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.
Objective To analyze the correlation between postoperative complications and combined deflection angle classification adduction type (CDAC-ADT) of femoral neck fractures after cannulated screw internal fixation. MethodsThe clinical data of 121 patients with CDAC-ADT femoral neck fracture admitted between January 2018 and December 2021 and met the selected criteria were retrospectively analyzed. There were 69 males and 52 females, the age ranged from 19 to 79 years (mean, 48.1 years). The causes of injury included 52 cases of traffic accident, 24 cases of falling from height, and 45 cases of fall. The time from injury to operation ranged from 2 to 12 days, with an average of 6.0 days. Among them, there were 18 cases of CDAC-ADT type Ⅰ, 46 cases of type Ⅱ, and 57 cases of type Ⅲ; 6 cases of Garden type Ⅱ, 103 cases of type Ⅲ, and 12 cases of type Ⅳ; and according to the location of the fracture line, there were 26 cases of subcapitate type, 88 cases of transcervical type, and 7 cases of basal type. All patients were treated with cannulated screw internal fixation. The occurrence of complications (including internal fixation failure, fracture nonunion, and osteonecrosis of the femoral head) was recorded, and the correlation between complications and CDAC-ADT typing, Garden typing, and fracture line location were analyzed. Results The patients were followed up 8-44 months, with a mean of 24.9 months. There were 10 cases of internal fixation failure, 7 cases of fracture nonunion, and 30 cases of osteonecrosis of the femoral head after operation. Correlation analysis showed that patients’ CDAC-ADT typing was significantly correlated with the overall incidence of complication and the incidence of internal fixation failure, fracture nonunion, and osteonecrosis of the femoral head (P<0.05), and the Pearson coefficient of contingency were 0.435, 0.251, 0.254, and 0.241, respectively. Garden typing did not correlate with the overall incidence of complication and the incidence of internal fixation failure and fracture nonunion (P>0.05), but correlated with the incidence of osteonecrosis of the femoral head (P<0.05), and the Pearson coefficient of contingency was 0.251. Fracture line position typing had no correlation with the overall incidence of complication and the incidence of internal fixation failure, fracture nonunion, and osteonecrosis of the femoral head (P>0.05). Conclusion CDAC-ADT typing has obvious correlation with postoperative complications of femoral neck fracture and can be used to predict complications of femoral neck fracture.
Stem cells belong to a subgroup of undifferentiated cells in organisms, which has the features of proliferation, self maintaining, and self renewal, and may produce plentiful filial generation with functions. According to the researches on embryonic stem cells, retinal stem cells in adults, and intraocular tumor stem cells, stems cells exist in human embryo, adult retina, and also intraocular tumors like retinoblastoma and choroidal melanoma. Different stem cells transplanted into subretinal interspace or vitreous cavity may differentiate into structure of neurone or retina. Stem cells may become a newest target of the researches on pathogenesis and treatment of diseases. (Chin J Ocul Fundus Dis, 2007, 23: 83-86)
Arrhythmia is a significant cardiovascular disease that poses a threat to human health, and its primary diagnosis relies on electrocardiogram (ECG). Implementing computer technology to achieve automatic classification of arrhythmia can effectively avoid human error, improve diagnostic efficiency, and reduce costs. However, most automatic arrhythmia classification algorithms focus on one-dimensional temporal signals, which lack robustness. Therefore, this study proposed an arrhythmia image classification method based on Gramian angular summation field (GASF) and an improved Inception-ResNet-v2 network. Firstly, the data was preprocessed using variational mode decomposition, and data augmentation was performed using a deep convolutional generative adversarial network. Then, GASF was used to transform one-dimensional ECG signals into two-dimensional images, and an improved Inception-ResNet-v2 network was utilized to implement the five arrhythmia classifications recommended by the AAMI (N, V, S, F, and Q). The experimental results on the MIT-BIH Arrhythmia Database showed that the proposed method achieved an overall classification accuracy of 99.52% and 95.48% under the intra-patient and inter-patient paradigms, respectively. The arrhythmia classification performance of the improved Inception-ResNet-v2 network in this study outperforms other methods, providing a new approach for deep learning-based automatic arrhythmia classification.
