Objective To propose a lightweight end-to-end neural network model for automated Korotkoff sound phase recognition and subsequent blood pressure (BP) measurement, aiming to improve measurement accuracy and population adaptability. Methods We developed a streamlined architecture integrating depthwise separable convolution (DSConv), multi-head attention (MHA), and bidirectional gated recurrent unit (BiGRU). The model directly processes Korotkoff sound time-series signals to identify auscultatory phases. Systolic BP (SBP) and diastolic BP (DBP) were determined using phase Ⅰ and phaseⅤdetections, respectively. Given the clinical relevance of phase Ⅳ for specific populations (e.g., children and pregnant women, denoted as DBPⅣ), BP values from this phase were also recorded.Results The study enrolled 106 volunteers with 70 males and 36 females at mean age of (40.0±12.0) years. The model achieved 94.25% phase recognition accuracy. Measurement errors were (0.1±2.5) mm Hg (SBP), (0.9±3.4) mm Hg (DBPⅣ), and (0.8±2.6) mm Hg (DBP). Conclusion Our method enables precise phase recognition and BP measurement, demonstrating potential for developing population-adaptive blood pressure monitoring systems.

Objective The objective of this study is to improve the accuracy of automatic identification in complex background herbal slice images.The goal is to achieve accurate recognition of herbal slice images in the presence of complex backgrounds.Methods The experiment was conducted on a collected and organized dataset of Tibetan herbal slice images.The RGB,HOG,and LBP features of the slices were analyzed.An improved HOG algorithm was used to fuse multiple features,and a deep learning network was utilized for image recognition.Results The proposed method of multi-feature fusion combined with deep learning achieved an identification accuracy of 91.68%on 3610 Tibetan herbal slice images with complex backgrounds.Furthermore,the average identification accuracy for 20 common traditional Chinese medicine slices,such as Chuan Beimu,Hawthorn,and Pinellia,reached 98.00%.This method outperformed existing methods for identifying herbal slices in complex backgrounds,indicating its feasibility and wide applicability for the identification of other traditional Chinese herbal medicines.Conclusion The fusion of multiple features effectively captures distinguishing characteristics of herbal slices in complex backgrounds.It exhibits high recognition rates for Tibetan herbal slices with complex and heavily occluded backgrounds,and can be successfully applied to the recognition of natural scene-based traditional Chinese herbal medicines and herbal slices.This approach shows promising prospects for practical applications.

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 investigate the safety and efficacy of laparoscopic simultaneous bilateral adrenalectomy in treating ectopic ACTH syndrome (ACTH)caused by medullary thyroid carcinoma(MTC).Methods:A 56-year-old male patient was admitted after MTC surgery and 7 months of general fatigue. The patient had a history of two open thyroid surgeries for medullary thyroid carcinoma, with previous pathological reports indicating lymph node metastasis in the upper mediastinum and mediastinum, accompanied by weak cytoplasmic expression of ACTH and negative CRH staining. After the operation, the patient developed diabetes, hypertension, and hypokalemia. Upon admission, the patient presented with a blood pressure reading of 200/95 mmHg (1 mmHg = 0.133 kPa), a weight of 61.5 kg, a height of 160 cm, a body mass index (BMI)of 24.02 kg/cm 2, and a waist circumference of 83 cm. Laboratory tests revealed the following: blood potassium level of 2.71 mmol/L, blood calcium level of 1.47 mmol/L, parathyroid hormone level of 6.0 pg/ml, fasting blood glucose level of 10.51 mmol/L, glycated hemoglobin level of 8.2%, blood calcitonin level exceeding 2 000 pg/ml, and blood CEA level of 70.8 μg/L. The plasma ACTH levels at 8∶00, 16∶00, and 24∶00 were 189.0, 125.0, and 65.0 pg/ml, respectively. Serum cortisol levels at 08∶00, 16∶00, and 24∶00 were 429.30, 408.14, and 446.61 μg/L, respectively. The 24-hour urine free cortisol measurement was 1 200 μg, and after the midnight 1mg dexamethasone suppression test at 8∶00, the plasma ACTH level was 183.0 pg/ml, and the serum cortisol level was 538.27 μg/L. The aldosterone level in standing position after 2 hours was 8.2 pg/ml. There were no significant abnormality in catecholamine hormone detection or thyroid function in blood and urine samples. An 18F-FDG-PET/CT examination showed multiple lymph node metastases in the neck, while an abdominal CT scan revealed bilateral adrenal hyperplasia. Enhanced MRI revealed pituitary gland thinning, and lung CT and sputum culture examinations showed scattered multiple lung infections. After a multidisciplinary discussion, the patient was diagnosed with EAS, postoperative MTC metastasis, diabetes, hypertension, hypokalemia, pulmonary infection, mild anemia, liver dysfunction, hypoparathyroidism, and hypocalcemia. The patient were accepted laparoscopic bilateral adrenalectomy via an abdominal approach under general anesthesia. The left adrenal gland was removed first, followed by the right adrenal gland after repositioning. Results:The surgery was successful with a surgical duration of approximately 60 minutes and an intraoperative bleeding volume of about 20 ml. No surgical complications occurred during the perioperative period. Pathological examination confirmed nodular hyperplasia of the adrenal cortex and bilateral adrenal medullary hyperplasia with negative ACTH staining. After a 3-month postoperative follow-up, blood calcitonin levels remained above 2000 pg/ml. The blood ACTH levels at 1 week, 1 month, and 3 months after surgery were 183.0, 220.0, and 731.0 pg/ml, respectively. However, hypertension, diabetes, and hypokalemia rapidly improved. One month after surgery, blood pressure was 100/80 mmHg, fasting blood glucose was 4.4 mmol/L, and blood potassium was 3.87 mmol/L. Pulmonary infection showed improvement, and no adrenal crisis occurred. Glucocorticoid replacement therapy consisted of 20 mg of hydrocortisone tablets in the morning and 10 mg in the afternoon, and thyroid hormone replacement therapy involved daily administration of 100 μg of levothyroxine. Genetic testing revealed heterozygous mutations in the Ret gene. The patient is currently undergoing clinical trial treatment with Ret inhibitors.Conclusions:Based on the data from this case and existing literature reports, laparoscopic simultaneous bilateral adrenalectomy might be safe and effective treatment option for EAS caused by unresectable MTC metastasis. It can correct hypertension, diabetes, and hypokalemia and increase the opportunity for MTC treatment.

