NUTRIGETNE: A Prediction Tool for Malnutrition and Sarcopenia in GEP-NEN Patients

A Spanish study of 399 patients with gastroenteropancreatic neuroendocrine neoplasms (GEP-NENs) developed a predictive model for malnutrition and sarcopenia. The model, built using LASSO regression on a 4:1 training-validation split, identified key predictive factors like tumor differentiation and functional difficulties. The dataset, authored by Maria Argente-Pla and last updated in 2026, includes a diagnostic nomogram based on the study results.

Use Cases

• Predicting malnutrition risk in GEP-NEN patients based on tumor differentiation and symptoms like nausea/vomiting.
• Assessing sarcopenia risk based on patient-reported difficulties in activities of daily living and long walks.
• Developing clinical nomograms for nutritional screening using factors like diabetes and functional status.
• Validating predictive models for cancer-related cachexia using a dataset of 399 patient records.

Strengths

• Includes 399 patient records, providing a substantial clinical cohort for analysis.
• Model performance metrics are provided, with external accuracy of 65.3% for malnutrition and 71.2% for sarcopenia.
• Key predictive factors are quantified with odds ratios and confidence intervals, such as poor tumor differentiation (OR: 4.4) and troubles in daily activities for sarcopenia (OR: 19.7).

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count for the underlying data is unknown, which may limit suitability assessment.
• The dataset's 13.5 KB size suggests it contains summary model results rather than the full patient-level data.

Provenance

Source

NUTRIGETNE (GETNE-S2109) study, likely from a Spanish clinical network.

Collection Method

Patients were randomized 4:1 into training and validation sets to build a LASSO model, corrected by sex, age, and BMI.

Freshness

Last updated 2026-05-26 04:37:22; freshness should be verified.

Geography

Spain