ObjectiveTo explore the effect of blood flow restriction training (BFRT) under different intensities combined with low-intensity resistance training (LIRT) on motor function in stroke patients with frailty. MethodsFrom August, 2024 to August, 2025, 200 elderly ischemic stroke patients with frailty from Affiliated Hospital, North China University of Science and Technology were randomized into control group and observation groups 1, 2 and 3, with 50 cases in each group. All the groups received 30% 1RM resistance training. In addition, the observation groups received BFRT of 40%, 50% and 60% arterial occlusion pressure (AOP), respectively. Before training, and four and eight weeks after training, their motor function was evaluated with Fugl-Meyer Assessment-Upper Extremities (FMA-UE) and Fugl-Meyer Assessment-Lower Extremities (FMA-LE), grip strength, 10-Metre Walk Test (10MWT) and Berg Balance Scale (BBS); Fried Frailty Phenotype (FFP) was used to assess frailty status; and the score of modified Ashworth Scale (MAS), blood pressure and resting heart rate were recorded. ResultsOne case dropped out in each group. For the scores of FMA-UE and FMA-LE, the grip strength of both hands, the time of 10MWT and the score of BBS, the main effects of group and time, and interaction effect were all significant (F > 2.745, P < 0.05); four weeks after training, the above indexes were better in the observation groups than in the control group (P < 0.05); eight weeks after training, the scores of FMA-UE and FMA-LE, the grip strength of both hand and the score of BBS were better in the observation group 3 than in the observation groups 1 and 2 (P < 0.05), and the time of 10MWT was better in the observation group 3 than in the observation group 1 (P < 0.05). For the score of FFP, the main effect of group was significant (F = 688.360, P < 0.001), however, the effects of time and interaction were not significant (P > 0.05). For the score of MAS, the main effect of group was significant (F = 7.171, P = 0.008), however, the effects of time and interaction were not significant (P > 0.05). For the blood pressure and resting heart rate, the main effects of group and time, and interaction effect were not significant (P > 0.05). ConclusionBFRT under different intensities combined with LIRT can safely improve the motor function, grip strength, walking ability in elderly stroke patients, and 60% AOP may be more effective.

OBJECTIVE To construct three-class （insufficient， normal， excessive） and two-class （insufficient， normal） models for predicting plasma concentration of valproic acid （VPA）， and compare the performance of these two models， with the aim of providing a reference for formulating clinical medication strategies. METHODS The clinical data of 480 patients who received VPA treatment and underwent blood concentration test at the Xi’an International Medical Center Hospital were collected from November 2022 to September 2024 （a total of 695 sets of data）. In this study， predictive models were constructed for target variables of three-class and two-class models. Feature ranking and selection were carried out using XGBoost scores. Twelve different machine learning algorithms were used for training and validation， and the performance of the models was evaluated using three indexes: accuracy， F1 score， and the area under the working characteristic curve of the subject （AUC）. RESULTS XGBoost feature importance scores revealed that in the three-class model， the importance ranking of kidney disease and electrolyte disorders was higher. However， in the two-class model， the importance ranking of these features significantly decreased， suggesting a close association with the excessive blood concentration of VPA. In the three-class model， Random Forest method performed best， with F1 score of 0.704 0 and AUC of 0.519 3 on the test set； while in the two-class model， CatBoost method performed optimally， with F1 score of 0.785 7 and AUC of 0.819 5 on the test set. CONCLUSIONS The constructed three-class model has the ability to predict excessive VPA blood concentration， but its prediction and model generalization abilities are poor； the constructed two-class model can only perform classification prediction for insufficient and normal blood concentration cases， but its model performance is stronger.

