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.
ObjectiveTo evaluate the differences of visual evoked potentials (amplitudes and latency) between cerebral palsy (CP) children and normal children. MethodsThis study involved fourteen children aged from 4 to 7 years with CP (monoplegia) between 2009 and 2013. Another 14 normal children aged from 5 to 9 years treated in the Department of Ophthalmology in West China Hospital during the same period were regarded as the control group. Both eyes of all the participants were examined by multifocal visual evoked potential (mfVEP). The mfVEP examination results were recorded, and amplitude and latency were analyzed. First, we analyzed the differences of amplitudes and latency time between monoplegia children and children in the control group. Second, gross motor function classification system (GMFCS) was used to classify the fourteen monoplegia children among whom there were five GMFCS Ⅰ patients and nine GMFCS Ⅱ patients. The differences of mfVEP were analyzed between the two GMFCS groups. ResultsThe amplitude and latency of mfVEP in children with CP showed gradual changes similar to those in the normal children. The amplitudes were decreasing and the latencies were delaying from the first eccentricity to the sixth eccentricity. The amplitudes in children with CP were lower than those in the control group in the first to the third eccentricities for both eyes (P＜0.05), and latency of left eye was delayed in the first eccentricity in children with CP (P=0.045). No difference was found between the two GMFCS groups (P>0.05) except the amplitude of the first eccentricity (P=0.043). ConclusionsThe results of mfVEP show significant differences of amplitude and latency between CP and normal children, suggesting the existence of visual pathway impairments in cerebral palsy children. The results of mfVEP can provide an objective basis of visual impairments for cerebral palsy children.
Objective To investigate the self-made classification criterion for mucous cysts of distal interphalangeal joint and the effectiveness of the surgical treatment. Methods Between July 2008 and August 2015, 33 patients with mucous cysts of distal interphalangeal joint were treated, and the clinical data were retrospectively analyzed. Among 33 cases, 15 were male and 18 were female, aged from 45 to 74 years (mean, 58 years). The disease duration ranged from 3 weeks to 1 year (mean, 5 months). The cyst located at thumb in 18 cases, index finger in 4 cases, middle finger in 6 cases, ring finger in 4 cases, and little finger in 1 case. According to location, mucous cysts were typed: proximity to one side of the finger extensor tendon and deviation from the midline of the finger named lateral type (22 cases); and at both sides of the finger extensor tendon named intermediate type (11 cases). The bilateral digital dorsal incision was made in the intermediate type patients, and the reverse L-shaped incision was made in the lateral type patients, then the degenerative tissue was resected, the osteophyte was removed, and the capsule was repaired; finally, mucous cysts were resected. Results All the patients were followed up 4 months to 2 years (mean, 14.5 months). The incision healed by first intention without infection after operation. Clinical symptoms obtained improvement and no recurrence was observed in 29 patients except 4 patients who died of other diseases during follow-up. Conclusion A surgical treatment for mucous cysts of distal interphalangeal joint is feasible according to the self-made classification criterion and it has the advantage of simple operation and definite effectiveness.
It's common that general rules exist in a certain classification. The general rules of expense classification enable us to judge the category of a patient as soon as possible and to curb the expense. Theory of rough set helps us reach the best reduction of attributes. Based on the core attributes, classification rules are put forward by value reduction. The results show that 10 core attributes remain in 21 attributes of 1527 inpatients' information and 76 classification rules are founded. All of 76 rules guide classification of the patients. 44 of the 76 rules define the only category of a patient, the other 32 rules defines the potential catagories of a patient. Meanwhile, equal attributes of the same category are summerized to guide the cost control of patients. The results indicate that the theory of rough set is effective in attributes reduction and rule generalization of patient expense classification, and it has important significance on medical practice.
According to system reform of the current medical insurance diagnosis related groups, quality control of rehabilitation medicine and requirements of information management, this paper constructs a rehabilitation information system by using the theoretical framework and core sets of International Classification of Functioning, Disability and Health (ICF). Then, the constructed system is embedded into the work of rehabilitation medicine team. By the four processes of ICF items evaluation, rehabilitation goal setting, team cooperation scheme formulation and reevaluation, the operation process of rehabilitation information management based on ICF is formed, which strengthens comprehensively the rehabilitation diagnosis and treatment standards and improves the efficiency of quality control management. The big data mining and multi-dimensional analysis in this platform can provide support of medical insurance payment, achieve exchanging and sharing rehabilitation medical quality control data among hospitals at different levels in different regions, assist tertiary referral and remote rehabilitation, improve the rehabilitation medical service system, and enhance the level of rehabilitation medical care. This paper will summarize the application experience of constructing ICF rehabilitation information management system.
