Artificial Intelligence in Malnutrition: A Systematic Literature Review

Area of Science:

• Medical Informatics
• Artificial Intelligence in Healthcare
• Nutritional Science

Background:

• Malnutrition is a prevalent, underdiagnosed global health issue affecting both children and adults.
• Early detection and intervention are crucial to prevent severe, long-term health complications.
• Current malnutrition screening tools often rely on questionnaires and consensus guidelines.

Purpose of the Study:

• To systematically review artificial intelligence (AI) applications for malnutrition detection.
• To identify patient groups, screening tools, machine learning algorithms, data types, and variables used in AI-based malnutrition detection.
• To assess the limitations and implementation status of AI tools in clinical practice.

Main Methods:

• Systematic literature review of AI-based malnutrition screening and diagnostic tools.
• Analysis of patient cohorts, AI methodologies, data sources, and variables employed.
• Evaluation of the clinical implementation and limitations of identified AI tools.

Main Results:

• Over 90% of developed AI models for malnutrition are not utilized in daily clinical practice.
• Supervised learning models were the most frequently used machine learning approach.
• Disease-related malnutrition was the most common category analyzed in the primary studies.

Conclusions:

• AI holds significant potential for early malnutrition detection, but faces substantial barriers to clinical adoption.
• Further research is needed to bridge the gap between AI model development and real-world clinical implementation.
• This review serves as a resource for guiding future research in AI for malnutrition.