Leveraging ChatGPT to strengthen pediatric healthcare systems: a systematic review.

Abstract

This systematic review is the first to investigate ChatGPT's applications in pediatric healthcare systems by assessing its accuracy and readability, with a focus on its impact across key areas such as clinical decision-making, clinical documentation, patient education, and training. The primary question guiding this review is: How does ChatGPT impact pediatric healthcare systems, for example, in terms of improving patient education, enhancing providers' efficiency, and assisting with clinical decision-making? A systematic review was conducted using PubMed, EMBASE, and Web of Science (February 16, 2025). Inclusion criteria encompassed peer-reviewed studies evaluating ChatGPT in pediatric healthcare (ages 0-18 and guardians). Of 475 screened articles, 58 met eligibility criteria. Two independent reviewers extracted data on study characteristics, intervention types, outcomes, and results. ChatGPT's primary applications were patient education (n = 38), clinical decision-making (n = 12), and clinical documentation (n = 5). Accuracy was highest in patient education, where it generated educational materials and answered FAQs, though readability was often at a high school level, necessitating adaptation. Clinical documentation benefits included improved efficiency in drafting notes and discharge instructions. However, clinical decision-making and training (n = 3) showed mixed accuracy, particularly in management recommendations and patient care plans.

Conclusion: ChatGPT demonstrates potential in enhancing physician efficiency and tailoring patient education in pediatric healthcare. However, most studies relied on observational designs, with only one quasi-experimental study. Further experimental research is required to evaluate AI's impact on pediatric care system effectiveness and patient outcomes.

What is known: • AI has been increasingly integrated into pediatric healthcare, particularly in imaging, diagnostics, and decision support. • Prior studies have explored LLMs like ChatGPT in medical education and training.

What is new: • This is the first systematic review assessing ChatGPT's broader applications in pediatric healthcare, including decision-making, patient education, clinical documentation, and training. • ChatGPT shows high accuracy in patient education and documentation but variable performance in decision-making and training, emphasizing the need for medical supervision.