Nomogram-Based Prediction of Asparaginase-Associated Pancreatitis in Children with ALL

A retrospective study of 352 children with Acute Lymphoblastic Leukemia (ALL) diagnosed at Hebei Children’s Hospital from January 2020 to June 2025. The dataset was used to develop a nomogram model predicting asparaginase-associated pancreatitis (AAP) based on six clinical and laboratory risk factors. The model, created by Xiangyu Ding, achieved an area under the curve (AUC) of 0.926.

Use Cases

• Developing a clinical risk prediction tool based on identified risk factors like albumin level and blood glucose.
• Validating a predictive model for drug-associated pancreatitis using metrics like AUC and Brier score.
• Analyzing the relationship between laboratory parameters (e.g., total bilirubin, aspartate aminotransferase) and adverse drug events.
• Training logistic regression models for binary classification of medical outcomes using retrospective patient data.

Strengths

• Model performance is quantitatively validated with an AUC of 0.926 and a Brier score of 0.012.
• The study includes data from 352 pediatric patients, with 36 confirmed cases of the target condition.
• Risk factors are clearly identified with associated odds ratios and p-values, such as a history of AAP (OR=13.20).

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.
• Data is from a single hospital, which may reflect geographic or institutional bias.

Provenance

Source

Hebei Children’s Hospital

Collection Method

Retrospective study of patient records, with data collection and analysis following the CCLG–ALL–2018 treatment protocol.

Time Range

January 2020 to June 2025

Freshness

Last updated 2026-05-19 04:20:57; freshness should be verified.

Geography

China (Hebei province)