The rapid development of digital intelligence technologies is providing a powerful boost to the high-quality development of the healthcare system.Considering the current state of our healthcare services and guided by General Secretary Xi Jinping's insights on new quality productive forces and the directives from Third Plenary Session of Communist Party of China's 20th Central Committee,the high-quality development of the healthcare service system should focus on digital intelligence technologies such as cloud computing,big data,privacy computing,blockchain,Internet of Things(IoT),mobile computing,and AI.The key measures should include the optimization of production factors,services,and governance.Emphasis should be placed on enhancing the efficient and intensive development of the development model,ensuring the high-quality and continuous integration of the supply model,and transitioning to scientific and modern management methods.Herein,we analyzed the"factor optimization—service optimization—governance optimization"development mechanism driven by digital intelligence and proposed corresponding implementation pathways,intending to provide references for establishing a high-quality and efficient healthcare service system with Chinese characteristics.

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 analyze the relationship between dietary and lifestyle inflammatory scores and metabolic syndrome, diabetes mellitus, cardiovascular disease, non-alcoholic fatty liver disease, tumor and other common metabolic diseases, and to explore the impact of dietary and lifestyle inflammatory potential on metabolic diseases, so as to provide new ideas for the diagnosis, treatment and prevention of metabolic diseases. Methods Databases such as CNKI, Wanfang , and PubMed were searched, and literatures related to the dietary and lifestyle inflammatory scores (DLIS) and metabolic diseases were reviewed . Results Seven articles showed that dietary and lifestyle inflammation scores had a positive correlation with metabolic diseases, and two articles showed that only lifestyle inflammatory scores had a positive correlation with metabolic diseases. Conclusion Dietary and lifestyle inflammatory scores may be positively correlated with metabolic diseases, but some results are still controversial. Further studies are needed to prove the correlation between DLIS and metabolic diseases.

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.

BACKGROUND: This study aimed to develop a comprehensive instrument for evaluating and ranking clinical practice guidelines, named Scientific, Transparent and Applicable Rankings tool (STAR), and test its reliability, validity, and usability. METHODS: This study set up a multidisciplinary working group including guideline methodologists, statisticians, journal editors, clinicians, and other experts. Scoping review, Delphi methods, and hierarchical analysis were used to develop the STAR tool. We evaluated the instrument's intrinsic and interrater reliability, content and criterion validity, and usability. RESULTS: STAR contained 39 items grouped into 11 domains. The mean intrinsic reliability of the domains, indicated by Cronbach's α coefficient, was 0.588 (95% confidence interval [CI]: 0.414, 0.762). Interrater reliability as assessed with Cohen's kappa coefficient was 0.774 (95% CI: 0.740, 0.807) for methodological evaluators and 0.618 (95% CI: 0.587, 0.648) for clinical evaluators. The overall content validity index was 0.905. Pearson's r correlation for criterion validity was 0.885 (95% CI: 0.804, 0.932). The mean usability score of the items was 4.6 and the median time spent to evaluate each guideline was 20 min. CONCLUSION The instrument performed well in terms of reliability, validity, and efficiency, and can be used for comprehensively evaluating and ranking guidelines.
Reproducibility of Results ; Surveys and Questionnaires ; Practice Guidelines as Topic ; Humans

Globally, gynecological malignancies are common types of female cancer and the main cause of cancer death among women. Cervical cancer, endometrial cancer and ovarian cancer, which are the main types of gynecological cancers, pose a significant threat to women's health worldwide. Studies have shown that diet plays an important role in the occurrence and development of gynecological cancers such as cervical cancer, endometrial cancer, and ovarian cancer, for which added sugar may be an influencing factor due to its food source characteristic and related biological effect. However, this paper reviewed the research progress on the relationship between consumption of added sugar and gynecological cancers such as endometrial cancer, ovarian cancer and cervical cancer, with a view to providing a reference for the active prevention of gynecological cancer.