Repository logo
  • English
  • Deutsch
  • Français
Log In
New user? Click here to register.Have you forgotten your password?
  1. Home
  2. CRIS
  3. Publication
  4. Development and evaluation of a novel voice-enabled prototype to support consistent application of surgical safety checklists: a proof-of-concept study
 

Development and evaluation of a novel voice-enabled prototype to support consistent application of surgical safety checklists: a proof-of-concept study

URI
https://arbor.bfh.ch/handle/arbor/46446
Version
Published
Identifiers
10.1186/s13037-025-00460-0
Date Issued
2025-12-24
Author(s)
Medroa, Pedro Miguel Inácio
Heining, Sandro-Michael
Saltan, Marcel
Denecke, Kerstin  
Type
Article
Language
English
Subjects

Surgical checklist

Voice assistant

Speech-to-text

Patient safety

Clinical documentatio...

Abstract
Background Surgical safety checklists are essential for reducing errors and improving outcomes, but consistent, full-phase adherence remains suboptimal. Traditional paper-based systems can disrupt workflow and limit team engagement. Voice-enabled solutions offer potential to improve compliance while preserving sterile conditions and communication flow in the operating room (OR). Methods This study aimed to develop and evaluate a prototype voice-controlled digital assistant for surgical checklists-referred to as 'VoiceCheck'-with a focus on usability, technical performance, and feasibility in real-world clinical settings. VoiceCheck guides clinical teams through the "Sign In", "Time-out", and "Sign Out" phases of the surgical checklist using voice commands and speech transcription. The system operates offline, incorporating Rhasspy for intent recognition and Whisper for speech-to-text transcription. Twelve surgical team members participated in a field evaluation, completing structured tasks alongside routine workflows. Usability was assessed using the System Usability Scale (SUS) and a custom questionnaire. Technical evaluations tested Whisper V2 and V3 under quiet and noisy conditions, and Rhasspy's intent and wake word recognition across 1'125 commands in two environments (noisy, quiet). Results Participants rated usability positively (SUS median score 76.04). Whisper V3 achieved 90.7-97.3% transcription accuracy, outperforming V2 in noisy settings. Rhasspy recognized intents with 92.8-94.8% accuracy and maintained a low false-positive rate. VoiceCheck functioned reliably offline and was preferred with a conference microphone for multiuser interaction. Conclusion VoiceCheck demonstrates feasibility for voice-assisted checklist execution in surgical settings. It was well accepted by users and performed reliably under realistic conditions. Further research should explore clinical integration, workflow impact, and multilingual capabilities.
DOI
https://doi.org/10.24451/arbor.12786
Publisher DOI
10.1186/s13037-025-00460-0
Journal or Serie
Patient Safety in Surgery
ISSN
1754-9493
Publisher URL
https://link.springer.com/article/10.1186/s13037-025-00460-0
Organization
Technik und Informatik  
Institute for Patient-centered Digital Health  
AI for Health  
Volume
19
Publisher
BioMed Central (United Kingdom)
Submitter
Denecke, Kerstin
Citation apa
Medroa, P. M. I., Heining, S.-M., Saltan, M., & Denecke, K. (2025). Development and evaluation of a novel voice-enabled prototype to support consistent application of surgical safety checklists: a proof-of-concept study. In Patient Safety in Surgery (Vol. 19). BioMed Central (United Kingdom). https://doi.org/10.24451/arbor.12786
File(s)
Loading...
Thumbnail Image
Download

open access

Name

Medroa_et_al-2025-Patient_Safety_in_Surgery.pdf

License
Attribution-NonCommercial-NoDerivatives 4.0 International
Version
published
Size

1.94 MB

Format

Adobe PDF

Checksum (MD5)

fb2becbd0494e9d13d9b88ac4a3ab4e7

About ARBOR

Built with DSpace-CRIS software - System hosted and mantained by 4Science

  • Cookie settings
  • Privacy policy
  • End User Agreement
  • Send Feedback
  • Our institution