Čedna Tomasović-Lončarić

Gliomas are notably challenging to treat due to their invasive nature and resistance to conventional therapies. The ABCG2 protein has attracted attention for its role in multidrug resistance, complicating treatment effectiveness. This study scrutinized the relationship between ABCG2 expression and glioma grade and the role of ABCG2 in the process of glioma progression, aiming to evaluate ABCG2 expression as a predictive factor of tumor progression and patient survival. Conducted at Dubrava University Hospital, Zagreb, Croatia, the study analyzed 152 glioma specimens from 2013 to 2022, assessing ABCG2 expression alongside standard clinical markers. A significant association was found between patients’ survival and the ABCG2 profile (p = 0.003, r = 0.24), separately for patients who underwent chemotherapy (p = 0.0004, r = 0.32) and radiotherapy (p = 0.003, r = 0.29). Furthermore, the ABCG2 profile was significantly associated with disease progression (p = 0.007, r = 0.23), tumor grade (p = 0.0002, r = 0.31), and Ki67 expression (p = 0.0004, r = 0.31). ABCG2-positive tumor cells only showed association with Ki67 expression (p = 0.002, r = 0.28). The ABCG2 profile was found to affect the overall patient survival (p = 0.02) and represent a moderate indicator of tumor progression (p = 0.01), unlike the percentage of ABCG2-positive tumor cells. ABCG2 may serve as a marker of angiogenesis and vascular abnormalities within tumors, predicting glioma progression and treatment response. Targeting ABCG2 could enhance chemoradiotherapy efficacy and improve patient outcomes, which highlights its value in assessing tumor aggressiveness and designing treatment strategies.

Background: Due to recent changes in breast cancer treatment strategy, significantly more patients are treated with neoadjuvant systemic therapy (NST). Radiological methods do not precisely determine axillary lymph node status, with up to 30% of patients being misdiagnosed. Hence, supplementary methods for lymph node status assessment are needed. This study aimed to apply and evaluate machine learning models on clinicopathological data, with a focus on patients meeting NST criteria, for lymph node metastasis prediction. Methods: From the total breast cancer patient data (n = 8381), 719 patients were identified as eligible for NST. Machine learning models were applied for the NST-criteria group and the total study population. Model explainability was obtained by calculating Shapley values. Results: In the NST-criteria group, random forest achieved the highest performance (AUC: 0.793 [0.713, 0.865]), while in the total study population, XGBoost performed the best (AUC: 0.762 [0.726, 0.795]). Shapley values identified tumor size, Ki-67, and patient age as the most important predictors. Conclusion: Tree-based models achieve a good performance in assessing lymph node status. Such models can lead to more accurate disease stage prediction and consecutively better treatment selection, especially for NST patients where radiological and clinical findings are often the only way of lymph node assessment.