The use of artificial intelligence in paediatric postgraduate medical education: A scoping review

Abstract Background Artificial intelligence (AI) encompasses a wide range of technologies that enable computers to mimic human intellect and is playing a significant role in healthcare education. Objectives To review the current applications of AI in paediatric postgraduate medical education programs. Methods A scoping review was conducted using a comprehensive literature search involving Ovid MEDLINE, Ovid Embase, and ERIC conducted from 1946 to May 27, 2024. Inclusion criteria involved articles that discussed AI in postgraduate paediatric education. Articles that addressed undergraduate education and other health professional education were excluded. Results Nine articles met the inclusion criteria. Four studies were conducted in the United States, two in China, and one each in France, Korea, and Canada. The studies discussed the use of AI in general paediatrics, paediatric oncology, developmental paediatrics, and paediatric genetics. AI was used as a clinical decision support tool in postgraduate training in seven studies with mixed results on the accuracy of AI predictions. One study used AI models to assess residents’ intubation competency, and another assessed the experiences and general perspectives of AI among paediatric residents and junior faculty. Conclusions Amongst included studies, AI was largely used as a clinical decision support tool in paediatric postgraduate education and the accuracy of AI predictions are improved when large amounts of data are used to train and tune the AI model. As such, physicians should be trained in AI use and take an active role in training and tuning AI models on an ongoing basis to ensure appropriate use of AI in healthcare.