Skip to main content
Download PDF

A trial of a chat service for patients and their family members in an emergency department

BMC Health Services Research volume 24, Article number: 1058 (2024) Cite this article

Abstract

Background

Effective communication between patients and healthcare providers in the emergency department (ED) is challenging due to the dynamic nature of the ED environment. This study aimed to trial a chat service enabling patients in the ED and their family members to ask questions freely, exploring the service’s feasibility and user experience.

Objectives

To identify the types of needs and inquiries from patients and family members in the ED that could be addressed through the chat service and to assess the user experience of the service.

Methods

We enrolled patients and family members aged over 19 years in the ED, providing the chat service for up to 4 h per ED visit. Trained research nurses followed specific guidelines to respond to messages from the participants. After participation, participants were required to complete a survey. Those who agreed also participated in interviews to provide insights on their experiences with the ED chat service.

Results

A total of 40 participants (20 patients and 20 family members) sent 305 messages (72 by patients and 233 by family members), with patients sending an average of 3.6 messages and family members 11.7. Research nurses resolved 41.4% of patient inquiries and 70.9% of family member inquiries without further healthcare provider involvement. High usability was reported, with positive feedback on communication with healthcare workers, information accessibility, and emotional support.

Conclusions

The ED chat service was found to be feasible and led to positive user experiences for both patients and their family members.

Peer Review reports

Background

The importance of communication between patients and healthcare workers is well-documented, with better communication linked to improved health outcomes, including reduced morbidity and mortality rates, and enhanced patient experiences [1,2,3,4]. However, the ED environment poses significant challenges to effective communication. While understanding and communicating a patient’s needs and symptoms is a core responsibility of ED physicians, the limited time available often challenges their ability to do so comprehensively, and patients may find it difficult to inquire about various aspects of their care [5,6,7,8,9].

Attempts have been made to improve communication between patients and healthcare workers in different settings [10, 11]. For example, outpatient services have utilized short message services to remind patients of appointments [12, 13], and patient portals and secure messaging have provided patients easier access to their health records, educational materials, and communication channels with healthcare providers [14]. In inpatient settings, where patient needs and communication opportunities differ from those of outpatient services, studies have shown a willingness among patients, families, and healthcare teams to use messaging [15, 16].

Despite these efforts, short message services in the ED have primarily focused on disease prevention and follow-up compliance among discharged patients [17,18,19]. Given the ED’s complex environment and diverse patient population, the feasibility and effectiveness of a chat service for providing personalized information remain uncertain. This study, therefore, aimed to assess the feasibility and user experience of a chat service during an ED stay, utilizing bilateral text messaging.

Objectives

The primary objective of our study was to evaluate text messages from patients and family members to identify the types of needs and inquiries that could be resolved through the chat service and those that required further assistance. The secondary objective was to evaluate users’ experiences with the ED chat service and to assess the feasibility of implementing such services by determining the level of independent problem solving achieved through the chat service.

Methods

Study design and settings

This study examined the content, types, topics, and volume of text messages within the Emergency Department (ED) chat service of an academic tertiary hospital in Seoul, South Korea. The hospital has approximately 2,000 inpatient beds and accommodates an average of 200 ED patients daily. The chat service was operational from June to August 2022, spanning roughly 2 months.

To recruit study participants, information about the chat service was posted on a bulletin board in front of the ED. A research nurse approached patients and their family members in the waiting room, enrolling participants without pairing them. The response rate was calculated as the proportion of those who agreed to participate out of the total number the research nurse attempted to recruit. The chat service was offered exclusively to those who consented to participate in the study.

The service utilized the Kakao Talk platform, a widely used mobile messaging application in South Korea, engaging about 85% of the population and managed by Kakao Corporation [20]. Research nurses with ED experience managed the chat responses, calling upon emergency physicians for support when needed.

