Background: Artificial intelligence chatbot research has focused on technical advances in natural language processing and validating the effectiveness of human-machine conversations in specific settings. However, real-world chat data remain proprietary and unexplored despite their growing popularity, and new analyses of chatbot uses and their effects on mitigating negative moods are urgently needed. Objective: In this study, we investigated whether and how artificial intelligence chatbots facilitate the expression of user emotions, specifically sadness and depression. We also examined cultural differences in the expression of depressive moods among users in Western and Eastern countries. Methods: This study used SimSimi, a global open-domain social chatbot, to analyze 152,783 conversation utterances containing the terms “depress” and “sad” in 3 Western countries (Canada, the United Kingdom, and the United States) and 5 Eastern countries (Indonesia, India, Malaysia, the Philippines, and Thailand). Study 1 reports new findings on the cultural differences in how people talk about depression and sadness to chatbots based on Linguistic Inquiry and Word Count and n-gram analyses. In study 2, we classified chat conversations into predefined topics using semisupervised classification techniques to better understand the types of depressive moods prevalent in chats. We then identified the distinguishing features of chat-based depressive discourse data and the disparity between Eastern and Western users. Results: Our data revealed intriguing cultural differences. Chatbot users in Eastern countries indicated stronger emotions about depression than users in Western countries (positive: P<.001; negative: P=.01); for example, Eastern users used more words associated with sadness (P=.01). However, Western users were more likely to share vulnerable topics such as mental health (P<.001), and this group also had a greater tendency to discuss sensitive topics such as swear words (P<.001) and death (P<.001). In addition, when talking to chatbots, people expressed their depressive moods differently than on other platforms. Users were more open to expressing emotional vulnerability related to depressive or sad moods to chatbots (74,045/148,590, 49.83%) than on social media (149/1978, 7.53%). Chatbot conversations tended not to broach topics that require social support from others, such as seeking advice on daily life difficulties, unlike on social media. However, chatbot users acted in anticipation of conversational agents that exhibit active listening skills and foster a safe space where they can openly share emotional states such as sadness or depression. Conclusions: The findings highlight the potential of chatbot-assisted mental health support, emphasizing the importance of continued technical and policy-wise efforts to improve chatbot interactions for those in need of emotional assistance. Our data indicate the possibility of chatbots providing helpful information about depressive moods, especially for users who have difficulty communicating emotions to other humans.

Background: Nurse burnout leads to an increase in turnover, which is a serious problem in the health care system. Although there is ample evidence of nurse burnout, interventions developed in previous studies were general and did not consider specific burnout dimensions and individual characteristics. Objective: The objectives of this study were to develop and optimize the first tailored mobile intervention for nurse burnout, which recommends programs based on artificial intelligence (AI) algorithms, and to test its usability, effectiveness, and satisfaction. Methods: In this study, an AI-based mobile intervention, Nurse Healing Space, was developed to provide tailored programs for nurse burnout. The 4-week program included mindfulness meditation, laughter therapy, storytelling, reflective writing, and acceptance and commitment therapy. The AI algorithm recommended one of these programs to participants by calculating similarity through a pretest consisting of participants’ demographics, research variables, and burnout dimension scores measured with the Copenhagen Burnout Inventory. After completing a 4-week program, burnout, job stress, stress response using the Stress Response Inventory Modified Form, the usability of the app, coping strategy by the coping strategy indicator, and program satisfaction (1: very dissatisfied; 5: very satisfied) were measured. The AI recognized the recommended program as effective if the user’s burnout score reduced after the 2-week program and updated the algorithm accordingly. After a pilot test (n=10), AI optimization was performed (n=300). A paired 2-tailed t test, ANOVA, and the Spearman correlation were used to test the effect of the intervention and algorithm optimization. Results: Nurse Healing Space was implemented as a mobile app equipped with a system that recommended 1 program out of 4 based on similarity between users through AI. The AI algorithm worked well in matching the program recommended to participants who were most similar using valid data. Users were satisfied with the convenience and visual quality but were dissatisfied with the absence of notifications and inability to customize the program. The overall usability score of the app was 3.4 out of 5 points. Nurses’ burnout scores decreased significantly after the completion of the first 2-week program (t=7.012; P<.001) and reduced further after the second 2-week program (t=2.811; P=.01). After completing the Nurse Healing Space program, job stress (t=6.765; P<.001) and stress responses (t=5.864; P<.001) decreased significantly. During the second 2-week program, the burnout level reduced in the order of participation (r=–0.138; P=.04). User satisfaction increased for both the first (F=3.493; P=.03) and second programs (F=3.911; P=.02). Conclusions: This program effectively reduced burnout, job stress, and stress responses. Nurse managers were able to prevent nurses from resigning and maintain the quality of medical services using this AI-based program to provide tailored interventions for nurse burnout. Thus, this app could improve qualitative health care, increase employee satisfaction, reduce costs, and ultimately improve the efficiency of the health care system.

