Machine Learning Model for Classifying the Results of Fetal Cardiotocography Conducted in High-Risk Pregnancies

Purpose@#Fetal well-being is usually assessed via fetal heart rate (FHR) monitoring during the antepartum period. However, the interpretation of FHR is a complex and subjective process with low reliability. This study developed a machine learning model that can classify fetal cardiotocography results as normal or abnormal. @*Materials and Methods@#In total, 17492 fetal cardiotocography results were obtained from Ajou University Hospital and 100 fetal cardiotocography results from Czech Technical University and University Hospital in Brno. Board-certified physicians then reviewed the fetal cardiotocography results and labeled 1456 of them as gold-standard; these results were used to train and validate the model. The remaining results were used to validate the clinical effectiveness of the model with the actual outcome. @*Results@#In a test dataset, our model achieved an area under the receiver operating characteristic curve (AUROC) of 0.89 and area under the precision-recall curve (AUPRC) of 0.73 in an internal validation dataset. An average AUROC of 0.73 and average AUPRC of 0.40 were achieved in the external validation dataset. Fetus abnormality score, as calculated from the continuous fetal cardiotocography results, was significantly associated with actual clinical outcomes [intrauterine growth restriction: odds ratio, 3.626 (p=0.031); Apgar score 1 min: odds ratio, 9.523 (p<0.001), Apgar score 5 min: odds ratio, 11.49 (p=0.001), and fetal distress: odds ratio, 23.09 (p<0.001)]. @*Conclusion@#The machine learning model developed in this study showed precision in classifying FHR signals. This suggests that the model can be applied to medical devices as a screening tool for monitoring fetal status.

Clinicopathologic characteristics of ovarian clear cell carcinoma in the background of endometrioma: a surveillance strategy for an early detection of malignant transformation in patients with asymptomatic endometrioma

OBJECTIVE: This study aimed to analyze the clinical features of clear cell carcinoma in relation to endometriosis and to determine an appropriate surveillance strategy for the early detection of malignant transformation of endometrioma in asymptomatic patients. METHODS: We retrospectively reviewed the clinicopathologic data of 50 patients with ovarian clear cell carcinoma. Clinicopathologic characteristics, treatment outcomes, and the association between endometriosis and the risk of malignant transformation were analyzed. RESULTS: Ten (20%) patients had been diagnosed with endometrioma before the diagnosis of clear cell carcinoma. The median period from the diagnosis of endometrioma to clear cell carcinoma diagnosis was 50 months (range, 12–213 months). After complete staging surgery, histological confirmation of endometriosis was possible in 35 (70%) patients. Of the 50 patients, 39 (78%) had not undergone any gynecologic surveillance until the onset of symptoms, at which time many of them presented with a rapidly growing pelvic mass (median 10 cm, range 4.6–25 cm). With the exception of 2 patients, all cancer diagnoses were made when the patients were in their late thirties, and median tumor size was found to increase along with age. Asymptomatic patients (n=11) who had regular gynecologic examinations were found to have a relatively smaller tumor size, lesser extent of tumor spread, and lower recurrence rate (P=0.011, 0.283, and 0.064, respectively). The presence of endometriosis was not related to the prognosis. CONCLUSION: Considering the duration of malignant transformation and the timing of cancer diagnosis, active surveillance might be considered from the age of the mid-thirties, with at least a 1-year interval, in patients with asymptomatic endometrioma.

Radioactive Iodine-Induced Graves' Disease in a Patient with Toxic Adenoma / 대한갑상선학회지

We report a rare case of radioactive iodine (RAI)-induced Graves' disease in a patient with toxic adenoma. A 42-year-old woman presented with neck masses. A hot nodule was detected on a thyroid scan, which suggested toxic adenoma. She was treated with RAI. Three months after the treatment, she complained of thyrotoxic symptoms such as weight loss, palpitation, diarrhea, and menstrual irregularity. A new thyroid scan showed diffuse increased uptake, while the toxic adenoma previously detected was now a cold nodule. Moreover, an increased level of antibodies against the thyroid-stimulating hormone receptor was detected. These findings indicated Graves' disease. Hence she was treated with anti-thyroid drug. This case serves as a reminder for physicians to consider RAI-induced Graves' disease if thyrotoxicosis is noted after RAI treatment.

Long-term Complete Response with Lapatinib Plus Capecitabine in a Patient with HER2-Positive Breast Cancer Metastasized to the Pancreas / 이화의대지

A 37-year-old woman underwent a total mastectomy and adjuvant chemotherapy for HER2-positive breast cancer (pT1N0M), and then recurred in the right lung followed by the pancreas. Lung lobectomy and pylorus-preserving pancreaticoduodenectomy were performed, and systemic chemotherapies including trastuzumab were sequentially administered. However, metastasis to the pancreatic tail was detected. She underwent image-guided radiation therapy, but this was not effective. Lapatinib plus capecitabine combination was administered as forth-line treatment and the metastatic lesion was disappeared. She is continuing this regimen with a complete response for 48 months until now.