Prognostic value of prognostic nutritional index on extranodal natural killer/T-cell lymphoma patients: A multicenter propensity score matched analysis of 1022 cases in Huaihai Lymphoma Working Group.

Prognostic nutritional index (PNI), comprised of serum albumin level and lymphocyte count, is associated with the prognosis of several malignant diseases, while the prognostic value of PNI in extranodal natural killer/T cell lymphoma, nasal type (ENKTL) remains unclear. This retrospective multicenter study aimed to investigate the value of PNI in predicting the prognosis of newly diagnosed ENKTL patients by using propensity score matched analysis (PSM). A total of 1022 newly diagnosed ENKTL patients were retrieved from Huaihai Lymphoma Working Group and clinicopathological variables were collected. MaxStat analysis was used to calculate the optimal cut-off points of PNI and other continuous variables. The median age at diagnosis was 47 years and 69.4% were males, with the 5-year OS of 71.7%. According to the MaxStat analysis, 41 was the optimal cut-off point for PNI. The Pseudo R2 before matching was 0.250, and it decreased to less than 0.019 after matching. Confounding factors of the two groups were well balanced after PSM. Multivariable analysis revealed that PNI, Korean Prognostic Index (KPI), eastern cooperative oncology group performance status (ECOG PS), the prognostic index of natural killer lymphoma (PINK) and hemoglobin were independent prognostic factors for ENKTL. The results of subgroup analysis demonstrated that patients with low PNI could predict worse prognosis and re-stratify patients in ECOG PS ≥ 2, EBER-positive, the International Prognostic Index (IPI) (HIR + HR), and PINK (HR) groups. PNI combined with IPI, PINK and KPI could improve the prediction efficiency. In conclusion, PNI could accurately stratify the prognosis of ENKTL by PSM analysis and patients with low PNI had poorer prognosis.

LASSO Model Better Predicted the Prognosis of DLBCL than Random Forest Model: A Retrospective Multicenter Analysis of HHLWG.

Background: Diffuse large B-cell lymphoma (DLBCL) is a heterogeneous non-Hodgkin's lymphoma with great clinical challenge. Machine learning (ML) has attracted substantial attention in diagnosis, prognosis, and treatment of diseases. This study is aimed at exploring the prognostic factors of DLBCL by ML. Methods: In total, 1211 DLBCL patients were retrieved from Huaihai Lymphoma Working Group (HHLWG). The least absolute shrinkage and selection operator (LASSO) and random forest algorithm were used to identify prognostic factors for the overall survival (OS) rate of DLBCL among twenty-five variables. Receiver operating characteristic (ROC) curve and decision curve analysis (DCA) were utilized to compare the predictive performance and clinical effectiveness of the two models, respectively. Results: The median follow-up time was 43.4 months, and the 5-year OS was 58.5%. The LASSO model achieved an Area under the curve (AUC) of 75.8% for the prognosis of DLBCL, which was higher than that of the random forest model (AUC: 71.6%). DCA analysis also revealed that the LASSO model could augment net benefits and exhibited a wider range of threshold probabilities by risk stratification than the random forest model. In addition, multivariable analysis demonstrated that age, white blood cell count, hemoglobin, central nervous system involvement, gender, and Ann Arbor stage were independent prognostic factors for DLBCL. The LASSO model showed better discrimination of outcomes compared with the IPI and NCCN-IPI models and identified three groups of patients: low risk, high-intermediate risk, and high risk. Conclusions: The prognostic model of DLBCL based on the LASSO regression was more accurate than the random forest, IPI, and NCCN-IPI models.