RESUMO
OBJECTIVES: Malignant struma ovarii (MSO) is a rare ovarian tumor characterized by mature thyroid tissue. The diverse symptoms and uncommon nature of MSO can create difficulties in its diagnosis and treatment. This study aimed to analyze data and use machine learning methods to understand the prognostic factors and potential management strategies for MSO. METHODS: In this retrospective cohort, the Surveillance, Epidemiology, and End Results (SEER) database provided the data used for this study's analysis. To identify the prognostic variables, we conducted Cox regression analysis and constructed prognostic models using five machine learning algorithms to predict the 5-year survival. A validation method incorporating the area under the curve of the receiver operating characteristic curve was used to validate the accuracy and reliability of the machine learning models. We also investigated the role of multiple therapeutic options using the Kaplan-Meier survival analysis. RESULTS: The study population comprised 329 patients. Multivariate Cox regression analysis revealed that older age, unmarried status, chemotherapy, and the total number of tumors in patients were poor prognostic factors. Machine learning models revealed that the multilayer perceptron accurately predicted outcomes, followed by the random forest classifier, gradient boosting classifier, K-nearest neighbors, and logistic regression models. The factors that contributed the most were age, marital status, and the total number of tumors in the patients. CONCLUSION: The present study offers a comprehensive approach for the treatment and prognosis assessment of patients with MSO. The machine learning models we have developed serve as a practical, personalized tool to aid in clinical decision-making processes.
RESUMO
BACKGROUND: Malignant Struma Ovarii (MSO) is a rare type of germ cell tumour which is diagnosed postoperatively on surgical pathology specimens by the presence of differentiated thyroid cancer in mature cystic teratomas in the ovaries. Treatment and follow-up procedures are not clearly established due to the paucity of MSO cases. CASE 1: A 44-year-old multiparous female presented with an irregular period. Ultrasound showed a left ovarian lesion mostly a dermoid cyst, however, CT showed a 3.8 × 2.7 × 4 cm complex cystic lesion with thick septation and enhancing soft tissue component. Laparoscopic left salpingo-oophorectomy was performed and histopathology showed a follicular variant of papillary thyroid carcinoma arising in a mature cystic teratoma. Peritoneal cytology was positive for malignancy. A thyroid function test was normal before surgery. Total thyroidectomy was performed followed by radioactive (RAI) iodine therapy. Later, a total laparoscopic hysterectomy and right salpingo-oophorectomy were performed. There is no evidence of recurrent disease during the 26-months follow-up. CASE 2: A 46-year-old single female presented with left lower abdominal pain that had persisted for 2 months. Imaging revealed an 8 × 9 × 9.5 cm left ovarian mass. Laparoscopic left salpingo-oophorectomy was performed and histopathology showed mature cystic teratoma with small papillary thyroid cancer. CT showed no evidence of metastatic disease. Later, the patient had a total thyroidectomy followed by radioactive (RAI) iodine therapy. She was started on thyroxine and later had total abdominal hysterectomy and right salpingo-oophorectomy. CONCLUSION: MSO is a very rare tumour. Preoperative diagnosis is very difficult because of the nonspecific symptoms and the lack of specific features in imaging studies. Also, there is no consensus on the optimal treatment of women with MSO. Our two cases add to the limited number of MSO cases.
