Cerebral small vessel disease represents a group of common vascular disorders involving pathological changes in arterioles,capillaries and venules,with microvascular investigation remaining a key challenge in stroke.With high signal-to-noise ratio and high contrast enabled by enhanced field strength,7T MRI can surpass the resolution limits of 3T MRI,revealing structural and functional abnormalities in cerebral small vessels below 400 μm,as well as detecting subtle lesions in brain tissue.This paper reviews the research progress of multimodal high-resolution imaging techniques based on 7T MRI,such as time-of-flight angiography,phase contrast imaging and susceptibility imaging,in the study of cerebral small vessel disease.Utilizing these technologies,7T MRI can clearly display the structure of cerebral small vessels,such as the lenticulostriate arteries and deep medullary veins,and measure functional parameters like flow velocity and susceptibility.Additionally,it can sensitively detect cerebral microbleeds and cortical cerebral microinfarct.These imaging data provide valuable information for detecting early features of cerebral small vessel disease and assessing its progression,offering new insights into its pathogenesis.Combined with artificial intelligence-based image analysis methods,7T MRI holds great promise for early diagnosis and progression evaluation in cerebral small vessel disease.

Objective:To summarize the best evidence for postoperative flap management in patients with oral cancer.Methods:Clinical decisions, guidelines, systematic reviews, expert consensus, and evidence summaries on postoperative flap management for patients with oral cancer were searched in databases and websites based on the 6S pyramid of evidence model. The search period was from January 1, 2014, to July 1, 2024. Two researchers trained in evidence-based nursing independently conducted a quality assessment of the literature and extracted the evidence.Results:A total of 14 articels were included, including one clinical decision, two guidelines, one evidence summary, eight systematic reviews, and two expert consensus. Twenty-eighgt pieces of evidence for postoperative flap management in patients with oral cancer were summarized from four aspects of risk factors, flap assessment, protective measures, and treatments.Conclusions:The summarized best evidence for postoperative flap management in oral cancer patients is scientific and applicable. Healthcare professionals need to select and apply the best evidence in a targeted manner, considering the clinical context.

Cerebral small vessel disease represents a group of common vascular disorders involving pathological changes in arterioles,capillaries and venules,with microvascular investigation remaining a key challenge in stroke.With high signal-to-noise ratio and high contrast enabled by enhanced field strength,7T MRI can surpass the resolution limits of 3T MRI,revealing structural and functional abnormalities in cerebral small vessels below 400 μm,as well as detecting subtle lesions in brain tissue.This paper reviews the research progress of multimodal high-resolution imaging techniques based on 7T MRI,such as time-of-flight angiography,phase contrast imaging and susceptibility imaging,in the study of cerebral small vessel disease.Utilizing these technologies,7T MRI can clearly display the structure of cerebral small vessels,such as the lenticulostriate arteries and deep medullary veins,and measure functional parameters like flow velocity and susceptibility.Additionally,it can sensitively detect cerebral microbleeds and cortical cerebral microinfarct.These imaging data provide valuable information for detecting early features of cerebral small vessel disease and assessing its progression,offering new insights into its pathogenesis.Combined with artificial intelligence-based image analysis methods,7T MRI holds great promise for early diagnosis and progression evaluation in cerebral small vessel disease.

Objective:To summarize the best evidence for postoperative flap management in patients with oral cancer.Methods:Clinical decisions, guidelines, systematic reviews, expert consensus, and evidence summaries on postoperative flap management for patients with oral cancer were searched in databases and websites based on the 6S pyramid of evidence model. The search period was from January 1, 2014, to July 1, 2024. Two researchers trained in evidence-based nursing independently conducted a quality assessment of the literature and extracted the evidence.Results:A total of 14 articels were included, including one clinical decision, two guidelines, one evidence summary, eight systematic reviews, and two expert consensus. Twenty-eighgt pieces of evidence for postoperative flap management in patients with oral cancer were summarized from four aspects of risk factors, flap assessment, protective measures, and treatments.Conclusions:The summarized best evidence for postoperative flap management in oral cancer patients is scientific and applicable. Healthcare professionals need to select and apply the best evidence in a targeted manner, considering the clinical context.

