Predictive Model Gauges Likelihood of DLBCL Recurrence

Scientists have created a predictive model to assess 2-year recurrence risk in patients with diffuse large B-cell lymphoma (DLBCL) who have achieved remission, according to a study published in the journal Computer Methods and Programs in Biomedicine.

“Treatments are limited for patients with relapsed/refractory DLBCL, and their survival rate is low,” wrote researchers from Shanxi Medical University and Shanxi Cancer Hospital in China. “Prediction of the recurrence hazard for each patient could provide a reference regarding chemotherapy regimens for clinicians to extend patients' period of long-term remission.”

Upon assessing 52 variables for 518 patients with DLBCL treated between January 2011 and July 2016, machine learning methods identified disease stage and five other variables as significant indicators for DLBCL recurrence after remission.

“This predictive model has high accuracy for almost all DLBCL patients,” researchers wrote, “and the six indicators can be recurrence signals.” 

—Jolynn Tumolo 

Reference: 

Wang L, Zhao Z, Luo Y, et al. Classifying 2-year recurrence in patients with dlbcl using clinical variables with imbalanced data and machine learning methods [published online ahead of print, 2020 Jun 9]. Comput Methods Programs Biomed. 2020;196:105567. doi:10.1016/j.cmpb.2020.105567