Objective To explore the predictive value of intratumor and peritumoral edema radiomics combined with the autoencoder algorithm for human epidermal growth factor receptor(HER-2)status in breast cancer to provide a new idea for preoperative noninvasive prediction of HER-2 status.Methods Totally 145 breast cancer patients from Yancheng Hospital Affiliated to Nanjing University Medical College(Center 1)and 52 ones from Jianhu Hospital Affiliated to Nantong University(Center 2)had their clinical and imaging data collected retrospectively,who were divided into a HER-2 positive group including 87 ones from Center 1 and 30 ones from Center 2 and a HER-2 negative group including 58 ones from Center 1 and 22 ones from Center 2.From December 2018 to October 2024 there were 78 patients with peritumoral edema from Center 1 randomly enrolled into a training set(55 patients)and a validation set(23 patients)in a ratio of 7∶3,and from November 2024 to March 2025 another 26 ones placed into a time validation set.The 52 patients with peritumoral edema from Center 2 were included into an external test set.Firstly,the Mazda software was used to delineate the regions of interest for the largest tumor layer and the peritumoral edema area.Secondly,multivariate analysis of variance(ANOVA),Kruskal-Wallis test,recursive feature elimination(RFE)and Relief algorithm were respectively employed to screen the radiomics features;finally,combined with ten-fold cross validation,the receiver operating characteristic curve was drawn,and the diagnostic efficacy of the models respectively constructed with radiomics parameters and ten types of machine learning algorithms,including auto encoder,support vector machine,linear discriminant analysis,random forest,Logistic regression,Logistic regression via Lasso,adaptive boosting,Gaussian process,native Bayes and decision tree,was evaluated for the HER-2 status in breast cancer.Results The model established by the auto encoder algorithm combined with three feature parameters including intratumor MaxNorm and Variance and peritumoral edema SumAverg behaved the best.The average AUC values of the training and validation sets were 0.808 and 0.735 resepctively,and the AUC values of the time validation and external test sets were 0.746 and 0.732 respectively.Conclusion The model developed with intratumor and peritumoral edema radiomics combined with the auto encoder algorithm can be used for preoperative noninvasive prediction of HER-2 status of breast cancer,which provides references for the preparation of individualized treatment scheme of breast cancer patients.[Chinese Medical Equipment Journal,2025,46(9):9-15]

Objective To explore the predictive value of intratumor and peritumoral edema radiomics combined with the autoencoder algorithm for human epidermal growth factor receptor(HER-2)status in breast cancer to provide a new idea for preoperative noninvasive prediction of HER-2 status.Methods Totally 145 breast cancer patients from Yancheng Hospital Affiliated to Nanjing University Medical College(Center 1)and 52 ones from Jianhu Hospital Affiliated to Nantong University(Center 2)had their clinical and imaging data collected retrospectively,who were divided into a HER-2 positive group including 87 ones from Center 1 and 30 ones from Center 2 and a HER-2 negative group including 58 ones from Center 1 and 22 ones from Center 2.From December 2018 to October 2024 there were 78 patients with peritumoral edema from Center 1 randomly enrolled into a training set(55 patients)and a validation set(23 patients)in a ratio of 7∶3,and from November 2024 to March 2025 another 26 ones placed into a time validation set.The 52 patients with peritumoral edema from Center 2 were included into an external test set.Firstly,the Mazda software was used to delineate the regions of interest for the largest tumor layer and the peritumoral edema area.Secondly,multivariate analysis of variance(ANOVA),Kruskal-Wallis test,recursive feature elimination(RFE)and Relief algorithm were respectively employed to screen the radiomics features;finally,combined with ten-fold cross validation,the receiver operating characteristic curve was drawn,and the diagnostic efficacy of the models respectively constructed with radiomics parameters and ten types of machine learning algorithms,including auto encoder,support vector machine,linear discriminant analysis,random forest,Logistic regression,Logistic regression via Lasso,adaptive boosting,Gaussian process,native Bayes and decision tree,was evaluated for the HER-2 status in breast cancer.Results The model established by the auto encoder algorithm combined with three feature parameters including intratumor MaxNorm and Variance and peritumoral edema SumAverg behaved the best.The average AUC values of the training and validation sets were 0.808 and 0.735 resepctively,and the AUC values of the time validation and external test sets were 0.746 and 0.732 respectively.Conclusion The model developed with intratumor and peritumoral edema radiomics combined with the auto encoder algorithm can be used for preoperative noninvasive prediction of HER-2 status of breast cancer,which provides references for the preparation of individualized treatment scheme of breast cancer patients.[Chinese Medical Equipment Journal,2025,46(9):9-15]