Selection of participants

Samsung Medical Center’s Institutional Review Board (IRB) approved this research protocol (IRB No. 2022-02-024-002). Written consent was secured from all participants. Patients and their family members were enrolled either in the waiting room or at their seats without being matched. Only individuals over 19 years of age who visited the ED were eligible for participation. We excluded patients with high-severity conditions, as indicated by Korean Triage and Acuity Scale (KTAS) scores of 1 or 2, and those who faced difficulties using mobile phones. In line with our institution’s policies, adult patients with mild symptoms were required to enter the ED alone, while their family members waited outside. However, pediatric patients, seniors, and those presenting with moderate to severe symptoms could have family members accompany them inside the ED.

Study process

After being recruited, participants were contacted by a research nurse via the chat service. Participants were allowed to send messages freely, with no restrictions on topics, frequency, or length. Upon receiving a message, the research nurse responded to the inquiry. For messages requiring medical knowledge, either an attending emergency physician or an ED nurse provided assisted in formulating the response. If the research nurse was unable to provide the requested information, participants were informed that the question could not be answered through the chat service due to its limitations. The service was accessible for 3–4 h during the participant’s stay in the ED, and access ended upon the participant’s discharge or admission to the hospital. To ensure consistency in responses, the research nurse was trained and followed pre-developed instructions based on common inquiries. At the conclusion of the chat service, participants were asked to complete a questionnaire and were invited to participate in interviews.

Measurements

Data collection

All text data were retrieved using the built-in function of the Kakao Talk mobile messaging application. We collected demographic information and electronic medical records data, including patient age, sex, type of ED arrival, KTAS score, chief complaint, and ED disposition. The number of texts sent by patients and their usage times of the chat service were also recorded.

Text messages analysis

Texts were segmented into sentences for analysis. We excluded initial greetings, messages consisting only of simple responses (e.g., “yes” or “no”), and expressions of gratitude from the analysis. The text data were categorized by message topics, drawing on methods from a previous study that examined secure inpatient messaging [16]. The analysis focused on identifying messages that required physician involvement.

Survey questionnaire

After using the chat service, participants completed a survey structured around four domains: (1) demographic information, (2) satisfaction with the chat service, (3) perceived necessity of the chat service, and (4) user interface, with emphasis on relevance, efficiency, attitude, and learnability (REAL) framework [21]. The REAL framework provides a structured approach to evaluating interventions and services, emphasizing reusable design elements and clear documentation to support usability and consistency. Given the lack of empirical research on chat services in hospitals, we looked at similar services in other settings to select evaluation tools based on the REAL parameter [22, 23].

Responses were rated on a 5-point Likert scale, ranging from “strongly disagree” (1 point) to “strongly agree” (5 points). See the Supplementary File for the survey questions.

Interview

Interviews were conducted with both patients and family members to gain qualitative insights into their experiences with the ED chat service. Semi-structured interviews were conducted by SJ and two research nurses trained to conduct interviews. The interview themes and questions were developed using evidence from the existing literature [24]. They included open-ended questions that allowed interviewee to express themselves freely. The questions addressed the following topics: effectiveness in obtaining information, communication with healthcare workers, emotional support, potential challenges, and recommendations for service improvement. See the Supplementary File for the interview questions.

The interviews were conducted in person or by telephone, depending on participant preference. Interviews were recorded, transcribed, and analyzed independently. To analyze the interview data, we used Braun and Clarke’s six-step thematic analysis [25] and NVIVO V.11 software.

Privacy policy

The Institutional Review Board (IRB) of Samsung Medical Center reviewed and approved the privacy policy. To maintain confidentiality, all data collected through the chat service and interviews were anonymized by removing all personally identifiable information. Data collected during the study was securely stored on servers with restricted access. Only authorized research team members were granted access to the data, and all data transfers were encrypted to prevent unauthorized access.

Statistical analysis

Categorical data were expressed as frequencies and percentages. For continuous data, we tested for normal distribution before summarizing them as means (with standard deviations) or medians (with interquartile ranges). The analysis of sent and received messages was carried out by an emergency physician and an operations management specialist.

Results

A total of 21 patients and 20 family members participated in this study. The response rate for enrollment was 37.8%, and all enrolled participants completed the survey except one patient who did not use the chat service during the ED stay and declined to participate in the survey, resulting in 40 participants completing the questionnaire for analysis. In addition, five patients and five family members who used the ED chat service participated in semi-structured interviews, for a response rate of 66.7%.

