Objective To address the personalized differences in motion gait between stroke patients and healthy older adults,as well as the issue of abnormal gait recognition,a deep learning fusion-based approach is proposed to effectively improve the accuracy of abnormal gait recognition.Methods A model fusing convolutional neural networks(CNN)and bidirectional long short-term memory networks(BiLSTM)was adopted,with the introduction of a residual network(ResNet).Unilateral ankle joint movement data at different walking speeds within a comfortable range were collected from healthy older adults and stroke patients.Signals from inertial sensors and electromyography sensors were used as inputs,while gait features were analyzed and gait differences between the two groups were compared.The effectiveness of the model was validated by comparing the classification performance of traditional deep learning models and CNN-ResNet-BiLSTM models with different layer combinations in terms of abnormal gait recognition accuracy.Results The CNN-ResNet-BiLSTM model,which introduced residual connectivity,performed excellently in abnormal gait recognition.Compared with traditional deep learning models such as the gated recurrent unit(GRU)and long short-term memory network(LSTM),its prediction accuracy was improved by 13.6％and 8.36％,respectively.Additionally,compared with other model combinations,this model achieved an overall accuracy of 97.78％.Conclusions The algorithm proposed in this study can be applied to stroke-related abnormal gait detection,providing technique support for the early diagnosis and precise monitoring of such diseases.

Objective To address the personalized differences in motion gait between stroke patients and healthy older adults,as well as the issue of abnormal gait recognition,a deep learning fusion-based approach is proposed to effectively improve the accuracy of abnormal gait recognition.Methods A model fusing convolutional neural networks(CNN)and bidirectional long short-term memory networks(BiLSTM)was adopted,with the introduction of a residual network(ResNet).Unilateral ankle joint movement data at different walking speeds within a comfortable range were collected from healthy older adults and stroke patients.Signals from inertial sensors and electromyography sensors were used as inputs,while gait features were analyzed and gait differences between the two groups were compared.The effectiveness of the model was validated by comparing the classification performance of traditional deep learning models and CNN-ResNet-BiLSTM models with different layer combinations in terms of abnormal gait recognition accuracy.Results The CNN-ResNet-BiLSTM model,which introduced residual connectivity,performed excellently in abnormal gait recognition.Compared with traditional deep learning models such as the gated recurrent unit(GRU)and long short-term memory network(LSTM),its prediction accuracy was improved by 13.6％and 8.36％,respectively.Additionally,compared with other model combinations,this model achieved an overall accuracy of 97.78％.Conclusions The algorithm proposed in this study can be applied to stroke-related abnormal gait detection,providing technique support for the early diagnosis and precise monitoring of such diseases.

Objective:To investigate the risk factors for refracture after percutaneous kyphoplasty (PKP) in patients with osteoporotic vertebral compression fracture (OVCF).Methods:A retrospective cohort study was conducted on the clinical data of 149 OVCF patients who were admitted to the First Affiliated Hospital of Soochow University from June 2019 to June 2022, including 21 males and 128 females, aged 56-97 years [(73.2±8.7)years]. Initial surgical segments included T 7 in 1 patient, T 8 in 10, T 9 in 6, T 10 in 6, T 11 in 19, T 12 in 28, L 1 in 38, L 2 in 18, L 3 in 11, L 4 in 7 and L 5 in 5. Patients were divided into refracture group ( n=32) and non-refracture group ( n=117) according to whether they had postoperative refracture after PKP. Refractured surgical segments included T 8 in 2 patients, T 9 in 2, T 11 in 4, T 12 in 5, L 1 in 7, L 2 in 4, L 3 in 6, and L 5 in 2. The age, gender, underlying diseases (hypertension, diabetes), body mass index (BMI), preoperative bone mineral density (BMD), smoking history, drinking history, follow-up time, preoperative visual analogue scale (VAS), and preoperative Oswestry dysfunction index (ODI) of the two groups were recorded. Preoperative paravertebral muscle-related parameters of the two groups were calculated including cross-sectional area of bilateral psoas, bilateral erector spinae, bilateral multifidus, and vertebral bodies, paravertebral muscle mass, and vertebral bone quality (VBQ) score. Univariate analysis was performed to evaluate the correlation between the fore-mentioned indicators and postoperative refracture after PKP in OVCF patients. Multivariate logistic regression analysis was employed to identify the independent risk factors for postoperative refracture after PKP in OVCF patients. Results:Univariate analysis revealed that there was certain correlation of BMI, preoperative BMD, cross-sectional area of bilateral psoas, bilateral erector spinae, bilateral multifidus, paravertebral muscle mass and VBQ score with postoperative refracture after PKP in OVCF patients ( P<0.01), while no correlation was found between age, gender, hypertension, diabetes, smoking history, drinking history, follow-up time, preoperative VAS, preoperative ODI, or cross-sectional area of vertebral bodies and postoperative refracture after PKP in OVCF patients ( P>0.05). Multivariate logistic regression analysis showed that preoperative BMD ≤-3.4 SD ( OR=0.27, 95% CI 0.09, 0.80, P<0.05), paravertebral muscle mass ≤281.2% ( OR=0.98, 95% CI 0.97, 0.99, P<0.01) and VBQ score ≥4.8 points ( OR=4.41, 95% CI 1.18, 16.44, P<0.05) were significantly correlated with postoperative refracture after PKP in OVCF patients. Conclusion:Preoperative BMD ≤-3.4 SD, paravertebral muscle mass ≤281.2%, and VBQ score ≥4.8 points are the independent risk factors for refracture after PKP in OVCF patients.

