Exploring ChatGPT’s Role in Educating Patients on Community Reintegration After Spinal Cord Injury: A Mixed-Method Study
DOI:
https://doi.org/10.63682/jns.v14i32S.8053Keywords:
Spinal cord injury, community reintegration, ChatGPT, artificial intelligence, patient education, mixed-methodsAbstract
Background: Community reintegration following spinal cord injury (SCI) involves navigating a complex web of physical, psychological, social, and environmental challenges. Patient education plays a critical role in this transition, yet many existing resources are either too generic or not readily accessible. The emergence of artificial intelligence tools like ChatGPT offers potential as a supplementary educational resource.
Objective: This study aimed to evaluate the reliability, readability, and perceived utility of ChatGPT in delivering educational content about community reintegration after SCI, using a mixed-methods approach.
Methods: In Phase I, 15 structured and clinically relevant questions were submitted to ChatGPT-4. The responses were assessed for reliability (using the DISCERN tool), readability (Flesch Reading Ease and Gunning Fog Index), and domain-specific comprehensiveness (via a custom rubric across physical, psychological, social, and environmental domains). In Phase II, semi-structured interviews were conducted with SCI patients, caregivers, and rehabilitation professionals to gather qualitative perspectives. Thematic analysis was used to explore recurring patterns.
Results: ChatGPT’s responses yielded a mean DISCERN score of 3.82 ± 0.51, with an inter-rater intraclass correlation coefficient (ICC) of 0.84. Readability analysis revealed a mean Flesch score of 70.4 and a Gunning Fog Index of 9.1, suggesting accessibility for most readers. Comprehensiveness ratings were highest in physical (4.5 ± 0.5) and social (4.2 ± 0.7) domains, but relatively lower in environmental aspects (3.1 ± 0.8). Thematic analysis of interviews revealed three key themes: ease of access, surface-level adequacy, and supportive emotional tone.
Conclusion: ChatGPT shows promise as a readable, moderately reliable, and emotionally supportive tool for patient education following SCI. However, its limitations in depth and individualization highlight the need for its integration under clinical guidance, rather than as a standalone solution..
Downloads
Metrics
References
Jeblick K, Schachtner B, Dexl J, et al. ChatGPT makes medicine easy to swallow: An exploratory case study on the utility of AI-generated patient education materials. JMIR Med Educ. 2023;9:e46844.
Gilson A, Safranek CW, Huang T, et al. How well does ChatGPT answer medical questions? J Med Syst. 2023;47(1):33.
Krittanawong C, Johnson KW, Rosenson RS, et al. Artificial intelligence in cardiology: current applications and future perspectives. J Am Coll Cardiol. 2021;77(3):312-329.
Charnock D, Shepperd S, Needham G, Gann R. DISCERN: an instrument for judging the quality of written consumer health information. J Epidemiol Community Health. 1999;53(2):105-111.
Kincaid JP, Fishburne RP Jr, Rogers RL, Chissom BS. Derivation of new readability formulas for Navy enlisted personnel. Research Branch Report. 1975;8-75.
Gunning R. The Technique of Clear Writing. New York: McGraw-Hill; 1952.
Braun V, Clarke V. Using thematic analysis in psychology. Qual Res Psychol. 2006;3(2):77–101.
Cascella M, Montomoli J, Bellini V, et al. Evaluating the reliability of ChatGPT in answering medical questions: A benchmark study. Cureus. 2023;15(4):e37643.
Patel SB, Lam K. ChatGPT: the future of discharge summaries? Lancet Digit Health. 2023;5(3):e107.
Xu J, Zhang Y. Empathy in artificial intelligence: Can language models support emotional well-being? Comput Human Behav. 2024;146:107783.
Yang Y, Guo Y, Li T, et al. Emotional responses to AI-generated messages: A study on tone and trustworthiness. J Med Internet Res. 2023;25:e41567
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
