Future Directions in Patient Education: Leveraging Artificial Intelligence for Spine Trauma Patients

Descriptive study.

To explore the role of artificial intelligence (AI) in disseminating information and addressing frequently asked questions related to spinal cord injuries (SCIs) and associated complications.

Advancements in AI have revolutionized patient education, particularly in the context of traumatic injuries. Spine trauma, owing to its potential to significantly alter the course of patients' lives, causes many concerns related to symptomatology, potential interventions, and recovery processes.

We utilized 4 commonly used AI models (ChatGPT, Bing AI, Google SGE, and Perplexity AI) to address common questions posed by individuals dealing with spine trauma. Responses were evaluated using the DISCERN instrument for information quality and readability indices for reading levels.

DISCERN scores highlighted variability in information quality across the AI models. Bing AI demonstrated reliability in specific categories, while ChatGPT exhibited balanced scores, showcasing versatility. Google SGE presented room for improvement, indicated by lower scores in various categories. Perplexity AI consistently provided high-quality information across all evaluated domains. Variability in AI performance was largely influenced by differences in training data and inference methods. A comprehensive approach that leverages the strengths of multiple models may enhance overall information dissemination, and addressing the limitations of lower-scoring models could improve AI's potential as an educational tool for spine trauma.

AI has a pivotal role in reshaping patient education for individuals grappling with spinal cord injuries. Our findings provide insights into the strengths and areas for improvement across different AI models, highlighting the need for a more informed and nuanced approach by health care providers leveraging AI in patient education. Future research should investigate AI integration into patient education across various conditions, focusing on clinical accuracy, relevance, and resource considerations.