Evaluating the Impact of AI Chatbots on Appointment Attendance and Patient Satisfaction in U.S. Primary and Specialty Care
Keywords:
AI chatbot, no-show appointments, patient satisfaction, digital health, U.S. healthcare, primary care, specialized care, regression analysis, chatbot usability, healthcare technologyAbstract
Utilization of AI chatbots in health care is continuing to grow as it can improve the quality of services, decrease administrative efforts and increase patient engagement. This study sought to determine if these tools reduce appointment no show rates and increase patient satisfaction in the U.S.-based healthcare systems. A cross-sectional survey conducted among a sample size of 400 adults by administering close-ended questionnaires. Statistical methods were chi-square tests, Mann–Whitney U-test, Kruskal Wallis H-test, independent t-tests and multiple linear regression. The results of the study demonstrated that chatbots had little influence on reducing no-show appointments (p =. 985). However, satisfaction, usability and adequacy of chatbot responses exerted 227 a strong indirect effect on general patient experience (R² = 0.47). Furthermore, clear responses were associated with perceiving a sense of connection with a provider (p =. 003) and were more satisfied with their chatbot recommendation (p =. 040). Taken together, our findings are supportive AI chatbots to improve patient satisfaction more so through usability and communication than by simply providing the treatment adherence reminders. When used culturally mindful, well-supervised and real-time monitored chatbots can help to improve more patient-centered care in primary care.
References
[1] M. Al Jnainati et al., “Transforming paperwork with AI: Applications across healthcare and other industries,” AI & Society, pp. 1–14, 2025.
[2] Y. M. AlSerkal et al., “Real-time analytics and AI for managing no-show appointments in primary health care in the United Arab Emirates: Before-and-after study,” JMIR Formative Research, vol. 9, art. e64936, 2025.
[3] K. Aij, J. Knoester, and B. Werkhoven, “An artificial intelligence-based model to reduce the no-show rate in outpatient clinics of an academic hospital,” 2024.
[4] A. L. Apio, J. Kissi, and E. K. Achampong, “A systematic review of artificial intelligence-based methods in healthcare,” Int. J. Public Health, vol. 12, art. 1259, 2023.
[5] Y. Bombard, G. S. Ginsburg, A. C. Sturm, A. Y. Zhou, and A. A. Lemke, “Digital health-enabled genomics: Opportunities and challenges,” Am. J. Hum. Genet., vol. 109, no. 7, pp. 1190–1198, 2022.
[6] E. Buijs, E. Maggioni, G. Carrafiello, F. Mazziotta, and F. Lega, “Artificial intelligence and healthcare applications,” in Artificial Intelligence. Bingley, U.K.: Emerald Publishing, 2024, pp. 21–48.
[7] A. M. Chen, “Crossing the digital chasm: A narrative review on how technology can improve healthcare access,” J. Hosp. Manag. Health Policy, vol. 8, 2024.
[8] C. O. Diyaolu, “Multi-agent AI systems for adaptive, culturally-concordant care routing in postpartum depression across Medicaid-dependent populations,” 2024.
[9] A. Haller and B. Reynolds, “Organizational perspective,” in Digital Health. London, U.K.: Academic Press, 2025, pp. 469–480.
[10] S. N. Imam, U. K. Braun, M. A. Garcia, and L. K. Jackson, “Evolution of telehealth—Its impact on palliative care and medication management,” Pharmacy, vol. 12, no. 2, art. 61, 2024.
[11] M. Javeedullah, “Using health informatics to streamline healthcare operations,” Am. J. Artif. Intell. Comput., vol. 1, no. 1, pp. 24–44, 2025.
[12] A. A. Kasasbeh, Applying Artificial Intelligence and Machine Learning to Improve Healthcare Outcomes in Marginalized Patient Populations, Ph.D. dissertation, State Univ. of New York at Binghamton, 2023.
[13] B. Kumar et al., “The role of AI in optimizing healthcare appointment scheduling,” in Proc. 3rd Int. Conf. Disruptive Technologies (ICDT). Piscataway, NJ, USA: IEEE, Mar. 2025, pp. 881–887.
[14] S. Maleki Varnosfaderani and M. Forouzanfar, “The role of AI in hospitals and clinics: Transforming healthcare in the 21st century,” Bioengineering, vol. 11, no. 4, art. 337, 2024.
[15] S. R. Milford, “Accuracy is inaccurate: Why a focus on diagnostic accuracy for medical chatbot AIs will not lead to improved health outcomes,” Bioethics, 2025.
[16] J. Pawelczyk et al., “Advancing musculoskeletal care using AI and digital health applications: A review of commercial solutions,” HSS Journal, 2025.
[17] M. H. Rahman, K. M. R. Hossan, M. K. S. Uddin, and M. D. Hossain, “Improving collaborative interactions between humans and artificial intelligence to achieve optimal patient outcomes in the healthcare industry,” SSRN, art. 5029975, 2024.
[18] M. Z. Rahman and M. S. A. Bhuiyan, “SMS medicine: Revolutionizing healthcare delivery through mobile technology,” Ann. Innov. Med., vol. 2, no. 4, 2024.
[19] N. C. Tan, R. H. L. Lim, and D. C. C. Ng, “Supporting quadruple aim in primary care using artificial intelligence,” 2025.
[20] G. Vijayasekaran et al., “A novel AI-assisted e-consult platform integrating deep learning for enhanced healthcare access and diagnostic precision,” in Proc. Int. Conf. Multi-Agent Systems for Collaborative Intelligence (ICMSCI). Piscataway, NJ, USA: IEEE, Jan. 2025, pp. 1103–1108.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 MD ASIF HASAN, Md. Tanvir Rahman Mazumder , Md. Caleb Motari, Md. Shahadat Hossain Shourov, Mrinmoy Sarkar, Tamanna Anjum Toma
This work is licensed under a Creative Commons Attribution 4.0 International License.