ObjectiveTo formulate the classification criteria of femoral intertrochanteric fractures based on irreducibility or not in order to predict the difficulty of fracture recovery.MethodsA clinical data of 244 patients with closed femoral intertrochanteric fractures admitted between January 2017 and March 2020 was retrospectively analyzed. There were 116 males and 128 females with an average age of 77.9 years (range, 45-100 years). The cause of injury included falling in 190 cases, traffic accident in 36 cases, smashing in 13 cases, and falling from height in 5 cases. The time from injury to operation was 1-14 days (mean, 3.6 days). According toAO/Orthopaedic Trauma Association (AO/OTA) classification, the fractures were classified as type 31-A1 in 38 cases, type 31-A2 in 160 cases, and type 31-A3 in 46 cases. According to whether the recovery difficulty occurred after intraoperative closed traction reset, the patients were divided into reducible-group and irreducible-group; combined with the literature and preoperative imaging data of two groups, the classification criteria of femoral intertrochanteric fractures was formulated based on the irreducibility or not. The 244 fractures were classified by the doctors who did not attend the operation according to the classification criteria, predicted the difficulty of fracture reduction, and compared with the actual intraoperative reduction situation.ResultsThe 244 patients were divided into reducible-group (n=164, 67.21%) and irreducible-group (n=80, 32.79%) according to the intraoperative difficulty of reduction. Comparing the imaging data and characteristics of the two groups, and formulating the classification criteria of femoral intertrochanteric fractures based on irreducibility or not, the fractures were mainly divided into two categories of irreducibility and reducibility. The fractures of irreducibility category was divided into typesⅠ-Ⅴ, among which type Ⅲ was divided into subtypes 1-4; the fractures of reducibility category was divided into typesⅠand Ⅱ. Compared with the actual intraoperative evaluation results, the total accuracy rate of the doctors who did not attend the operation was 81.15% (198/244) based on the classification criteria of femoral intertrochanteric fractures. The accuracy rate of irreducibility category was 65.74% (71/108), and the reducibility category was 93.38% (127/136). All patients were followed up 13-25 months, with an average of 17.6 months. All fractures healed except 2 cases died of infection.ConclusionThe classification criteria of femoral intertrochanteric fractures based on irreducibility or not can accurately predict the reducible cases preoperatively, and most of the irreducible cases can be correctly predicted in a wider way. But the classification criteria still need to be further improved and supplemented.
ObjectiveTo evaluate the effectiveness of total hip arthroplasty (THA) combined with subtrochanteric osteotomy in the treatment of Crowe type Ⅳdevelopmental dysplasia of the hip (DDH).MethodsBetween April 2008 and June 2016, 71 patients with unilateral Crowe type Ⅳ DDH were treated with THA. Of 71 cases, 44 were performed with subtrochanteric osteotomy (osteotomy group) and 27 were performed without subtrochanteric osteotomy (non-osteotomy group). There was no significant difference in gender, age, body mass, height, body mass index, affected side, and preoperative Harris score between 2 groups (P>0.05). The complications were recorded and the effectiveness was assessed by Harris score. Besides, the femoral dislocation height and the settling depth of sleeve were measured in the pelvic anteroposterior X-ray film pre- and post-operatively.ResultsOsteotomy group was followed up 12-90 months (mean. 34.77 months), and non-osteotomy group was followed up 12-79 months (mean, 34.33 months). There was no significant difference in follow-up time between 2 groups (t=–0.088, P=0.930). There was 11 cases of intraoperative or postoperative complications in osteotomy group, and 3 cases of postoperative complications in non-osteotomy group. Among the osteotomy group, 1 case had nonunion due to infection and received revision after 20 months. No loosening or dislocation of the implant occurred in both 2 groups. Significant differences were found in femoral dislocation height and settling depth of sleeve between 2 groups (t=–8.452, P=0.000; t=6.783, P=0.000). Moreover, the osteotomy length was not correlated with the settling depth of sleeve (r=–0.038, P=0.806). At last follow-up, there was no significant difference in Harris score between 2 groups (t=–1.160, P=0.254).ConclusionTHA combined with subtrochanteric osteotomy can provide a favorable outcome for treating Crowe type Ⅳ DDH. Furthermore, patients with higher femoral dislocation and severely narrow femoral proximal canals are prone to be peformed with subtrochanteric osteotomy.
Objective To analyze the spinal injury in Wenchuan earthquake and to investigate its cl inical features. Methods Data of 146 patients in Wenchuan earthquake with spinal injuries (79 males, 67 females; aged 11-88 years old, average 51 years old) were collected and analyzed epidemiologically. Two patients under 16 years of age, 15 patients withthe fractures of spinous process, transverse process or vertebra lamina, 1 patient with spinal fractures of type A2 according to AO classification but no corresponding type in Denis classification, and 9 patients with upper cervical injuries were excluded. The remaining 119 patients were divided into two groups according to their age: group A in which 78 patients were under 60 years of age, including 40 males and 38 females aged 18-58 years old (average 41 years old), and group B in which 41 patients were 60 years of age or above, including 24 males and 17 females aged 60-88 years old (average 71 years old). Analyses for the two groups were compared. Results The leading causes of spinal injuries were fall from high places (27.40%) and crush by heavy objects (67.81%). According to Denis classification, the major types of spinal injuries were burst fracture (54.62%) and compression fracture (33.61%). Serious nerve injury, defined as grade A, B and C in ASIA neurological function assessment, occurred in 31.51% of patients. The most common injured site was in thoracic or lumbar vertebrae (78.77%), and 52.74% of patients had combined injuries, among which the fractures of l imb (30.14%) and rib (19.86%) were the most common. Multilevel spinal fractures happened to 22.60% of patients. Comparative analysis revealed the rate of injury caused by fall from high places in group A (34.62%) was much higher than that in group B (12.20%). The commonest type of fracture in group A was burst fracture (58.97%), and it was compression fracture in group B (48.78%). The rate of serious nerve injury in group B (24.39%) was much lower than that in group A (44.87%). The rate of combined injury and multilevel vertebral body injury in group B was 70.73% and 39.02%, respectively, which was much higher than that in group A (combined injury 43.59%; multilevel vertebral body injury 21.79%). There were significant differences between two groups in all the indicators derived from cl inical data (P lt; 0.05). Conclusion In Wenchuan earthquake, the leading causes of spinal injuries are fall from high places and crush by heavy objects, the major types of fracture are compression fracture and burst fracture, and the occurrence rates of spinal injury, combined injury and multilevel vertebral body injury are high.
