Chu-Ying Huang, Wen-Pei Chang
Abstract
Digital tools are increasingly widespread in healthcare, particularly in the fields of emotion recognition and mental health assessment.
Introduction
Emotions are a crucial factor influencing mental and physical health. For those who work in high-stress environments, such as nurses, emotional management and mental health are even more critical [1]. It has been reported that the heavy workloads and high-stress environments of clinical nurses can exert adverse effects on their emotional state.
Materials and methods
Clinical nurses aged 20–45 were recruited from a medical center in northern Taiwan between 01/12/2023 and 30/06/2024. Those who were pregnant or taking hormonal drugs were excluded. All voice recordings and questionnaires were collected by a single research nurse to ensure data consistency.
Results
Data were collected from 349 nurses, most of whom were female (85.4%) and aged 25–29 years (43.6%). The majority had a university degree or higher (77.4%), were single (89.4%), and reported no religious affiliation (59.9%). Most had ≥ 5 years of work experience (40.7%), worked in general wards (63.6%), and were on the day shift (58.7%).
Discussion
The app detected four emotions: happiness was the most prominent; and anger, fear, and sadness were less intense. Nurses who exercised less showed more anger, those with peptic ulcers had higher fear, and female nurses with irregular menstrual cycles reported lower happiness and higher sadness.
Conclusion
This study found that peptic ulcers and irregular menstrual cycles were associated with higher fear and sadness, and lower happiness and that nurses without regular exercise habits exhibited more anger.
Citation: Huang C-Y, Chang W-P (2025) Reliability, validity, and correlates of an AI voice emotion recognition app among nurses. PLoS One 20(12): e0339365. https://doi.org/10.1371/journal.pone.0339365
Editor: Mikiyas Amare Getu, Shenzhen University, CHINA
Received: April 14, 2025; Accepted: December 7, 2025; Published: December 23, 2025
Copyright: © 2025 Huang, Chang. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Data Availability: All relevant data are within the manuscript and its Supporting Information files.
Funding: This research was funded through an industry-academia collaboration agreement between Shuang Ho Hospital, Taipei Medical University, and Bamboo Technology Co., Ltd. in Taiwan, with the project code A-112-006-S. The funders had no role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript. The first author, Chu-Ying Huang, is an employee of Bamboo Technology Co., Ltd. and contributed only to the conceptualization of the study. All other aspects of the research design, data collection and analysis, and manuscript preparation were solely carried out by the corresponding author, Wen-Pei Chang.
Competing interests: The authors have declared that no competing interests exist.