Study population

The baseline characteristics of the study participants are presented in Table 1. All participants were proficient in sending and receiving messages. The majority of both patients and family members were in their 40s, with females comprising over half of the participants. Among the family members, only eight (40%) stayed with the patients in the ED treatment area, while the rest waited outside. The family members were mostly sons or daughters, followed by spouses, parents, and siblings. The total number of messages sent ranged from 2 to 20, with patients using the chat service for an average of 3.11 h (SD, 1.53) and family members for 4.06 h (SD, 4.87).

Table 1 Baseline characteristics of participants
Full size table

Topics of messages sent by participants

We received 72 messages from patients and 233 messages from family members. Messages were categorized as either related or unrelated to medical treatment. Medical-related messages covered 11 topics, including scheduling, ED processes, waiting times, symptoms/pain, diagnostic testing, results, medications, consultations, dietary issues, patient status, and requests for care providers. Six topics were identified for messages unrelated to medical treatment: insurance and payment, facilities, customer feedback, ED environment, presence of family members in the ED, and dashboard inquiries.

Detailed information on message topics is presented in Table 2. Within the patient group, inquiries about waiting times were the most common, accounting for 15.3% of messages. Other frequent topics included diagnostic testing (12.5%) and symptoms/pain (11.1%). Among family members, questions about waiting times (16.3%), diagnostic testing (12.4%), and ED processes (9.0%) were most prevalent. Family members more frequently used the ED chat service for non-medical topics, sending 85 relevant texts (36.4%) compared to 14 (19.5%) by patients.

Table 2 Topics of received chat messages
Full size table

Messages analysis according to sender

To assess the feasibility of the ED chat service, we explored the extent to which research nurses could address messages independently, without needing physician intervention. The findings are detailed in Table 3. Research nurses successfully sent a total of 245 messages. Of these, 70 (28.6%) messages were sent to patients instead of to family members. Twenty-nine messages (41.4%) from patients and 124 messages (70.9%) from family members were resolved through the chat service without physician assistance. However, six messages (8.6%) from patients and six messages (3.4%) from family members required physician involvement. Additionally, 19 (27.1%) messages to patients and 17 (9.7%) messages to family members communicated that the questions could not be answered through the chat service.

Table 3 Analysis of messages sent by chat service provider
Full size table

Survey outcome

The survey results are presented in Supplementary Table S1. In terms of service satisfaction, the average score for questions related to medical treatment was the highest, at 4.40 points (SD, 0.84), while the average score for the waiting time for diagnostic testing was the lowest, at 3.86 points (SD, 1.15). The usability evaluation based on the REAL model is detailed in Table 4. Participants rated the concept of a chat service in the ED highly, with an average score of 4.68 points (SD, 0.66). The efficiency of the chat service’s flexible application in the ED received a lower score of 4.38 points (SD, 0.87), but all eight items scored above 4 out of 5 points, indicating high usability.

Table 4 Questions and answers regarding usability
Full size table

Interview outcomes

We interviewed a subset of study participants to discuss major issues encountered when using a chat service in the ED environment. The interviews, with a median duration of 15 min (interquartile range: 11–22 min), were transcribed and categorized into three main themes.

Communication with healthcare workers

Patients generally provided more positive feedback than family members, noting the chat service facilitated easier communication with healthcare workers. They mentioned saving time and easily moving to subsequent questions, with the added benefit of being able to revisit the chat history on their mobile phones for any forgotten or misunderstood information. This feature was particularly appreciated, as patients often feel hesitant to ask questions that may seem trivial or unrelated to their medical condition due to the apparent busyness of ED staff.

[P14] “Receiving a lot of information at once can be overwhelming. Being able to review the chat history is incredibly helpful.”

[P16] “Seeing how busy the healthcare workers were, I was reluctant to ask minor questions. The chat service alleviated this concern, making it easier to ask whatever I needed.”

However, three family members found the chat service less effective in facilitating communication with healthcare workers.

[F12] “Although I could obtain information via the chat service, my request for painkillers was not accommodated, showing the service’s limitations in certain areas.”