WRKY transcription factor is a type of transcription factor unique to plants and plays an important role in various physiological processes of plants. This study is based on the transcriptome data of Atractylodes lancea, the correlation between the FPKM values of the AlWRKY gene and the AlTPS gene of Atractylodes lancea was analyzed. Combined with the analysis results, the candidate gene AlWRKY65 with a significant positive correlation with the expression levels of AlTPS1 and AlTPS6 genes and a relatively high FPKM value was screened. The candidate gene was cloned to obtain the open reading frame ORF of the AlWRKY65 gene, and the related information of its encoded protein was analyzed and the gene expression was studied. The results showed that AlWRKY65 contains a 681 bp open reading frame and encoding 226 amino acids. Through amino acid sequence homology analysis, it was found that AlWRKY65 amino acid sequence had high homology with several plants such as HaWRKY65 and LsWRKY65; AlWRKY65 protein had a typical WRKYGQK domain, belonging to IIe subgroup of WRKY transcription factor family; phylogenetic analysis indicated that AlWRKY65 protein had the higher homology with CcWRKY65 protein; the expression of AlWRKY65 gene in different tissues of two producing areas of Atractylodes lancea were assayed via real-time fluorescence quantitative PCR, and the results showed that all of them were highly expressed in leaves and also has tissue differences. The expression level of AlWRKY65 gene was down-regulated within 48 h of methyl jasmonate (MeJA) induction; subcellular localization and transcriptional activation assay suggested that AlWRKY65 was located in the nucleus and had no transcriptional activation activity. This study provides a reference for further elucidating the biological function of AlWRKY65 in Atractylodes lancea.

Objective To design a remote diabetes management system based on dynamic blood glucose monitoring to solve the problems of traditional diabetes patient management in glucose data manual collection,unidirectional information flow and out-hospital glucose management.Methods A remote diabetes management system was developed with Java EE distributed microservices-based architecture and front-end and back-end separation mode,which used Vue for the front-end user interface design and IntelliJ IDEA development tools supporting Java language for the backend.The system developed was composed of a doctor App,a patient App and a background management terminal.The doctor App had three modules for user management,data viewing and intervention follow-up,the patient App had three modules for data monitoring,event recording and doctor-patient communication and the background management terminal had three modules for user management,data management and device management.Results The system developed realized individualized intervention and long-term glucose control based on real-time data acquisition of patient glucose fluctuation,diet,medication,exercise and other conditions.Conclusion The system developed can be used for the centralized online and offline management for in-hospital and out-hospital diabetes patients,which reduces the incidence of adverse events due to high or low blood glucose and improves the efficiency of medical staffs.[Chinese Medical Equipment Journal,2023,44(9):42-48]

OBJECTIVE: To develop a few-shot learning (FSL) approach for classifying optical coherence tomography (OCT) images in patients with inherited retinal disorders (IRDs). METHODS: In this study, an FSL model based on a student-teacher learning framework was designed to classify images. 2,317 images from 189 participants were included. Of these, 1,126 images revealed IRDs, 533 were normal samples, and 658 were control samples. RESULTS: The FSL model achieved a total accuracy of 0.974-0.983, total sensitivity of 0.934-0.957, total specificity of 0.984-0.990, and total F1 score of 0.935-0.957, which were superior to the total accuracy of the baseline model of 0.943-0.954, total sensitivity of 0.866-0.886, total specificity of 0.962-0.971, and total F1 score of 0.859-0.885. The performance of most subclassifications also exhibited advantages. Moreover, the FSL model had a higher area under curves (AUC) of the receiver operating characteristic (ROC) curves in most subclassifications. CONCLUSION This study demonstrates the effective use of the FSL model for the classification of OCT images from patients with IRDs, normal, and control participants with a smaller volume of data. The general principle and similar network architectures can also be applied to other retinal diseases with a low prevalence.
Humans ; Tomography, Optical Coherence ; Deep Learning ; Retinal Diseases/diagnostic imaging* ; Retina/diagnostic imaging* ; ROC Curve

