Objective To evaluate the characteristics, classification, treatment methods, and cl inical outcomes of the spoke heel injuries in children. Methods From June 2001 to June 2008, 289 children with bicycle or motorcycle spoke heel injuries were treated, including 179 males and 110 females aged 2-12 years old (average 3.9 years old). There were 179 cases of skin contusion and laceration (type I), 83 cases of skin and soft tissue defect with Achilles tendon exposure (type II), and 27 cases of wide skin and soft tissue defect with the Achilles tendon defect and rupture (type III). The defect size of the skin or the soft tissues ranged from 3 cm × 2 cm to 11 cm × 7 cm in type II and type III injury. The time between injury and hospital admission was 1-53 days (average 14.5 days). Child patients with type I injury were managed with dressing or suturing after debridement. For the child patients with type II injury, the wound was repaired with the regional fascia flap in 53 cases, the reverse sural neurocutaneous vascular flap in 19 cases, the reverse saphenous neurocutaneous vascular flap in 9 cases, and the lateral supramalleolar flap in 2 cases. For the child patients with type III injury, 6 cases underwent primary repair of the Achilles tendon followed by the transposition of the reverse sural neurocutaneous vascular flap, 3 cases received primary repair of the wound with the reverse sural neurocutaneous vascular flap and secondary reconstruction of the Achilles tendon with the upturned fascia strip or the ipsilateral il iotibial tract transplant, and 18 cases underwent primary repair of the wound and the Achilles tendon with the sl iding bi-pedicled gastrocnemius musculocutaneous flap. The flap size ranged from 4 cm × 2 cm to 30 cm × 12 cm. All the donor sites were closed bypartial suture and spl it-thickness skins graft. The lower l imbs were immobil ized with plaster spl ints after operation. Results All the flaps survived except for 1 case of type II suffering from distal flap venous crisis 3 days after operation and 6 cases of type III suffering from distal flap necrosis 3-5 days after operation. All those flaps survived after symptomatic treatment. All the skin grafts at the donor site survived uneventfully. All the wounds healed by first intention. All child patients were followed up for 15-820 days (average 42 days). Child patients with type I and type II injury had a full recovery of ankle functions. While 25 cases of type III injury had ankle dorsal extension degree loss (10-30°) and unilateral plantar flexion strength decrease 3 months after operationwithout influence on walking, and 2 cases recovered well. Conclusion Spoke heel injury in children has special mec hanisms of injury, and the choice of proper treatment method should be based on the types of injury.
This article aims to combine deep learning with image analysis technology and propose an effective classification method for distal radius fracture types. Firstly, an extended U-Net three-layer cascaded segmentation network was used to accurately segment the most important joint surface and non joint surface areas for identifying fractures. Then, the images of the joint surface area and non joint surface area separately were classified and trained to distinguish fractures. Finally, based on the classification results of the two images, the normal or ABC fracture classification results could be comprehensively determined. The accuracy rates of normal, A-type, B-type, and C-type fracture on the test set were 0.99, 0.92, 0.91, and 0.82, respectively. For orthopedic medical experts, the average recognition accuracy rates were 0.98, 0.90, 0.87, and 0.81, respectively. The proposed automatic recognition method is generally better than experts, and can be used for preliminary auxiliary diagnosis of distal radius fractures in scenarios without expert participation.
