Risk Assessment and Predictive Modeling of Suicide in Chronic Lymphocytic Leukemia/Small Lymphocytic Lymphoma (CLL/SLL) Patients

Background: Chronic lymphocytic leukemia/small lymphocytic lymphoma (CLL/SLL) predominantly affects older adults and is characterized by a prolonged disease course. While overall survival has improved, the psychosocial impact, including suicide risk, remains underexplored. Methods: A retrospective cohort study was conducted using data from 95,517 patients diagnosed with CLL/SLL between 2000 and 2021, extracted from the SEER 17 registry. LASSO regression was utilized for variable selection, followed by univariate and multivariate Cox proportional hazards and Fine-Gray competing risk analyses to identify independent predictors. A nomogram was developed based on significant predictors and validated using time-dependent receiver operating characteristic (ROC) curves, calibration plots, and decision curve analysis (DCA). Results:Although the suicide rate was only 0.1%, multivariate analyses demonstrated that advanced age (over 80 years), male sex, single or non-married status, and lower median household income were significantly associated with increased suicide risk, while non-White race was associated with a lower risk. However, age lost statistical significance in the competing risk model. The nomogram demonstrated good discriminative ability, with area under the curve (AUC) values exceeding 0.71 at 3, 5, and 10 years in both training and validation cohorts. Calibration plots indicated good agreement between predicted and observed outcomes, and DCA confirmed clinical utility. Conclusions: Sociodemographic factors, including sex, race, marital status, and income, are independently associated with suicide risk in CLL/SLL patients. The developed nomogram offers a practical, evidence-based tool for early identification of high-risk individuals, thereby facilitating targeted psychosocial interventions and improving survivorship care.