Background: Although higher-generation TKIs are associated with improved progression-free survival in advanced NSCLC patients with EGFR mutations, the optimal selection of TKI treatment remains uncertain. To address this gap, we developed a web application powered by a reinforcement learning (RL) algorithm to assist in guiding initial TKI treatment decisions. Methods: Clinical and mutational data from advanced NSCLC patients were retrospectively collected from 14 medical centers. Only patients with complete data and sufficient follow-up were included. Multiple supervised machine learning models were tested, with the Extra Trees Classifier (ETC) identified as the most effective for predicting progression-free survival. Feature importance scores were calculated by the ETC, and features were then integrated into a Deep Q-Network (DQN) RL algorithm. The RL model was designed to select optimal TKI generation and a treatment line for each patient and was embedded into an open-source web application for experimental clinical use. Results: In total, 318 cases of EGFR-mutant advanced NSCLC were analyzed, with a median patient age of 63. A total of 52.2% of patients were female, and 83.3% had ECOG scores of 0 or 1. The top three most influential features identified were neutrophil-to-lymphocyte ratio (log-transformed), age (log-transformed), and the treatment line of TKI administration, as tested by the ETC algorithm, with an area under curve (AUC) value of 0.73, whereas the DQN RL algorithm achieved a higher AUC value of 0.80, assigning distinct Q-values across four TKI treatment categories. This supports the decision-making process in the web-based ‘EGFR Mutant NSCLC Treatment Advisory System’, where clinicians can input patient-specific data to receive tailored recommendations. Conclusions: The RL-based web application shows promise in assisting TKI treatment selection for EGFR-mutant advanced NSCLC patients, underscoring the potential for reinforcement learning to enhance decision-making in oncology care.

Introduction: Molecular multitargeted small tyrosine kinase inhibitory (TKI) agents such as axitinib, sunitinib and pazopanib are commonly used in several types of solid tumors. Anemia is not a rare effect of these drugs which may occur at all grades. However, drug-induced immune hemolytic anemia (IHA), a very rare condition is distinctive from other types of anemia with its specific mechanism and management strategy. Case Reports: We reported three different TKI-induced IHA cases that occurred due to axitinib, sunitinib, and pazopanib, respectively. The first two cases were diagnosed with renal cell carcinoma and the last one was diagnosed with soft tissue sarcoma. They all presented with the characteristic symptoms of anemia and hemolysis. All the cases were detected positive for the complement C3d direct antiglobulin (direct coombs) test. Management and Outcomes: Discontinuation of the causative drug and 1 mg/kg/day dose of corticosteroid treatment were able to control IHA in all three cases. Excluding the other factors of IHA and an evident laboratory and clinical benefit after withholding the TKI led to the diagnosis of TKI-related IHA in each case. Discussion: TKIs are relatively new in clinical practice and are being used for more indications and in more patients. To our knowledge#these three cases are unique in terms of axitinib#sunitinib#and pazopanib-related IHA.

Background: Poly(ADP-ribose) polymerase (PARP) inhibitors have been established as a first-line maintenance therapy in advanced epithelial ovarian cancer (EOC) following platinum-based chemotherapy. While phase III trials have demonstrated significant progression-free survival (PFS) benefits with olaparib and niraparib, real-world data remain limited. Methods: This retrospective, multicenter real-world study included 179 patients with newly diagnosed epithelial ovarian treated with first-line maintenance olaparib or niraparib across 33 centers in Türkiye between January 2014 and March 2025. Clinical, pathological, and molecular data—including BRCA (Breast Cancer Susceptibility Gene) mutation status, origin, and variant classification—was collected. The primary endpoint was PFS, and secondary endpoints included overall survival (OS) and safety. Survival outcomes were analyzed using Kaplan–Meier methods. Results: Of 179 patients, 110 received olaparib and 69 received niraparib. BRCA mutations were present in 88.3% of patients, while 11.7% had unknown HRD status. Median follow-up was 16.5 months, and median PFS was not reached. Estimated PFS rates for the overall cohort were 91.0% at 6 months, 83.0% at 12 months, and 64.0% at 24 months. In the olaparib cohort, BRCA-mutant patients demonstrated PFS rates of 89%, 78%, 73%, and 64% at 6, 12, 18, and 24 months, respectively. In the niraparib cohort, corresponding PFS rates among BRCA-mutant patients were 87% at 6 months and 75% at 12 months. Patients harboring pathogenic BRCA variants experienced longer PFS compared with those with likely pathogenic variants. Any-grade adverse events occurred in 73.7% of patients, and grade 3–4 events in 29.6%, with hematologic toxicities predominating. Dose interruptions were more frequent with niraparib, while treatment discontinuation rates were low in both groups. No cases of myelodysplastic syndrome or acute myeloid leukemia were observed. Conclusions: In this large multicenter real-world cohort, first-line maintenance therapy with olaparib and niraparib provided durable PFS benefit in patients with advanced EOC, particularly among those with pathogenic BRCA mutations, confirming their effectiveness and manageable safety profiles in routine clinical practice.

