ABSTRACT
Objectives@#. Prognosticating idiopathic sudden sensorineural hearing loss (ISSNHL) is an important challenge. In our study, a dataset was split into training and test sets and cross-validation was implemented on the training set, thereby determining the hyperparameters for machine learning models with high test accuracy and low bias. The effectiveness of the following five machine learning models for predicting the hearing prognosis in patients with ISSNHL after 1 month of treatment was assessed: adaptive boosting, K-nearest neighbor, multilayer perceptron, random forest (RF), and support vector machine (SVM). @*Methods@#. The medical records of 523 patients with ISSNHL admitted to Korea University Ansan Hospital between January 2010 and October 2017 were retrospectively reviewed. In this study, we analyzed data from 227 patients (recovery, 106; no recovery, 121) after excluding those with missing data. To determine risk factors, statistical hypothesis tests (e.g., the two-sample t-test for continuous variables and the chi-square test for categorical variables) were conducted to compare patients who did or did not recover. Variables were selected using an RF model depending on two criteria (mean decreases in the Gini index and accuracy). @*Results@#. The SVM model using selected predictors achieved both the highest accuracy (75.36%) and the highest F-score (0.74) on the test set. The RF model with selected variables demonstrated the second-highest accuracy (73.91%) and F-score (0.74). The RF model with the original variables showed the same accuracy (73.91%) as that of the RF model with selected variables, but a lower F-score (0.73). All the tested models, except RF, demonstrated better performance after variable selection based on RF. @*Conclusion@#. The SVM model with selected predictors was the best-performing of the tested prediction models. The RF model with selected predictors was the second-best model. Therefore, machine learning models can be used to predict hearing recovery in patients with ISSNHL.
ABSTRACT
Ovarian cancer is common malignant disease with high mortality in the female. However, lymph node metastasis in the head and neck of ovarian cancer is very rare than in para-aortic, pelvic lymph node. A 49-year-old female patient came to our clinic with a left neck mass. After total thyroidectomy and left selective neck dissection for the cervical neck level II, III, IV, V, VI for ovarian cancer and thyroid cancer, she had already undergone chemotherapy (Paclitaxel+Carboplatin) 18 month ago. CT scan showed only lymph node enlargement in left neck level II. Positron emission tomography-computed tomography (PET-CT) revealed a hypermetabolic lesion in same area but no other hypermetabolic lesion, especially in the pelvic and abdominal cavity. Fine needle aspiration cytology revealed metastatic carcinoma. The serum level of CA-125 was elevated to 43.8U/mL, whereas other tumor markers (CA 19-9, CEA) were in the normal range. She underwent a revision of selective neck lymph node dissection for the cervical neck levels I, II, and III, and on the review of surgical pathology, metastatic carcinoma was suspected. Thus, we performed immunohistochemical staining for the tissue; as a result, it was finally diagnosed as metastatic ovarian cancer (positive for CK7, ER and PR, and negative for CK20). Adjuvant chemotherapy (Paclitaxel+Carboplatin) was planned on the tumor board, and the patient successfully received chemotherapy.
ABSTRACT
Ovarian cancer is common malignant disease with high mortality in the female. However, lymph node metastasis in the head and neck of ovarian cancer is very rare than in para-aortic, pelvic lymph node. A 49-year-old female patient came to our clinic with a left neck mass. After total thyroidectomy and left selective neck dissection for the cervical neck level II, III, IV, V, VI for ovarian cancer and thyroid cancer, she had already undergone chemotherapy (Paclitaxel+Carboplatin) 18 month ago. CT scan showed only lymph node enlargement in left neck level II. Positron emission tomography-computed tomography (PET-CT) revealed a hypermetabolic lesion in same area but no other hypermetabolic lesion, especially in the pelvic and abdominal cavity. Fine needle aspiration cytology revealed metastatic carcinoma. The serum level of CA-125 was elevated to 43.8U/mL, whereas other tumor markers (CA 19-9, CEA) were in the normal range. She underwent a revision of selective neck lymph node dissection for the cervical neck levels I, II, and III, and on the review of surgical pathology, metastatic carcinoma was suspected. Thus, we performed immunohistochemical staining for the tissue; as a result, it was finally diagnosed as metastatic ovarian cancer (positive for CK7, ER and PR, and negative for CK20). Adjuvant chemotherapy (Paclitaxel+Carboplatin) was planned on the tumor board, and the patient successfully received chemotherapy.
ABSTRACT
A thyroglossal duct cyst (TGDC) is the most common congenital anomaly of the neck. However, carcinoma arising from TGDC is extremely rare. We report 2 cases of TGDC carcinoma. In the first case, a 21-year-old male patient complained of an anterior cervical mass; computed tomography (CT) and sonography revealed cystic mass that was suspected to be a TGDC. Sistrunk operation was performed. Papillary carcinoma was confirmed in pathologic examination. Additionally, he underwent total thyroidectomy and central neck dissection. After radioactive iodine ablation (RAI) was performed. In the second case, a 28-year-old male patient visited our out-patient department complaining of submental mass. He had already been diagnosed TGDC carcinoma 13 years ago and had undergone Sistrunk operation and total thyroidectomy. Malignancy was confirmed using fine-needle aspiration; thus, lateral neck dissection was performed and following this, he underwent RAI. Till date, no evidence of recurrence has been observed in these patients.