Moderated Poster Abstract
Eposter Presentation
 
Accept format: PDF. The file size should not be more than 5MB
 
Accept format: PNG/JPG/WEBP. The file size should not be more than 2MB
 
Submitted
Abstract
Trialling Real-World Implementation of AI Voice Dictation in a Urology Outpatient Clinic: A Feasibility Study
Moderated Poster Abstract
Clinical Research
AI in Urology
Author's Information
5
No more than 10 authors can be listed (as per the Good Publication Practice (GPP) Guidelines).
Please ensure the authors are listed in the right order.
Australia
Emre Alpay emre.alpayy@gmail.com Austin Health Urology Melbourne Australia * University of Melbourne Medicine, Dentistry and Health Sciences Melbourne Australia
Shane Qin shane.s.qin@gmail.com Austin Health Urology Melbourne Australia - University of Melbourne Medicine, Dentistry and Health Sciences Melbourne Australia
Anthony Ta tonyta82@gmail.com Austin Health Urology Melbourne Australia -
Dixon Woon dixon.woon@gmail.com Austin Health Urology Melbourne Australia -
Joseph Ischia jjischia@unimelb.edu.au Austin Health Urology Melbourne Australia - University of Melbourne Medicine, Dentistry and Health Sciences Melbourne Australia
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Abstract Content
Generative AI is increasingly being utilised in healthcare documentation, with AI-powered ambient dictation tools documenting consultations and streamlining workflow. These technologies present a significant opportunity to reduce administrative workload and enhance patient–clinician interaction. Despite this, evidence supporting their efficacy and implementation, particularly among urologists with varying levels of technological familiarity remains limited. This study evaluated the implementation of Heidi Health, an AI dictation platform, in a urology outpatient clinic, focusing on feasibility, documentation quality, and user experience.
Over a three-week period in a public tertiary hospital urology clinic in Melbourne, Australia, consultant urologists used Heidi Health to dictate clinical notes in real time during consultations. Consultants, spanning <10 to >30 years post-fellowship, completed structured surveys assessing usability, integration into workflow, and perceived documentation quality. Patients provided anonymous feedback on their experience of being present during dictation. Dictation accuracy was assessed against direct audio recordings. Note quality was evaluated using the modified Physician Documentation Quality Instrument-9 (PDQI-9).
Dictation accuracy was 100%, with no corrections required. Notes rated highly across PDQI-9 domains, particularly for clarity, completeness, and organisation. All consultants found the tool easy to use, effective at capturing clinical content, and expressed interest in continued use. Feedback was positive across all levels of clinical experience. Patients reported that their doctor felt more present and engaged during the consultation. However, some raised concerns around how the AI worked and whether its use was secure.
AI powered dictation enabled accurate, high-quality, real-time documentation in a urology outpatient setting. The platform was easy to adopt and well received by both consultants and patients. These findings support the broader implementation of AI voice dictation tools to improve documentation and efficiency in clinical practice.
Artificial Intelligence, Generative AI, Urology, Dictation, Ambient AI, Real-World Implementation, Documentation, Heidi Health
 
 
 
 
 
 
 
 
 
 
2127
 
Presentation Details
Free Paper Moderated Poster(08): Transplantation & AI & Training/Education
Aug. 16 (Sat.)
13:44 - 13:48
2