ARTIFICIAL INTELLIGENCE CHATBOTS IN PATIENT EDUCATION: OPPORTUNITIES, RISKS, AND ETHICAL CHALLENGES

Wiktoria Sęk; Agata  Kowalczyk; Magdalena  Fąfara; Margarita Jeczkało; Monika Kosiorowska; Joanna  Lasoń; Marcelina Makulska; Weronika Płachta; Amelia Sieradzka; Cezary Wegenko

doi:10.31435/ijitss.2(50).2026.5829

Authors

Wiktoria Sęk Collegium Medicum Jan Kochanowski University in Kielce, Kielce, Poland https://orcid.org/0009-0001-3452-7025
Agata Kowalczyk Collegium Medicum Jan Kochanowski University in Kielce, Kielce, Poland https://orcid.org/0009-0000-9027-7270
Magdalena Fąfara Collegium Medicum Jan Kochanowski University in Kielce, Kielce, Poland https://orcid.org/0009-0001-8524-9870
Margarita Jeczkało Collegium Medicum Jan Kochanowski University in Kielce, Kielce, Poland https://orcid.org/0009-0003-1103-090X
Monika Kosiorowska Collegium Medicum Jan Kochanowski University in Kielce, Kielce, Poland https://orcid.org/0009-0002-5447-6365
Joanna Lasoń Collegium Medicum Jan Kochanowski University in Kielce, Kielce, Poland https://orcid.org/0009-0004-7463-7626
Marcelina Makulska Collegium Medicum Jan Kochanowski University in Kielce, Kielce, Poland https://orcid.org/0009-0008-2075-106X
Weronika Płachta Collegium Medicum Jan Kochanowski University in Kielce, Kielce, Poland https://orcid.org/0009-0003-2460-9435
Amelia Sieradzka Collegium Medicum Jan Kochanowski University in Kielce, Kielce, Poland https://orcid.org/0009-0005-9588-3065
Cezary Wegenko Collegium Medicum Jan Kochanowski University in Kielce, Kielce, Poland https://orcid.org/0009-0005-4920-7963

DOI:

https://doi.org/10.31435/ijitss.2(50).2026.5829

Keywords:

Artificial Intelligence, Chatbots, Patient Education, Health Literacy, Large Language Models; Medical Ethics

Abstract

Artificial intelligence chatbots and large language models are increasingly used to obtain, simplify, and personalize medical information for patients. This narrative medical review synthesizes 40 recent studies on chatbot-supported patient education across emergency medicine, cardiology, oncology, ophthalmology, gastroenterology, dermatology, orthopedics, otolaryngology, urology, pain medicine, nursing, and health-literacy research. The review evaluates opportunities, risks, and ethical challenges associated with patient-facing AI communication. The evidence suggests that chatbots can generate fluent explanations, improve access to plain-language materials, support appointment preparation, and reduce the workload of drafting educational content. However, important limitations recur across the literature, including excessive reading level, incomplete or unsafe advice, weak source transparency, fabricated references, model variability, language-related inequity, and patient overtrust in fluent but unverified answers. Ethically acceptable implementation should therefore treat chatbots as supervised communication-support tools rather than autonomous medical educators. Clinical use should require clinician-approved source material, explicit AI disclosure, readability testing, escalation instructions, model-version documentation, multilingual validation, and post-deployment monitoring. Under such safeguards, AI chatbots may strengthen patient education, but unsupervised deployment may intensify existing problems in online medical information.

References

Abdelmalek, G., Uppal, H., Garcia, D., Farshchian, J., Emami, A., & McGinniss, A. (2025). Leveraging ChatGPT to produce patient education materials for common hand conditions. Journal of Hand Surgery Global Online, 7, 37–40. https://doi.org/10.1016/j.jhsg.2024.10.002

Almagazzachi, A., Mustafa, A., Eighaei Sedeh, A., Vazquez Gonzalez, A. E., Polianovskaia, A., Abood, M., Abdelrahman, A., Muyolema Arce, V., Acob, T., & Saleem, B. (2024). Generative artificial intelligence in patient education: ChatGPT takes on hypertension questions. Cureus, 16(2), e53441. https://doi.org/10.7759/cureus.53441

Armbruster, J., Bussmann, F., Rothhaas, C., Titze, N., Grutzner, P. A., & Freischmidt, H. (2024). Doctor ChatGPT, can you help me? The patient’s perspective: Cross-sectional study. Journal of Medical Internet Research, 26, e58831. https://doi.org/10.2196/58831

