Role of artificial intelligence in predicting disease-related malnutrition-A narrative review

Background: disease-related malnutrition (DRM) affects 30-50 % of hospitalized patients and is often underdiagnosed, increasing risks of complications and healthcare costs. Traditional DRM detection has relied on manual methods that lack accuracy and efficiency. Objective: this narrative review explores how artificial intelligence (AI), specifically machine learning (ML) and deep learning (DL), can transform the prediction and management of DRM in clinical settings. Methods: we examine widely used ML and DL models, assessing their clinical applicability, advantages, and limitations. The integration of these models into electronic health record systems allows for automated risk detection and optimizes real-time patient management. Results: ML and DL models show significant potential for accurate assessment of nutritional status and prediction of complications in patients with DRM. These models facilitate improved clinical decision-making and more efficient resource management, although their implementation faces challenges related to the need for large volumes of standardized data and integration with existing systems. Conclusion: AI offers promising prospects for proactive DRM management, highlighting the need for interdisciplinary collaboration to overcome existing barriers and maximize its positive impact on patient care.