Objective:Middle ear cholesteatoma is a common otolaryngological disease, and traditional diagnostic methods have certain limitations. This study aims to construct a computer-aided diagnosis model for middle ear cholesteatoma based on integrated convolutional neural networks (CNNs) to improve diagnostic accuracy and efficiency.Methods:Firstly, Data were collected from patients who visited the Department of Otorhinolaryngology Head and Neck Surgery at the First People′s Hospital of Yinchuan between January 2020 and December 2021. 8 000 temporal bone CT images were collected, including 5 000 images diagnosed pathologically as middle ear cholesteatoma and 3 000 normal images. A five-fold cross-validation method was used to divide the dataset into training and testing sets. Next, a transfer learning approach was used to initialize model parameters, and the AlexNet, GoogleNet, and ResNet networks were pre-trained to extract deep features from the images. Then, the Softmax classification algorithm was applied to classify the features, resulting in three independent classifiers. These classifiers were combined using an ensemble learning method with a weighted voting approach to obtain the final diagnostic results. Finally, the model was evaluated by comparing the ensemble classifier with individual classifiers to assess its accuracy, precision, sensitivity, specificity, and diagnostic time, and a comparison with low-mid-and high-experience physician groups was conducted to comprehensively evaluate the model′s diagnostic performance.Results:The experimental results showed that the model achieved an accuracy of 88.8%(178/200), precision of 92.9%,(112/120) sensitivity of 89.8%(108/120), and specificity of 88.1%(70/80). The average diagnostic time for individual patient temporal bone CT images was reduced to 2-3 seconds. Compared to the diagnostic results from low-mid-and high-experience physician groups, the model demonstrated significant advantages and effectively assisted clinicians in making rapid and accurate middle ear cholesteatoma diagnoses.Conclusion:The proposed middle ear cholesteatoma diagnostic model based on integrated convolutional neural networks exhibits high recognition accuracy and rapid diagnostic speed, significantly improving clinical diagnostic efficiency, especially in early screening and auxiliary diagnosis, making it of considerable value in clinical practice.

Objective:Middle ear cholesteatoma is a common otolaryngological disease, and traditional diagnostic methods have certain limitations. This study aims to construct a computer-aided diagnosis model for middle ear cholesteatoma based on integrated convolutional neural networks (CNNs) to improve diagnostic accuracy and efficiency.Methods:Firstly, Data were collected from patients who visited the Department of Otorhinolaryngology Head and Neck Surgery at the First People′s Hospital of Yinchuan between January 2020 and December 2021. 8 000 temporal bone CT images were collected, including 5 000 images diagnosed pathologically as middle ear cholesteatoma and 3 000 normal images. A five-fold cross-validation method was used to divide the dataset into training and testing sets. Next, a transfer learning approach was used to initialize model parameters, and the AlexNet, GoogleNet, and ResNet networks were pre-trained to extract deep features from the images. Then, the Softmax classification algorithm was applied to classify the features, resulting in three independent classifiers. These classifiers were combined using an ensemble learning method with a weighted voting approach to obtain the final diagnostic results. Finally, the model was evaluated by comparing the ensemble classifier with individual classifiers to assess its accuracy, precision, sensitivity, specificity, and diagnostic time, and a comparison with low-mid-and high-experience physician groups was conducted to comprehensively evaluate the model′s diagnostic performance.Results:The experimental results showed that the model achieved an accuracy of 88.8%(178/200), precision of 92.9%,(112/120) sensitivity of 89.8%(108/120), and specificity of 88.1%(70/80). The average diagnostic time for individual patient temporal bone CT images was reduced to 2-3 seconds. Compared to the diagnostic results from low-mid-and high-experience physician groups, the model demonstrated significant advantages and effectively assisted clinicians in making rapid and accurate middle ear cholesteatoma diagnoses.Conclusion:The proposed middle ear cholesteatoma diagnostic model based on integrated convolutional neural networks exhibits high recognition accuracy and rapid diagnostic speed, significantly improving clinical diagnostic efficiency, especially in early screening and auxiliary diagnosis, making it of considerable value in clinical practice.