Hepatocellular carcinoma (HCC) is the most common liver malignancy, where HCC segmentation and prediction of the degree of pathological differentiation are two important tasks in surgical treatment and prognosis evaluation. Existing methods usually solve these two problems independently without considering the correlation of the two tasks. In this paper, we propose a multi-task learning model that aims to accomplish the segmentation task and classification task simultaneously. The model consists of a segmentation subnet and a classification subnet. A multi-scale feature fusion method is proposed in the classification subnet to improve the classification accuracy, and a boundary-aware attention is designed in the segmentation subnet to solve the problem of tumor over-segmentation. A dynamic weighted average multi-task loss is used to make the model achieve optimal performance in both tasks simultaneously. The experimental results of this method on 295 HCC patients are superior to other multi-task learning methods, with a Dice similarity coefficient (Dice) of (83.9 ± 0.88)% on the segmentation task, while the average recall is (86.08 ± 0.83)% and an F1 score is (80.05 ± 1.7)% on the classification task. The results show that the multi-task learning method proposed in this paper can perform the classification task and segmentation task well at the same time, which can provide theoretical reference for clinical diagnosis and treatment of HCC patients.
Objective To study the anatomy and variations of hepatic veins draining into inferior vena cava （IVC）， and to classify the surgical techniques of piggyback liver transplantation （PBLT） based on the view of hepatic veins anatomy with IQQA liver image analysis system so as to provide the important basis for the perioperative clinical decision making. Methods Two hundred and forty-eight cases of PBLT were preformed in the Zhongnan Hospital of Wuhan University and the 3rd Xiangya Hospital of Central South University from May 2000 to August 2007， the types of hepatic veins were summarized according to the anatomy of hepatic veins and short hepatic veins draining into IVC at the second and third hepatic hilars. Forty cases of PBLT were preformed in the Zhongnan Hospital of Wuhan University from March 2010 to April 2013， and the anatomy of hepatic veins was reviewed with IQQA liver image analysis system. The anatomy of hepatic veins and technological type of liver transplantation were recorded respectively. Results Of these 248 livers studied in our center， type Ⅰ（the left and middle hepatic vein joined as one trunk ） was found in 142 cases （57.25%）， type Ⅱ （the right and middle hepatic vein joined as one trunk） was 54 cases （21.77%）， type Ⅲ （three hepatic veins joined as one trunk） in 14 cases （5.64%）， type Ⅳ （the left， middle， and right hepatic veins were all unique）in 34 cases （13.71%）， and type Ⅴ （no hepatic veins but short hepatic veins） in 4 cases （1.61%）. The data of 40 cases of PBLT from IQQA liver image analysis system showed that type Ⅰwere found in 24 cases （60.00%）， type Ⅱin 9 cases（22.50%）， type Ⅲ in 2 cases （5.00%）， type Ⅳ in 4 cases （10.00%）， and type Ⅴ in 1 case （2.50%）， which were matched with hepatic vein classification standard of the author. Conclusions Studying the anatomy and variations of hepatic veins draining into IVC with IQQA liver image analysis system and classifying the surgical techniques of PBLT （type Ⅰ，Ⅱ，Ⅲ，andⅣA patients can be performed classical PBLT；Type ⅣB and Ⅴ patients can only be performed ameliorative PBLT） could provide an important basis for clinical preoperative decision.
Objective To review the clinical operation methods of abdominal incisional hernia. Methods Classification, operation method and fellow-up of 78 patients with abdominal incisional hernia were retrospectively analyzed. Results The average time of fellow-up was 26 months. Nineteen cases were repaired with simple suture with 3 cases (15.8%) recurrence, 57 cases were repaired with man-made material with 2 case （3.4%） recurrence. Conclusions Individual operation method should be chosen according to body condition, classification of the size of abdominal loss and abdominal hypertension. It is an effective method to repair the hernia of abdominal incision with man-made material.
Objective To discuss the concept of ulnar tunnel at thewrist, the types, causes, traits of compression, diagnosis, and clinical significance of ulnar tunnel syndrome(UTS). Methods Thirty-nine cases diagnosed as having UTS from 1986 were retrospectively reviewed combined with previous relevant literature. Results Ulnar tunnel included Guyon’s canal, pisohamate tunnel and hypothenar segment. There were 8 types andmany causes of UTS. Some patients had compression in more than one zones and might be associated with carpal tunnel syndrome or cubital tunnel syndrome. UTS could be diagnosed through clinical manifestations and electrophysiological examination. Conclusion Defining the concept of ulnar tunnel and the knowledge of the complexity and rarity of UTS can effectively guide diagnosis and treatment.
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.