Integration of longitudinal deep-radiomics and clinical data improves the prediction of durable benefits to anti-PD-1/PD-L1 immunotherapy in advanced NSCLC patients.

BACKGROUND: Identifying predictive non-invasive biomarkers of immunotherapy response is crucial to avoid premature treatment interruptions or ineffective prolongation. Our aim was to develop a non-invasive biomarker for predicting immunotherapy clinical durable benefit, based on the integration of radiomics and clinical data monitored through early anti-PD-1/PD-L1 monoclonal antibodies treatment in patients with advanced non-small cell lung cancer (NSCLC). METHODS: In this study, 264 patients with pathologically confirmed stage IV NSCLC treated with immunotherapy were retrospectively collected from two institutions. The cohort was randomly divided into a training (n = 221) and an independent test set (n = 43), ensuring the balanced availability of baseline and follow-up data for each patient. Clinical data corresponding to the start of treatment was retrieved from electronic patient records, and blood test variables after the first and third cycles of immunotherapy were also collected. Additionally, traditional radiomics and deep-radiomics features were extracted from the primary tumors of the computed tomography (CT) scans before treatment and during patient follow-up. Random Forest was used to implementing baseline and longitudinal models using clinical and radiomics data separately, and then an ensemble model was built integrating both sources of information. RESULTS: The integration of longitudinal clinical and deep-radiomics data significantly improved clinical durable benefit prediction at 6 and 9 months after treatment in the independent test set, achieving an area under the receiver operating characteristic curve of 0.824 (95% CI: [0.658,0.953]) and 0.753 (95% CI: [0.549,0.931]). The Kaplan-Meier survival analysis showed that, for both endpoints, the signatures significantly stratified high- and low-risk patients (p-value< 0.05) and were significantly correlated with progression-free survival (PFS6 model: C-index 0.723, p-value = 0.004; PFS9 model: C-index 0.685, p-value = 0.030) and overall survival (PFS6 models: C-index 0.768, p-value = 0.002; PFS9 model: C-index 0.736, p-value = 0.023). CONCLUSIONS: Integrating multidimensional and longitudinal data improved clinical durable benefit prediction to immunotherapy treatment of advanced non-small cell lung cancer patients. The selection of effective treatment and the appropriate evaluation of clinical benefit are important for better managing cancer patients with prolonged survival and preserving quality of life.

Immune checkpoint inhibitors-associated thrombosis in patients with lung cancer and melanoma: a study of the Spanish society of medical oncology (SEOM) thrombosis and cancer group.

PURPOSE: Immune Checkpoint Inhibitors (ICI) can be associated with thrombotic events, both venous and arterial (VTE/AT). However, there is a paucity of information regarding patients in routine clinical practice. METHODS/PATIENTS: Retrospective, multicenter study promoted by the Thrombosis and Cancer Section of the Spanish Society of Medical Oncology (SEOM). Patients with melanoma and lung cancer who initiated ICI between 01/01/2015 and 31/12/2019 were recruited. Minimum follow-up was 6 months (unless it was not possible because of death). The primary objective was to calculate the incidence of ICI-associated VTE/AT and the secondary objectives included to analyze its impact on survival and to identify predictor variables for VTE/AT. RESULTS: 665 patients with lung cancer were enrolled. The incidence of VTE/AT during follow-up was 8.4%. Median overall survival (OS) was lower in the VTE/AT group (12 months 95% CI 4.84-19.16 vs. 19 months 95% CI 16.11-21.9; p = 0.0049). Neutrophil/lymphocyte ratio (NLR) and anemia upon initiation of IT, as well as a history of thrombosis between cancer diagnosis and the start of ICI, were predictive variables for developing of VTE/AT (p < 0.05). 291 patients with melanoma were enrolled. There was a 5.8% incidence rate of VTE/AT during follow-up. Median OS was lower in the VTE/AT group (10 months 95% CI 0.0-20.27 vs. 29 months 95% CI 19.58-36.42; p = 0.034). NLR and lactate dehydrogenase (LDH) at the beginning of ICI were predictor variables for VTE/AT (p < 0.05). CONCLUSIONS: ICI increases the risk of VTE/AT in patients with lung cancer and melanoma, which impact OS.