OBJECTIVE: To study a new kind of operation for displaced talar neck fractures. METHODS: From April 1996 to March 2001, 9 talar neck fractures were treated by internal fixation of absorbable lag screw with a medial approach and cut of medial malleolus to expose the fractures. A non-weight-bearing below-knee cast was applied for 6 to 12 weeks after operation. Once union of the fracture site is apparent, the patient should remain non-weight bearing in a removable short-leg and keep exercise every day. RESULTS: All the patients received follow-up from 15 to 60 months with an average of 28 months. The fractures healed from 20 to 42 weeks. The excellent and good rate of function was 77.8% (7/9) according to American Orthopedic Foot and Ankle Society Score(AOFAS). One case had the complication of superficial infection of wound and skin edge necrosis after operation, which was Hawkins type III. Late complication included two cases of avascular necrosis(AVN). Among them, one AVN of Hawkins type II was caused by early weight-bearing five weeks after operation and gained the fair score. The other AVN of Hawkins type III was inefficient to conservative therapy and proceeded ankle fusion in the end. The AOFAS of the patient was bad. CONCLUSION: Treatment of talar neck fractures by internal fixation of absorbable lag screw with a medial approach is an ideal method. It can gain a satisfactory result by the operation, strict postoperative care and rehabilitation.
Aiming at the problem that the unbalanced distribution of data in sleep electroencephalogram(EEG) signals and poor comfort in the process of polysomnography information collection will reduce the model's classification ability, this paper proposed a sleep state recognition method using single-channel EEG signals (WKCNN-LSTM) based on one-dimensional width kernel convolutional neural networks(WKCNN) and long-short-term memory networks (LSTM). Firstly, the wavelet denoising and synthetic minority over-sampling technique-Tomek link (SMOTE-Tomek) algorithm were used to preprocess the original sleep EEG signals. Secondly, one-dimensional sleep EEG signals were used as the input of the model, and WKCNN was used to extract frequency-domain features and suppress high-frequency noise. Then, the LSTM layer was used to learn the time-domain features. Finally, normalized exponential function was used on the full connection layer to realize sleep state. The experimental results showed that the classification accuracy of the one-dimensional WKCNN-LSTM model was 91.80% in this paper, which was better than that of similar studies in recent years, and the model had good generalization ability. This study improved classification accuracy of single-channel sleep EEG signals that can be easily utilized in portable sleep monitoring devices.