[F17] “I preferred face-to-face interactions with doctors, which the chat service couldn’t provide, leading to a perceived gap in communication.”

Getting information

Participants expressed high satisfaction with the information received through the chat service, appreciating its promptness and accuracy. Both patients and family members confirmed their ability to access necessary information, including details about diagnostic plans, ED processes, waiting times, and received treatments. Despite the availability of mobile hospital applications and dashboards for general information, the chat service was praised for offering detailed and personalized information.

[P15] “The chat service promptly and accurately answered my dietary questions.”

[P18] “I was quickly provided with a portal link to view my lab results, which was very efficient.”

[F17] “The external dashboard gives a broad overview of the ED process, but it lacks detail. The chat service, on the other hand, provided timely and specific information, enhancing my satisfaction.”

Participants favored the chat service over verbal communication for its clarity, permanence, reliability, and accessibility.

[F14] “The chat service’s accessibility and the clarity of written communication surpassed verbal exchanges.”

Emotional support

The chat service also provided significant emotional support during the ED stay. Most patients and all family members felt that the chat service offered a comforting presence. For some, the mere existence of a two-way communication channel was enough to alleviate fears.

[P15] “I was afraid because I didn’t know what kinds of tests and treatments I would receive, but [the chat service] helped to ease the tension by providing me with such information in real time.”

[F13] “It reduced my anxiety. When the patient entered the ED, the family member waited outside with worry and anxiety, but the chat service answered the patient’s status, and it was possible to predict the time required, which helped to reduce anxiety.”

Discussion

This study represents the first investigation into the feasibility of a chat service in the ED, uncovering that it significantly addressed requests or inquiries, leading to high usability and satisfaction rates. Usability scores were particularly high among family members not physically present with the patient in the ED.

While the hospital offers various information systems, such as mobile apps and portal sites, for accessing personalized information [26,27,28,29], these systems are limited within the fast-paced ED environment, where patient conditions can change rapidly. Despite the availability of dashboards showing each patient’s ED process, feedback from family members indicated a need for more personalized information, underscoring the limitations of current unilateral information systems.

Our findings suggest that the chat service offers a viable and acceptable means to deliver personalized information to patients and their families in the ED. It proved instrumental in reducing anxiety and complaints by addressing numerous treatment-related questions. Although not every request for medical advice or information could be fulfilled through the chat service, the overall satisfaction was high, highlighting its ability to address non-medical concerns effectively.

The chat service has the potential to alleviate the workload of ED nurses. Often, nurses field questions from patients or family members that, while not directly related to their immediate tasks, disrupt their workflow and can lead to stress, impacting work efficiency and potentially patient safety [30,31,32]. By providing information on parking, insurance, and facilities through the chat service, we alleviated additional burdens on ED nurses. That is, a chat service in the ED could enhance nurse work efficiency by handling general inquiries and requests that do not necessitate specialized knowledge.

The rising implementation of chatbot services across various sectors, integrating AI with human assistance, points toward a future direction for enhancing ED chat services [33,34,35,36]. An AI chatbot could automate responses to common queries, with human operators stepping in when necessary [37, 38], suggesting a promising area for future research.

Limitations

The effectiveness of live chat interactions can vary depending on the communicator. We trained a research nurse and established chat protocols to ensure consistency. To maintain privacy, sensitive information regarding diagnosis and treatment was not provided via chat. However, addressing these requests in future services may increase acceptance and satisfaction. We provided this service through mobile phones, so patients with high-severity conditions or those who have difficulty using mobile phones were excluded. The requests or questions may vary depending on the severity of the patient’s illness. For example, family members of critically ill or unconscious patients may have more questions than those of patients with minor illnesses. Improving accessibility, possibly through speech recognition technology or other user-friendly platforms, is critical for wider implementation.

Conclusion

The ED chat service was found to be feasible and significantly improved the user experience by enhancing communication with healthcare workers, facilitating information acquisition, and providing emotional support. This innovation represents a valuable addition to emergency care, offering a new avenue for improving patient and family member experiences in the ED.

Data availability

No datasets were generated or analysed during the current study.

