JMIR Publications

ABSTRACT

Artificial Intelligence (AI) technologies, such as machine learning and natural language processing, have the potential to provide new insights into complex health data. While powerful, these algorithms rarely move from experimental studies to direct clinical care implementation. This work describes the modifications leading to the successful development and integration of two AI technology-based research pipelines for clinical practice. In specific, the work highlights two different clinical systems: (1) epilepsy surgical candidate identification in an ambulatory neurology clinic; and (2) real-time patient identification for research studies in a pediatric emergency department. These projects showcase novel interactions between machine learning recommendations and providers during clinical care. Our deployment provides seamless, real-time integration of AI technology to provide decision support and improve patient care. The success of each project was largely dependent upon the collaboration between machine learning experts, research and operational information technology professionals, longitudinal support from clinical providers, and institutional leadership.