"Graded early warning system" of RET germline mutation carriers in MEN2A/MEN2B families and total thyroidectomy (report of 7 cases) / 中华耳鼻咽喉头颈外科杂志

Objective: To explore the reasonable time of prophylactic thyroidectomy for RET gene carriers in multiple endocrine neoplasia(MEN) 2A/2B families. Methods: From May 2015 to August 2021, RET gene carriers in MEN2A/MEN2B families were dynamically followed up at the Department of Thyroid Head and Neck Surgery, Beijing Tongren Hospital of Capital Medical University. The high-risk patients were encouraged to undergo prophylacitc total thyroidectomy according to the principle of "graded early warning system", namely the evaluation of gene detection, calcitonin value and ultrasound examination successively. Seven cases underwent the surgery, including 3 males and 4 females, aged from 7 to 29 years. According to the risk stratification listed in the guidelines of the American Thyroid Association in 2015, there were 2 cases of the highest risk, 2 cases of the high risk and 3 cases of the modest risk. Calcitonin index remained within the normal range in 3 cases and elevated in 4 cases before operation. All 7 patients underwent thyroidectomy with lymph node dissection of the level Ⅵ performed in 4 patients. Results: The time from suggestion to operation was 2 to 37 months, with an average of 15.1 months. The 6 patients were medullary thyroid carcinoma and 1 case with C-cell hyperplasia. The follow-up time was 2 to 82 months, with an average of 38.4 months. Postoperative serum calcitonin levels of all cases decreased to normal level, with biochemical cure. There was no sign of recurrence on ultrasound examination. All 7 patients had no serious complications, no obvious thyroid dysfunction. Their height, weight and other indicators of pediatric patients were similar to those of their peers, with normal growth and development. Conclusion: For healthy people with MEN2A/MEN2B family history, prophylactic thyroidectomy can be carried out selectively based on the comprehensive evaluation of "graded early warning system" with strict screening and close monitoring.

Prediction of neural tube defect using support vector machine / 生物医学与环境科学（英文）

<p><b>OBJECTIVE</b>To predict neural tube birth defect (NTD) using support vector machine (SVM).</p><p><b>METHOD</b>The dataset in the pilot area was divided into non overlaid training set and testing set. SVM was trained using the training set and the trained SVM was then used to predict the classification of NTD.</p><p><b>RESULT</b>NTD rate was predicted at village level in the pilot area. The accuracy of the prediction was 71.50% for the training dataset and 68.57% for the test dataset respectively.</p><p><b>CONCLUSION</b>Results from this study have shown that SVM is applicable to the prediction of NTD.</p>