Nutritional Risk and Hospital Stay Data for Upper Gastrointestinal Disease Patients

896 patient records from a retrospective study at the PLA General Hospital assessing predictors of long hospital stays. Data includes demographic information, lifestyle factors, primary diagnosis, comorbidities, laboratory values, and length of stay. The dataset was created by Ruiqing Zhu and last updated on June 4, 2026.

Use Cases

• Predicting long hospital stays based on nutritional risk scores and serum albumin levels.
• Analyzing the relationship between patient comorbidities and length of stay.
• Evaluating the performance of the NRS2002 screening tool as a clinical predictor.
• Training models to identify high-risk patients for targeted nutritional interventions.

Strengths

• Includes data for 896 patients with a median age of 61.0 years.
• Contains key clinical variables like NRS2002 score, serum albumin level, and length of stay.
• Results from the study show an AUC of 0.721 for the NRS2002 score as a predictor.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Data is from a single-center study, which may limit generalizability.

Provenance

Source

Department of Esophagogastric, Senior Department of Gastroenterology, the First Medical Center of PLA General Hospital.

Collection Method

Retrospective data extraction from the Electronic Medical Record (EMR) system.

Freshness

Last updated 2026-06-04 04:32:16; freshness should be verified.

Geography

Likely China, based on the hospital location.