Ayers, J. W., Poliak, A., Dredze, M., Leas, E. C., Zhu, Z., Kelley, J. B., Faix, D. J., Goodman, A. M., Longhurst, C. A., Hogarth, M., & Smith, D. M. (2023). Comparing physician and artificial intelligence chatbot responses to patient questions posted to a public social media forum. JAMA Internal Medicine, 183(6), 589–596. https://doi.org/10.1001/jamainternmed.2023.1838

Ayre, J., Mac, O., McCaffery, K., McKay, B. R., Liu, M., Shi, Y., Rezwan, A., & Dunn, A. G. (2024). New frontiers in health literacy: Using ChatGPT to simplify health information for people in the community. Journal of General Internal Medicine, 39(4), 573–577. https://doi.org/10.1007/s11606-023-08469-w

Campbell, D. J., Estephan, L. E., Mastrolonardo, E. V., Amin, D. R., Huntley, C. T., & Boon, M. S. (2023). Evaluating ChatGPT responses on obstructive sleep apnea for patient education. Journal of Clinical Sleep Medicine, 19(12), 1989–1995. https://doi.org/10.5664/jcsm.10728

Cohen, S. A., Fisher, A. C., Xu, B. Y., & Song, B. J. (2024). Comparing the accuracy and readability of glaucoma-related question responses and educational materials by Google and ChatGPT. Journal of Current Glaucoma Practice, 18(3), 111–115. https://doi.org/10.5005/jp-journals-10078-1448

Covarrubias, O., Ghanem, D., Murdock, C., Domes, C., & Shafiq, B. (2025). Improving the readability of trauma patient education materials: A ChatGPT solution demonstrated using materials by the Orthopaedic Trauma Association. OTA International, 8(2), e417. https://doi.org/10.1097/OI9.0000000000000417

Dejenie, R. A., Gantt, B. K., Alexis, M. M., Shockley, S. M., Foote, K., Woolfolk, M. S., Banyard, D., & Butler, P. D. (2026). Bridging the gap: A pilot study using artificial intelligence to make plastic surgery research accessible. Plastic and Reconstructive Surgery—Global Open, 14, e7539. https://doi.org/10.1097/GOX.0000000000007539

Gencer, A. (2024). Readability analysis of ChatGPT’s responses on lung cancer. Scientific Reports, 14, 17234. https://doi.org/10.1038/s41598-024-67293-2

Gibson, D., Jackson, S., Shanmugasundaram, R., Seth, I., Siu, A., Ahmadi, N., Kam, J., Mehan, N., Thanigasalam, R., Jeffery, N., Patel, M. I., & Leslie, S. (2024). Evaluating the efficacy of ChatGPT as a patient education tool in prostate cancer: Multimetric assessment. Journal of Medical Internet Research, 26, e55939. https://doi.org/10.2196/55939

Golan, R., Ripps, S. J., Reddy, R., Loloi, J., Bernstein, A. P., Connelly, Z. M., Golan, N. S., & Ramasamy, R. (2023). ChatGPT’s ability to assess quality and readability of online medical information: Evidence from a cross-sectional study. Cureus, 15(7), e42214. https://doi.org/10.7759/cureus.42214

Gondode, P., Duggal, S., Garg, N., Sethupathy, S., Asai, O., & Lohakare, P. (2024). Comparing patient education tools for chronic pain medications: Artificial intelligence chatbot versus traditional patient information leaflets. Indian Journal of Anaesthesia, 68(7), 631–636. https://doi.org/10.4103/ija.ija_204_24

He, Z., Liu, Y., Wang, Z., Zhou, X., Fan, X., He, M., Wang, C., Fu, H., Wang, Z., & Bai, Y. (2025). Revolutionizing inflammatory bowel disease healthcare communication: A head-to-head comparison of gastroenterologist and ChatGPT responses. Gastroenterology Report, 13, goaf087. https://doi.org/10.1093/gastro/goaf087

Kacmaz, H. Y., Kahraman, H., Akutay, S., & Dagdelen, D. (2025). Development and validation of an artificial intelligence-assisted patient education material for ostomy patients: A methodological study. Journal of Advanced Nursing, 81, 3859–3867. https://doi.org/10.1111/jan.16542

