Current Understanding of Urachal Adenocarcinoma and Management Strategy.

PURPOSE OF REVIEW: The aim of this review is to sum up the state of the art of urachal carcinoma (UC) in order to easily guide clinicians. RECENT FINDINGS: UC is a rare and aggressive disease with consequent few data about diagnosis and treatment. Dates are mainly based on retrospective trial and case reports with limited prospective trial. Clinical presentation is not specific, often with urinary symptoms. Diagnosis is mainly based on CT scan and MRI, useful to evaluate local invasion and nodal status and to detect the presence of distant metastases. Therefore, biopsy is needed to obtain histological confirmation. Surgery is the gold standard for localized disease, while different chemotherapy schemes have been used in metastatic setting. Novel findings based on mutational analysis of the tumor include the use of biological treatment, such as cetuximab, and immunotherapy, such as atezolizumab, with satisfactory responses, suggesting that personalized treatment could be the most suitable option for UC.

High bone tumor burden to identify advanced non-small cell lung cancer patients with survival benefit upon bone targeted agents and immune checkpoint inhibitors.

BACKGROUND: Bone-targeted agents (BTA), such as denosumab (DN) and zoledronic acid (ZA), have historically reduced the risk of skeletal related events in cancer patients with bone metastases (BM), with no improvement in survival outcomes. In the immunotherapy era, BM have been associated with poor prognosis upon immune-checkpoint inhibitors (ICI). Currently, the impact of bone tumor burden on survival upon BTAs in advanced non-small cell lung cancer (aNSCLC) patients treated with ICI remains unknown. METHODS: Data from ICI-treated aNSCLC patients with BM (4/2013-5/2022) in one institution were retrospectively collected. BTA-ICI concurrent treatment was defined as BTA administration at any time before or within 90 days from ICI start. High bone tumor burden (HBTB) was defined as ≥ 3 sites of BM. Median OS (mOS) was estimated with Kaplan-Meier. Aikaike's information criterion (AIC) was used to select the best model for data analysis adjusted for clinical variables. RESULTS: Of 134 patients included, 51 (38 %) received BTA. At a mFU of 39.6 months (m), BTA-ICIs concurrent treatment did not significantly impact on mOS [8.3 m (95% CI 3.9-12.8) versus (vs) 6.8 m (95% CI 4.0-9.6) p = 0.36]; these results were confirmed after adjustment for clinical variables selected by AIC. A multivariate model showed a significant interaction between BTA use and HBTB or radiation therapy to BM. In subgroup analyses, only HBTB confirmed to be associated with significantly longer mOS [8.3 m (95% CI 2.4-14.2) vs 3.5 m (95% CI 2.9-4.1), p = 0.003] and mPFS [3.0 m (95% CI 1.6-4.4) vs 1.8 m (95% CI 1.6-2.0) p = 0.001] upon BTA-ICI concurrent treatment, with the most pronounced OS benefit observed for DN-ICI concurrent regimen [15.2 m (95% CI 0.1-30.7) vs 3.5 m (95% CI 2.9-4.1) p = 0.002]. CONCLUSIONS: In the immunotherapy era, HBTB can identify patients experiencing survival benefit with BTA, especially with DN-ICI combination. HBTB should be included as a stratification factor in the upcoming trials assessing BTA and ICI combinations in patients with aNSCLC and BM.

Machine Learning Using Real-World and Translational Data to Improve Treatment Selection for NSCLC Patients Treated with Immunotherapy.

(1) Background: In advanced non-small cell lung cancer (aNSCLC), programmed death ligand 1 (PD-L1) remains the only biomarker for candidate patients to immunotherapy (IO). This study aimed at using artificial intelligence (AI) and machine learning (ML) tools to improve response and efficacy predictions in aNSCLC patients treated with IO. (2) Methods: Real world data and the blood microRNA signature classifier (MSC) were used. Patients were divided into responders (R) and non-responders (NR) to determine if the overall survival of the patients was likely to be shorter or longer than 24 months from baseline IO. (3) Results: One-hundred sixty-four out of 200 patients (i.e., only those ones with PD-L1 data available) were considered in the model, 73 (44.5%) were R and 91 (55.5%) NR. Overall, the best model was the linear regression (RL) and included 5 features. The model predicting R/NR of patients achieved accuracy ACC = 0.756, F1 score F1 = 0.722, and area under the ROC curve AUC = 0.82. LR was also the best-performing model in predicting patients with long survival (24 months OS), achieving ACC = 0.839, F1 = 0.908, and AUC = 0.87. (4) Conclusions: The results suggest that the integration of multifactorial data provided by ML techniques is a useful tool to select NSCLC patients as candidates for IO.