Objective To recognize and reevaluate the pathologic anatomic classification of ventricular septal defect （VSD）. Methods From January,2002 to October,2004,119 patients less than 10kg of body weight with simple VSD whose pathologic anatomic classification was determined by preoperative echocardiography and ascertained during surgery were choosed randomly. Results （1） There were fihy-one patients with perimembranous VSD （diameter 0. 6±1.0 cm）, 8 VSD situated in the membranous septum （diameter 0. 5±0.4 cm）, 21 VSD extending to inlet （diameter 0.8±0.5 cm）, 14 extending to outlet （diameter 1.0±0. 6 cm） and 8 extending to trabecula （diameter 0. 8±0.6 cm）. In this group, accessory tricuspid valve tissue was formed in 14 patients（diameter 0. 5±0.3 cm）. （2） Twenty-one patients had conoventricular VSD （diameter 1.2±0. 8 cm）, among them 13 VSD had muscle margins, 8 extending to membranous septum, 14 had septal band hypertrophy, and 5 had subaortic stenosis. （3） Twenty-six patients had subpulmonary VSD（diameter 0.8±0.8 cm）, 18 VSD lay immediately below pulmonary valve, 8 had muscle distant from pulmonary valve, 20 lay completely below pulmonary valve, and 6 lay below pulmonary valve and aortic valve. （4） Ten patients were atrioventricular canal type or inlet VSD （diameter 1.2±0.8 cm）. （5）Eleven patients had muscular VSD, among them 3 were single ,and 8 multiple （diameter 0. 4±0.3 cm）. Conclusion It will be more clinically significant that VSD is classified into perimembranous, conoventricular, atrioventricular canal or inlet, muscular and subpulmonary artery or conical types.
Objective To introduce a modified Sakakibara classification system for a ruptured sinus of Valsalva aneurysm （RSVA），and suggest different surgical approaches for corresponding types of RSVA. Methods Clinical data of 159 patients undergoing surgical repair for RSVA in Fu Wai Hospital between February 2006 and January 2012 were retrospectively analyzed. There were 105 male and 54 female patients with their age of 2-71 （33.4±10.7） years. All these patients were divided into 5 types as a modified Sakakibara classification system. Type I: rupture into the right ventricle just beneath the pulmonary valve （n=66），including 84.8% patients with ventricular septal defect （VSD） and 53.8% patients with aortic valve insufficiency （AI）. TypeⅡ：rupture into or just beneath the crista supraventricularis of the right ventricle （n=17），including 88.2% patients with VSD and 23.5% patients with AI. Type Ⅲ：rupture into the right atrium （typeⅢ a，n=21） or the right ventricle （typeⅢv，n=6） near or at the tricuspid annulus，including 18.5% patients with VSD and 25.9% patients with AI. TypeⅣ：rupture into the right atrium （n=46），including 23.9% patients with AI but no patient with VSD. TypeⅤ：other rare conditions，such as rupture into the left atrium，left ventricle or pulmonary artery （n=3），including 100% patients with AI and 33.3% patients with VSD. Most RSVA originated in the right coronary sinus （n=122），and others originated in the noncoronary sinus （n=35） or left coronary sinus （n=2）. Results All the type V patients （100%） and 50% patients with typeⅢv received RSVA repair through aortotomy. In most patients of typeⅠ，II andⅣ，repair was achieved through the cardiac chamber of the fistula exit （71.2%，64.7% and 69.6% respectively）. Both routes of repair were used in 76.2% patients with typeⅢ a. The cardiopulmonary bypass time （92.4±37.8 minutes） and aortic cross-clamp time （61.2±30.7 minutes） was the shortest to repair typeⅣRSVA. There was no in-hospital death in this group. Two patients （type I andⅡrespectively） underwent reoperation during the early postoperative period because of restenosis of the right ventricular outflow tract. Most patients received reinforcement patch for RSVA repair （n=149），and only 10 patients received simple suture repair （including 5 patients with typeⅣ，4 patients with typeⅢ a and 1 patient with typeⅡ）. Aortic valve replacement was performed for 33 patients （66.7% of those with typeⅠ）. A total of 147 patients （92.5%） were followed up after discharge. Two patients （type I andⅢ a respectively） developed atrial fibrillation and received radiofrequency ablation treatment，1 patient （typeⅣ） underwent reoperation for residual shunt，and there was no late death during follow-up. Conclusion Modified Sakakibara classification system for RVSA provides a guidance to choose an appropriate surgical approach，and satisfactory clinical outcomes can be achieved for all types of RSVA.