Abbreviations

ED:

Emergency Department

IRB:

Institutional Review Board

KTAS:

Korean Triage and Acuity Scale

REAL:

Relevance, efficiency, attitude, and learnability

References

  1. Lewis C, Riddington M, Hill M, Bevan C, Fisher J, Lyas L, et al. The communication and support from the health professional is incredibly important: a qualitative study exploring the processes and practices that support parental decision-making about postmortem examination. Prenat Diagn. 2019;39(13):1242–53.

    Article  PubMed  PubMed Central  Google Scholar 

  2. Brindley PG, Commentary. Communication: the most important Procedure in Healthcare and Bioethics. Camb Q Healthc Ethics. 2019;28(3):415–21.

    Article  PubMed  Google Scholar 

  3. Blackburn J, Ousey K, Goodwin E. Information and communication in the emergency department. Int Emerg Nurs. 2019;42:30–5.

    Article  PubMed  Google Scholar 

  4. Brennan RA, Keohane CA. How communication among members of the Health Care Team affects maternal morbidity and mortality. J Obstet Gynecol Neonatal Nurs. 2016;45(6):878–84.

    Article  PubMed  Google Scholar 

  5. Graham B, Endacott R, Smith JE, Latour JM. They do not care how much you know until they know how much you care’: a qualitative meta-synthesis of patient experience in the emergency department. Emerg Med J. 2019;36(6):355–63.

    Article  PubMed  Google Scholar 

  6. Potter AR, Sauzet O, Borde T, Naghavi B, Razum O, Sehouli J et al. Influence of appropriate emergency department utilization and verbal communication on physicians’ (dis)satisfaction with doctor-patient interactions with special consideration of migrational backgrounds. Wien Med Wochenschr. 2022.

  7. McIntyre H, Reeves V, Loughhead M, Hayes L, Procter N. Communication pathways from the emergency department to community mental health services: a systematic review. Int J Ment Health Nurs. 2022.

  8. Dorsey BF, Kamimura A, Cook LJ, Kadish HA, Cook HK, Kang A, et al. Communication gaps between providers and caregivers of patients in a Pediatric Emergency Department. J Patient Exp. 2022;9:23743735221112223.

    PubMed  PubMed Central  Google Scholar 

  9. Carpenter CR, Leggett J, Bellolio F, Betz M, Carnahan RM, Carr D, et al. Emergency Department Communication in persons living with dementia and Care partners: a scoping review. J Am Med Dir Assoc. 2022;23(8):1313. e15- e46.

    Article  PubMed Central  Google Scholar 

  10. Yoo S, Lee KH, Baek H, Ryu B, Chung E, Kim K, et al. Development and user research of a Smart Bedside Station System toward patient-centered Healthcare System. J Med Syst. 2015;39(9):86.

    Article  PubMed  Google Scholar 

  11. Ryu B, Kim S, Lee KH, Hwang H, Yoo S. Inpatient satisfaction and usage patterns of personalized smart bedside station system for patient-centered service at a tertiary university hospital. Int J Med Inf. 2016;95:35–42.

    Article  Google Scholar 

  12. Lam TYT, Hui AJ, Sia F, Wong MY, Lee CCP, Chung KW, et al. Short Message Service reminders reduce outpatient colonoscopy nonattendance rate: a randomized controlled study. J Gastroenterol Hepatol. 2021;36(4):1044–50.

    Article  PubMed  Google Scholar 

  13. Youssef A. Use of short message service reminders to improve attendance at an internal medicine outpatient clinic in Saudi Arabia: a randomized controlled trial. East Mediterr Health J. 2014;20(5):317–23.

    Article  CAS  PubMed  Google Scholar 

  14. Walker DM, Sieck CJ, Menser T, Huerta TR, Scheck McAlearney A. Information technology to support patient engagement: where do we stand and where can we go? J Am Med Inf Assoc. 2017;24(6):1088–94.

    Article  Google Scholar 

  15. Prey JE, Woollen J, Wilcox L, Sackeim AD, Hripcsak G, Bakken S, et al. Patient engagement in the inpatient setting: a systematic review. J Am Med Inf Assoc. 2014;21(4):742–50.

