To address the limitations of the existing automatic electrocardiogram(ECG)diagnosis models in learning long-term dependencies,an automatic 12-lead long-term ECG signal diagnosis model which combines bidirectional selective state space model(bidirectional mamba,BiMamba)with residual multi-scale receptive field block(RMSF)is proposed:(1)designing a multi-scale receptive field module with residual connections to realize more extensive feature extraction and fusion;(2)introducing BiMamba block to enhance the model's temporal modeling capability by employing both forward and backward temporal processing;(3)using the classifier to process features from BiMamba for accomplishing multi-label ECG classification.Five major diagnostic categories from the PTB-XL dataset are extracted and subjected to 5-fold cross-validation experiments.The experimental results from the comparative study show that BiMamba-RMSF achieves an average accuracy of 89.42%,an average AUC of 0.9356,and an average F1 score of 72.85%,outperforming the other 4 automatic ECG diagnosis models.Additionally,ablation study further validates the effectiveness of BiMamba block.It is demonstrated that the proposed model has a high precision in the multi-label classification for 12-lead long-term ECG signals.

Objective:To explore the effects of deep hyperthermia on chemotherapy-related adverse effects and immune-inflammatory indicators in the patients undergoing postoperative adjuvant chemotherapy for colorectal cancer.Methods:This retrospective study included 52 patients who underwent surgery for colorectal cancer at the Affiliated Zhongshan Hospital of Dalian University from September 2021 to December 2023. The patients were divided into two groups based on treatment method: the combination group ( n=29) received postoperative adjuvant chemotherapy combined with deep hyperthermia, while the chemotherapy group ( n=23) received postoperative adjuvant chemotherapy alone. Both groups were treated with the XELOX regimen (oxaliplatin + capecitabine). The degree of bone marrow suppression during treatment was assessed by analyzing peripheral blood parameters, including hemoglobin, leukocyte count, neutrophil count, and platelet count. Immune-inflammatory indicators, including complement, procalcitonin (PCT), interleukin-6 (IL-6), systemic immune-inflammation index (SII), neutrophil-to-lymphocyte ratio (NLR), and platelet-to-lymphocyte ratio (PLR), were compared before and after treatment in both groups to evaluate the effects of deep hyperthermia on the immune-inflammatory response. Chi-square test or Fisher's exact test (two-tailed) was used to compare bone marrow suppression rates, and the immune-inflammatory indicators between the two groups were compared using t-tests or non-parametric tests, depending on whether the data conformed to a normal distribution. Results:In terms of myelosuppression, the incidence rates of moderate to severe decreases in leukocytes, neutrophils, platelets, and hemoglobin in the combination group were 31%, 31%, 21%, and 14%, respectively, compared to 52%, 61%, 48%, and 9% in the chemotherapy group. The change in PCT levels before and after treatment was significantly greater in the combination group than in the chemotherapy group ( P = 0.010). Both the combination group and the chemotherapy group showed significant reductions in SII, NLR and PLR after treatment, and the differences were statistically significant (all P < 0.05). The change in NLR before and after treatment was significantly greater in the combination group than in the chemotherapy group ( P = 0.031). Conclusions:Deep hyperthermia can alleviate chemotherapy-induced adverse effects such as thrombocytopenia and neutropenia in patients undergoing postoperative adjuvant chemotherapy for colorectal cancer. It also appears to improve the inflammatory response in these patients.

OBJECTIVES: To design a deep learning model that balances model complexity and performance to enable its integration into wearable ECG monitoring devices for automated diagnosis of atrial fibrillation. METHODS: This study was performed based on data from 84 patients with atrial fibrillation, 25 patients with atrial fibrillation, and 18 subjects without obvious arrhythmia collected from the publicly available datasets LTAFDB, AFDB, and NSRDB, respectively. A lightweight attention network based on depthwise separable convolution and fusion of channel-spatial information, namely DSC-AttNet, was proposed. Depthwise separable convolution was introduced to replace standard convolution and reduce model parameters and computational complexity to realize high efficiency and light weight of the model. The multilayer hybrid attention mechanism was embedded to compute the attentional weights of the channels and spatial information at different scales to improve the feature expression ability of the model. Ten-fold cross-validation was performed on LTAFDB, and external independent testing was conducted on AFDB and NSRDB datasets. RESULTS: DSC-AttNet achieved a ten-fold average accuracy of 97.33% and a precision of 97.30% on the test set, both of which outperformed the other 4 comparison models as well as the 3 classical models. The accuracy of the model on the external test set reached 92.78%, better than those of the 3 classical models. The number of parameters of DSC-AttNet was 1.01M, and the computational volume was 27.19G, both smaller than the 3 classical models. CONCLUSIONS This proposed method has a smaller complexity, achieves better classification performance, and has a better generalization ability for atrial fibrillation classification.
Atrial Fibrillation/diagnosis* ; Humans ; Electrocardiography ; Deep Learning ; Wearable Electronic Devices ; Neural Networks, Computer