ObjectiveTo define the classification of sternal wound complications after cardiac surgery and to explore the appropriate surgical treatment. MethodsBetween July 2008 and January 2014, 260 patients with sternal wound complications after cardiac surgery were treated. There were 124 males and 136 females, aged 11-75 years (mean, 49.5 years). The disease duration was 13-365 days (mean, 26.6 days) with a wound length of 1-25 cm (mean, 13.4 cm). The wounds were divided into type I (n=70), type Ⅱ (n=64), type Ⅲ (n=42), type IV (n=78), and type V (n=6) according to self-generated classification for sternal wound complications after cardiac surgery. After debridement, wounds of type I and type Ⅱ were repaired with local flap transplantation; wounds of type Ⅲ were repaired with local flap transplantation combined with butterfly sternal fixation (n=28), with bilateral pectoralis muscle flap combined with butterfly sternal fixation (n=11), and with bilateral pectoralis muscle flap (n=3); wounds of type IV were repaired with bilateral pectoralis muscle flap (n=65), rectus abdominis muscle flap (n=5), and pedicled omental flap (n=8); and wounds of type V were repaired with pedicled omental flap. ResultsAll the operations were successfully performed. Three patients died after pedicled omental flap repair, including 1 case of type IV and 2 cases of type V. The hospitalization time were 4-86 days (mean, 18.3 days). Primary wound healing was obtained in 248 cases (96.5%); poor healing occurred in 9 patients, which were cured after second surgery in 8 cases and after the third surgery in 1 case. ConclusionThe surgical treatment based on self-generated classification is appropriate to sternal wound complications after cardiac surgery. It can provide clinical evidence for the choice of subsequent operation.
Objective To recognize the different phases of Korotkoff sounds through deep learning technology, so as to improve the accuracy of blood pressure measurement in different populations. Methods A classification model of the Korotkoff sounds phases was designed, which fused attention mechanism (Attention), residual network (ResNet) and bidirectional long short-term memory (BiLSTM). First, a single Korotkoff sound signal was extracted from the whole Korotkoff sounds signals beat by beat, and each Korotkoff sound signal was converted into a Mel spectrogram. Then, the local feature extraction of Mel spectrogram was processed by using the Attention mechanism and ResNet network, and BiLSTM network was used to deal with the temporal relations between features, and full-connection layer network was applied in reducing the dimension of features. Finally, the classification was completed by SoftMax function. The dataset used in this study was collected from 44 volunteers (24 females, 20 males with an average age of 36 years), and the model performance was verified using 10-fold cross-validation. Results The classification accuracy of the established model for the 5 types of Korotkoff sounds phases was 93.4%, which was higher than that of other models. Conclusion This study proves that the deep learning method can accurately classify Korotkoff sounds phases, which lays a strong technical foundation for the subsequent design of automatic blood pressure measurement methods based on the classification of the Korotkoff sounds phases.
Feature extraction methods and classifier selection are two critical steps in heart sound classification. To capture the pathological features of heart sound signals, this paper introduces a feature extraction method that combines mel-frequency cepstral coefficients (MFCC) and power spectral density (PSD). Unlike conventional classifiers, the adaptive neuro-fuzzy inference system (ANFIS) was chosen as the classifier for this study. In terms of experimental design, we compared different PSDs across various time intervals and frequency ranges, selecting the characteristics with the most effective classification outcomes. We compared four statistical properties, including mean PSD, standard deviation PSD, variance PSD, and median PSD. Through experimental comparisons, we found that combining the features of median PSD and MFCC with heart sound systolic period of 100–300 Hz yielded the best results. The accuracy, precision, sensitivity, specificity, and F1 score were determined to be 96.50%, 99.27%, 93.35%, 99.60%, and 96.35%, respectively. These results demonstrate the algorithm’s significant potential for aiding in the diagnosis of congenital heart disease.