Objective To investigate the levels and clinical significance of serum microRNA(miR)-651 and miR-630 in patients with cervical cancer.Methods From June 2017 to May 2020,108 cervical cancer patients accepted by our hospital were collected as the cervical cancer group.Meantime,100 cervical intraepithelial neoplasia(CIN)patients treated in our hospital were regarded as the CIN group,and 110 healthy individuals who underwent physical examination were regarded as the control group.Real-time fluorescence quantitative PCR(qRT-PCR)was applied to detect serum levels of miR-651 and miR-630,while analyzing the relationship between serum miR-651 and miR-630 as well as clinical features and prognosis of patients.Results The serum levels of miR-651 and miR-630 in the cervical cancer group and CIN group were obviously lower than those in the control group(P<0.05),while the serum levels of miR-651 and miR-630 in the cervical cancer group were obviously lower than those in the CIN group(P<0.05).The expression levels of serum miR-651 and miR-630 were positively corre-lated(r = 0.542,P<0.05).The serum levels of miR-651 and miR-630 were related to HPV infection,differentia-tion,lymph node metastasis,and FIGO staging(P<0.05).The overall survival rate of patients with low levels of miR-651 and miR-630 was lower than that of patients with high levels.Cox regression analysis showed that,HPV infection,degree of differentiation,lymph node metastasis,FIGO staging,miR-651,and miR-630 were all influ-encing factors for the prognosis of cervical cancer patients(P<0.05).Conclusion The serum levels of miR-651 and miR-630 in cervical cancer patients decrease,which are related to HPV infection,differentiation,lymph node metastasis,FIGO staging,and prognosis.

Objective:To explore the application value of qualitative characteristics and quantitative parameters of contrast-enhanced ultrasound (CEUS) in the differential diagnosis of pancreatic ductal adenocarcinoma (PDAC) and non-PDAC presenting as pancreatic solid focal lesions.Methods:A retrospective analysis was conducted on 64 cases of PDAC(the PDAC group) and 52 cases of non-PDAC(the non-PDAC group) who underwent CEUS examination at Tianjin Medical University Cancer Institute and Hospital from July 2022 to June 2023. Clinical characteristics, two-dimensional ultrasound features, CEUS qualitative characteristic, and quantitative parameters were compared between the two groups. ROC curves were plotted, and the Delong test was used to evaluate the diagnostic performance of qualitative and quantitative analyses in distinguishing PDAC from non-PDAC. Binary logistic regression analysis was employed to assess the independent predictors of PDAC.Results:①There were significant differences in serum CA19-9, lesion size, boundary, the main pancreatic duct (MPD) diameter, degree of enhancement and enhancement pattern between the PDAC group and the non-PDAC group (all P<0.05). ②The relative peak intensity (rPE), and relative wash-in and wash-out area under the curve (rWiWoAUC) were lower in the PDAC group than the non-PDAC group, with statistically significant differences(all P<0.001). ③The areas under the curve (AUC) for diagnosing PDAC using enhancement pattern, venous phase(VP) enhancement degree, rPE, and rWiWoAUC were 0.698, 0.707, 0.863, and 0.867, respectively. The AUCs of quantitative parameters were superior to those of qualitative characteristics, with statistically significant differences ( P<0.05). Using CEUS mode B, low VP enhancement, rPE<72.44, and rWiWoAUC<86.59 as cut-off values, the accuracies for diagnosing PDAC were 0.698, 0.741, 0.828, and 0.802, respectively. ④Serum CA19-9, lesion size, MPD diameter, rPE, and rWiWoAUC were independent predictors of PDAC (all P<0.05). Conclusions:CEUS qualitative and quantitative analyses are helpful in the differential diagnosis of PDAC and non-PDAC, with rPE and rWiWoAUC being useful indicators for diagnosing PDAC.

