Objective:To investigate the ultra-long-term antihypertensive efficacy, safety, major adverse events, and survival benefits of renal denervation (RDN) in patients with resistant hypertension (rHTN) and mild chronic kidney disease (CKD).Methods:This real-world, single-center retrospective study enrolled patients with rHTN and mild CKD who underwent RDN at Tianjin First Central Hospital between October 2011 and June 2016. Office blood pressure, home self-measured blood pressure, 24-hour ambulatory blood pressure, serum creatinine, estimated glomerular filtration rate, and urine albumin-to-creatinine ratio were collected at baseline and at 1, 5, and 13 years post-RDN. The total daily defined dose of antihypertensive medications at 13 years post-RDN was recorded, along with endpoint events during follow-up, including cardiovascular death, all-cause death, hospitalization for heart failure, myocardial infarction, and stroke. Patients were stratified according to CKD stage (G1-G2 vs. G3a) and baseline systolic blood pressure (mild-to-moderate vs. severe hypertension), and follow-up data were compared across subgroups.Results:A total of 40 patients were included, aged (51±15) years, including 26 (65%) males. At the 13-year follow-up, office systolic blood pressure (SBP) and diastolic blood pressure (DBP) decreased by (-32±20) mmHg and (-15±14) mmHg (1 mmHg=0.133 kPa), respectively; reductions in home self-measured blood pressure (SBP: (-25±14) mmHg, DBP: (-10±11) mmHg) and 24-hour ambulatory blood pressure (SBP: (-16±9 mmHg, DBP: (-10±6) mmHg) were also observed, alongside a reduction in the total daily defined dose of antihypertensive medications by (1.1±0.9) compared to baseline. Renal function assessments showed no significant differences at 13 years versus baseline in serum creatinine ((105±51) μmol/L vs. (96±22) μmol/L), estimated glomerular filtration rate ((72±22) ml·min -1·1.73 m -2 vs. (78±17) ml·min -1·1.73 m -2), or urine albumin-to-creatinine ratio ((101±86) mg/g vs. (127±82) mg/g) (all P>0.05). All-cause and cardiovascular mortality rates during follow-up were 13% (5/40) and 8% (3/40), respectively. Subgroup analysis results showed that, although CKD G1-G2 patients had smaller reductions in office SBP ((-31±20) mmHg vs. (-34±19) mmHg) and DBP ((-13±10) mmHg vs. (-25±18) mmHg) compared to G3a patients at 13 years, intergroup differences were not significant (all P>0.05). In contrast, severe hypertension subgroup exhibited greater reductions in office SBP ((-55±13) mmHg vs. (-20±10) mmHg) and DBP ((-24±17) mmHg vs. (-13±10) mmHg) versus mild-to-moderate hypertension subgroup (all P<0.05). Conclusion:RDN demonstrates sustained antihypertensive efficacy with favorable renal safety in rHTN patients with mild CKD. Patients with higher baseline systolic blood pressure may exhibit better responsiveness to RDN.

Hepatic encephalopathy and malnutrition due to hyperammonemia often interact with each other, forming a vicious circle in patients with cirrhosis. In addition, hepatic encephalopathy and malnutrition have a high incidence in patients with cirrhosis, which seriously affects the quality of life and prognosis. Therefore, identifying whether malnutrition is present in patients with cirrhosis combined with hepatic encephalopathy is crucial for providing appropriate interventions.This article reviews the pathogenesis, nutritional assessment methods, and nutritional management of malnutrition in patients with liver cirrhosis combined with hepatic encephalopathy.

Objective To propose a novel method for immunohistochemically positive cell counting based on the improved YOLOv5s.Methods Regarding the small target characteristics of positive cells,a small target detection layer was added to refine feature extraction.Then,a bidirectional weighted feature pyramid network was used to replace path aggregation network(PANet)in the neck network for realizing multi-scale feature fusion.Additionally,the method used coordinate attention mechanism to make the model pay more attention to small target characteristics,and replaced the original GIoU with EIoU loss function for enhancing the detection performance.Results The model was trained on the self-built immunohistochemical image dataset.The average accuracy of the improved model was 89.3%,which was 4.0%higher than the original model and surpassed mainstream target detection models.The 5-year survival prediction model constructed with the method achieved an average accuracy of 76.8%and an average area under the curve of 0.81,demonstrating its superior prediction ability.Conclusion The proposed model can quickly detect the number of immunohistochemically positive cells and effectively assist doctors in survival prediction.

