Predictive modeling in neurocritical care using causal artificial intelligence

Abstract

Artificial intelligence (AI) and digital twin models of various systems have long been used in industry to test products quickly and efficiently. Use of digital twins in clinical medicine caught attention with the development of Archimedes, an AI model of diabetes, in 2003. More recently, AI models have been applied to the fields of cardiology, endocrinology, and undergraduate medical education. The use of digital twins and AI thus far has focused mainly on chronic disease management, their application in the field of critical care medicine remains much less explored. In neurocritical care, current AI technology focuses on interpreting electroencephalography, monitoring intracranial pressure, and prognosticating outcomes. AI models have been developed to interpret electroencephalograms by helping to annotate the tracings, detecting seizures, and identifying brain activation in unresponsive patients. In this mini-review we describe the challenges and opportunities in building an actionable AI model pertinent to neurocritical care that can be used to educate the newer generation of clinicians and augment clinical decision making.

Keywords: Artificial intelligence; Digital twin; Critical care; Neurology; Causal artificial intelligence; Predictive modeling

Core Tip: The modern clinical environment is increasingly surrounded by data. The existing literature is sparse concerning the creation of a “digital twin” artificial intelligence (AI) model as a tool for education and potentially clinical decision making in the neurologic intensive care unit setting. This mini review will give readers an introduction to applications of AI inside and outside of healthcare, the idea of the “digital twin” as a model of disease, how AI has been applied in neurocritical care, and methodology for building a neurocritical care digital twin AI model that is based on a solid understanding of underlying pathophysiology.