The role of novel risk-scoring systems in predicting the efficacy of immunotherapy

Background. Metastatic non-small cell lung cancer (mNSCLC) remains a significant oncological challenge despite major advancements in treatment with immune checkpoint inhibitors (ICIs). However, some patients resist ICIs, highlighting the need for novel risk-scoring systems to predict immunotherapy efficacy. Purpose – to evaluate the Lung Immune Prognostic Index (LIPI), Advanced Lung Cancer Inflammation Index (ALI), Patras Immunotherapy Score (PIOS), Prognostic Nutritional Index (PNI), and LEM score (Leukocytes, ECOG, Metastases) as predictors of ICI therapy efficacy in patients with mNSCLC. Materials and Methods. A retrospective study included 105 patients with mNSCLC who received ICI therapy at the Sumy Regional Clinical Oncology Center between 2016 and 2024. Risk stratification was based on clinical parameters (performance status, use of antibiotics and steroids, height, weight) and laboratory markers (white blood cell count, albumin, and lactate dehydrogenase levels). Treatment efficacy was assessed using iRECIST criteria. Statistical analysis was performed using the chi-square test, Kaplan-Meier method, and Cox proportional hazards regression model. A p-value of <0.05 was considered statistically significant. Results. Among the patients, an objective response rate (ORR) was achieved at 51.4%, and the disease control rate (DCR) was 86.6%. Patients with 3 LEM risk factors were significantly less likely to achieve OS (χ2 = 14.8014, p = 0.002) and SVR (χ2 = 22.3377, p = 0.0001). Response to treatment in patients with no LEM risk factors, 1 or 2 risk factors was comparable. Patients with 3 LEM risk factors had the worst survival rates: median progression-free survival (PFS) – 3.0 months (p = 0.001), overall survival (OS) – 4.2 months (p = 0.0001). Cox regression analysis confirmed that LEM was an independent predictor of PFS (HR = 1.59; 95% CI 1.22–2.08; p = 0.001) and OS (HR = 1.81; 95% CI 1.38–2.39; p = 0.0001). The LIPI, ALI, LIPS, PIOS, and PNI risk scoring systems were similar in their predictive value. Conclusions. Only LEM was a significant predictor of ICI therapy efficacy among the analyzed risk-scoring systems in patients with mNSCLC. The use of LEM may facilitate personalized treatment approaches and optimize therapeutic decision-making.