Kim, D. D., Zhang, J., Sagae, K., Devon, H. A., Hoffmann, T. J., Rountree, L., & Fukuoka, Y. (2025). Human-delivered conversation versus AI chatbot conversation in increasing heart attack knowledge in women in the United States: Quasi-experimental studies. Journal of Medical Internet Research, 27, e73184. https://doi.org/10.2196/73184

Kirchner, G. J., Kim, R. Y., Weddle, J. B., & Bible, J. E. (2023). Can artificial intelligence improve the readability of patient education materials? Clinical Orthopaedics and Related Research, 481, 2260–2267. https://doi.org/10.1097/CORR.0000000000002668

Kufta, A. Y., & Djalilian, A. R. (2025). Enhancing patient education with AI: A readability analysis of AI-generated versus American Academy of Ophthalmology online patient education materials. Journal of Clinical Medicine, 14, 6968. https://doi.org/10.3390/jcm14196968

Laily, A., Schwab-Reese, L. M., Davish, M., Cahue, E., LaRoche, K. J., Rodriguez, N. M., Duncan, R. J., Hubach, R. D., & Kasting, M. L. (2026). Examining artificial intelligence chatbots’ responses in providing human papillomavirus vaccine information for young adults: Qualitative content analysis. JMIR Public Health and Surveillance, 12, e79720. https://doi.org/10.2196/79720

Lee, T. J., Campbell, D. J., Rao, A. K., Hossain, A., Elkattawy, O., Radfar, N., Lee, P., & Gardin, J. M. (2024). Evaluating ChatGPT responses on atrial fibrillation for patient education. Cureus, 16(6), e61680. https://doi.org/10.7759/cureus.61680

Lv, X., Zhang, X., Li, Y., Ding, X., Lai, H., & Shi, J. (2024). Leveraging large language models for improved patient access and self-management: Assessor-blinded comparison between expert- and AI-generated content. Journal of Medical Internet Research, 26, e55847. https://doi.org/10.2196/55847

Mendoza-Pinto, C., Munguia-Realpozo, P., Etchegaray-Morales, I., Ramirez-Lara, E., & Solis-Poblano, J. C. (2025). Artificial intelligence in patient education: Evaluating large language models for understanding rheumatology literature. Frontiers in Digital Health, 7, 1623399. https://doi.org/10.3389/fdgth.2025.1623399

Michalska, A. A., Stefaniak, M. M., & Gotlib-Malkowska, J. (2025). Can ChatGPT provide patient-friendly and reliable information on cervical cancer screening? A study of ChatGPT-generated information in Polish. Medical Science Monitor, 31, e947992. https://doi.org/10.12659/MSM.947992

Naufal, M., Kannan, S., Senthilkumar, S., Palaniappan, T., Kumar, S. S., & Kulkarni, P. P. (2025). Patient education using AI: A cross-sectional study comparing ChatGPT and Google Gemini-generated patient education brochures on various surgical management of breast cancer. Cureus, 17(11), e97525. https://doi.org/10.7759/cureus.97525

Richlitzki, C., Mansoorian, S., Kasmann, L., Stoleriu, M. G., Kovacs, J., Sienel, W., Kauffmann-Guerrero, D., Duell, T., Schmidt-Hegemann, N. S., Belka, C., Corradini, S., & Eze, C. (2025). Assessing ChatGPT’s educational potential in lung cancer radiotherapy from clinician and patient perspectives: Content quality and readability analysis. JMIR Cancer, 11, e69783. https://doi.org/10.2196/69783

Rodler, S., Cei, F., Ganjavi, C., Checcucci, E., De Backer, P., Rivero Belenchon, I., Taratkin, M., Puliatti, S., Veccia, A., Piazza, P., Baekelandt, L., Kowalewski, K. F., Gomez Rivas, J., Fankhauser, C. D., Moschini, M., Gandaglia, G., Campi, R., De Castro Abreu, A., Russo, G. I., ... Cacciamani, G. E. (2025). GPT-4 generates accurate and readable patient education materials aligned with current oncological guidelines: A randomized assessment. PLOS ONE, 20, e0324175. https://doi.org/10.1371/journal.pone.0324175

Rossettini, G., & Palese, A. (2026). Accurate but not accessible: Artificial intelligence chatbots and the limits of patient education. Proceedings (Baylor University Medical Center), 39(2), 294–295. https://doi.org/10.1080/08998280.2026.2613616

Roster, K., Kann, R. B., Farabi, B., Gronbeck, C., Brownstone, N., & Lipner, S. R. (2024). Readability and health literacy scores for ChatGPT-generated dermatology public education materials: Cross-sectional analysis of sunscreen and melanoma questions. JMIR Dermatology, 7, e50163. https://doi.org/10.2196/50163

