ABSTRACT
Objective:To study the effect of CBL on the teaching of knee magnetic resonance image (MRI) for orthopedic residents.Methods:From September 2015 to March 2018, CBL teaching method was applied in the teaching of knee MRI among 90 orthopedic residents of Arthritis Clinical & Research Center of Peking University People’s Hospital. The teaching effect of CBL was evaluated with questionnaire method. The scores of Knee MRI theoretical knowledge and image diagnosis were statistically compared after CBL teaching. SPSS 19.0 was performed for t test. Results:According to the questionnaire of 90 orthopedic residents, in the teaching of knee MRI, CBL teaching improved the residents' learning interest[77.8%(70/90)], fortified their theoretical knowledge[80.0%(72/90)], and enhanced their diagnosis ability of knee MRI[88.8%(80/90)], diagnosis ability of knee diseases[86.6%(78/90)], autonomous learning ability[84.5%(76/90)], expression ability[83.3%(75/90)], and the ability of creating active classroom atmosphere[51.1%(46/90)]. The performances of knee MRI theoretical knowledge and image analysis were significantly increased after CBL teaching, respectively from (65.35±10.36) points to (89.20±10.55) points and from (66.64±9.88) points to (89.50±10.06) points.Conclusion:CBL teaching can improve independent diagnostic ablity of knee MRI of orthopedic residents and lay a solid foundation of diagnosis and treatment for knee diseases, thus improving their clinical skills.
ABSTRACT
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.
ABSTRACT
The present study shows the case of a patient with acetabular protrusions secondary to rheumatoid arthritis progressing to femoral neck fracture.The patient,a 64 years female,had a history of rheumatoid arthtitis for 38 years.The left hip pain and abnormal sound occurred when hip flexion for picking up.She was diagnosed with rheumatoid arthritis secordary to acetabular pelvic retraction and left femoral neck fracture by medical history,physical examination and imaging.Total hip arthroplasty was performed after preoperative examination.Hip dislocation,femoral head removal,acetabular reconstruction;cup fixation,and bone mass assessment are technical challenges during surgery.Based on literature review,this case is belonging to secondary acetabular pelvic retraction,which may be related to acetabular softening caused by rheumatoid arthritis.Whenthe stress from the femoral head exceeds the endurance of the softened acetabulum,the acetabulum protrudes into the pelvis and gradually wraps around the femoral head.Based on the pathological characteristics,itis speculated that the cause of femoral neck fracture is the direct hit of the femoral neck-acetabular rim during hip flexion.In this case,spiral cup prosthesis was used to achieve both the initial stability of the prosthesis and saving bone mass around the acetabulum.The patient was followed up for 3 months with satisfactory position of prosthesis and joint function.