Immune-Checkpoint Inhibitors in Advanced Non-Small Cell Lung Cancer With Uncommon Histology.

BACKGROUND: Immune-checkpoint inhibitors (ICIs) have significantly improved outcome of advanced non-small cell lung cancer (aNSCLC) patients. However, their efficacy remains uncertain in uncommon histologies (UH). MATERIALS AND METHODS: Data from ICI treated aNSCLC patients (April,2013-January,2021) in one Institution were retrospectively collected. Univariate and multivariate survival analyses were estimated by Kaplan-Meier and Cox proportional hazards regression model, respectively. Objective response rate (ORR) and disease control rate (DCR) were assessed. RESULTS: Of 375 patients, 79 (21.1%) had UH: 19 (24.1%) sarcomatoid carcinoma, 15 (19.0%) mucinous adenocarcinoma, 10 (12.6%) enteric adenocarcinoma, 8 (10.1%) adenocarcinoma not otherwise specified, 7 (8.9%) large-cell neuroendocrine carcinoma, 6 (7.6%) mixed histology non-adenosquamous, 5 (6.3%) adenosquamous carcinoma, 9 (11.4%) other UH. In UH group, programmed death-ligand 1 (PD-L1) <1%, 1-49%, ≥50% and unknown expression were reported in 27.8%, 22.8%, 31.7% and 17.7% patients respectively and ICI was the second/further-line in the majority of patients. After a median follow-up of 35.64 months (m), median progression-free survival (mPFS) was 2.5 m in UH [95% CI 2.2-2.9 m] versus (vs.) 2.7 m in CH [95% CI 2.3-3.2 m, P-value = .584]; median overall survival (mOS) was 8.8 m [95% CI 4.9-12.6 m] vs. 9.7 m [95% CI 8.0-11.3 m, P-value = .653]. At multivariate analyses only ECOG PS was a confirmed prognostic factor in UH. ORR and DCR were 25.3% and 40.5% in UH vs. 21.6% and 49.5% in CH [P-value = .493 and .155 respectively]. CONCLUSIONS: No significant differences were detected between UH and CH groups. Prospective trials are needed to understand ICIs role in UH population.

Real-world data to build explainable trustworthy artificial intelligence models for prediction of immunotherapy efficacy in NSCLC patients.

Introduction: Artificial Intelligence (AI) methods are being increasingly investigated as a means to generate predictive models applicable in the clinical practice. In this study, we developed a model to predict the efficacy of immunotherapy (IO) in patients with advanced non-small cell lung cancer (NSCLC) using eXplainable AI (XAI) Machine Learning (ML) methods. Methods: We prospectively collected real-world data from patients with an advanced NSCLC condition receiving immune-checkpoint inhibitors (ICIs) either as a single agent or in combination with chemotherapy. With regards to six different outcomes - Disease Control Rate (DCR), Objective Response Rate (ORR), 6 and 24-month Overall Survival (OS6 and OS24), 3-months Progression-Free Survival (PFS3) and Time to Treatment Failure (TTF3) - we evaluated five different classification ML models: CatBoost (CB), Logistic Regression (LR), Neural Network (NN), Random Forest (RF) and Support Vector Machine (SVM). We used the Shapley Additive Explanation (SHAP) values to explain model predictions. Results: Of 480 patients included in the study 407 received immunotherapy and 73 chemo- and immunotherapy. From all the ML models, CB performed the best for OS6 and TTF3, (accuracy 0.83 and 0.81, respectively). CB and LR reached accuracy of 0.75 and 0.73 for the outcome DCR. SHAP for CB demonstrated that the feature that strongly influences models' prediction for all three outcomes was Neutrophil to Lymphocyte Ratio (NLR). Performance Status (ECOG-PS) was an important feature for the outcomes OS6 and TTF3, while PD-L1, Line of IO and chemo-immunotherapy appeared to be more important in predicting DCR. Conclusions: In this study we developed a ML algorithm based on real-world data, explained by SHAP techniques, and able to accurately predict the efficacy of immunotherapy in sets of NSCLC patients.