A Wearable System for Cervical Spondylosis Prevention Based on Artificial Intelligence / 中国医疗器械杂志

Accompanied by changes in modern work and lifestyle, the incidence of cervical spondylosis has increased year by year. In view of the fact long-term fixed posture of the head and neck is one of the main causes of cervical spondylosis, a set of wearable cervical spondylosis prevention system is developed. The system comprises a head and neck movement collection module based on the acceleration sensor and a head and neck motion recognition module based on artificial intelligence. Experimental results showed that the system can accurately identify long-term posture of the head and neck, and guide users to complete effective exercise therapy under the supervision of motion recognition module. Using this system can be beneficial for the prevention of cervical spondylosis.

A Domestic Diagnosis System for Early Restless Legs Syndrome Based on Deep Learning / 中国医疗器械杂志

Restless legs syndrome,as a common sleep disorder,has nowadays long been diagnosed by self-rating scale and polysomnography.In this paper,a domestic diagnosis system for early restless legs syndrome based on deep learning is proposed,which is suitable for early patients with unstable symptoms in routine diagnosis.The hardware system is installed in the bed.And the non-contact sleeping dynamic signal acquisition is realized based on the acceleration sensors.The software system uses deep learning to classify and recognize the signals.A Fully Connected Feedforward Network based on Keras framework is constructed to recognize seven kinds of activities during sleeping.The accuracy of comprehensive classification is 97.83%.Based on former results,the periodic limb movement index and awakening index were evaluated to make the diagnosis of restless legs syndrome.

Influence of Combined Detection of Serum Midkine and TBIL Levels in Diagnostic Efficacy of Diabetic Retinopathy / 医学研究杂志

Objective To explore the diagnostic efficacy of combined detection of serum midkine (MK) and total bilirubin (TBIL)levels of diabetic retinopathy(DR),and determine the value in diagnosis of DR.Methods Clinical data of 215 cases of patients with type 2 diabetes mellitus (T2DM) treated in our hospital from July 2014 to December 2016 were collected,and diabetes mellitus without retinal lesions (NDR) in 79 cases,non-proliferative diabetic retinopathy (NPDR) in 81 cases,proliferative diabetic retinopathy (PDR) in 55 cases.Another 70 cases of physical examination persons in the same period were as the control group.Serum MK and TBIL levels were detected in the four groups,and the relationship between indexes and DR was done by Person correlation analysis and Logistic regression analysis,and diagnostic efficacy of Midkine and TBIL was evaluated in DR.Results Serum MK and TBIL levels were compared between the four groups,with statistically significant differences (P ＜ 0.05).MK level increased in normal control group,NDR group,NPDR group and PDR group,while TBIL levels decreased in each group.MK was positively correlated with DR (r =0.779,P =0.005),and TBIL was negatively correlated with DR (r =-0.657,P =0.012),and both were independent factors influencing DR (OR =2.257,0.681,P ＜ 0.05).The sensitivity of combined detection of MK and TBIL in diagnosis of DR was higher than that of each index detected separately (P ＜ 0.05).Conclusion Serum MK and TBIL levels are closely related to the occurrence of DR and severity of the disease,and the combined detection has high diagnostic efficacy for DR.

The association between serum Angptl 2 and macrovascular complications in type 2 diabetes mellitus / 中华内分泌代谢杂志

[Summary] This paper was to investigate whether serum angiopoietin-like protein 2 (Angptl 2) is associated with macrovascular complications in type 2 diabetes mellitus.The results showed that there were statistically significant differences in serum Angptl 2 levels among control group and groups of type 2 diabetic patients with or without carotid atherosclerosis [0.98 (0.82-1.22),3.70 (2.69-4.85),1.17 (0.76-2.47) ng/ml].Logistic regression showed that Angptl 2 was an independent risk factor of macrovascular complications in the patients with type 2 diabetes.