Male ; Humans ; Urinary Bladder/diagnostic imaging* ; Prostate/diagnostic imaging* ; Multiparametric Magnetic Resonance Imaging ; Cystitis/diagnostic imaging* ; Hemorrhage/etiology* ; Urinary Bladder Neoplasms/complications*

Traditional Chinese medicine(TCM) has a long history and abundant experience in external therapy, which marks human wisdom. In the early history of human, people found that fumigation, coating, and sticking of some tree branches and herb stems can help alleviate scabies and remove parasites in productive labor, which indicates the emergence of external therapy. Pathogen usually enters the body through the surface, so external therapy can be used to treat the disease. External therapy is among the major characteristic of surgery of TCM. As one of the external therapies in TCM, external application to acupoints smooths the zang-fu organs through meridians and collaterals, thereby harmonizing yin and yang. This therapy emerged in the early society, formed the Spring and Autumn Period and the Warring States Period, improved in the Song and Ming dynasties, and matured in the Qing dynasty. With the efforts of experts in history, it has had a mature theory. According to modern research, it can avoid the first-pass effect of liver and the gastrointestinal irritation and improve the bioavailability of Chinese medicine. Based on the effect of Chinese medicine and the theory of meridian and collateral, it can stimulate the acupoints, exert regulatory effect on acupoints, and give full play to the efficacy of TCM and the interaction of the two. Thereby, it can regulate qi and blood and balance yin and yang, thus being widely used in the treatment of diseases. In this paper, the use of external application to acupoints, the effect on skin immunity, the regulation of neuro-inflammatory mechanism, the relationship between acupoint application and human circulation network, and the development of its dosage form were summarized through literature review. On this basis, this study is expected to lay a foundation for further research.
Humans ; Acupuncture Points ; Biological Availability ; Fumigation ; Medicine, Chinese Traditional ; Meridians

Objective: To investigate the feasibility and safety of extracorporeal membrane oxygenation (ECMO)-supported percutaneous coronary intervention (PCI) in chronic coronary total occlusion (CTO) patients with reduced left ventricular ejection fraction (LVEF). Methods: The CTO patients with LVEF≤35% and undergoing CTO-PCI assisted by ECMO in the General Hospital of Northern Theater Command from December 2018 to March 2022 were enrolled in this study. The post-procedure complications, changes of LVEF from pre-procedure to post-procedure during hospitalization, and the incidence of all-cause mortality and changes of LVEF after discharge were assessed. Results: A total of 17 patients aged (59.4±11.8) years were included. There were 14 males. The pre-procedure LVEF of these patients were (29.00±4.08)%. Coronary angiography results showed that there were 29 CTO lesions in these 17 patients. There was 1 in left main coronary artery, 7 in left anterior descending artery, 11 in left circumflex artery, and 10 in right coronary artery. ECMO was implanted in all patients before procedure. Among 25 CTO lesions attempted to cross, 24 CTO were successfully implanted with stents. All patients underwent successful PCI for at least one CTO lesion. The number of drug-eluting stents implantation per patient were 4.6±1.3. After procedure, there were 8 patients with hemoglobin decreased>20 g/L, and 1 patient with ECMO-access-site related bleeding. The LVEF value at a median duration of 2.5 (2.0-5.5) days after procedure significantly increased to (38.73±7.01)% (P<0.001 vs. baseline). There were no in-hospital deaths. Patients were followed up for 360 (120, 394) days after discharge, 3 patients died (3/17). The LVEF value was (41.80±7.32)% at 155 (100, 308) days after discharge, which was significantly higher than the baseline value (P<0.001). Conclusion: The results of present study demonstrate that it is feasible, efficient and safe to perform ECMO)-supported CTO-PCI in CTO patients with reduced LVEF.
Male ; Humans ; Stroke Volume ; Ventricular Function, Left ; Extracorporeal Membrane Oxygenation ; Percutaneous Coronary Intervention ; Heart ; Vascular Diseases