Objective:To investigate the effect of tofacitinib,a pan-Janus kinase(JAK)inhibitor,on transforming growth factor-beta 1(TGF-β1)-induced fibroblast to myofibroblast transition(FMT)and to explore its mechanism.To provide a theoretical basis for the clinical treatment of connective tissue disease-related interstitial lung disease(CTD-ILD).Methods:(1)Human fetal lung fibroblast 1(HFL-1)were cultured in vitro,and 6 groups were established:DMSO blank control group,TGF-β1 in-duction group,and TGF-β1 with different concentrations of tofacitinib(0.5,1.0,2.0,5.0 μmol/L)drug intervention experimental groups.CCK-8 was used to measure the cell viability,and wound-healing assay was performed to measure cell migration ability.After 48 h of combined treatment,quantitative real-time PCR(RT-PCR)and Western blotting were used to detect the gene and protein expression levels of α-smooth muscle actin(α-SMA),fibronectin(FN),and collagen type Ⅰ(COL1).(2)RT-PCR and enzyme-linked immunosorbnent assay(ELISA)were used to detect the interleukin-6(IL-6)gene and protein expression changes,respectively.(3)DMSO carrier controls,1.0 μmol/L and 5.0 μmol/L tofacitinib were added to the cell culture media of different groups for pre-incubation for 30 min,and then TGF-β1 was added to treat for 1 h,6 h and 24 h.The phosphorylation levels of Smad2/3 and signal transducer and activator of transcription 3(STAT3)protein were detected by Western blotting.Results:(1)Tofacitinib inhibited the viability and migration ability of HFL-1 cells after TGF-β1 induction.(2)The expression of α-SMA,COL1A1 and FN1 genes of HFL-1 in the TGF-β1-induced groups was signifi-cantly up-regulated compared with the blank control group(P＜0.05).Compared with the TGF-β1 in-duction group,α-SMA expression in the 5.0 μmol/L tofacitinib intervention group was significantly inhi-bited(P＜0.05).Compared with the TGF-β1-induced group,FN1 gene was significantly inhibited in each intervention group at a concentration of 0.5-5.0 μmol/L(P＜0.05).Compared with the TGF-β1-induced group,the COL1A1 gene expression in each intervention group did not change significantly.(3)Western blotting results showed that the protein levels of α-SMA and FN1 in the TGF-β1-induced group were significantly higher than those in the control group(P＜0.05),and there was no significant difference in the expression of COL1A1.Compared with the TGF-β1-induced group,the α-SMA protein level in the intervention groups with different concentrations decreased.And the differences between the TGF-β1-induced group and 2.0 μmol/L or 5.0 μmol/L intervention groups were statistically significant(P＜0.05).Compared with the TGF-β1-induced group,the FN1 protein levels in the intervention groups with different concentrations showed a downward trend,but the difference was not statistically sig-nificant.There was no difference in COL1A1 protein expression between the intervention groups com-pared with the TGF-β1-induced group.(4)After TGF-β1 acted on HFL-1 cells for 48 h,the gene ex-pression of the IL-6 was up-regulated and IL-6 in culture supernatant was increased,the intervention with tofacitinib partly inhibited the TGF-β1-induced IL-6 gene expression and IL-6 in culture supernatant.TGF-β1 induced the increase of Smad2/3 protein phosphorylation in HFL-1 cells for 1 h and 6 h,STAT3 protein phosphorylation increased at 1 h,6 h and 24 h,the pre-intervention with tofacitinib inhibited the TGF-β1-induced Smad2/3 phosphorylation at 6 h and inhibited TGF-β1-induced STAT3 phosphorylation at 1 h,6 h and 24 h.Conclusion:Tofacitinib can inhibit the transformation of HFL-1 cells into myofi-broblasts induced by TGF-β1,and the mechanism may be through inhibiting the classic Smad2/3 path-way as well as the phosphorylation of STAT3 induced by TGF-β1,thereby protecting the disease progres-sion of pulmonary fibrosis.

