Objective To retrospectively analyze and classify 23 open fractures that resulted in severe infection, in order to provide evidence that can be used in future disaster scenarios. Methods Based on medical records of 23 cases of open fracture and subsequent bacterial infection, we analyzed the clinical diagnosis, treatment, laboratory tests, bacterial smear of wound secretion, and the bacterial culture of the wound secretion. We then analyzed which antimicrobial agents were used and how they were applied, and the subsequent effect on controlling the serious infection.? Results All cases were related to seismic injury and belonged to class VI open fracture. Eight cases were male and 15 were female. All cases had similar symptoms such as chills, fever, large scale muscle necrosis, and severe infection. A direct smear of the wound showed that the number of cases with one bacterial infection was 6 (26.09%), the number that had double bacterial infections was 12 (52.18%), and the number with multiple bacterial infections was 5 (21.74%).There were 18 strains of 11 types of bacteria recovered from wound samples. Conclusion Early treatment with the joint application of multiple antibacterial agents, early debridement, and adequate drainage all helped to control the infection and avoid nosocomial infection. Employing these strategies in the future will control infection in disaster situations.
Objective To investigate the therapeutic effects of retinal angiomatosis in different clinical stages. To discuss the indication of vitrectomy for retinal hemangioblastoma. Methods The clinical data of 22 cases (33 eyes) were retrospectively analyzed. The retinal hemangiomas were divided into 5 stages according to their degrees of development from simple angioma without vessel dilation to feeder vessel dilation and intra-retinal exudates, local retinal detachment, massive retinal detachment and co mplication occurrence in proper order. The methods of treatment were laser photo coagulation, trans－scleral cryotherapy and vitrectomy. 13 eyes were treated with laser photocoagulation, 5 eyes with cryotherapy combined with laser and 11 eye s with vitrectomy. Tumor resection and silicone oil tamponade was performed in 3 eyes during vitrectomy. The patients were followed up for 46 months on average. Visual acuity (VA), the condition of the hemangioma and retina was compared pre- and post-operation respectively. Results In all 13 eyes treated with laser photocoagulation the hemangiomas regressed and the retina remained attached. VA improved in 2 eyes, and remained unchanged in 11 eyes. Cryother apy combined with laser photocoagulation was performed on 5 eyes. In this group, 4 eyesprime; hemangiomas regressed and no new hemangiomas occurred, proliferative vitreous retinopathy and vitreous hemorrhage was observed in 1 eye which vitrecto my was performed later. VA improved in 2 eyes, unchanged in 2 eyes and decreased in 1 eye. In the 11 eyes treated with vitreoretinal surgery, new hemangiomas wa s found in 1 eye, exudative retinal detachment was caused by hemangiomas in 2 eyes, proliferative vitreous retinopathy was observed in 2 eyes, and the retina re mained attached in 8 eyes. VA improved in 3 eyes, unimproved in 3 eyes, and decreased in 5 eyes. In the 3 eyes with surgical resection of retinal hemangioma during vitrectomy, 2 eyesprime; retina remained attached, 1 eye had exu dative retinal detachment and no new hemangiomas occurred. VA improved in 2 eyes and decreased in 1 eye. Conclusions Laser photocoagulation or combined with cryotherapy is effective in treating the hemangiomas in early stage. Vitrectomy is advisable for late stage of retinal angiomatosis, especially with vitreous hemorrhage, epiretinal membrane, proliferation and large scale of r etinal detachment. Surgical resection of isolated large retinal hemangioblastoma may be useful for selected patients. (Chin J Ocul Fundus Dis,2008,24:107-110)
Objective To summarize the classification, diagnosis, and treatment of iatrogenic bile duct injury. Method The clinical data of 27 cases of iatrogenic bile duct injuries who treated in Central Hospital of Huzhou City from 2008–2013 were retrospectively analyzed. Results The classification of 27 cases: 5 cases of type Ⅰ, 18 cases of type Ⅱ, 2 cases of type Ⅲ, 2 cases of type Ⅳ. Diagnosis: 11 cases were immediately discovered at the time of the initial operation, include 1 case of type Ⅰ, 8 cases of type Ⅱ, 1 case of type Ⅲ, 1 case of type Ⅳ; 10 cases were detected in early stage after the initial operation, include 2 cases of type Ⅰ, 7 cases of type Ⅱ, 1 case of type Ⅲ; 6 cases were detected in delayed stage after the initial operation, include 2 cases of type Ⅰ, 3 cases of type Ⅱ, 1 case of type Ⅳ. Treatment effect: 17 cases for excellent, 5 cases for good, 4 cases for bad, the well recover rate was 84.6% (22/26). One case died after operation. A total of 26 cases were followed up, 1 case was lost to follow up. During the follow-up period, bile leakage occurred in 3 cases, infection of incision occurred in 2 cases, cholangitis occurred in 3 cases, and bile duct stricture occurred in 2 cases. Conclusions The best time of repairing for the iatrogenic bile duct injuries is at the time of the initial operation or early stage. According to the type of injury and the time of the injury was diagnosed, timely and effective treatment by intervention and (or) surgery is the key.
