Research progress on predictive models for malnutrition in cancer patients

Area of Science:

• Oncology
• Nutritional Science
• Medical Informatics

Background:

• Disease-related malnutrition affects 40-80% of cancer patients, leading to adverse outcomes like prolonged hospitalization and reduced quality of life.
• Malnutrition impairs tolerance to cancer therapies (surgery, chemotherapy, radiotherapy), causing treatment delays and complications.
• Current objective assessment models exist, but advancements in artificial intelligence offer potential for improved accuracy.

Purpose of the Study:

• To provide a comprehensive overview of recent models for predicting malnutrition risk in cancer patients.
• To offer guidance for healthcare professionals in clinical decision-making.
• To serve as a reference for developing more efficient future risk prediction models.

Main Methods:

• Literature review of recently developed malnutrition risk prediction models for cancer patients.
• Focus on models incorporating advanced technologies, including artificial intelligence.
• Analysis of model accuracy and clinical applicability.

Main Results:

• Identification and categorization of various recently developed malnutrition risk prediction models.
• Comparison of traditional methods with newer AI-driven approaches.
• Highlighting the potential advantages of advanced models in accuracy and efficiency.

Conclusions:

• Accurate malnutrition risk prediction is crucial for optimizing cancer patient care and treatment outcomes.
• Emerging AI-based models show promise for enhancing prediction accuracy over traditional methods.
• Further research and validation are needed to integrate these advanced models into routine clinical practice.