Status of glycosylated hemoglobin and prediction of glycemic control among patients with insulin-treated type 2 diabetes in North China: a multicenter observational study / 中华医学杂志(英文版)

BACKGROUND@#Blood glucose control is closely related to type 2 diabetes mellitus (T2DM) prognosis. This multicenter study aimed to investigate blood glucose control among patients with insulin-treated T2DM in North China and explore the application value of combining an elastic network (EN) with a machine-learning algorithm to predict glycemic control.@*METHODS@#Basic information, biochemical indices, and diabetes-related data were collected via questionnaire from 2787 consecutive participants recruited from 27 centers in six cities between January 2016 and December 2017. An EN regression was used to address variable collinearity. Then, three common machine learning algorithms (random forest [RF], support vector machine [SVM], and back propagation artificial neural network [BP-ANN]) were used to simulate and predict blood glucose status. Additionally, a stepwise logistic regression was performed to compare the machine learning models.@*RESULTS@#The well-controlled blood glucose rate was 45.82% in North China. The multivariable analysis found that hypertension history, atherosclerotic cardiovascular disease history, exercise, and total cholesterol were protective factors in glycosylated hemoglobin (HbA1c) control, while central adiposity, family history, T2DM duration, complications, insulin dose, blood pressure, and hypertension were risk factors for elevated HbA1c. Before the dimensional reduction in the EN, the areas under the curve of RF, SVM, and BP were 0.73, 0.61, and 0.70, respectively, while these figures increased to 0.75, 0.72, and 0.72, respectively, after dimensional reduction. Moreover, the EN and machine learning models had higher sensitivity and accuracy than the logistic regression models (the sensitivity and accuracy of logistic were 0.52 and 0.56; RF: 0.79, 0.70; SVM: 0.84, 0.73; BP-ANN: 0.78, 0.73, respectively).@*CONCLUSIONS@#More than half of T2DM patients in North China had poor glycemic control and were at a higher risk of developing diabetic complications. The EN and machine learning algorithms are alternative choices, in addition to the traditional logistic model, for building predictive models of blood glucose control in patients with T2DM.

Contralateral head leading turning accompanied by ipsilateral eye staring in a patient with seizure onset from posterior inferior temporal sulcus, a SEEG case report

The epileptic eye and head movements during epileptic seizures may be much more complicated thanpeople originally understood, which can be ipsilateral or contralateral to the electroencephalographyfocus. Here, we describe a male patient with drug resistant focal seizures associated with a directionalseparation between head and eye movement before evolving into generalized tonic-clonic seizure.His contralateral head leading turning showed forced, sustained, and unnatural features companiedby ipsilateral eye staring. Stereoeletroencephalography monitoring was performed, and 4 habitualseizures were recorded over 5 days. Three seizures showed left head leading turning and generalizedtonic-clonic seizure, and only one showed dizziness and ringing in the ears. All the seizures showedthat the ictal onset contacts were located in the posterior inferior temporal sulcus which borders onthe anterolateral part of medial superior temporal area. The patient underwent a resection includingtemporooccipital region, and the histopathology showed focal cortical dysplasia type Ic. He has beenseizure free for two years after operation. The scores of the intelligence and memory quotient improvedhalf year after operation.

The clinical and EEG features and mutation analysisin a Chinese patient with severe hypoplasia of the cerebellum and pons

We report here a Chinese female infant with severe hypoplasia of the cerebellum and pons, and heterozygous mutation (c.18G >T, p.E6D) in the TSEN54 gene. This mutation was not present in her parents and the 100 Chinese controls, which proved to be a de novo missense mutation. MR imaging of the patient revealed severe hypoplasia of the bilateral cerebellar hemispheres and vermis with moderate flattening of the pons. A video EEG during hospitalization demostrated abnormal background activities and generalized burst and attenuation patterns during interictal stage. The spasms and tonic spasms occurred frequently in clusters with generalized voltage attenuation.