The future of artificial intelligence in clinical nutrition

Abstract

Purpose of review Artificial intelligence has reached the clinical nutrition field. To perform personalized medicine, numerous tools can be used. In this review, we describe how the physician can utilize the growing healthcare databases to develop deep learning and machine learning algorithms, thus helping to improve screening, assessment, prediction of clinical events and outcomes related to clinical nutrition. Recent findings Artificial intelligence can be applied to all the fields of clinical nutrition. Improving screening tools, identifying malnourished cancer patients or obesity using large databases has been achieved. In intensive care, machine learning has been able to predict enteral feeding intolerance, diarrhea, or refeeding hypophosphatemia. The outcome of patients with cancer can also be improved. Microbiota and metabolomics profiles are better integrated with the clinical condition using machine learning. However, ethical considerations and limitations of the use of artificial intelligence should be considered. Summary Artificial intelligence is here to support the decision-making process of health professionals. Knowing not only its limitations but also its power will allow precision medicine in clinical nutrition as well as in the rest of the medical practice.

Applications of Artificial Intelligence, Machine Learning, and Deep Learning in Nutrition: A Systematic Review

“…Furthermore, applying deep learning algorithms to predict serum PLP concentration solely based on dietary intake reveals the importance of AI in nutrition assessment and disease prevention. All these studies collectively suggest that AI can reshape clinical nutrition in the future, offering personalized interventions and predictive capabilities for disease prevention and management [42][43][44][45][46][47][48][49].…”

“…The backbone of their study suggests that digital technologies and AI are promising tools for health promotion, disease prevention, and management in nutrition assessment. Singer et al [43] discuss the potential of artificial intelligence (AI) in clinical nutrition, focusing on how AI can be used to enhance screening and assessment, successful applications for identifying malnourished cancer patients and predicting clinical events in intensive care, and the ethical considerations and limitations associated with AI in clinical nutrition. Kim et al [44] focused on the relationship between nutritional intake and the risk of developing overweight/obesity, dyslipidemia, hypertension, and type 2 diabetes mellitus.…”

“…Food recognition is more effective when it follows dietary assessment because it facilitates the user's decision on food choices and considers user expectations and requirements after the evaluation. Furthermore, patients with specific medical conditions can use AI techniques for disease-predictive modeling, diagnosis, and monitoring [42][43][44][45][46][47][48][49][50][51][52]. The application of AI aims to prevent and control disease development in the human body from a nutritional perspective.…”

“…Addressing this limitation is essential to ensure that AI applications in nutrition benefit a broad spectrum of individuals. The ethical implications of AI applications in nutrition emerged as a notable challenge [43,47]. Privacy concerns related to collecting and sharing personal health data and the responsible use of AI influencing dietary behaviors require careful consideration.…”

“…Privacy concerns related to collecting and sharing personal health data and the responsible use of AI influencing dietary behaviors require careful consideration. Past studies recognized the need for transparent and ethical frameworks to guide the development and deployment of AI technologies [43]. The scalability of AI applications in nutrition, particularly in healthcare settings, poses a challenge.…”