Pulmonary adenocarcinoma in situ is reclassified as precursor glandular lesions in the fifth edition of WHO classification of thoracic tumours, causing widespread attention and heated debate among domestic thoracic oncologists, radiologists, pathologists and surgeons. We would like to comment on the topic and make a few suggestions on the management of pulmonary nodule during lung cancer screening. We are open to all suggestion and welcome debates.
Objective To introduce a novel comprehensive classification for femoral intertrochanteric fractures, and to accommodate the clinical requirement for the world-wide outbreak of geriatric hip fractures and surgical operations. Methods On the basis of reviewing the history of classification of femoral intertrochanteric fractures and analyzing the advantages and disadvantages of AO/Orthopaedic Trauma Association (AO/OTA) classification in different periods, combined with the current situation of extensive preoperative CT scan and three-dimensional reconstruction and widespread use of intramedullary nail fixation in China, the “Elderly Hip Fracture” Research Group of the Reparative and Reconstructive Surgery Committee of the Chinese Rehabilitation Medical Association proposed a novel comprehensive classification for femoral intertrochanteric fractures, focusing on the structure of fracture stability reconstruction during internal fixation. Results The novel comprehensive classification of femoral intertrochanteric fractures incorporates multiple indicators of fracture classification, including the orientation of the fracture line, the degree of fracture fragmentation, the lesser trochanteric bone fragment and its distal extension length (>2 cm), the posterior coronal bone fragment and its anterior extension width (involving the lateral cortex of the head and neck implant entry point), transverse fracture of the lateral and anterior wall and its relationship with the implant entry point in the head and neck, and whether the cortex of the anteromedial inferior corner can be directly reduced to contact, etc. The femoral intertrochanteric fractures are divided into 4 types (type A1 is simple two-part fractures, type A2 is characterized by lesser trochanter fragment and posterior coronal fractures, type A3 is reverse obliquity and transverse fractures, type A4 is medial comminution which lacks anteromedial cortex transmission of compression force), each of which is subdivided into 4 subtypes and further subdivide into finer subgroups. In a review of 550 trochanteric hip fracture cases by three-dimensional CT, type A1 accounted for 20.0%, type A2 for 62.5%, type A3 for 15.5%, and type A4 for 2.0%, respectively. For subtypes, A2.2 is with a “banana-like” posterior coronal fragment, A2.4 is with distal cortex extension >2 cm of the lesser trochanter and anterior cortical expansion of the posterior coronal fragment to the entry portal of head-neck implants, A3.4 is a primary pantrochanteric fracture, and A4.4 is a concomitant ipsilateral segmental fracture of the neck and trochanter region. ConclusionThe novel comprehensive classification of femoral intertrochanteric fractures can describe the morphological characteristics of fractures in more detail, include more rare and complex types, provide more personalized subtype selection, and adapt to the clinical needs of both fractures and surgeries.
Cardiovascular disease (CVD) is one of the leading causes of death worldwide. Heart sound classification plays a key role in the early detection of CVD. The difference between normal and abnormal heart sounds is not obvious. In this paper, in order to improve the accuracy of the heart sound classification model, we propose a heart sound feature extraction method based on bispectral analysis and combine it with convolutional neural network (CNN) to classify heart sounds. The model can effectively suppress Gaussian noise by using bispectral analysis and can effectively extract the features of heart sound signals without relying on the accurate segmentation of heart sound signals. At the same time, the model combines with the strong classification performance of convolutional neural network and finally achieves the accurate classification of heart sound. According to the experimental results, the proposed algorithm achieves 0.910, 0.884 and 0.940 in terms of accuracy, sensitivity and specificity under the same data and experimental conditions, respectively. Compared with other heart sound classification algorithms, the proposed algorithm shows a significant improvement and strong robustness and generalization ability, so it is expected to be applied to the auxiliary detection of congenital heart disease.
