Bilgesah Kilictas

Introduction. Cholangiocarcinoma (CCA) is a rare and highly aggressive malignancy of the bile ducts with a poor prognosis and a 5-year survival rate of approximately 5%. Chronic eosinophilic leukemia (CEL), characterized by clonal eosinophil proliferation, is a rare hematologic malignancy often progressing to acute leukemia. The simultaneous occurrence of these two malignancies is exceedingly rare, according to available research, this is the first case reported in the literature. Case report. This is the case of a 44-year-old female presenting with fatigue, diagnosed with metastatic CCA following imaging and biopsy. During chemotherapy with gemcitabine and cisplatin, the patient developed unexplained leukocytosis and eosinophilia, leading to a subsequent diagnosis of CEL. Despite aggressive treatment, the patient experienced complications, including cholangitis and renal failure, and succumbed to her illness four months post-diagnosis. Conclusions. This case highlights the rare co-occurrence of CCA and CEL, emphasizing the importance of vigilant monitoring for secondary hematologic malignancies in oncology patients. Early recognition and treatment of concurrent disorders can improve clinical outcomes and inform future research on such rare malignancy combinations. Keywords: cholangiocarcinoma chronic eosinophilic leukemia chemotherapy concurrent malignancies

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.

In this case report, we present a rare condition of ptosis due to sphenoid sinus metastasis of prostate adenocarcinoma. Malignancies of paranasal sinuses are rare and account for approximately 5% of all head and neck malignancies. Metastasis to the sphenoid sinus is even rarer. Prostate cancer is the most common cancer in men. While bone and lymph node metastases are common, metastasis to the head and neck region is rare. A 67-year-old male patient reported headache, drooping of the left eyelid (ptosis), and painful eye movements. Contrast-enhanced MRI of the brain and orbits showed a solid mass of approximately 3 × 3 cm predominantly occupying the left half of the left sphenoid sinus. The patient’s prostate-specific antigen (PSA) levels were elevated (56). Contrast-enhanced pelvic MRI revealed similar masses in the peripheral and transitional zones of the prostate and lymph node metastasis. A prostate biopsy revealed prostate adenocarcinoma (acinar type) with a Gleason score of 4 + 5. Ga-68 PET-PSMA imaging showed increased uptake in the prostate gland and seminal vesicles. Since there was no increased uptake in the mass in the left sphenoid sinus, a biopsy was performed to determine whether the mass was a metastasis; it confirmed that it was a metastasis of prostate adenocarcinoma. The patient was diagnosed with high-risk and high-volume hormone-sensitive metastatic prostate adenocarcinoma and was started on treatment with bicalutamide, LHRH agonist, and abiraterone. Follow-up visits showed significant decreases in PSA levels, and at the 10th month, Ga-68 PET-PSMA imaging showed significant regression in the prostate and other metastatic lesions. Significant regression was also observed in the solid component of the mass in the left sphenoid sinus. This case demonstrates that prostate cancer can present with ptosis as an initial symptom due to a rare sphenoid sinus metastasis, and although this symptom represents advanced-stage disease, it can indicate diagnosis. Therefore, prostate cancer should be considered in differential diagnosis for masses and related symptoms occurring in the head and neck region. Keywords: ptosis sphenoid sinus metastasis prostate adenocarcinoma