Objective:To explore the effects of deep hyperthermia on chemotherapy-related adverse effects and immune-inflammatory indicators in the patients undergoing postoperative adjuvant chemotherapy for colorectal cancer.Methods:This retrospective study included 52 patients who underwent surgery for colorectal cancer at the Affiliated Zhongshan Hospital of Dalian University from September 2021 to December 2023. The patients were divided into two groups based on treatment method: the combination group ( n=29) received postoperative adjuvant chemotherapy combined with deep hyperthermia, while the chemotherapy group ( n=23) received postoperative adjuvant chemotherapy alone. Both groups were treated with the XELOX regimen (oxaliplatin + capecitabine). The degree of bone marrow suppression during treatment was assessed by analyzing peripheral blood parameters, including hemoglobin, leukocyte count, neutrophil count, and platelet count. Immune-inflammatory indicators, including complement, procalcitonin (PCT), interleukin-6 (IL-6), systemic immune-inflammation index (SII), neutrophil-to-lymphocyte ratio (NLR), and platelet-to-lymphocyte ratio (PLR), were compared before and after treatment in both groups to evaluate the effects of deep hyperthermia on the immune-inflammatory response. Chi-square test or Fisher's exact test (two-tailed) was used to compare bone marrow suppression rates, and the immune-inflammatory indicators between the two groups were compared using t-tests or non-parametric tests, depending on whether the data conformed to a normal distribution. Results:In terms of myelosuppression, the incidence rates of moderate to severe decreases in leukocytes, neutrophils, platelets, and hemoglobin in the combination group were 31%, 31%, 21%, and 14%, respectively, compared to 52%, 61%, 48%, and 9% in the chemotherapy group. The change in PCT levels before and after treatment was significantly greater in the combination group than in the chemotherapy group ( P = 0.010). Both the combination group and the chemotherapy group showed significant reductions in SII, NLR and PLR after treatment, and the differences were statistically significant (all P < 0.05). The change in NLR before and after treatment was significantly greater in the combination group than in the chemotherapy group ( P = 0.031). Conclusions:Deep hyperthermia can alleviate chemotherapy-induced adverse effects such as thrombocytopenia and neutropenia in patients undergoing postoperative adjuvant chemotherapy for colorectal cancer. It also appears to improve the inflammatory response in these patients.

To address the limitations of the existing automatic electrocardiogram(ECG)diagnosis models in learning long-term dependencies,an automatic 12-lead long-term ECG signal diagnosis model which combines bidirectional selective state space model(bidirectional mamba,BiMamba)with residual multi-scale receptive field block(RMSF)is proposed:(1)designing a multi-scale receptive field module with residual connections to realize more extensive feature extraction and fusion;(2)introducing BiMamba block to enhance the model's temporal modeling capability by employing both forward and backward temporal processing;(3)using the classifier to process features from BiMamba for accomplishing multi-label ECG classification.Five major diagnostic categories from the PTB-XL dataset are extracted and subjected to 5-fold cross-validation experiments.The experimental results from the comparative study show that BiMamba-RMSF achieves an average accuracy of 89.42%,an average AUC of 0.9356,and an average F1 score of 72.85%,outperforming the other 4 automatic ECG diagnosis models.Additionally,ablation study further validates the effectiveness of BiMamba block.It is demonstrated that the proposed model has a high precision in the multi-label classification for 12-lead long-term ECG signals.

