Related Experiment Videos
A Scoping Review of Malnutrition Risk Prediction Models in Cancer Patients.
Nianfei Tang1, Huiru Zeng1, Biao He1
1School of Nursing, Chengdu Medical College, Chengdu, China.
Journal of Clinical Nursing
|July 1, 2026
Summary
This review identified 36 malnutrition risk prediction models for cancer patients. Current models have limitations in development and validation, necessitating future improvements with advanced data and AI for better early screening.
Area of Science:
- Oncology
- Nutritional Science
- Biostatistics
Background:
- Malnutrition is common in cancer patients, impacting outcomes.
- Early identification and intervention are crucial for improving quality of life.
- Risk prediction models can forecast future disease risk.
Purpose of the Study:
- To systematically review and map existing malnutrition risk prediction models for cancer patients.
- To identify gaps in the development and validation of these models.
- To provide references for clinical practice and future research.
Main Methods:
- Scoping review following PRISMA Extension and Arksey/O'Malley framework.
- Systematic searches across multiple databases (PubMed, Web of Science, EMbase, etc.).
- Inclusion of original studies on malnutrition risk prediction model development or validation in cancer patients.
Main Results:
- 36 studies were included, analyzing model development, predictors, and performance.
- Traditional statistical analysis and retrospective data collection were predominant.
- Models covered various cancers (rectal, liver, gastric, etc.), frequently using age and BMI as predictors.
Conclusions:
- Existing malnutrition prediction models for cancer patients show limitations in construction and validation.
- Future research should focus on longitudinal, multimodal data and artificial intelligence (AI).
- Optimized tools are needed for early screening and intervention to improve patient care.