Objective To propose a novel method for immunohistochemically positive cell counting based on the improved YOLOv5s.Methods Regarding the small target characteristics of positive cells,a small target detection layer was added to refine feature extraction.Then,a bidirectional weighted feature pyramid network was used to replace path aggregation network(PANet)in the neck network for realizing multi-scale feature fusion.Additionally,the method used coordinate attention mechanism to make the model pay more attention to small target characteristics,and replaced the original GIoU with EIoU loss function for enhancing the detection performance.Results The model was trained on the self-built immunohistochemical image dataset.The average accuracy of the improved model was 89.3%,which was 4.0%higher than the original model and surpassed mainstream target detection models.The 5-year survival prediction model constructed with the method achieved an average accuracy of 76.8%and an average area under the curve of 0.81,demonstrating its superior prediction ability.Conclusion The proposed model can quickly detect the number of immunohistochemically positive cells and effectively assist doctors in survival prediction.

Hepatic encephalopathy and malnutrition due to hyperammonemia often interact with each other, forming a vicious circle in patients with cirrhosis. In addition, hepatic encephalopathy and malnutrition have a high incidence in patients with cirrhosis, which seriously affects the quality of life and prognosis. Therefore, identifying whether malnutrition is present in patients with cirrhosis combined with hepatic encephalopathy is crucial for providing appropriate interventions.This article reviews the pathogenesis, nutritional assessment methods, and nutritional management of malnutrition in patients with liver cirrhosis combined with hepatic encephalopathy.

Objective:To investigate the ultra-long-term antihypertensive efficacy, safety, major adverse events, and survival benefits of renal denervation (RDN) in patients with resistant hypertension (rHTN) and mild chronic kidney disease (CKD).Methods:This real-world, single-center retrospective study enrolled patients with rHTN and mild CKD who underwent RDN at Tianjin First Central Hospital between October 2011 and June 2016. Office blood pressure, home self-measured blood pressure, 24-hour ambulatory blood pressure, serum creatinine, estimated glomerular filtration rate, and urine albumin-to-creatinine ratio were collected at baseline and at 1, 5, and 13 years post-RDN. The total daily defined dose of antihypertensive medications at 13 years post-RDN was recorded, along with endpoint events during follow-up, including cardiovascular death, all-cause death, hospitalization for heart failure, myocardial infarction, and stroke. Patients were stratified according to CKD stage (G1-G2 vs. G3a) and baseline systolic blood pressure (mild-to-moderate vs. severe hypertension), and follow-up data were compared across subgroups.Results:A total of 40 patients were included, aged (51±15) years, including 26 (65%) males. At the 13-year follow-up, office systolic blood pressure (SBP) and diastolic blood pressure (DBP) decreased by (-32±20) mmHg and (-15±14) mmHg (1 mmHg=0.133 kPa), respectively; reductions in home self-measured blood pressure (SBP: (-25±14) mmHg, DBP: (-10±11) mmHg) and 24-hour ambulatory blood pressure (SBP: (-16±9 mmHg, DBP: (-10±6) mmHg) were also observed, alongside a reduction in the total daily defined dose of antihypertensive medications by (1.1±0.9) compared to baseline. Renal function assessments showed no significant differences at 13 years versus baseline in serum creatinine ((105±51) μmol/L vs. (96±22) μmol/L), estimated glomerular filtration rate ((72±22) ml·min -1·1.73 m -2 vs. (78±17) ml·min -1·1.73 m -2), or urine albumin-to-creatinine ratio ((101±86) mg/g vs. (127±82) mg/g) (all P>0.05). All-cause and cardiovascular mortality rates during follow-up were 13% (5/40) and 8% (3/40), respectively. Subgroup analysis results showed that, although CKD G1-G2 patients had smaller reductions in office SBP ((-31±20) mmHg vs. (-34±19) mmHg) and DBP ((-13±10) mmHg vs. (-25±18) mmHg) compared to G3a patients at 13 years, intergroup differences were not significant (all P>0.05). In contrast, severe hypertension subgroup exhibited greater reductions in office SBP ((-55±13) mmHg vs. (-20±10) mmHg) and DBP ((-24±17) mmHg vs. (-13±10) mmHg) versus mild-to-moderate hypertension subgroup (all P<0.05). Conclusion:RDN demonstrates sustained antihypertensive efficacy with favorable renal safety in rHTN patients with mild CKD. Patients with higher baseline systolic blood pressure may exhibit better responsiveness to RDN.

A three-dimensional feature construction method based on spectral information is presented,in which the power values of each channel are arranged into two-dimensional feature vectors based on electrode positions.The different frequency band features are arranged into a three-dimensional integral feature tensor to extract the information in frequency domain.Meanwhile,in order to reduce the influence of volume conductor effect,functional connectivity is utilized to map the temporal electroencephalogram data to the spatial brain functional network for extracting the spatial information.By analyzing the relationship between features and target classes,a 3D-CNN-Attention network model is proposed to incorporate an Attention mechanism in 3D-CNN network to enhance the electroencephalogram feature learning capability.A series of comparative experiments on publicly available datasets show that 3D-CNN-Attention network framework outperforms other methods in depression detection,obtaining an accuracy rate of up to 96.32%.The proposed method provides an effective solution for depression detection.