Purpose: Individuals below the age of 40 make up only 3%-11% of colorectal cancer (CRC) cases. In this study, we aimed to review clinicopathological characteristics of rectal cancer in young adults. Methods: Rectal adenocancer patients aged ≤40 were included in this study from Antalya Training and Research Hospital. A single-arm descriptive study was designed. Results: There were 85 patients in the final analyses (n = 85). The median age was 37 (19-40). Mucinous adenocarcinoma and signet-cell carcinoma rates were 11.8% for each. Twenty patients (24.4%) had high-grade cancer. Fourteen patients (16.5%) had CRC history in a first-degree relative. None of the patients were diagnosed through a screening test. Of the 85 patients, 41 (48.2%) were stage 3 and 23 (27.1%) were stage 4 at the time of diagnosis. Thirty-four (54.8%) of the 62 nonmetastatic patients had neoadjuvant and 27 (43.5%) had adjuvant treatment because of having an upfront surgery before presentation. In the nonmetastatic population, the 5-year disease-free survival rate was 69.7 ± 6.5%. De-novo metastatic underwent chemotherapy, and biological agents were administered when feasible. KRAS mutation rate was 56.5% among metastatic patients. The median progression-free survival for the first-line treatment was 11.2 months (5.7-16.6), and the median overall survival was 22.3 months (15.4-29.1). Conclusion: We demonstrated that rectal cancer is usually diagnosed at late stages in young individuals which is compatible with the previous reports. Low cancer awareness in young patients and their caregivers and adverse histological features were advocated as the reason for the diagnostic delay. However, future studies may elucidate the reason behind the common diagnosis at advanced stages.

Purpose: The prognostic value of cetuximab-related electrolyte disturbances in metastatic colorectal cancer (CRC) remains unclear. The available reports on the prognostic effect of hypomagnesemia are controversial, while there are no comprehensive analyses regarding hypokalemia. This study aimed to evaluate the impact of hypomagnesemia and hypokalemia on treatment outcomes in patients with RAS/RAF wild-type metastatic CRC receiving first-line cetuximab-based therapy. Patients and Methods: We retrospectively analysed 305 patients treated across seven oncology centers between March 2013 and December 2024. Patients with baseline renal insufficiency or pre-existing electrolyte disturbance were excluded. Serum magnesium and potassium levels were assessed from the initiation of cetuximab until one month after its discontinuation. Results: There was one patient with missing magnesium levels and one patient with missing potassium levels. Three-hundred and four patients were available for the final analyses (n=304). Hypomagnesemia and hypokalemia occurred in 29.9% and 20.7% of the patients, respectively. Neither hypomagnesemia nor hypokalemia was significantly associated with progression-free survival (PFS) (11.9 vs 11.7 months for each; p=0.528 and p=0.327) or overall survival (OS) (25.3 vs 27.9 months; p=0.705 and 22.0 vs 28.8 months; p=0.824, respectively). Hypokalemia was correlated with a higher disease control rate (96.8% vs 87.1%, p= 0.028). In multivariate analyses, only metastatic burden (≥ 2 sites) independently associated with inferior outcomes for both PFS (HR 1.61, 95% CI 1.25– 2.08, p< 0.001) and OS (HR 1.77, 95% CI 1.31– 2.39, p< 0.001). Conclusion: Hypomagnesemia and hypokalemia did not significantly impact survival outcomes despite previous studies indicating otherwise. Moreover, hypokalemia was linked to improved disease control. These results provide incremental evidence regarding the clinical relevance of electrolyte disturbances, particularly hypokalemia, and highlight the need for prospective studies to clarify their prognostic and predictive significance.