Objective:To investigate the sedative effect of remimazolam on ICU elderly patients undergoing mechanical ventilation and its influence on circulatory system.Methods:Using a prospective research approach, 189 ICU elderly patients undergoing mechanical ventilation in Hebei Petro China Central Hospital from October 2021 to June 2023 were selected. The patients were divided into remimazolam group, dexmedetomidine group and propofol group by random number table method with 63 cases in each group. The patients in remimazolam group, dexmedetomidine group and propofol group were sedated with remimazolam, dexmedetomidine and propofol, respectively. The sedation standard time, sedation standard rate, sedation maintenance time and recovery time after drug withdrawal were compared among the three groups. The heart rate, mean arterial pressure (MAP), respiratory rate and pulse oxygen saturation (SpO 2) before medication (T 0) and medication for 15 min (T 1), 30 min (T 2), 1 h (T 3), 6 h (T 4), 12 h (T 5) were recorded. The incidences of bradycardia, hypotension, respiratory depression, body movement and delirium during sedation were recorded. Results:The sedation standard time and recovery time after drug withdrawal in remimazolam group were significantly shorter than those in dexmedetomidine group and propofol group: (22.27 ± 5.31) min vs. (29.45 ± 6.24) and (30.12 ± 5.87) min, (28.66 ± 7.06) min vs. (32.22 ± 6.85) and (34.34 ± 7.24) min, and there were statistical differences ( P<0.05); there were no statistical difference between dexmedetomidine group and propofol group ( P>0.05). The sedation standard rate in remimazolam group and dexmedetomidine group was significantly higher than that in propofol group: 87.43% (661/756) and 83.60% (632/756) vs. 72.49% (548/756), and there was statistical difference ( P<0.016 7); there was no statistical difference between remimazolam group and dexmedetomidine group ( P>0.016 7). There was no statistical difference in sedation maintenance time among the three groups ( P>0.05). There were no statistical difference in T 0 heart rate, MAP, respiratory rate and SpO 2 among the three groups ( P>0.05). The T 1 to T 5 heart rate and MAP in remimazolam group were significantly higher than those in dexmedetomidine group and propofol group, the T 2 to T 5 heart rate and MAP in dexmedetomidine group were significantly lower than those in propofol group, and there were statistical differences ( P<0.05). The T 2 to T 5 respiratory rate in remimazolam group was significantly lower than that in dexmedetomidine group, the T 1 to T 5 respiratory rate in remimazolam group and dexmedetomidine group was significantly higher than that in propofol group, and there were statistical differences ( P<0.05). The T 2 to T 5 SpO 2 in remimazolam group and dexmedetomidine group was significantly higher than that in propofol group, and there was statistical difference ( P<0.05). The incidence of bradycardia in remimazolam group was significantly lower than that in dexmedetomidine group: 7.94% (5/63) vs. 25.40% (16/63), the incidence of hypotension was significantly lower than that in propofol group: 6.35% (4/63) vs. 23.81% (15/63), and there were statistical differences ( P<0.016 7). The incidence of respiratory depression in remimazolam group and dexmedetomidine group was significantly lower than that in propofol group: 4.76% (3/63) and 1.59% (1/63) vs. 22.22% (14/63), and there was statistical difference ( P<0.016 7). There was statistical difference in incidence of delirium among the three groups ( P<0.05), but there was no statistically significant difference in pairwise comparison ( P>0.016 7). There was no statistical difference in the incidence of body movement among the three groups ( P>0.05). Conclusions:The effect of remimazolam sedation in ICU elderly patients undergoing mechanical ventilation is satisfactory, with little influence on circulation and respiratory system and few adverse reactions.

