Search

Ovarian cancer is one of the most frequent malignancies in women. The treatment landscape underwent significant changes as new agents were introduced in ovarian cancer management over the last decade. We present two cases of long responses to Olaparib in BRCA (BReast CAncer gene) mutant ovarian cancer patients. The first case belongs to a 42-year-old female diagnosed with advanced ovarian carcinoma with a rare germinal mutation (BRCA1 c.68_69delAG, commonly found in descendants of Ashkenazi Jewish populations, but also Arabic and Asian ones) and a significant family history of ovarian and breast cancers. After poorly tolerated neoadjuvant chemotherapy, the patient underwent total hysterectomy, bilateral adnexectomy, and intraperitoneal hyperthermic chemotherapy. After eight months, the disease progressed, and first-line platinum chemotherapy was administered. Although not well-tolerated (grade 3 anemia, allergic reactions), chemotherapy resulted in a partial response, and given the patient's characteristics, maintenance with Olaparib was recommended. Treatment is ongoing (total current duration 69 months) and tolerated well (grade 1 side effects). This case illustrates the long-term benefits that novel therapies like Olaparib may offer in patients with platinum-sensitive relapsed ovarian cancer harboring a rare BRCA mutation. The second case highlights a 55-year-old postmenopausal woman diagnosed with ovarian cancer, FIGO stage IVA. Initial treatment included six cycles of chemotherapy, which led to a partial response, followed by interval debulking surgery and another four cycles of chemotherapy. Subsequent Olaparib maintenance therapy post BRCA1 mutation identification contributed to a significant progression-free survival of 65 months until disease recurrence and secondary cytoreductive surgery, showcasing the effectiveness of PARP inhibitors in personalized oncology treatment of ovarian cancer. [ABSTRACT FROM AUTHOR]

Background: Machine learning models learn about general behavior from data by finding the relationships between features. Our purpose was to develop a predictive model to identify and predict which subset of colorectal cancer patients are more likely to experience chemotherapy-induced toxicity and to determine the specific attributes that influence the presence of treatment-related side effects., Methods: The predictor was general toxicity, and for the construction of our data training, we selected 95 characteristics that represent the health state of 74 patients prior to their first round of chemotherapy. After the data were processed, Random Forest models were trained to offer an optimal balance between accuracy and interpretability., Results: We constructed a machine learning predictor with an emphasis on assessing the importance of numerical and categorical variables in relation to toxicity., Conclusions: The incorporation of artificial intelligence in personalizing colorectal cancer management by anticipating and overseeing toxicities more effectively illustrates a pivotal shift towards more personalized and precise medical care.