Sriram, N., Bajaj, A., Li, M., Adam, T., Nguyen, A., Chon, J., & Galiano, R. D. (2026). Comparing the readability and content quality of online patient education materials and ChatGPT-generated patient education materials for breast cancer surgery and reconstruction. Archives of Plastic Surgery, 53, 191–198. https://doi.org/10.1055/a-2794-9984

Stephenson-Moe, C. A., Behers, B. J., Gibons, R. M., Behers, B. M., De Jesus Herrera, L., Anneaud, D., Rosario, M. A., Wojtas, C. N., Bhambrah, S., & Hamad, K. M. (2025). Assessing the quality and readability of patient education materials on chemotherapy cardiotoxicity from artificial intelligence chatbots: An observational cross-sectional study. Medicine, 104(15), e42135. https://doi.org/10.1097/MD.0000000000042135

Sudharshan, R., Shen, A., Gupta, S., & Zhang-Nunes, S. (2024). Assessing the utility of ChatGPT in simplifying text complexity of patient educational materials. Cureus, 16(3), e55304. https://doi.org/10.7759/cureus.55304

Thia, I., & Saluja, M. (2024). ChatGPT: Is this patient education tool for urological malignancies readable for the general population? Research and Reports in Urology, 16, 31–37. https://doi.org/10.2147/RRU.S440633

Tiller, N. B., Marcon, A. R., Zenone, M., Kidd, K. E., Jeukendrup, A. E., Master, Z., & Caulfield, T. (2026). Generative artificial intelligence-driven chatbots and medical misinformation: An accuracy, referencing and readability audit. BMJ Open, 16, e112695. https://doi.org/10.1136/bmjopen-2025-112695

Todorov, D., Park, J. Y., Ng Hing Cheung, J. A., Avramidou, E., & Gnanappiragasam, D. (2025). Assessing the readability of dermatological patient information leaflets generated by ChatGPT-4 and its associated plugins. Skin Health and Disease, 5, 14–21. https://doi.org/10.1093/skinhd/vzae015

Will, J., Gupta, M., Zaretsky, J., Dowlath, A., Testa, P., & Feldman, J. (2025). Enhancing the readability of online patient education materials using large language models: Cross-sectional study. Journal of Medical Internet Research, 27, e69955. https://doi.org/10.2196/69955

Wu, L. L., Hong, A. T., Davuluru, S. S., Moreno-Diaz, E. A., Gutierrez-Hernandez, J. C., Martinez-Camarillo, J. C., Xu, B. Y., & Zhang-Nunes, S. (2026). Utility of ChatGPT-4o in creating patient handouts in ophthalmology: A comparison with American Academy of Ophthalmology educational materials. Translational Vision Science & Technology, 15(2), 14. https://doi.org/10.1167/tvst.15.2.14

Yan, Z., Liu, J., Fan, Y., Lu, S., Xu, D., Yang, Y., Wang, H., Mao, J., Tseng, H.-C., Chang, T.-H., & Chen, Y. (2025). Ability of ChatGPT to replace doctors in patient education: Cross-sectional comparative analysis of inflammatory bowel disease. Journal of Medical Internet Research, 27, e62857. https://doi.org/10.2196/62857

Yau, J. Y.-S., Saadat, S., Hsu, E., Murphy, L. S.-L., Roh, J. S., Suchard, J., Tapia, A., Wiechmann, W., & Langdorf, M. I. (2024). Accuracy of prospective assessments of 4 large language model chatbot responses to patient questions about emergency care: Experimental comparative study. Journal of Medical Internet Research, 26, e60291. https://doi.org/10.2196/60291

Zalzal, H. G., Abraham, A., Cheng, J., & Shah, R. K. (2024). Can ChatGPT help patients answer their otolaryngology questions? Laryngoscope Investigative Otolaryngology, 9, e1193. https://doi.org/10.1002/lio2.1193

Zhang, Y., Wan, X.-H., Kong, Q.-Z., Liu, H., Liu, J., Guo, J., Yang, X.-Y., Zuo, X.-L., & Li, Y.-Q. (2025). Evaluating large language models as patient education tools for inflammatory bowel disease: A comparative study. World Journal of Gastroenterology, 31(6), 102090. https://doi.org/10.3748/wjg.v31.i6.102090