Objective To propose a heart sound segmentation method based on multi-feature fusion network. Methods Data were obtained from the CinC/PhysioNet 2016 Challenge dataset (a total of 3 153 recordings from 764 patients, about 91.93% of whom were male, with an average age of 30.36 years). Firstly the features were extracted in time domain and time-frequency domain respectively, and reduced redundant features by feature dimensionality reduction. Then, we selected optimal features separately from the two feature spaces that performed best through feature selection. Next, the multi-feature fusion was completed through multi-scale dilated convolution, cooperative fusion, and channel attention mechanism. Finally, the fused features were fed into a bidirectional gated recurrent unit (BiGRU) network to heart sound segmentation results. Results The proposed method achieved precision, recall and F1 score of 96.70%, 96.99%, and 96.84% respectively. Conclusion The multi-feature fusion network proposed in this study has better heart sound segmentation performance, which can provide high-accuracy heart sound segmentation technology support for the design of automatic analysis of heart diseases based on heart sounds.

Objective:To understand the health needs of patients with non-dementia cognitive impairment after stroke, to provide reference for targeted interventions.Methods:Using the convergent mixed research method, convenience sampling was used to select post-stroke patients with non-dementia cognitive impairment in China-Japan Friendship Hospital and Beijing University of Chinese Medicine Third Affiliated Hospital, a cross-sectional survey was conducted on 191 patients with non-dementia cognitive impairment after stroke using the health needs questionnaire in March to August 2023. A descriptive study was used to conduct semi-structured interviews with 16 patients.Results:A total of 191 questionnaires were distributed and 191 valid questionnaires were collected, including 103 male and 88 female patients, aged from 34 to 90 years old. The items of the post-stroke health questionnaire were (3.47 ± 0.54), with the highest need for understanding the rehabilitation program (148/191); multiple linear regression analysis showed that gender and primary caregiver type were factors influencing their health needs ( t = 2.39, 2.73, both P<0.05). A total of 16 patients with non-dementia cognitive impairment after stroke, 10 males and 6 females, aged from 58 to 90 years old, were interviewed. Four themes were extracted, namely, information support and behavioral guidance needs, psychological care needs, social support needs, and pre-established medical care plan needs. Conclusions:The health needs of patients with non-dementia cognitive impairment after stroke are at an above medium level and have diversified characteristics. Medical staff should conduct systematic health management based on patients′specific conditions and actual needs to help patients recover or maintain cognitive function.

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.

Objective    To explore the application of Tsetlin Machine (TM) in heart beat classification. Methods    TM was used to classify the normal beats, premature ventricular contraction (PVC) and supraventricular premature beats (SPB) in the 2020 data set of China Physiological Signal Challenge. This data set consisted of the single-lead electro-cardiogram data of 10 patients with arrhythmia. One patient with atrial fibrillation was excluded, and finally data of the other 9 patients were included in this study. The classification results were then analyzed. Results    The classification results showed that the average recognition accuracy of TM was 84.3%, and the basis of classification could be shown by the bit pattern interpretation diagram. Conclusion    TM can explain the classification results when classifying heart beats. The reasonable interpretation of classification results can increase the reliability of the model and facilitate people's review and understanding.

bjective    To use machine learning technology to predict the recurrence of atrial fibrillation (AF) after radiofrequency ablation, and try to find the risk factors affecting postoperative recurrence. Methods    A total of 300 patients with valvular AF who underwent radiofrequency ablation in West China Hospital and its branch (Shangjin Hospital) from January 2017 to January 2021 were enrolled, including 129 males and 171 females with a mean age of 52.56 years. We built 5 machine learning models to predict AF recurrence, combined the 3 best performing models into a voting classifier, and made prediction again. Finally, risk factor analysis was performed using the SHApley Additive exPlanations method. Results    The voting classifier yielded a prediction accuracy rate of 75.0%, a recall rate of 61.0%, and an area under the receiver operating characteristic curve of 0.79. In addition, factors such as left atrial diameter, ejection fraction, and right atrial diameter were found to have an influence on postoperative recurrence. Conclusion    Machine learning-based prediction of recurrence of valvular AF after radiofrequency ablation can provide a certain reference for the clinical diagnosis of AF, and reduce the risk to patients due to ineffective ablation. According to the risk factors found in the study, it can provide patients with more personalized treatment.