ObjectiveTo compare the predictive value of Balthazar computed tomography severity index (CTSI), Modified computed tomography severity index (MCTSI) and extrapancreatic inflammation on CT (EPIC) in patients diagnosed as acute pancreatitis with organ dysfunction based on the revised Atlanta classification. MethodsThe clinical data of patients diagnosed as acute pancreatitis from December 2013 to January 2014 were analyzed retrospectively. Four imaging score systems (CTSI, MCTSI, EPIC, and local complications) and two clinical score systems were assessed with ROC and AUC. Results①There were no statistical significances in the age, gender, time after onset of symptoms to CT scanning in 54 patients (P > 0.05).②CTSI, MCTSI, EPIC, and local complications were good independent predictors of organ dysfunction in the early phase (P < 0.05), while BISAP and NJSS were not (P > 0.05). ConclusionCT scoring systems can accurately evaluate organ dysfunction of acute pancreatitis in the early phase.
Identification of molecular subtypes of malignant tumors plays a vital role in individualized diagnosis, personalized treatment, and prognosis prediction of cancer patients. The continuous improvement of comprehensive tumor genomics database and the ongoing breakthroughs in deep learning technology have driven further advancements in computer-aided tumor classification. Although the existing classification methods based on gene expression omnibus database take the complexity of cancer molecular classification into account, they ignore the internal correlation and synergism of genes. To solve this problem, we propose a multi-layer graph convolutional network model for breast cancer subtype classification combined with hierarchical attention network. This model constructs the graph embedding datasets of patients’ genes, and develops a new end-to-end multi-classification model, which can effectively recognize molecular subtypes of breast cancer. A large number of test data prove the good performance of this new model in the classification of breast cancer subtypes. Compared to the original graph convolutional neural networks and two mainstream graph neural network classification algorithms, the new model has remarkable advantages. The accuracy, weight-F1-score, weight-recall, and weight-precision of our model in seven-category classification has reached 0.851 7, 0.823 5, 0.851 7 and 0.793 6 respectively. In the four-category classification, the results are 0.928 5, 0.894 9, 0.928 5 and 0.865 0 respectively. In addition, compared with the latest breast cancer subtype classification algorithms, the method proposed in this paper also achieved the highest classification accuracy. In summary, the model proposed in this paper may serve as an auxiliary diagnostic technology, providing a reliable option for precise classification of breast cancer subtypes in the future and laying the theoretical foundation for computer-aided tumor classification.
ObjectiveTo explore the risk factors of perioperative severe complications (Clavien-Dindo grade Ⅲ and above) after laparoscopic radical resection of colorectal cancer (CRC). MethodsThe clinicopathologic data of CRC patients who met the inclusion and exclusion criteria treated in the Shaanxi Provincial People’s Hospital from January 2018 to December 2020 were retrospectively analyzed. The univariate and multivariate logistic analyses were used to explore the risk factors of perioperative severe complications after the laparoscopic radical resection of CRC. ResultsAtotal of 170 eligible patients were included in this study, and the postoperative complications occurred in 45 patients, 24 of whom were severe complications. The univariate analysis results showed that the age (P<0.001), body mass index (BMI, P=0.047), age adjusted Charlson complication index (aCCI) score (P=0.002), American Association of Anesthesiologists (ASA) classification (P<0.001), prognostic nutritional index (PNI, P=0.011), preoperative anemia (P=0.011), operation numbers of surgeon (P=0.003), and operation time (P=0.026) were related to the perioperative severe complications in the patients underwent the laparoscopic radical resection of CRC. The statistic indexes of univariate analysis (P<0.05) combined with indexes of clinical significance were included in the multivariate analysis, the results showed that the ASA classification Ⅲ– Ⅳ (OR=3.536, P=0.027), BMI ≥25 kg/m2 (OR=3.228, P=0.031), preoperative anemia (OR=2.876, P=0.049), operation numbers of surgeon <300 (OR=0.324, P=0.046), and the operation time ≥300 min (OR=3.480, P=0.020) increased the probability of perioperative severe complications in the patients underwent the laparoscopic radical resection of CRC. ConclusionsThe results of this study suggest that clinicians should pay attention to the perioperative management of patients with CRC, such as adequately evaluating the preoperative status of patients by ASA classification, PNI, and aCCI to adjust the malnutrition of patients; after operation, the patients with BMI ≥25 kg/m2 and operation time more than 300 min should be paid more attention. At the same time, the surgeon should continuously accumulate the operation numbers and improve the operation proficiency so as to reduce the occurrence of perioperative severe complications after laparoscopic radical resection of CRC.