1.Distal pedical fibular osteoseptocutaneous flap transfer for the lateral forefoot defect
Zongyu LI ; Jinfang CAI ; Hailei YIN ; Yidong CUI ; Lin ZOU ; Jinlong ZHENG ; Lifeng LIU ; Xuecheng CAO
Chinese Journal of Microsurgery 2010;33(6):454-456,后插4
Objective The anterior-lateral defect of foot that lost one of the three supporting point of foot can lead to collapse of the lateral longitudinal arch, overload of the first metatarsal heads, and painful callus formation. It is meaningful to investigate the effect of reconstructing the lateral forefoot defect with pedical fibular osteoseptocutaneous flap. Methods From March 1989 to June 2008, there were 38 patients with anterior-lateral defect of foot were constructed. The supporting point with the local distal based pedical fibular osteoseptocutaneous flap was constracted. Results All the 38 flaps survived. All 38 patients had been followed up from 6 months to 10 years (mean 23.5 months) postoperatively. The constructed supporting point of the foot was functional. The patients could walk freely with no pain, and was satisfied with the operation. Assessed with the rating system for foot and ankle established by the American Orthopaedic Foot And Anke Society, 8 patients got a score above 85, 23 patients between 75 to 85, 7 patients between 60 to 75. Conclusion It is effective that transferring local distal based pedical fibular osteoseptocutaneous flap to repair the anterior-lateral defect of foot.
2.Research on the construction of drug knowledge base based on machine learning
Yunfei HOU ; Yicheng LI ; Zongyu ZOU ; Zijun ZHOU
Chinese Journal of Hospital Administration 2021;37(3):232-236
Objective:To construct a drug knowledge base based on drug instructions.Methods:Six hundred randomly selected drug instructions were labeled manually and divided into training set and test set. The training was based on bidirectional long short-term memory(Bi-LSTM) and conditional random fields(CRF) model to complete the recognition of medical entities. The extracted entities were standardized by the hybrid model of " similarity calculation and rule mapping table" , and then the drug information was imported into the Access database.Results:In the task of named entity recognition based on Bi-LSTM and CRF model, except for the crowd entities, the other entities had achieved good results with an F-value higher than 85%. Based on the hybrid model of " similarity calculation and rule mapping table" , the accuracy of entity standardization was 88.23%.Conclusions:The effect of the machine learning model in this study is similar to that of other named entity recognition and entity standardization studies, which can complete the task of drug knowledge base construction satisfactorily.
3.Relationship between tube voltage kV value for head and neck CT angiography and body weight
Caisheng ZOU ; Ping LIANG ; Gengrui CHEN ; Jiaguo YE ; Xiankun WANG ; Xiaomei CHEN ; Guanhua GAO ; Zongyu HU ; Ke PAN ; Haiyan WEN ; Shihao XIA
Chinese Journal of Primary Medicine and Pharmacy 2022;29(12):1771-1776
Objective:To investigate the relationship between tube voltage kV value for head and neck CT angiography and body weight.Methods:A total of 120 patients with suspected vascular disease of the head and neck who underwent CT angiography of the head and neck in Beihai People's Hospital from January 2020 to May 2022 were included in this study. Patients were divided into three groups according to different tube voltages: group A (tube voltage 120 kV, n = 45), group B (tube voltage 100 kV, n = 45) and group C (tube voltage 80 kV, n = 30). Patients in group A were divided into group A1 (< 70 kg, n = 15), group A2 (70-85 kg, n = 15) and group A3 (> 85 kg, n = 15) according to different body weights. Patients in group B were divided into group B1 (< 70 kg, n = 15), group B2 (70-85 kg, n = 15) and group B3 (> 85 kg, n = 15) according to different body weights. Patients in group C were divided into group C1 (< 70 kg, n = 15) and group C2 (70-85 kg, n = 15) according to different body weights. Group C3 was not used. The contrast medium used was Loversol. The CT value, image noise, signal-to-noise ratio, contrast to noise ratio, and effective radiation dose of arterial vessels in each group were measured. The images were subjectively evaluated by two physicians who had senior professional titles using a 5-point rating scale. Results:Subjective score of image quality was all ≥ 3 grade in each group. There was no significant difference in image quality rating between groups A1 and A2 and groups B1, B2, and C1. There was a remarkable difference in image quality rating between groups A3, B3, and C2 and the other groups. There was a significant difference in the CT value of blood vessels at four different levels between groups A1, B1 and C1 ( F = 76.82, 64.62, 98.79, 71.85, all P < 0.001). There was a significant difference in CT value of blood vessels at four different levels between groups A2, B2 and C2 ( F = 159.82, 112.33, 108.22, 135.18, all P < 0.001). There was a significant difference in CT value of blood vessels at four different levels between groups A3 and B3 ( t = 4.40, 4.27, 3.91, 3.59, all P < 0.05). In groups B3 and C2, the image noise was remarkably increased, signal to noise ratio and contrast to noise ratio were remarkably decreased compared with those in the other groups. The effective radiation dose of arterial vessels in group B1 was 47% lower than that in group A1 and the effective radiation dose of arterial vessels in group C1 was 73% lower than that in group A1 ( F = 116.18, P < 0.001). The effective radiation dose of arterial vessels in group B2 was 49% lower than that in group A2, and the effective radiation dose of arterial vessels in group C2 was 66% lower than that in group A2 ( H = 35.40, P < 0.001). The effective radiation dose in group B3 was 35% lower than that in group A3 ( t = 3.59, P < 0.05). Conclusion:In CT angiography of the head and neck, the selection of tube voltage kV value is related to body weight. Tube voltage 80 kV is suitable for patients with a body weight < 70 kg, tube voltage 100 kV for patients with a body weight of 70-85 kg, and tube voltage 120 kV for patients with a body weight > 85 kg. These tube voltages can decrease effective radiation dose and ensure image quality, meeting the requirement for clinical diagnosis.