Objective:To investigate the correlation between the prognosis of late-onset depression(LOD)in the elderly and lncRNA expression levels and coping styles.Methods:Differential expression of lncRNAs in peripheral blood of LOD 92 patients was detected by a real-time quantitative PCR(qPCR)detection system, and the Hamilton Depression Scale(HAMD)and the Trait Coping Style Questionnaire(TCSQ)were used for psychological assessment.Results:Compared with the control group, the expression levels of TCONS_00019174(7.55 vs.4.36), ENST00000566208(6.48 vs.3.26), ENST00000517573(8.33 vs.5.32)and NONHSAT142707(6.78 vs.3.26)in elderly patients of the LOD group were significantly down-regulated( Z=5.09, 5.87, 4.35, 6.44, P<0.05); Compared with the low-expression subgroup, scores of anxiety/somatization[(3.83±1.40) vs.(6.39±2.35)], diurnal variation[(0.22±0.42) vs.(0.83±0.94)], retardation[(5.74±0.96) vs.(6.48±1.28)], hopelessness[(2.78±0.67) vs.(4.52±1.56)]and HAMD[(20.39±1.75) vs.(26.83±4.88)]in the high-expression subgroup were significantly lower( t=-4.50, -2.84, -2.22, -4.90, -5.96, P<0.05). The ΔCT value of TCONS_00019174 was negatively correlated with the reduction rates of anxiety/somatization, diurnal variation, retardation, sleep disturbance, hopelessness and HAMD( r=-0.40-0.66, P<0.05). The ΔCT value of ENST00000566208 was negatively correlated with the reduction rates of anxiety/somatization, sleep disturbance, hopelessness and HAMD( r=-0.47-0.62, P<0.01). The ΔCT values of ENST00000517573, NONHSAT034045 and NONHSAT142707 were negatively correlated with the reduction rates of retardation, sleep disturbance, hopelessness and HAMD( r=-0.39-0.76, P<0.05). The positive coping style was positively correlated with the reduction rates of HAMD, anxiety/somatization, retardation, sleep disturbance and hopelessness( r=0.38-0.55), while the negative coping style was negatively correlated with the reduction rates of HAMD, anxiety/somatization, sleep disturbance and hopelessness( r=-0.39-0.67, P<0.05). When TCONS_00019174, ENST00000566208, NONHSAT034045, NONHSAT142707, positive coping and negative coping were taken into the regression equation as variables for HAMD reduction, it was found that they were able to explain 32.4% of the variance for the reduction rate of the total HAMD score( t=-8.713, -3.584, -3.864, -2.257, 5.675, -2.357, P<0.05). Conclusions:TCONS_00019174, ENST00000566208, NONHSAT034045, NONHSAT142707, positive coping style and negative coping style are predictors of the prognosis of LOD in the elderly.

Objective:To compare the efficacy of conventional Western medicine alone and acupuncture combined with acupoint application in treating intestinal dysfunction secondary to mechanical ventilation in elderly patients with emergency sepsis.Methods:A retrospective analysis was performed on 111 elderly patients with mechanical ventilation for sepsis admitted to the emergency department of Dongzhimen Hospital of Beijing University of Chinese Medicine from January 2019 to June 2021. They were divided into two groups according to the time of admission: Western medicine treatment group alone (patients from January 2019 to December 2019, n=47) and acupuncture combined with acupoint application group (patients from January 2020 to June 2021, n=64). Acupuncture combined with acupoint application group was treated with acupuncture combined with acupoint application on the basis of conventional Western medicine. The intestinal dysfunction score, abdominal circumference and mortality after 4 weeks were compared between the two groups. Results:The abdominal circumference and intestinal dysfunction score in acupuncture combined with acupoint application group were significantly lower than those before treatment [(100.56±9.34)cm vs (106.25±9.74)cm; (0.92±0.72)point vs (2.31±0.69)point, all P< 0.05], while there was no significant difference in the above indexes before and after treatment in the Western medicine treatment group (all P>0.05). The abdominal circumference, intestinal dysfunction score and mortality after 4 weeks in the acupuncture combined with acupoint application group were significantly lower than those in the Western medicine treatment group [(100.56±9.34)cm vs (108.09±10.52)cm; (0.92±0.72)point vs (2.43±0.62)point; (29.7%, 19/64) vs (48.9%, 23/47), all P<0.05]. Conclusions:The curative effect of acupuncture combined with acupoint application in the treatment of intestinal dysfunction secondary to mechanical ventilation in elderly patients with sepsis in emergency is better than that of routine treatment of Western medicine alone. The gastrointestinal function and prognosis of patients have been significantly improved, which is worthy of clinical promotion.

