Beyond the Checklist: Designing Emotional Engagement in Conversational Chatbots for Medical Education, between Dyadic and Triadic Interaction.
Parole chiave:
Conversational Chatbots; Engagement; Medical Humanities.Abstract
The integration of artificial intelligence (AI) into medical training opens up extraordinary opportunities to practice communication and interpersonal skills in simulated environments with virtual patients. However, excessive reliance on technology carries the risk of reducing clinical empathy to a purely procedural task, thereby compromising the authenticity of the care provided by doctors. This paper addresses this tension and examines pedagogical and design criteria for the development of chatbots based on Large Language Models (LLMs). The aim is to foster genuine cognitive, emotional and relational engagement amongst medical students. Methodologically, the study proposes a theoretical and conceptual synthesis based on a critical re-analysis of two complementary scoping reviews: The first analysis identifies design requirements for dyadic interaction (doctor and adult patient), while the second extends these parameters to the pediatric context, where the presence of a caregiver gives rise to a more complex triadic dynamic. The study develops a theoretical framework rooted in the “Medical Humanities” and defines pedagogical indicators to avoid the reification of empathy. The results provide a conceptual reference architecture for the future implementation of conversation simulators that can support socio-affective learning and contribute to a more humanized clinical practice.
Riferimenti bibliografici
Abedi, A. J., Jain, A., Zubair, M. Y., Mehnaz, S., & Sujir, N. R. (2025). Community-based interprofessional training for undergraduate medical students through family adoption programme centering on infant and young child feeding. Indian Journal of Community Health, 37(5), 787–794. https://doi.org/10.47203/IJCH.2025.v37i05.024
Ba, H., Xu, L., Gu, Y., Li, Y., Jiang, X., Li, X., & Li, S. (2025). Comparative study of problem-based learn-ing and traditional teaching methods on medical students’ outcomes in pediatrics clerkships. Advances in medical education and practice, 615-624. https://doi.org/10.2147/AMEP.S515527
Baile, W. F., Buckman, R., Lenzi, R., Glober, G., Beale, E. A., & Kudelka, A. P. (2000). SPIKES—a six-step protocol for delivering bad news: application to the patient with cancer. The oncologist, 5(4), 302-311. https://doi.org/10.1634/theoncologist.5-4-302
Borg, A., Jobs, B., Huss, V., Gentline, C., Espinosa, F., Ruiz, M., ... & Parodis, I. (2024). Enhancing clinical reasoning skills for medical students: a qualitative comparison of LLM-powered social robotic versus computer-based virtual patients within rheumatology. Rheumatology International, 44(12), 3041-3051. https://doi.org/10.1007/s00296-024-05731-0
Brandt, J. B., Bibl, K., Grafeneder, J., Masel, E. K., Bergsträsser, E., Aburn, G., ... & Peyrl, A. (2026). The SimCom-Method: Impact of Simulated Communication Teaching in Pediatric Resuscitation Scenarios. Academic Pediatrics, 103204. https://doi.org/10.1016/j.acap.2025.103204
Brügge, E., Ricchizzi, S., Arenbeck, M., Keller, M. N., Schur, L., Stummer, W., ... & Darici, D. (2024). Large language models improve clinical decision making of medical students through patient simulation and structured feedback: a randomized controlled trial. BMC medical education, 24(1), 1391. https://doi.org/10.1186/s12909-024-06399-7
Chiu, J., Castro, B., Ballard, I., Nelson, K., Zarutskie, P., Olaiya, O. K., ... & Zhao, Y. (2025). Exploration of the role of ChatGPT in teaching communication skills for medical students: A pilot study. Medical Sci-ence Educator, 35(4), 1871-1882. https://doi.org/10.1007/s40670-025-02394-9
Comulada, W. S., Ganz, P. A., Huang, Y. M., Weisman, D., Sugarman, A., Lee, D., ... & Sugarman, A. W. (2025). A pilot test of an AI voice-driven simulation with feedback for medical students to practice dis-cussing diagnostic mammogram results With patients. Cureus, 17(10). https:/doi.org/10.7759/cureus.95606
de Araújo Baptista, V. I., Braga, L. P., de Sousa Mata, Á. N., Carreiro, B. O., dos Santos Rosa, L. P. G., de Morais, H. H. A., ... & Appenzeller, S. (2024). Validation of clinical simulation scenarios for the teach-ing of soft skills in child-centered care. BMC Medical Education, 24(1), 355. https://doi.org/10.1186/s12909-024-05284-7
De Padova, V., Amatori, G., & Dipace, A. (2026). L’uso dell’Intelligenza Artificiale nella formazione medica pre-laurea: una Scoping Review. MEDICAL HUMANITIES & MEDICINA NARRATIVA, 12(1), 243-260. https://doi.org/10.53136/979122182756917
De Padova, V., Amatori, G., & Dipace, A. (in press). Communication and Empathy Skills Training in Pedia-tric Settings in Undergraduate Medical Education: A Scoping Review, Paper presented at the 8th Interna-tional Conference on Higher Education Learning Methodologies and Technologies Online (HELMeTO 2026), Cagliari, Italy, September 28-30, 2026.
