Serum Albumin Predicts Immune-Related Adverse Events and Outcomes in Non–Small Cell Lung Cancer

Background Immune checkpoint inhibitors (ICIs) are a standard treatment for advanced non–small cell lung cancer (NSCLC), but clinically practical predictors of immune-related adverse events (irAEs) and treatment continuity remain limited. Methods We conducted a retrospective cohort study using two nationwide Japanese administrative claims databases: Medical Data Vision (MDV) and the Japan Medical Data Center (JMDC). Patients with advanced NSCLC treated with ICIs were identified. Those with available thyroid function data were included in analyses of ICI-induced hypothyroidism (MDV, n = 1,786; JMDC, n = 1,083), and patients receiving first-line ICIs were analyzed for treatment continuity (MDV, n = 1,088; JMDC, n = 1,007). Baseline demographics, laboratory biomarkers, and concomitant medications were evaluated. Machine learning models including Elastic Net were developed and externally validated to predict hypothyroidism. Treatment durability was assessed using time to next treatment or death (TTNT-D). Results Elastic Net showed the most consistent performance across cohorts (AUC: 0.72 training, 0.73 validation, 0.71 test). Baseline thyroid-stimulating hormone was the strongest predictor of hypothyroidism. Serum albumin consistently emerged as an important predictor across all machine learning models. Higher albumin levels were associated with a reduced risk of hypothyroidism and significantly prolonged TTNT-D (MDV: HR 0.75; JMDC: HR 0.79, ; both p < 0.05). Patients with albumin ≥ 3.5 g/dL had markedly longer median TTNT-D compared with those < 3.0 g/dL (MDV: 15.3 vs 6.2 months; JMDC: 16.0 vs 5.4 months; both p < 0.001). Conclusions Across two independent real-world datasets, serum albumin was robustly associated with ICI-induced hypothyroidism and treatment continuity, suggesting its utility as a practical biomarker for optimizing ICI therapy.