Diabetic Foot Ulcer Pre-Screening Model with Alb/HbA1c Ratio, 2012-2025

1,854 hospitalized and 678 outpatient records were used to develop a simplified pre-screening model for diabetic foot ulcer (DFU) identification. The model, created by Weidi Wang and last updated in May 2026, uses four predictors: age, history of injury, alcohol consumption, and the albumin-to-glycated hemoglobin ratio (Alb/HbA1c). It achieved an area under the curve (AUC) of 0.807 in the training set and 0.817 in the validation set.

Use Cases

• Developing a clinical risk score for diabetic foot ulcers based on age, injury history, alcohol consumption, and Alb/HbA1c ratio.
• Validating a predictive model for diabetic complications using retrospective patient data from hospital systems.
• Analyzing the interaction between nutritional status (via Alb/HbA1c) and age on DFU risk as described in the results.
• Creating a pre-screening tool for resource-limited settings based on the model's reported high negative predictive value.

Strengths

• Model performance is quantitatively validated with an optimism-corrected AUC of 0.803 and Brier scores of 0.127 and 0.118.
• Dataset includes a substantial patient cohort of 1,854 training and 678 validation records.
• Clear temporal coverage from January 2012 to December 2025 for model development and validation.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count for the underlying data tables is unknown, which may limit suitability assessment.
• Data may reflect geographic and institutional bias inherent to the single hospital system source.

Provenance

Source

figshare, author Weidi Wang.

Collection Method

Retrospective analysis of hospitalized patients and outpatients from a hospital system.

Time Range

Training set: January 2012–December 2020. Validation set: January 2021–December 2025.

Freshness

Last updated 2026-05-29 04:47:36; freshness should be verified.

Geography

Patients from a geographically distinct branch of a hospital system; specific location not stated.