Objective: To investigate the feasibility and safety of extracorporeal membrane oxygenation (ECMO)-supported percutaneous coronary intervention (PCI) in chronic coronary total occlusion (CTO) patients with reduced left ventricular ejection fraction (LVEF). Methods: The CTO patients with LVEF≤35% and undergoing CTO-PCI assisted by ECMO in the General Hospital of Northern Theater Command from December 2018 to March 2022 were enrolled in this study. The post-procedure complications, changes of LVEF from pre-procedure to post-procedure during hospitalization, and the incidence of all-cause mortality and changes of LVEF after discharge were assessed. Results: A total of 17 patients aged (59.4±11.8) years were included. There were 14 males. The pre-procedure LVEF of these patients were (29.00±4.08)%. Coronary angiography results showed that there were 29 CTO lesions in these 17 patients. There was 1 in left main coronary artery, 7 in left anterior descending artery, 11 in left circumflex artery, and 10 in right coronary artery. ECMO was implanted in all patients before procedure. Among 25 CTO lesions attempted to cross, 24 CTO were successfully implanted with stents. All patients underwent successful PCI for at least one CTO lesion. The number of drug-eluting stents implantation per patient were 4.6±1.3. After procedure, there were 8 patients with hemoglobin decreased>20 g/L, and 1 patient with ECMO-access-site related bleeding. The LVEF value at a median duration of 2.5 (2.0-5.5) days after procedure significantly increased to (38.73±7.01)% (P<0.001 vs. baseline). There were no in-hospital deaths. Patients were followed up for 360 (120, 394) days after discharge, 3 patients died (3/17). The LVEF value was (41.80±7.32)% at 155 (100, 308) days after discharge, which was significantly higher than the baseline value (P<0.001). Conclusion: The results of present study demonstrate that it is feasible, efficient and safe to perform ECMO)-supported CTO-PCI in CTO patients with reduced LVEF.
Male ; Humans ; Stroke Volume ; Ventricular Function, Left ; Extracorporeal Membrane Oxygenation ; Percutaneous Coronary Intervention ; Heart ; Vascular Diseases

INTRODUCTION: Identifying peripheral arterial disease (PAD) during diabetic foot screening (DFS) is crucial in reducing the risk of diabetic foot ulcerations and lower limb amputations. Screening assessments commonly used include absolute systolic toe pressure (ASTP) and toe-brachial index (TBI). There is a lack of research defining the threshold values of both assessment methods. We aimed to compare the accuracy of ASTP and TBI and establish optimal threshold values of ASTP and TBI with reference to the internationally accepted ankle-brachial pressure index (ABPI) screening test, for a multiethnic diabetic population in Singapore. METHODS: A retrospective, observational study of DFS results from January 2017 to December 2017 was conducted. Receiver operating characteristic analysis was conducted for ASTP and TBI using the internationally accepted ABPI cut-off value of ≤0.9 to indicate PAD. RESULTS: A total of 1,454 patients with mean (standard deviation) age of 63.1 (12.4) years old were included. There were 50.8% men and 49.2% women, comprising 69.7% Chinese, 13.5% Indian, 10.1% Malay and 6.7% other ethnicities. Areas under the curve for ASTP and TBI were 0.89 (95% confidence interval [Cl] 0.85-0.94) and 0.94 (95% Cl 0.90-0.98), respectively, and the difference was statistically significant (P<0.001). Derived optimal threshold values to indicate ABPI≤0.9 for ASTP and TBI were <95.5mmHg (specificity 0.86, sensitivity 0.84) and <0.7 (specificity 0.89, sensitivity 0.95), respectively. CONCLUSION ASTP or TBI may be used to detect ABPI-determined PAD in DFS. The optimal threshold values derived from a multiethnic Asian diabetic population were <95.5mmHg for ASTP and <0.7 for TBI.
Ankle Brachial Index/methods* ; Diabetes Mellitus/epidemiology* ; Diabetic Foot/diagnosis* ; Female ; Humans ; Male ; Middle Aged ; Peripheral Arterial Disease/diagnosis* ; Retrospective Studies ; Toes