    Article  Google Scholar 

  16. Sieck CJ, Walker DM, Hefner JL, Volney J, Huerta TR, McAlearney AS. Understanding Secure Messaging in the Inpatient Environment: a New Avenue for Communication and Patient Engagement. Appl Clin Inf. 2018;9(4):860–8.

    Article  Google Scholar 

  17. Wilkinson TA, Berardi MR, Crocker EA, Nordt C, Silverstein M. Feasibility of using text message reminders to increase fulfilment of emergency contraception prescriptions by adolescents. J Fam Plann Reprod Health Care. 2017;43(1):79–80.

    Article  PubMed  Google Scholar 

  18. Salinero EA, Ramirez J, Cramm-Morgan K, Papa L. Does receiving a text message reminder increase follow-up Compliance after Discharge from a Pediatric Emergency Department? Pediatr Emerg Care. 2021;37(9):e507–11.

    Article  PubMed  Google Scholar 

  19. Burner E, Zhang M, Terp S, Ford Bench K, Lee J, Lam CN, et al. Feasibility and acceptability of a text message-based intervention to reduce overuse of Alcohol in Emergency Department patients: controlled proof-of-Concept Trial. JMIR Mhealth Uhealth. 2020;8(6):e17557.

    Article  PubMed  PubMed Central  Google Scholar 

  20. Choi S-E. The most popular apps in the first half of the year: KakaoTalk, YouTube, Naver in order. MADTIMES. 2023. Retrieved from https://www.madtimes.org/news/articleView.html?idxno=17956

  21. Löwgren J, Laurén U. Supporting the use of guidelines and style guides in professional user interface design. Interact Comput. 1993;5(4):385–96.

    Article  Google Scholar 

  22. Matteson ML, Salamon J, Brewster LA, Systematic Review of Research on Live Chat Service, Reference. & User Services Quarterly; Vol 51, No 2 (2011): WinterDO – 10.5860/rusq.51n2.172. 2011.

  23. Åberg J, Shahmehri N. The role of human web assistants in e-commerce: an analysis and a usability study. Internet Res. 2000;10(2):114–25.

    Article  Google Scholar 

  24. Nuzhat Naz FGMA. Development of qualitative semi-structured interview guide for Case Study Research. Competitive Social Sci Res J. 2022;3(2):42–52.

    Google Scholar 

  25. Braun V, Clarke V. Using thematic analysis in psychology. Qualitative Res Psychol. 2006;3(2):77–101.

    Article  Google Scholar 

  26. Drapeau AI, Onwuka A, Koppera S, Leonard JR. Hospital Case-volume and patient outcomes following Pediatric Brain Tumor surgery in the Pediatric Health Information System. Pediatr Neurol. 2022;133:48–54.

    Article  PubMed  Google Scholar 

  27. Huang S, Kuo ML, Yu HM, Huang CH, Shieh WY, Hsu WH, et al. Clinical information and guidance shared via a patient infotainment system can reduce hospital stay and maintain 2 medical quality for total knee arthroplasty: a single-blinded quasi-randomised controlled trial. Int J Nurs Stud. 2020;104:103440.

    Article  PubMed  Google Scholar 

  28. Abhichaya A, Songkhamchai L, Buavaroon S, Surasak T. The Quality Improvement Information System for Surveillance and Monitoring for Patient Safety and Personal Safety in Kalasin Hospital, Kalasin Province, Thailand. Stud Health Technol Inf. 2020;272:67–70.

    Google Scholar 

  29. Mohan PL, Shaji S, Ashraf T, Anas VU, Basheer B. Effectiveness of a reminder card system versus a mobile application to improve medication adherence among asthma patients in a tertiary care hospital. J Taibah Univ Med Sci. 2018;13(6):541–6.

    PubMed  PubMed Central  Google Scholar 

  30. Wundavalli L, Kumar P, Dutta S. Workload indicators of staffing need as a tool to determine nurse staffing for a high volume academic Emergency Department: an observational study. Int Emerg Nurs. 2019;46:100780.

