Construction of nomogram for the clinical outcome for pediatric acute lymphoblastic leukemia patients.
Using SEER data from 13,869 pediatric ALL patients diagnosed between 2000 and 2019, the study developed a nomogram based on age, race, and radiotherapy that showed moderate-to-good discrimination for 1-, 3-, and 5-year overall survival in training and validation cohorts.
Open original publication →What the AI sees
Using SEER data from 13,869 pediatric ALL patients diagnosed between 2000 and 2019, the study developed a nomogram based on age, race, and radiotherapy that showed moderate-to-good discrimination for 1-, 3-, and 5-year overall survival in training and validation cohorts.
Research significance
The evidence supports prognostic risk estimation rather than a treatment effect; it may be inferred that validated risk predictions could help clinicians identify patients needing closer assessment or treatment-planning review, but the record does not show that nomogram-guided care improves survival or that radiotherapy itself is beneficial or harmful.
Source abstract
Acute lymphoblastic leukemia (ALL) is one of the most common hematologic cancers in children, accounting for about 25% of all pediatric cancers. However, survival data for pediatric ALL patients remain limited. We selected clinicopathological data from pediatric ALL patients diagnosed between 2000 and 2019 from the SEER database. Univariable and multivariable Cox proportional hazards regression analyses were applied to identify independent prognostic factors for overall survival (OS) in ALL patients. A predictive nomogram was then constructed. Calibration curves, receiver operating characteristic (ROC) curves, and decision curve analysis (DCA) were used to evaluate the nomogram's performance. A total of 13,869 ALL patients were included in the study, with 1447 (10%) patients dying from various causes. On univariable analysis, survival was significantly worse in male patients, those aged 13-17, and Black patients. Multivariable analysis identified age, race, and radiotherapy as independent prognostic factors for OS, whereas sex was not independently associated with survival. The nomogram predicted the 1-year, 3-year, and 5-year OS rates with AUCs of 0.807, 0.796, and 0.772 in the training cohort, and 0.854, 0.837, and 0.816 in the validation cohort, respectively. Good agreement was observed between observed outcomes and predicted probabilities in the calibration curves. DCA further demonstrated the nomogram's clinical utility. The nomogram demonstrates good accuracy and reliability in predicting OS for pediatric ALL patients, providing valuable theoretical support for clinicians in making treatment decisions.