EUVIMEDExplore EUVIMED
Open access

Assessing ChatGPT’s Educational Potential in Lung Cancer Radiotherapy From Clinician and Patient Perspectives: Content Quality and Readability Analysis

Cedric Richlitzki iD, Sina Mansoorian iD, Lukas Käsmann iD, Mircea Gabriel Stoleriu iD, Julia Kovacs iD, Wulf Sienel iD, Diego Kauffmann-Guerrero iD, Thomas Duell iD, Nina Sophie Schmidt-Hegemann iD, Claus Belka iD, Stefanie Corradini iD, Chukwuka Eze iD

JMIR Cancer · 2025-08-13 · 11 · e69783-e69783

DOI: 10.2196/69783 ↗

At a glance

Journal article in JMIR Cancer, published online on 2025-08-13. Written by Cedric Richlitzki and 11 co-authors. Institution: Department of Radiation Oncology, University Hospital LMU, Marchioninistrasse 15, Munich, 81377, Germany, 49 89440073770. Major MEDLINE topics: Lung Neoplasms, Patient Education as Topic, Comprehension. Cited 9 times so far (Crossref); 44 references. The full text is freely available in PubMed Central.

AbstractSubjectsBibliographic detailsCiteRelated studies

Abstract (original language)

Background

Large language models (LLMs) such as ChatGPT (OpenAI) are increasingly discussed as potential tools for patient education in health care. In radiation oncology, where patients are often confronted with complex medical terminology and complex treatment plans, LLMs may support patient understanding and promote more active participation in care. However, the readability, accuracy, completeness, and overall acceptance of LLM-generated medical content remain underexplored.

Objective

This study aims to evaluate the potential of ChatGPT-4 as a supplementary tool for patient education in the context of lung cancer radiotherapy by assessing the readability, content quality, and perceived usefulness of artificial intelligence–generated responses from both clinician and patient perspectives.

Methods

A total of 8 frequently asked questions about radiotherapy for lung cancer were developed based on clinical experience from a team of clinicians specialized in lung cancer treatment at a university hospital. The questions were submitted individually to ChatGPT-4o (version as of July 2024) using the prompt: “I am a lung cancer patient looking for answers to the following questions.” Responses were evaluated using three approaches: (1) a readability analysis applying the Modified Flesch Reading Ease (FRE) formula for German and the 4th Vienna Formula (WSTF); (2) a multicenter expert evaluation by 6 multidisciplinary clinicians (radiation oncologists, medical oncologists, and thoracic surgeons) specialized in lung cancer treatment using a 5-point Likert scale to assess relevance, correctness, and completeness; and (3) a patient evaluation during the first follow-up appointment after radiotherapy, assessing comprehensibility, accuracy, relevance, trustworthiness, and willingness to use ChatGPT for future medical questions.

Results

Readability analysis classified most responses as “very difficult to read” (university level) or “difficult to read” (upper secondary school), likely due to the use of medical language and long sentence structures. Clinician assessments yielded high scores for relevance (mean 4.5, SD 0.52) and correctness (mean 4.3, SD 0.65), but completeness received slightly lower ratings (mean 3.9, SD 0.59). A total of 30 patients rated the responses positively for clarity (mean 4.4, SD 0.61) and relevance (mean 4.3, SD 0.64), but lower for trustworthiness (mean 3.8, SD 0.68) and usability (mean 3.7, SD 0.73). No harmful misinformation was identified in the responses.

Conclusions

ChatGPT-4 shows promise as a supplementary tool for patient education in radiation oncology. While patients and clinicians appreciated the clarity and relevance of the information, limitations in completeness, trust, and readability highlight the need for clinician oversight and further optimization of LLM-generated content. Future developments should focus on improving accessibility, integrating real-time readability adaptation, and establishing standardized evaluation frameworks to ensure safe and effective clinical use.

Subjects

MeSH terms (MEDLINE)

Lung NeoplasmsPatient Education as TopicComprehensionHumansSurveys and QuestionnairesFemaleMaleArtificial IntelligenceGenerative Artificial Intelligence

Author keywords

ChatGPTLLMNSCLCartificial intelligencelarge language modellung cancernon-small cell lung cancerpatient educationradiation oncologyradiotherapy

Authors and institutions

  • Department of Radiation Oncology, University Hospital LMU, Marchioninistrasse 15, Munich, 81377, Germany, 49 89440073770.
  • Asklepios Lung Clinic Munich - Gauting, Division of Thoracic Surgery, LMU University Hospital, Munich, Germany.
  • Division for Thoracic Surgery, Asklepios Medical Center, Ludwig-Maximilians-University of Munich, Munich, Germany.
  • Department of Medicine V, University Hospital, Ludwig-Maximilians-University Munich, Munich, Germany.
  • Comprehensive Pneumology Center Munich, German Center for Lung Research, Munich, Germany.
  • German Cancer Research Center (DKFZ), German Cancer Consortium (DKTK), partner site Munich, Heidelberg, Germany.

ORCID profiles: Cedric Richlitzki, Sina Mansoorian, Lukas Käsmann, Mircea Gabriel Stoleriu, Julia Kovacs, Wulf Sienel, Diego Kauffmann-Guerrero, Thomas Duell, Nina Sophie Schmidt-Hegemann, Claus Belka, Stefanie Corradini, Chukwuka Eze

Cite

APA

Richlitzki, C., Mansoorian, S., Käsmann, 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-e69783. https://doi.org/10.2196/69783

Vancouver

Richlitzki C, Mansoorian S, Käsmann L, Stoleriu MG, Kovacs J, Sienel W, et al. Assessing ChatGPT’s Educational Potential in Lung Cancer Radiotherapy From Clinician and Patient Perspectives: Content Quality and Readability Analysis. JMIR Cancer. 2025;11:e69783-e69783. doi:10.2196/69783

BibTeX
@article{Richlitzki2025,
  author = {Richlitzki, Cedric and Mansoorian, Sina and Käsmann, Lukas and Stoleriu, Mircea Gabriel and Kovacs, Julia and Sienel, Wulf and Kauffmann-Guerrero, Diego and Duell, Thomas and Schmidt-Hegemann, Nina Sophie and Belka, Claus and Corradini, Stefanie and Eze, Chukwuka},
  title = {Assessing ChatGPT’s Educational Potential in Lung Cancer Radiotherapy From Clinician and Patient Perspectives: Content Quality and Readability Analysis},
  journal = {JMIR Cancer},
  year = {2025},
  volume = {11},
  pages = {e69783--e69783},
  doi = {10.2196/69783}
}
Start for free →