Artificial intelligence in clinical nutrition. A narrative review

Area of Science:

• Healthcare Technology
• Clinical Nutrition
• Artificial Intelligence

Background:

• Artificial Intelligence (AI) is rapidly integrating into healthcare, including clinical nutrition.
• Clinicians often lack adequate understanding of AI principles, capabilities, and limitations, potentially hindering adoption and effective use.
• This gap presents challenges for leveraging AI in diagnostics, risk prediction, and personalized therapeutic support in nutrition.

Purpose of the Study:

• To provide an accessible overview of foundational AI concepts relevant to clinical nutrition.
• To explore practical applications of AI, including machine learning, deep learning, and large language models, in nutritional care.
• To highlight the importance of clinician preparedness for AI integration in healthcare.

Main Methods:

• This study is a narrative review.
• It synthesizes information on AI concepts and their applications in clinical nutrition.
• The review focuses on foundational AI principles and their practical relevance for healthcare professionals.

Main Results:

• AI, encompassing machine learning, deep learning, and large language models, presents transformative potential for clinical nutrition.
• Successful AI implementation necessitates clinicians understanding AI's capabilities and limitations.
• Key areas for AI application include enhanced diagnostics, risk prediction, and personalized therapeutic support.

Conclusions:

• AI can significantly advance nutritional care, offering personalized and patient-centered approaches.
• Effective integration requires tailored education programs for healthcare professionals and interdisciplinary collaboration.
• Robust ethical oversight is essential for responsible AI deployment, ensuring human expertise remains central to decision-making.