Thoracolumbar fractures are common injuries. Accurate diagnosis and classification are of great significance for guiding treatment. Although there are many classification systems, they have not been universally accepted and used to guide clinical practice. Denis classification, load sharing classification, Magerl/AO classification, and Thoracolumbar Injury Classification and Severity Score have a great clinical influence, but they also have some shortcomings. Recently, some new classifications of thoracolumbar fractures have been proposed, and some of them have been updated and revised, which makes it easy to cause confusion, and puts forward new requirements on how to grasp and apply these classification systems. This article reviews the main and commonly used classification systems of thoracolumbar fractures, discusses the main viewpoints, advantages and disadvantages of each classification system, and looks ahead to the future research direction.
ObjectiveTo explore the effect of a new rehabilitation intervention model based on International Classification of Functioning, Disability and Healthy (ICF) concept in perioperative treatment on patients with adolescent idiopathic scoliosis (AIS).MethodsFrom June 2017 to January 2019, AIS patients with Cobb angle below 80° were randomly divided into experimental group and control group by the method of randomized block design. The patients in the control group received routine perioperative rehabilitation intervention, while the patients in the experimental group received rehabilitation mode intervention based on ICF concept. The therapeutic effect of the two groups including functional and activity dimensions was observed.ResultsA total of 40 patients were included, with 20 in each group. Two patients withdrew the control group. On the fourth day after surgery, the total score of Modified Barthel Index (50.55±8.87 vs. 18.99±5.63; t=13.264, P<0.001) and Scoliosis Research Society-22 (SRS-22) (3.68±0.13 vs. 3.27±0.11; t=10.355, P<0.001) in the experimental group were all better than those in the control group. In the SRS-22 scores, statistically significant differences in comparison of function (2.79±0.29 vs. 1.90±0.48; t=6.884, P<0.001), and self image (3.91±0.27 vs. 3.38±0.32; t=5.539, P<0.001) between the two groups were found. There was no statistically significant difference in pain indicators and muscle strength between the two groups in the two postoperative evaluations (P>0.05). ConclusionsThe treatment based on the concept of ICF can improve the daily living ability in the short term with the safe and acceptable premise. The concept of stimulating patient autonomy, improving patient independence, and promoting social treatment, may improve the overall state of the patients.
ObjectiveTo investigate the feasibility of modified classification of terrible triad of the elbow and the effectiveness of treatment strategy which was chosen by modified classification results. MethodsBetween March 2007 and November 2013, 12 cases of terrible triad of the elbow were treated by operation. There were 5 males and 7 females with an average age of 37.2 years (range, 26-74 years). The mechanism of injury was falling from height in 8 cases and traffic accident in 4 cases. The time from injury to operation was 4 to 11 days (mean, 6.8 days). According to the radial head, coronoid process, olecranon, and medial and lateral collateral ligament complexes injury situation, and based on Mason classification standard and O'Driscoll criteria, the classification standard of terrible triad of the elbow was improved. According to classification results, the approach was determined. The fracture reduction and fixation were performed and soft tissue was repaired. ResultsDehiscence of incision occurred in 1 case and was cured after dressing change; primary healing was obtained in the other patients. All the cases were followed up 19-35 months (mean, 21.6 months). The X-ray films showed fracture healing at 10-17 weeks (mean 12.8 weeks). At last follow-up, the mean flexion-extension arc of the elbow was 117.9° (range, 95-135°) and the mean forearm pronation and supination were 77.1° (range, 70-85°) and 62.5° (range, 45-75°). According to Mayo elbow performance score (MEPS), the results were excellent in 4 cases, good in 5 cases, and fair in 3 cases. One patient had valgus deformity of elbow who refused radial head replacement, and 5 cases had heterotopic ossification of the elbow on the X-ray films. ConclusionThe modified classification of the terrible triad of the elbow is simple and practical, based on the damage assessment of bony structures (radial head, coronoid process, and olecranon) and the soft tissue (medial and lateral collateral ligament complexes). The modified classification can be used effectively for guiding treatment decisions.