    Article  PubMed  Google Scholar 

  31. Udod S, MacPhee M, Wagner JIJ, Berry L, Perchie G, Conway A. Nurse perspectives in the emergency department: the synergy tool in workload management and work engagement. J Nurs Manag. 2021;29(6):1763–70.

    Article  PubMed  Google Scholar 

  32. Korn R, Mansfield M, editors. ED overcrowding: an assessment tool to monitor ED registered nurse workload that accounts for admitted patients residing in the emergency department. J Emerg Nurs. 2008;34(5):441-6.

  33. Martinengo L, Lum E, Car J. Evaluation of chatbot-delivered interventions for self-management of depression: content analysis. J Affect Disord. 2022;319:598–607.

    Article  PubMed  Google Scholar 

  34. Luk TT, Lui JHT, Wang MP. Efficacy, usability, and acceptability of a Chatbot for promoting COVID-19 vaccination in unvaccinated or booster-hesitant young Adults: Pre-post Pilot Study. J Med Internet Res. 2022;24(10):e39063.

    Article  PubMed  PubMed Central  Google Scholar 

  35. Jin E, Eastin MS. When a Chatbot smiles at you: the psychological mechanism underlying the effects of Friendly Language Use by Product Recommendation Chatbots. Cyberpsychol Behav Soc Netw. 2022;25(9):597–604.

    Article  PubMed  Google Scholar 

  36. Jiang Q, Zhang Y, Pian W. Chatbot as an emergency exist: mediated empathy for resilience via human-AI interaction during the COVID-19 pandemic. Inf Process Manag. 2022;59(6):103074.

    Article  PubMed  PubMed Central  Google Scholar 

  37. Collobert R, Weston J, Bottou L, Karlen M, Kavukcuoglu K, Kuksa P. Natural Language Processing (almost) from scratch. J Mach Learn Res. 2011;12(null):2493–537.

    Google Scholar 

  38. Battineni G, Chintalapudi N, Amenta F. AI Chatbot Design during an Epidemic like the Novel Coronavirus. Healthc (Basel). 2020;8(2).

Download references

Acknowledgements

This study was supported by the Institute of Management Research at Seoul National University.

Funding

Not applicable.

Author information

Authors and Affiliations

  1. Department of Emergency Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, 06355, Republic of Korea

    Sejin Heo, Se Uk Lee, Sung Yeon Hwang, Hee Yoon, Tae Gun Shin, Hansol Chang, Taerim Kim & Won Chul Cha

  2. Department of Digital Health, Samsung Advanced Institute for Health Science & Technology (SAIHST), Sungkyunkwan University, Seoul, 06355, Republic of Korea

    Won Chul Cha

  3. SNU Business School, Seoul National University, Seoul, 08826, Republic of Korea

    Song-Hee Kim

Authors
  1. Sejin Heo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Song-Hee Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Se Uk Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Sung Yeon Hwang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Hee Yoon
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Tae Gun Shin
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Hansol Chang
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Taerim Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Won Chul Cha
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

W.-C.C. contributed to the idea and design of the study. S.H. contributed to the development of chat instructions, prepared the survey questionnaire, and analyzed the text messages, survey results, and interview results. S.-H.K. and S.H. wrote the draft, and S.-U.L. and S.-Y.H. contributed to subsequent drafts. H.Y., T.-G.S., C.H. advised on data analysis and contributed to the chat service process. T.-R.K. reviewed data interpretation. All authors read and approved the final version of the report.

Corresponding author

Correspondence to Won Chul Cha.

Ethics declarations

Ethics approval and consent to participate

Samsung Medical Center’s Institutional Review Board (IRB) approved this research protocol (IRB No. 2022-02-024-002). Informed consent was obtained from all participants before enrollment in the study, in accordance with IRB policies.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary Table S1. Survey outcomes of participants.

Supplementary Material 2

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Heo, S., Kim, SH., Lee, S.U. et al. A trial of a chat service for patients and their family members in an emergency department. BMC Health Serv Res 24, 1058 (2024). https://doi.org/10.1186/s12913-024-11414-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1186/s12913-024-11414-0

Keywords

BMC Health Services Research

ISSN: 1472-6963

Contact us