the PubMed-indexed research productivity of applicants matching into top 50 urology programs.
Introduction: We aimed to characterize patient portal messaging use after urologic surgery to identify administrative burden and evaluate postoperative clinical associations.
Methods: Epic was queried for all urologic surgeries performed at the Mayo Clinic enterprise between 2019 and 2022. Data from the highest volume procedures were extracted including patient-generated portal messages to their provider and emergency department (ED) visits within 6 months of surgery.
Article Synopsis
- Patients with urologic conditions, like Peyronie's disease, are increasingly seeking health information online despite having access to clinicians through electronic health records.
- The study aimed to evaluate the quality, accuracy, and readability of information provided by four large language model (LLM) chatbots, particularly in response to specific patient queries about Peyronie's disease.
- Results indicated that unprompted responses from LLMs were of moderate quality but improved to high quality when prompted; however, the reading level of responses was too complex for general understanding, averaging at a grade 12.9 level.