Artificial Intelligence in Pediatric Hospital Medicine: Foundations, Clinical Applications, and Emerging Case Uses.

Abstract

Artificial intelligence (AI) is rapidly transforming health care and has important implications for pediatric hospital medicine. Advances in machine learning and large language models have enabled applications that support patient care in the areas of clinical documentation, decision making, and prognostic modeling. Pediatric AI systems leverage diverse data sources, including electronic health records, medical imaging, physiologic monitoring, wearable devices, and genomic data. Current applications include AI-powered scribes, chart summarization, clinical decision support, prediction of sepsis and clinical deterioration, precision pharmacotherapy, rare disease diagnosis, and mental health interventions. These technologies have demonstrated potential to reduce clinician workload, enhance diagnostic accuracy, and facilitate earlier therapeutic interventions. However, significant challenges remain, including limited and heterogeneous pediatric datasets by virtue of age and developmental characteristics in children, bias, privacy concerns, lack of representativeness, and the need for rigorous validation and oversight. As AI adoption expands, pediatric hospitalists require foundational knowledge of AI principles and limitations to ensure safe, equitable, and effective implementation. With appropriate governance and multidisciplinary collaboration, AI has the potential to improve pediatric inpatient outcomes and health care delivery.