BACKGROUND: The therapeutic potential of exosomes from human umbilical cord mesenchymal stem cells (HUMSCsExo) for delivering specific circular RNAs (circRNAs) in treating premature ovarian failure (POF) is not well understood.This study aimed to explore the efficacy of HUMSCs-Exo in delivering hsa_circ_0002021 for POF treatment, focusing on its effects on granulosa cell (GC) senescence and ovarian function. METHODS: Bioinformatic analysis was conducted on circRNA profiles using the GSE97193 dataset from GEO, targeting granulosa cells from varied age groups. To simulate granulosa cell senescence, KGN cells were treated with cyclophosphamide (CTX). HUMSCs were transfected with pcDNA 3.1 vectors to overexpress hsa_circ_0002021, and the HUMSCsExo secreted were isolated. These exosomes were characterized by transmission electron microscopy (TEM) and Western blotting to confirm exosomal markers CD9 and CD63. Co-culture of these exosomes with CTX-treated KGN cells was performed to assess b-galactosidase activity, oxidative stress markers, ROS levels, and apoptosis via flow cytometry.Interaction between hsa_circ_0002021, microRNA-125a-5p (miR-125a-5p), and cyclin-dependent kinase 6 (CDK6) was investigated using dual-luciferase assays and RNA immunoprecipitation (RIP). A POF mouse model was induced with CTX, treated with HUMSCs-Exo, and analyzed histologically and via immunofluorescence staining. Gene expression was quantified using RT-qPCR and Western blot. RESULTS: hsa_circ_0002021 was under expressed in both in vivo and in vitro POF models and was effectively delivered by HUMSCs-Exo to KGN cells, showing a capability to reduce GC senescence. Overexpression of hsa_circ_0002021 in HUMSCs-Exo significantly enhanced these anti-senescence effects. This circRNA acts as a competitive adsorbent of miR-125a-5p, regulating CDK6 expression, which is crucial in modulating cell cycle and apoptosis. Enhanced expression of hsa_circ_0002021 in HUMSCs-Exo ameliorated GC senescence in vitro and improved ovarian function in POF models by modulating oxidative stress and cellular senescence markers. CONCLUSION This study confirms that hsa_circ_0002021, when delivered through HUMSCs-Exo, can significantly mitigate GC senescence and restore ovarian function in POF models. These findings provide new insights into the molecular mechanisms of POF and highlight the therapeutic potential of circRNA-enriched exosomes in treating ovarian aging and dysfunction.

Objective To develop a method for accurate identification of multiscale carotid plaques in ultrasound images.Methods We proposed a two-stage carotid plaque detection method based on deep convolutional neural network(SM-YOLO).A series of algorithms such as median filtering,histogram equalization,and Gamma transformation were used to preprocess the dataset to improve image quality.In the first stage of the model construction,a candidate plaque set was built based on the YOLOX_l target detection network,using multiscale image training and multiscale image prediction strategies to accommodate carotid artery plaques of different shapes and sizes.In the second stage,the Histogram of Oriented Gradient(HOG)features and Local Binary Pattern(LBP)features were extracted and fused,and a Support Vector Machine(SVM)classifier was used to screen the candidate plaque set to obtain the final detection results.This model was compared quantitatively and visually with several target detection models(YOLOX_l,SSD,EfficientDet,YOLOV5_l,Faster R-CNN).Results SM-YOLO achieved a recall of 89.44%,an accuracy of 90.96%,a F1-Score of 90.19%,and an AP of 92.70%on the test set,outperforming other models in all performance indicators and visual effects.The constructed model had a much shorter detection time than the Faster R-CNN model(only one third of that of the latter),thus meeting the requirements of real-time detection.Conclusion The proposed carotid artery plaque detection method has good performance for accurate identification of carotid plaques in ultrasound images.