Introduction: Accurate and rapid triage can reduce undertriage and overtriage, which may improve emergency department flow. This study aimed to identify the effects of a prospective study applying artificial intelligence‐based triage in the clinical field.Design: Systematic review of prospective studies.Methods: CINAHL, Cochrane, Embase, PubMed, ProQuest, KISS, and RISS were searched from March 9 to April 18, 2023. All the data were screened independently by three researchers. The review included prospective studies that measured outcomes related to AI‐based triage. Three researchers extracted data and independently assessed the study's quality using the Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) protocol.Results: Of 1633 studies, seven met the inclusion criteria for this review. Most studies applied machine learning to triage, and only one was based on fuzzy logic. All studies, except one, utilized a five‐level triage classification system. Regarding model performance, the feed‐forward neural network achieved a precision of 33% in the level 1 classification, whereas the fuzzy clip model achieved a specificity and sensitivity of 99%. The accuracy of the model's triage prediction ranged from 80.5% to 99.1%. Other outcomes included time reduction, overtriage and undertriage checks, mistriage factors, and patient care and prognosis outcomes.Conclusion: Triage nurses in the emergency department can use artificial intelligence as a supportive means for triage. Ultimately, we hope to be a resource that can reduce undertriage and positively affect patient health.Protocol Registration: We have registered our review in PROSPERO (registration number: CRD 42023415232).

Background: Health professionals face significant psychological burdens including burnout, anxiety, and depression. These can negatively impact their well-being and patient care. Traditional psychological health interventions often encounter limitations such as a lack of accessibility and privacy. Artificial intelligence (AI) chatbots are being explored as potential solutions to these challenges, offering available and immediate support. Therefore, it is necessary to systematically evaluate the characteristics and effectiveness of AI chatbots designed specifically for health professionals. Objective: This scoping review aims to evaluate the existing literature on the use of AI chatbots for psychological health support among health professionals. Methods: Following Arksey and O’Malley’s framework, a comprehensive literature search was conducted across eight databases, covering studies published before 2024, including backward and forward citation tracking and manual searching from the included studies. Studies were screened for relevance based on inclusion and exclusion criteria, among 2465 studies retrieved, 10 studies met the criteria for review. Results: Among the 10 studies, six chatbots were delivered via mobile platforms, and four via web-based platforms, all enabling one-on-one interactions. Natural language processing algorithms were used in six studies and cognitive behavioral therapy techniques were applied to psychological health in four studies. Usability was evaluated in six studies through participant feedback and engagement metrics. Improvements in anxiety, depression, and burnout were observed in four studies, although one reported an increase in depressive symptoms. Conclusions: AI chatbots show potential tools to support the psychological health of health professionals by offering personalized and accessible interventions. Nonetheless, further research is required to establish standardized protocols and validate the effectiveness of these interventions. Future studies should focus on refining chatbot designs and assessing their impact on diverse health professionals.

Background: High‐stress environments, heavy workloads, and the emotional demands of patient care, which are common challenges faced by nurses, are factors that can lead to burnout. Shift work can make traditional burnout interventions costly and difficult to implement. Artificial intelligence (AI) could offer solutions that are less constrained by time, resources, and labor.Aim: To investigate the effectiveness of an AI‐assisted intervention in reducing nurse burnout.Methods: A single‐blind, three‐group, randomized controlled trial of 120 nurses (40 per group) was conducted from June 2023 to July 2023. The AI‐assisted tailored intervention included two 2‐week programs, delivering one of four programs to the intervention group: mindfulness meditation, acceptance commitment therapy, storytelling and reflective writing, or laughter therapy. The experimental group received tailored programs based on demographic and work‐related characteristics, job stress, stress response, coping strategy, and burnout dimensions (client‐related, personal, and work‐related). Control Group 1 self‐selected their programs, while Control Group 2 was provided with online information on burnout reduction. Primary outcomes, client‐related, personal, and work‐related burnout, were measured at baseline, week 2, and week 4. Secondary outcomes, job stress, stress responses, and coping strategies, were assessed at baseline and week 4. Data were analyzed using ANOVA, repeated measures ANOVA, and the Scheffé test for post hoc analysis.Results: The experimental group showed significant reductions in client‐related burnout (F = 7.725, p = 0.001) and personal burnout (F = 10.967, p < 0.0001) compared to the other groups. Significant effects of time and time × group interactions were observed for client‐related and personal burnout, with time effects noted for work‐related burnout. Stress response reduction was highest in Control Group 1, followed by the experimental group and Control Group 2 (F = 3.07, p = 0.017).Linking Evidence to Action: AI algorithms could provide tailored programs to mitigate nurse burnout, particularly in client‐related and personal burnout. Reducing nurse burnout could contribute to the quality of care.Trial Registration: This trial is registered with the Clinical Research Information Service (KCT0008546)