V04-01 ARTIFICIAL INTELLIGENCE (AI) GENERATED PATIENT INFORMATION VIDEOS (PIVS) FOR PARTIAL NEPHRECTOMY BY MEDICAL STUDENTS WITH EXPERT VALIDATION - A PILOT STUDY

You have accessJournal of UrologyAdrenal/Renal Oncology I (V04)1 May 2024V04-01 ARTIFICIAL INTELLIGENCE (AI) GENERATED PATIENT INFORMATION VIDEOS (PIVS) FOR PARTIAL NEPHRECTOMY BY MEDICAL STUDENTS WITH EXPERT VALIDATION - A PILOT STUDY Collin E.R.H. Ho, Wei Zheng So, Kenneth Leung, Simone Ong, Hong Min Peng, Nicholas HP Wong, and Ho Yee Tiong Collin E.R.H. HoCollin E.R.H. Ho , Wei Zheng SoWei Zheng So , Kenneth LeungKenneth Leung , Simone OngSimone Ong , Hong Min PengHong Min Peng , Nicholas HP WongNicholas HP Wong , and Ho Yee TiongHo Yee Tiong View All Author Informationhttps://doi.org/10.1097/01.JU.0001009444.59519.d3.01AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: The role of Artificial Intelligence (AI) in the medical field has been expanding exponentially, and has been met with excitement, and uncertainty. While there has been much research done in AI's role in objective parameters that impact surgical planning, there is a a paucity of research that investigates its utility of enhancing intangible but equally important aspects of patient care, such as patient education. There is strong evidence supporting the use of patient information videos (PIV) preoperatively to improve anxiety in patients. Optimal preoperative counselling resulted in decreased anxiety, as well as decreased rehabilitation requirements. We sought to validate an AI generated PIV for Partial Nephrectomy (PN) to augment the preoperative counselling process. METHODS: Commercially available AI software (ChatGPT, MidJourney, ElevenLabs, D-ID) were employed to create the PIV, in a process first described by Mr. Kenneth Leung (https://tinyurl.com/kennethleunggenai). Prompts were entered into ChatGPT to outline the scope of discussion of the PIV, to encompass various aspects of preoperative counselling. The unedited script from ChatGPT was then converted to an audio file and subsequently to a video using other platforms mentioned above. The PIV was validated with the DISCERN Questionnaire by urologists to ensure the accuracy of the information presented in the video. The DISCERN questionnaire is a validated questionnaire, consisting of 3 sections to objectively evaluate quality of information. RESULTS: Fifteen expert urologists were involved in the validation of the AIGPIV. The mean DISCERN questionnaire score was 53.1 (±8.3), or 70.8% of the maximum score. This places the PIV squarely in the "Good" category of the DISCERN questionnaire. 80% (n=12) and 73% (n=11) of the urologists agreed that the AIGPIV would be informative for patients and useful for counselling a patient for PN respectively. CONCLUSIONS: This pilot study has validated the information generated by AI regarding PN. Although the information was the video assessed to be accurate, improvements could be made for to be more engaging and interactive. The AIGPIV creation may be performed at an exceptionally resourceful rate with minimal costs and manpower requirements. In addition, this can be repeated for various types of procedures for potential mass adoption. Further research is anticipated in assessing the impact of these AIGPIVs in the peri-operative context as the utility of AI in healthcare continues to develop. Source of Funding: No funding was obtained for the purposes of this study © 2024 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 211Issue 5SMay 2024Page: e196 Advertisement Copyright & Permissions© 2024 by American Urological Association Education and Research, Inc.Metrics Author Information Collin E.R.H. Ho More articles by this author Wei Zheng So More articles by this author Kenneth Leung More articles by this author Simone Ong More articles by this author Hong Min Peng More articles by this author Nicholas HP Wong More articles by this author Ho Yee Tiong More articles by this author Expand All Advertisement PDF downloadLoading ...