ObjectiveTo evaluate the effect and safety of Jiuxin Pill （救心丸） on exercise tolerance and quality of life in patients with stable angina pectoris （SAP）. MethodsA randomised， double-blind， placebo-controlled， multicentre study design was used to enroll 170 patients of SAP from nine centres， which were divided into 85 patients each in the trial group and control group with 1∶1 ratio. Both groups maintained the original western medicine treatment plan， and added Jiuxin Pill or placebo respectively， 2 pills （0.05 g） each time twicely for 28 days. The main outcomes were total exercise time （TED） in the exercise treadmill test and Seattle Angina Questionnaire （SAQ） scores including physical limitation （PL）， angina stability （AS）， angina frequency （AF）， treatment satisfaction （TS）， and disease perception （DP）. The secondary outcomes were exercise treadmill test indicators including heart rate recovery in 1 min （HRR1）， metabolic equivalents （METs）， maximum magnitude of ST-segment depression， and the Borg rating of perceived exertion scale， the average number of angina attacks per week， withdrawal and reduction rate of nitroglycerin， traditional Chinese medicine syndrome scores， incidence of major adverse cardiovascular events. Safety indicators were evaluated and the occurrence of adverse events during the trial was recorded. Data was collected before treatment， day 28±2 in treatment period， and follow-up at day 56 which is 28±2 days after treatment period finished. ResultsEighty-four and eighty-five patients respectively from trial group and control group were included to the full analysis set （FAS） and safety analysis set （SS）. Compared with the group before treatment and with the control group after treatment， the trial group had higher TED， HRR1， and METs， and lower maximum magnitude of ST-segment depression and Borg rating of perceived exertion scores after treatment （P＜0.01）. Compared with the group before treatment and with the control group after treatment and at follow-up， the total SAQ score and scores of AS， AF， TS and DP of the trial group after treatment and at follow-up elevated， while the average number of angina attacks per week and traditional Chinese medicine syndrome scores reduced （P＜0.01）. There was no statistically significant difference in the withdrawal and reduction rate of nitroglycerin between groups （P＞0.05）. Major adverse cardiovascular events occurred in 1 case （1/84， 1.19%） in the trial group and 1 case （1/85， 1.18%） in the control group， and the difference between groups was not statistically significant （P＞0.05）. A total of 3 cases of adverse events occurred in the trial group （3/84， 3.57%）， and a total of 6 cases of adverse events occurred in the control group （6/85， 7.06%）， and there was no statistically significant difference in the incidence of adverse events between groups （P＞0.05）. ConclusionIn the treatment of SAP， Jiuxin Pill combined with conventional western medicine can further enhance exercise tolerance， improve quality of life， and demonstrate great safety.

Objective To develop a method for accurate identification of multiscale carotid plaques in ultrasound images.Methods We proposed a two-stage carotid plaque detection method based on deep convolutional neural network(SM-YOLO).A series of algorithms such as median filtering,histogram equalization,and Gamma transformation were used to preprocess the dataset to improve image quality.In the first stage of the model construction,a candidate plaque set was built based on the YOLOX_l target detection network,using multiscale image training and multiscale image prediction strategies to accommodate carotid artery plaques of different shapes and sizes.In the second stage,the Histogram of Oriented Gradient(HOG)features and Local Binary Pattern(LBP)features were extracted and fused,and a Support Vector Machine(SVM)classifier was used to screen the candidate plaque set to obtain the final detection results.This model was compared quantitatively and visually with several target detection models(YOLOX_l,SSD,EfficientDet,YOLOV5_l,Faster R-CNN).Results SM-YOLO achieved a recall of 89.44%,an accuracy of 90.96%,a F1-Score of 90.19%,and an AP of 92.70%on the test set,outperforming other models in all performance indicators and visual effects.The constructed model had a much shorter detection time than the Faster R-CNN model(only one third of that of the latter),thus meeting the requirements of real-time detection.Conclusion The proposed carotid artery plaque detection method has good performance for accurate identification of carotid plaques in ultrasound images.

OBJECTIVE: To develop a noninvasive method for prediction of 1p/19q codeletion in diffuse lower-grade glioma (DLGG) based on multimodal magnetic resonance imaging (MRI) radiomics. METHODS: We collected MRI data from 104 patients with pathologically confirmed DLGG between October, 2015 and September, 2022. A total of 535 radiomics features were extracted from T₂WI, T₁WI, FLAIR, CE-T₁WI and DWI, including 70 morphological features, 90 first order features, and 375 texture features. We constructed logistic regression (LR), logistic regression least absolute shrinkage and selection operator (LRlasso), support vector machine (SVM) and Linear Discriminant Analysis (LDA) radiomics models and compared their predictive performance after 10-fold cross validation. The MRI images were reviewed by two radiologists independently for predicting the 1p/19q status. Receiver operating characteristic curves were used to evaluate classification performance of the radiomics models and the radiologists. RESULTS: The 4 radiomics models (LR, LRlasso, SVM and LDA) achieved similar area under the curve (AUC) in the validation dataset (0.833, 0.819, 0.824 and 0.819, respectively; P>0.1), and their predictive performance was all superior to that of resident physicians of radiology (AUC=0.645, P=0.011, 0.022, 0.016, 0.030, respectively) and similar to that of attending physicians of radiology (AUC=0.838, P>0.05). CONCLUSION Multiparametric MRI radiomics models show good performance for noninvasive prediction of 1p/19q codeletion status in patients with in diffuse lower-grade glioma.
Humans ; Magnetic Resonance Imaging ; Chromosome Aberrations ; Area Under Curve ; Glioma/genetics* ; ROC Curve