Fredricks, J. A., Blumenfeld, P. C., & Paris, A. H. (2004). School engagement: Potential of the concept, state of the evidence. Review of educational research, 74(1), 59-109. https://doi.org/10.3102/00346543074001059
Frost, K. A., Metcalf, E. P., Brooks, R., Kinnersley, P., Greenwood, S. R., & Powell, C. V. (2015). Teaching pediatric communication skills to medical students. Advances in medical education and practice, 35-43. https://doi.org/10.2147/AMEP.S68413
Gao, C., Plansky, C., Ferguson, N., Caputo-Seidler, J., Weiss, A., & Kiluk, V. (2026). Adolescent-Parent Dyad and Adolescent Eating Disorders: A Standardized Patient Simulation. Cureus, 18(1). https://doi.org/10.7759/cureus.101237
Guo, E., Ramchandani, R., Park, Y. J., & Gupta, M. (2025). OSCEai: personalized interactive learning for un-dergraduate medical education. Canadian Medical Education Journal, 16(6), 7-14. https://doi.org/10.36834/cmej.79220
Holderried, F., Stegemann-Philipps, C., Herrmann-Werner, A., Festl-Wietek, T., Holderried, M., Eickhoff, C., & Mahling, M. (2024a). A language model–powered simulated patient with automated feedback for his-tory taking: Prospective study. JMIR Medical Education, 10, e59213. https://doi.org/10.2196/59213
Holderried, F., Stegemann-Philipps, C., Herschbach, L., Moldt, J.-A., Nevins, A., Griewatz, J., Holderried, M., Herrmann-Werner, A., Festl-Wietek, T., & Mahling, M. (2024b). A generative pretrained trans-former (GPT)–powered chatbot as a simulated patient to practice history taking: Prospective, mixed methods study. JMIR Medical Education, 10, e53961. https://doi.org/10.2196/53961
Hryszko, J., Michałek, A., & Roman, A. (2026). Application of large language models in medical interview training: a study with medical students. BMC Medical Education, 26(1), 586. https://doi.org/10.1186/s12909-026-08819-2
Kis, H., Endres, K., Karwowska, A., Harrison, M., Lau, S., Lemire, O., & Zucker, M. (2022). “Teddy Bear Hospital Project” school visits improve pre-clerkship students’ comfort explaining medical concepts to children. Canadian Medical Education Journal, 13(3), 70-74. https://doi.org/10.36834/cmej.73167
Kurtz, S. M., & Silverman, J. D. (1996). The Calgary-Cambridge Referenced Observation Guides: an aid to defining the curriculum and organizing the teaching in communication training programmes. Medical Education, 30(2), 83–89. https://doi.org/10.1111/j.1365-2923.1996.tb00724.x
Liu, Y., Shi, C., Wu, L., Lin, X., Chen, X., Zhu, Y., ... & Zhang, W. (2025). Development and validation of a large language model-based system for medical history-taking training: prospective multicase study on evaluation stability, human-AI consistency, and transparency. JMIR Medical Education, 11(1), e73419. https://doi.org/10.2196/73419
McCall, N., Bekele, A., Ewnte, B., Abaho, J., & Ibrahim, O. (2024). Child standardized patients in pediatric OSCEs: a feasibility study for otoscope examination among undergraduate students in Rwanda. BMC Medical Education, 24(1), 1546. https://doi.org/10.1186/s12909-024-06587-5
McCarrick, C. A., McEntee, P. D., Boland, P. A., Donnelly, S., O’Meara, Y., Heneghan, H., & Cahill, R. A. (2025). A randomized controlled trial of a deep language learning model-based simulation tool for un-dergraduate medical students in surgery. Journal of Surgical Education, 82(9), 103629. https://doi.org/10.1016/j.jsurg.2025.103629
Mukadam, A., Suresh, S., & Jacobs, C. (2025). Beyond traditional simulation: an exploratory study on the effectiveness and acceptability of ChatGPT 4o advanced voice mode for communication skills practice among medical students. Cureus, 17(5). https://doi.org/10.7759/cureus.84381
Paglialonga, M., & Simonetti, C. (2025). Beyond the algorithm: the importance of medical humanities in the age of AI. Monash Bioethics Review, 1-13. https://doi.org/10.1007/s40592-025-00259-w
Peralta Ramírez, A. A., Trujillo López, S., Navarro Armendariz, G. A., De la Torre Othón, S. A., Sierra Cer-vantes, M. R., & Medina Aguirre, J. A. (2025). Clinical simulation with ChatGPT: a revolution in medi-cal education?. Journal of CME, 14(1), 2525615. https://doi.org/10.1080/28338073.2025.2525615
Persson, E., Haines, C., & Lang, M. (2013). Parent assessment of medical student’s skills in ambulatory pedi-atrics. Canadian Medical Education Journal, 4(2), e18.
