Title: Integration of artificial intelligence and nutrigenomics in clinical care has implications for large scale population health

Abstract:

As Big Data becomes available concerning nutrition from studies of nutrigenomics and metabolomics the complexity of programs needed to analyze this information necessitates what is considered AI. In addition to data analysis, AI can assist at the point of care by helping doctors and patients more actively track changes in health status. In both applications, the level of complexity achieved in programming falls under the umbrella of Machine Learning [ML] which is a specific subtype of AI. In this review, we will focus on emerging applications of ML in clinical nutrition and the prospective use of this technology in healthcare management. ML programs are already being widely used in ordinary practice, meanwhile, analysis of nutrigenomics and the interactome is revealing a previously unknown influence of nutrition’s effects. We will discuss the implication of novel insights into nutrition in healthcare and review a few examples of current clinical practices utilizing ML technology. Considering the emerging focus on the relation of genomics in modulating individual nutritional status, we will propose a future research direction to streamline the translation of study data to clinical adjuncts. Detailed reasoning is provided for innovative objectives that support the use of nutritional intervention as a mode of therapy that might impact the progression of many diseases such as neurodegenerative disorders. Overall this represents a paradigm shift in the healthcare system that can have broad global implications.