Summaries of Must-Read Clinical Literature, Guidelines, and FDA Actions
Predictive model shows high accuracy for almost all DLBCL patients
Key clinical point: Disease stage and other 5 variables were significant indicators for recurrence.
Major finding: The best model showed a sensitivity = 97.3%; area under the ROC curve = 96%; and a root-mean-squared error = 19.6% in all classifiers.
Study details: 518 patients with DLBCL had 52 variables measured for modeling.
Disclosures: This research was supported by the National Natural Science Foundation of China. The authors reported they had no competing interests.
Citation:
Wei L et al. Computer Methods and Programs in Biomedicine. 2020;196:doi.org/10.1016/j.cmpb.2020.105567.