What question did this study set out to answer?

The study aims to create a machine learning model that predicts early death in patients diagnosed with peripheral T-cell lymphoma-NOS.

June 13, 2026Annals of HematologyOpen Access

Prediction of early death in peripheral T-cell lymphoma-NOS patients based on machine learning

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial develops a machine learning model predicting early death in PTCL-NOS patients, suggesting improved treatment planning.

The study aims to create a machine learning model that predicts early death in patients diagnosed with peripheral T-cell lymphoma-NOS.
Data from the SEER database (2016-2021) was used, including 1,156 peripheral T-cell lymphoma-NOS patients; divided into training (n=809) and validation (n=347) sets.
Predictive factors were identified using Boruta and LASSO algorithms.
Seven machine learning models, including XGBoost, were evaluated using AUROC, AUPRC, calibration curves, Brier scores, and decision curve analysis.
XGBoost achieved the best AUROC of 0.842 in the training set and 0.774 in the validation set.
Key predictive factors included chemotherapy, radiotherapy, age, B symptoms, primary tumor site, Summary Stage, and Ann Arbor Stage.
The model aids in early risk stratification and personalized treatment planning.

Liang et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark