Development of a Voice-Assisted Application to Support Emergency Responders during Out-of-Hospital Cardiac Arrest (OHCA)
Main Article Content
Abstract
Out-of-hospital cardiac arrest (OHCA) is a time-critical emergency requiring rapid and accurate adherence to Advanced Cardiovascular Life Support (ACLS) protocols. Conventional manual documentation during resuscitation can increase cognitive workload and lead to incomplete or inaccurate records. This study aimed to develop and evaluate a multilingual voice-assisted artificial intelligence (AI) application to support real-time ACLS workflow guidance and automated documentation during OHCA management. The prototype was developed using Python and Streamlit based on the American Heart Association (AHA) ACLS guidelines. It incorporated offline speech recognition using Vosk, optional cloud-based Google Speech Recognition and Text-to-Speech services, Thai and English voice commands, automated timers, event logging, and structured report generation. The application was evaluated through simulation-based ACLS scenarios involving 20 emergency healthcare professionals, including physicians, nurses, and emergency medical technicians. Evaluation focused on documentation accuracy, workflow efficiency, voice recognition performance, and usability. The results demonstrated that the proposed system improved documentation accuracy, workflow efficiency, and user satisfaction compared with conventional manual documentation. Automated reminders and hands-free voice documentation also helped reduce cognitive workload and support situational awareness during simulated resuscitation. Voice recognition performed reliably under controlled conditions, although environmental noise affected recognition accuracy. Overall, the findings demonstrate the feasibility of integrating voice-assisted AI into OHCA resuscitation workflows to improve documentation quality and support ACLS protocol adherence. Further research should evaluate the system in real clinical settings with larger participant groups and integration with electronic health record systems.
Downloads
Article Details

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
[1] Hsu, S. H.; Sun, J. T.; Huang, E. P. C.; Nishiuchi, T.; Song, K. J.; Leong, B.; Hisamuddin, N.; Khruekarnchana, P.; Naroo, G.; Hsieh, M. J.; Chang, S. H.; Chiang, W. C.; Ma, H. M. The Predictive Performance of Current Termination-of-Resuscitation Rules in Patients Following Out-of-Hospital Cardiac Arrest in Asian Countries: A Cross-Sectional Multicentre Study. PLoS One 2022, 17(8), e0270986. https://doi.org/10.1371/journal.pone.0270986
[2] Böttiger, B. W.; Becker, L. B.; Kern, K. B.; Lippert, F.; Lockey, A.; Ristagno, G.; Semeraro, F.; Wingen, S. BIG FIVE Strategies for Survival Following Out-of-Hospital Cardiac Arrest. Eur. J. Anaesthesiol. 2020, 37(11), 955–958. https://doi.org/10.1097/EJA.0000000000001247
[3] Okubo, M.; Chan, H. K.; Callaway, C. W.; Mann, N. C.; Wang, H. E. Characteristics of Paediatric Out-of-Hospital Cardiac Arrest in the United States. Resuscitation 2020, 153, 227–233. https://doi.org/10.1016/j.resuscitation.2020.04.023
[4] Tsao, C. W.; Aday, A. W.; Almarzooq, Z. I.; Alonso, A.; et al. Heart Disease and Stroke Statistics—2022 Update: A Scientific Statement from the American Heart Association. Circulation 2022, 145(8), e153–e639. https://doi.org/10.1161/CIR.0000000000001052
[5] Merchant, R. M.; Becker, L. B.; Brooks, S. C.; Chan, P. S.; Rios, M. D.; McBride, M. E.; Neumar, R. W.; Previdi, J. K.; Uzendu, A.; Sasson, C. The American Heart Association Emergency Cardiovascular Care 2030 Impact Goals and Call to Action to Improve Cardiac Arrest Outcomes: A Scientific Statement from the American Heart Association. Circulation 2024, 149(8), e914–e933. https://doi.org/10.1161/CIR.0000000000001196
[6] William, M.; Eric, G.; John, S. B.; Adam, B. L. Quality of Layperson CPR Instructions from Artificial Intelligence Voice Assistants. JAMA Netw. Open 2023, 6(8), e2331205. https://doi.org/10.1001/jamanetworkopen.2023.31205
[7] Sevil, H.; Bastan, V.; Gültürk, E.; El Majzoub, I.; Göksu, E. Effect of Smartphone Applications on Cardiopulmonary Resuscitation Quality Metrics in a Mannequin Study: A Randomized Trial. Turk. J. Emerg. Med. 2021, 21(2), 56–61. https://doi.org/10.4103/2452-2473.313333
[8] Dainty, K. N.; Debaty, G.; Waddick, J.; Vaillancourt, C.; Malta Hansen, C.; Olasveengen, T.; Bray, J. Interventions to Optimize Dispatcher-Assisted CPR Instructions: A Scoping Review. Resusc. Plus 2024, 19, 100715. https://doi.org/10.1016/j.resplu.2024.100715
[9] Aadit, J.; Owen, S.; Rajesh, B. The Growing Impact of Natural Language Processing in Healthcare and Public Health. J. Health Care Organ. Provis. Financ. 2024, 61, 1–10. https://doi.org/10.1177/00469580241290095
[10] Hao, W.; Naomi, A.; Laura, H.; Thomas, K. S.; Nathan, H.; Daniel, P.; Heidi, K.; Sara, A. S.; Prachi, M.; Usha, S. Using Natural Language Processing in Emergency Medicine Health Service Research: A Systematic Review and Meta-Analysis. Acad. Emerg. Med. 2024, 31(7), 696–706.