Schwarz, H. L., Straub, C., Bode, S. F., Ferschl, N., Brickmann, C., Berberat, P. O., & Krüger, M. (2025). Learning and working on an interprofessional training ward in neonatology improves interprofessional competencies. Frontiers in medicine, 12, 1483551. https://doi.org/10.3389/fmed.2025.1483551
Tervajärvi, L., Tervajärvi, S., Storvik-Sydänmaa, S., & Hutri, N. (2024). Using Simulation Exercises to Deal With the Death of a Child as Part of Healthcare Studies. Cureus, 16(1). https://doi.org/10.7759/cureus.53284
Thng, J. Z. H., Tan, F. Y. Y., Aw, M. M. H. Y., & Hu, S. (2022). Combination of teddy bear hospital and virtual reality training increases empathy of medical students. The Asia Pacific Scholar, 7(3), 33. https://doi.org/10.29060/TAPS.2022-7-3/OA2739
Tian, J. D., Wu, F. F., & Wen, C. (2022). Effects of a teaching mode combining SimBaby with standardized patients on medical students’ attitudes toward communication skills. BMC Medical Education, 22(1), 825. https://doi.org/10.1186/s12909-022-03869-8
Tyrrell, E. G., Sandhu, S. K., Berry, K., Ghannam, S. F., Lewis, S. A., Crowfoot, D., Sahota, G. S., Carson, J., Wilson, E. E., & Taggar, J. (2025). Web-based AI-driven virtual patient simulator versus actor-based simulation for teaching consultation skills: Multicenter randomized crossover study. JMIR Formative Research, 9, e71667. https://doi.org/10.2196/71667
Wang, Z., Fan, T.-T., Li, M.-L., Zhu, N.-J., & Wang, X.-C. (2025). Feasibility study of using GPT for histo-ry-taking training in medical education: A randomized clinical trial. BMC Medical Education, 25, 1030. https://doi.org/10.1186/s12909-025-07614-9
Woods, J. L., Pasold, T. L., Boateng, B. A., & Hensel, D. J. (2014). Medical student self-efficacy, knowledge and communication in adolescent medicine. International Journal of Medical Education, 5, 165. https://doi.org/10.5116/ijme.53d3.7b30
Yamamoto, A., Koda, M., Ogawa, H., Miyoshi, T., Maeda, Y., Otsuka, F., & Ino, H. (2024). Enhancing med-ical interview skills through AI-simulated patient interactions: nonrandomized controlled trial. JMIR medical education, 10(1), e58753. https://doi.org/10.2196/58753
Yu, H., Zhou, J., Li, L., Chen, S., Gallifant, J., Shi, A., ... & Fan, L. (2026). Simulated patient systems pow-ered by large language model-based AI agents offer potential for transforming medical education. Com-munications Medicine, 6(1), 27 https://doi.org/10.1038/s43856-025-01283-x
##submission.downloads##
Pubblicato
Come citare
Fascicolo
Sezione
Licenza
Copyright (c) 2026 Valeria De Padova, Gianluca Amatori, Anna Dipace

Questo lavoro è fornito con la licenza Creative Commons Attribuzione - Non commerciale - Non opere derivate 4.0 Internazionale.