Objective:To predict the clinical value of World Health Organization/International Society of Urological Pathology (WHO/ISUP) grading of clear cell renal cell carcinoma (ccRCC) pre-scholarly based on ultrasound imaging group.Methods:Clinical and ultrasound imaging data of patients with surgically pathologically confirmed ccRCC at Tianjin Medical University Cancer Institue and Hospital from January 2021 to October 2022 were retrospectively collected and divided into a low grade group (grade Ⅰ and Ⅱ, 105 cases) and a high grade group (grade Ⅲ and Ⅳ, 70 cases) using WHO/ISUP pathological grading criteria. The clear image of the largest diameter of the tumor was selected and imported into ITK-SNAP software for manual segmentation of the image and extraction of ultrasonographic radiomics features. The patients were randomly divided into a training group and a test group in the ratio of 7∶3, with 122 cases in the training group and 53 cases in the test group. Stable radiomics features were obtained by dimensionality reduction. The support vector machines (SVM) algorithm was applied to predict the pathological grading of ccRCC. Finally, a clinical-ultrasound imaging model, an ultrasonographic radiomics model and a comprehensive model combining the two were constructed. The predictive effects of the three models were analyzed by the area under the ROC curve (AUC). The performance of each model was evaluated by applying the calibration curve. The net benefit of patients was obtained by applying the decision curve.Results:A total of 873 radiomics features were extracted, and 10 features were finally obtained for model construction after dimensionality reduction. Final test results showed that the AUC, sensitivity, specificity and accuracy of the clinical-ultrasound imaging model were 0.68, 0.47, 0.78, 0.66. The AUC, sensitivity, specificity and accuracy of the ultrasonographic radiomics model were 0.74, 0.53, 0.88, 0.74. The AUC, sensitivity, specificity and accuracy of the comprehensive model were 0.84, 0.63, 0.86, 0.77. The AUC of the comprehensive model being larger than that of the clinical-ultrasound imaging model ( Z=-3.224, P=0.001) and ultrasonographic radiomics model ( Z=-2.594, P=0.009). The calibration curves showed that the comprehensive model was more stable than the other two models. The decision curve showed a higher net clinical benefit for the comprehensive model than for the other two models within a threshold of 0.1-1.0. Conclusions:The preoperative prediction of ccRCC pathological grading by the radiomics model based on ultrasound images is effective. The comprehensive model constructed by combining relevant clinical and ultrasound parameters has better performance, which can help predict ccRCC pathological grading preoperatively to a certain extent. It is crucial to help physicians choose the best management plan in the era of personalized medicine.

Objective:To investigate the prediction of National Institute of Healthy (NIH) risk stratification of gastrointestinal stromal tumor(GIST) based on clinical ultrasound model, ultrasonographic radiomics model and combined model by oral contrast enhanced ultrasonography.Methods:The clinical and ultrasound imaging data of 204 gastric GIST patients attending Tianjin Medical University Cancer Institute and Hospital from June 2021 to June 2022 were retrospectively analyzed, among whom a total of 101 patients with high and moderate NIH risk stratification GIST confirmed by postoperative pathology were included in the high risk group, and a total of 103 patients with low and extremely low NIH risk stratification GIST were in the low risk group. The ultrasound images of the largest diameter of the GIST were manually segmented by ITK-SNAP software, and Pyradiomics (v3.0.1) module in Python 3.8.7 was applied to extract ultrasonographic radiomics features from the ROI segmented images. The patients were randomly divided into training and validation sets in the ratio of 7∶3. The XGBoost of Sklearn module was applied to construct the clinical ultrasound imaging model, ultrasonographic radiomics model, and combined model. Then the area under ROC curve (AUC), sensitivity, specificity, and accuracy were evaluated; the predictive ability of the three models was compared by Delong test. Calibration Curve was applied to evaluate the model performance, and the clinical Decision Curve Analysis was applied to determine the net benefit to patients.Results:A total of 578 ultrasonographic radiomics features were extracted from ROI, and 8 ultrasonographic radiomics features were finally retained for modeling after regression and dimensionality reduction. Finally, test results showed that AUC, sensitivity, specificity and accuracy of clinical ultrasound imaging model, ultrasonographic radiomics model and combined model were 0.75, 69.3%, 68.9%, 69.1%; 0.87, 79.2%, 81.6%, 80.4%; 0.91, 80.2%, 83.5%, 81.9%, respectively. Delong test showed that the difference of AUC between ultrasonographic radiomics model and clinical ultrasound imaging model was statistically significant ( Z=2.698, P<0.001), and the combined model was significantly better than clinical ultrasound imaging model ( Z=4.062, P<0.001) and ultrasonographic radiomics model ( Z=2.225, P=0.026). Calibration Curve showed the high performance of combined model, and Decision Curve Analysis showed the superior clinical usefulness of combined model. Conclusions:It is feasible to construct an ultrasonographic radiomics model for GIST NIH risk stratification based on oral contrast enhanced ultrasonography images, and the combined model has more advantageous diagnostic performance, which can identify high risk NIH GIST objectively and stably for clinical purposes.