Objective:To apply self-directed learning-oriented multi-channel teaching to clinical digestive system integration course and explore its teaching effect.Methods:Seventy undergraduates of Batch 2015 majoring in clinical medicine in a medical college of Shandong Province were selected as subjects. In the clinical digestive system integration course, we designed and implemented multi-channel teaching methods including problem-based learning (PBL), integrated teaching of theory and practice, standardized patient teaching, group focus teaching and moral education. The scores of students' practice examination under the two teaching methods were compared, and the self-assessment of students' autonomous learning ability before and after the intervention was compared. SPSS 20.0 was used for t test. Results:The average total score of practical assessment in the intervention group was (86.10±6.01), which was higher than that (81.84±7.08) of the Batch 2014 students ( P<0.05). The total score of students' self-assessment of autonomous learning ability was (145.41±9.42) before the intervention. By comparison, the total score was (152.94±10.18) after the intervention. Except for the dimension of "self-innovation", the scores of self-directed learning ability in general and other dimensions were significantly different before and after the intervention ( P<0.05). Conclusion:Self-directed learning-oriented multi-channel teaching is a suitable teaching method for the integration curriculum of clinical digestive system.

Objective To compare the function recovery of multiple injuries combined with floating knee joint injury and simple knee joint injury,and to analyze the risk factors.Methods A retrospective case control study was conducted to analyze the clinical data of 41 patients with multiple injuries combined with Blake and McBryde Ⅱ A floating knee injury admitted to Xijing Hospital of Air Force Medical University from June 2011 to June 2017.There were 26 males and 15 females,aged 18-76 years,with an average of 34.5 years.There were 25 patients with simple knee joint injury and and 16 patients with multi-joint combined injury involving knee joint and ipsilateral hip joint or ankle joint injury.Surgical fixation was performed in different parts by external fixation,intramedullary nail and plate screw fixation.According to the Kalstr(o)m and Olerud functional evaluation criteria,the excellent and good rate of postoperative functional recovery was compared between the two groups.The surgical fixation methods of the two groups were compared.Logistic regression analysis was performed on the influencing factors of functional recovery.Results The patients were followed up for 1-7 years,with an average of 3 years.The excellent and good rate of overall functional recovery in the two groups was 68％,and the rate was 84％ in simple knee injury group and 44％ in multi-joint combined injury group (P ＜ 0.01).There was no significant difference in the ratio of intramedullary nail and plate screw fixation between the two groups (P ＞ 0.05),while the proportion of the external fixation in the multi-joint combined injury group [31％ (5/16)] was significantly higher than that in the simple knee joint injury group [16％ (4/25)] (P ＜ 0.05).Logistic regression analysis showed that the rate of external fixation was an independent factor affecting the postoperative function (OR =0.15,P ＜ 0.01).Conclusions The postoperative function in multi-joint injury patients is poorer than in the single joint injury patients.The higher rate of using external fixation in multi-joint injury patients is a risk factor.For Blake and McBryde Ⅱ A floating knee injury combined with multi-joint injury,less external fixation should be used,so as to improve the postoperative function.

Hepatic alveolar echinococcosis is a kind of zoonosis with poor prognosis.At present,the diagnosis and treatment are mainly based on ultrasound,CT diagnosis,MRI and other classical imaging by detecting the terminal effects of the changes on the cell molecules of the disease itself,the organ anatomy changes.However,it is found that the above imaging techniques have limitations in the diagnosis and treatment.For example,the infiltration zone of the lesion is not clear and the degree of biological activity can not be determined.This leads to a higher recurrence rate in the late stage of clinical treatment.In recent years,the molecular imaging shows the abnormal cell and molecular level in the disease process has been developed rapidly.This has led to several diagnosis and treatment problems related to liver vesicular disease.This paper mainly reviews the research results of the disease in the field of molecular imaging and the development direction of this field in the future,to provide guidance for future clinical and scientific research.

Objective To evaluate the efifcacy of endoscopic Over-The-Scope-Clip system (OTSC) system for the acute iatrogenic digestive tract perforation. Methods To collect 11 cases with digestive tract perforation closed with the OTSC system, including 7cases of gastric perforation, 1 case of duodenal perforation,3 cases of colorectal perforation. Results 11 cases were successfully closed with OTSC system in time, the average time needed for the endoscopic closure is 6~15 min. And the perforation diameter is 0.6~3.7 cm, average diameter is (1.89 ± 0.27) cm. No intraoperative bleeding and delayed hemorrhages, no deaths occurred. Conclusion Endoscopic OTSC system is a successful method for the digestive tract perforation and is worth to popularize.

PurposeSupport vector machine (SVM) is a machine learning method based on statistical learning theory of Vapnik-Chervonenkis (VC) dimension structure and risk minimization theory. We analyzed the gem spectrum CT scan data of patients with thyroid nodules and established the SVM diagnostic model. The experimental targets were then reduced and the forecast analysis was carried out based on SVM model. The diagnostic model and experimental methods were proved to provide guidance for clinical diagnosis of thyroid nodules.