ObjectiveTo investigate the effectiveness of fixation the posterior malleolus or not to treat different Haraguchi’s classification of posterior malleolus fractures.MethodsThe clinical data of 86 trimalleolar fracture patients who were admitted between January 2015 and September 2019 and met the selection criteria were retrospectively reviewed. There were 29 males and 57 females; the age ranged from 26 to 82 years with a mean age of 55.2 years. According to Haraguchi’s classification, 38 patients were in type Ⅰ group, 30 patients in type Ⅱ group, and 18 patients in type Ⅲ group. There was no significant difference in the general data such as gender, age, and fracture location among the 3 groups (P>0.05). The fixation of the posterior malleolus was performed in 23, 21, and 5 patients in type Ⅰ, Ⅱ, and Ⅲ groups, respectively. The operation time, fracture healing time, full weight-bearing time, postoperative joint flatness, and joint degeneration degree of the patients in each group were recorded and compared. The American Orthopedic Foot and Ankle Society (AOFAS) ankle and hindfoot score was used to evaluate ankle function, including pain, quality of daily life, joint range of motion, and joint stability. The AOFAS scores were compared between fixation and non-fixation groups in each group.ResultsThe procedure was successfully completed by all patients in each group, and there was no significant difference in operation time (F=3.677, P=0.159). All patients were followed up 12-36 months with a mean time of 16.8 months. At last follow-up, 6 patients were found to have suboptimal ankle planarity, including 2 patients (5.3%) in the type Ⅰ group and 4 patients (13.3%) in the type Ⅱ group, with no significant difference between groups (χ2=6.566, P=0.161). The ankle joints of all the patients in each group showed mild degeneration; the fractures all healed well and no delayed union or nonunion occurred. There was no significant difference in the fracture healing time and full weight-bearing time between groups (P>0.05). No complications such as incision infection, fracture displacement, or plate screw loosening and fracture occurred during follow-up. At last follow-up, the total scores and pain scores of the AOFAS scores in the type Ⅱ group were significantly lower than those in the type Ⅰand Ⅲ groups (P<0.05), there was no significant difference between groups in the scores for the quality of daily life, joint range of motion, and joint stability between groups (P>0.05). There was no significant difference in any of the scores between the unfixed and fixed groups, except for the pain and quality of daily life scores, which were significantly lower (P<0.05) in the unfixed group of type Ⅱ group than the fixed group.ConclusionHaraguchi type Ⅱ posterior malleolus fractures have a worse prognosis than types Ⅰ and Ⅲ fractures, especially in terms of postoperative pain, which can be significantly improved by fixing the posterior malleolus; the presence or absence of posterior malleolus fixation in types Ⅰ and Ⅲ has less influence on prognosis.
Objective To develop a deep learning system for CT images to assist in the diagnosis of thoracolumbar fractures and analyze the feasibility of its clinical application. Methods Collected from West China Hospital of Sichuan University from January 2019 to March 2020, a total of 1256 CT images of thoracolumbar fractures were annotated with a unified standard through the Imaging LabelImg system. All CT images were classified according to the AO Spine thoracolumbar spine injury classification. The deep learning system in diagnosing ABC fracture types was optimized using 1039 CT images for training and validation, of which 1004 were used as the training set and 35 as the validation set; the rest 217 CT images were used as the test set to compare the deep learning system with the clinician’s diagnosis. The deep learning system in subtyping A was optimized using 581 CT images for training and validation, of which 556 were used as the training set and 25 as the validation set; the rest 104 CT images were used as the test set to compare the deep learning system with the clinician’s diagnosis. Results The accuracy and Kappa coefficient of the deep learning system in diagnosing ABC fracture types were 89.4% and 0.849 (P<0.001), respectively. The accuracy and Kappa coefficient of subtyping A were 87.5% and 0.817 (P<0.001), respectively. Conclusions The classification accuracy of the deep learning system for thoracolumbar fractures is high. This approach can be used to assist in the intelligent diagnosis of CT images of thoracolumbar fractures and improve the current manual and complex diagnostic process.
ObjectiveTo explore the application of Tsetlin Machine (TM) in heart beat classification. MethodsTM was used to classify the normal beats, premature ventricular contraction (PVC) and supraventricular premature beats (SPB) in the 2020 data set of China Physiological Signal Challenge. This data set consisted of the single-lead electrocardiogram data of 10 patients with arrhythmia. One patient with atrial fibrillation was excluded, and finally data of the other 9 patients were included in this study. The classification results were then analyzed. ResultsThe classification results showed that the average recognition accuracy of TM was 84.3%, and the basis of classification could be shown by the bit pattern interpretation diagram. ConclusionTM can explain the classification results when classifying heart beats. The reasonable interpretation of classification results can increase the reliability of the model and facilitate people's review and understanding.
In the diagnosis of cardiovascular diseases, the analysis of electrocardiogram (ECG) signals has always played a crucial role. At present, how to effectively identify abnormal heart beats by algorithms is still a difficult task in the field of ECG signal analysis. Based on this, a classification model that automatically identifies abnormal heartbeats based on deep residual network (ResNet) and self-attention mechanism was proposed. Firstly, this paper designed an 18-layer convolutional neural network (CNN) based on the residual structure, which helped model fully extract the local features. Then, the bi-directional gated recurrent unit (BiGRU) was used to explore the temporal correlation for further obtaining the temporal features. Finally, the self-attention mechanism was built to weight important information and enhance model's ability to extract important features, which helped model achieve higher classification accuracy. In addition, in order to mitigate the interference on classification performance due to data imbalance, the study utilized multiple approaches for data augmentation. The experimental data in this study came from the arrhythmia database constructed by MIT and Beth Israel Hospital (MIT-BIH), and the final results showed that the proposed model achieved an overall accuracy of 98.33% on the original dataset and 99.12% on the optimized dataset, which demonstrated that the proposed model can achieve good performance in ECG signal classification, and possessed potential value for application to portable ECG detection devices.