Objective To research the clinical value of ultrasonic grey scale intensity in identifying the properties of pleural effusion.Methods A prospective study approach was used to collect data from patients who underwent puncture drainage due to clinical needs.We enrolled 120 patients for whom we performed routine ultrasonography and measured the ultrasonic grey scale intensity(echo intensity.EI)value.According to the clinical test results,pleural effusion was divided into exudate fluid,leakage fluid,malignant pleural effusion and benign pleural effusion.The subject operating characteristic curve(ROC curve)of the ultrasound intensity EI value was drawn,and the area under the curve and the optimal cut-off value was calculated.Results Of the 120 pleural effusions,there were 90 exudates[mean intensity EI value:(-46.55±6.35)],30 leaks[mean intensity EI value:(-55.51±5.30)],62 malignant pleural effusions[mean intensity EI value:(-47.24±5.37)],and 58 benign pleural effusions[mean intensity EI value:(-50.46±7.92)].The mean EI value of the exudate group was significantly higher than that of the leakage group(P＜0.05),and that of the benign pleural effusion group was lower than that of the malignant pleural effusion group(P＜0.05).ROC curve analysis revealed that the EI value had high accuracy in distinguishing exudate from lea-king fluid(the area under the curve is 0.856),and the optimal cut-off value was-50.95,with a sensitivity of 80.0％and speci-ficity of 83.3％.The area under the curve of the EI+TP+LDH value for distinguishing benign and malignant pleural effusion was 0.736,and the optimal cut-off was 89.10,with a sensitivity of 98.4％and a specificity of 46.6％.Conclusion The quanti-tative EI value of ultrasonic grey scale intensity has high diagnostic value in distinguishing pleural effusion from exudate or leak-age.The EI+TP+LDH value has a moderate ability to identify benign and malignant pleural effusion.

Objective:To investigate the feasibility and accuracy of computer vision-based artificial intelligence technology in detecting and recognizing instruments and organs in the scenario of radical laparoscopic gastrectomy for gastric cancer.Methods:Eight complete laparoscopic distal radical gastrectomy surgery videos were collected from four large tertiary hospitals in China (First Medical Center of Chinese PLA General Hospital [three cases], Liaoning Cancer Hospital [two cases], Liyang Branch of Jiangsu Province People's Hospital [two cases], and Fudan University Shanghai Cancer Center [one case]). PR software was used to extract frames every 5–10 seconds and convert them into image frames. To ensure quality, deduplication was performed manually to remove obvious duplication and blurred image frames. After conversion and deduplication, there were 3369 frame images with a resolution of 1,920×1,080 PPI. LabelMe was used for instance segmentation of the images into the following 23 categories: veins, arteries, sutures, needle holders, ultrasonic knives, suction devices, bleeding, colon, forceps, gallbladder, small gauze, Hem-o-lok, Hem-o-lok appliers, electrocautery hooks, small intestine, hepatogastric ligaments, liver, omentum, pancreas, spleen, surgical staplers, stomach, and trocars. The frame images were randomly allocated to training and validation sets in a 9:1 ratio. The YOLOv8 deep learning framework was used for model training and validation. Precision, recall, average precision (AP), and mean average precision (mAP) were used to evaluate detection and recognition accuracy.Results:The training set contained 3032 frame images comprising 30 895 instance segmentation counts across 23 categories. The validation set contained 337 frame images comprising 3407 instance segmentation counts. The YOLOv8m model was used for training. The loss curve of the training set showed a smooth gradual decrease in loss value as the number of iteration calculations increased. In the training set, the AP values of all 23 categories were above 0.90, with a mAP of 0.99, whereas in the validation set, the mAP of the 23 categories was 0.82. As to individual categories, the AP values for ultrasonic knives, needle holders, forceps, gallbladders, small pieces of gauze, and surgical staplers were 0.96, 0.94, 0.91, 0.91, 0.91, and 0.91, respectively. The model successfully inferred and applied to a 5-minutes video segment of laparoscopic gastroenterostomy suturing.Conclusion:The primary finding of this multicenter study is that computer vision can efficiently, accurately, and in real-time detect organs and instruments in various scenarios of radical laparoscopic gastrectomy for gastric cancer.

Objective:To investigate the feasibility and accuracy of computer vision-based artificial intelligence technology in detecting and recognizing instruments and organs in the scenario of radical laparoscopic gastrectomy for gastric cancer.Methods:Eight complete laparoscopic distal radical gastrectomy surgery videos were collected from four large tertiary hospitals in China (First Medical Center of Chinese PLA General Hospital [three cases], Liaoning Cancer Hospital [two cases], Liyang Branch of Jiangsu Province People's Hospital [two cases], and Fudan University Shanghai Cancer Center [one case]). PR software was used to extract frames every 5–10 seconds and convert them into image frames. To ensure quality, deduplication was performed manually to remove obvious duplication and blurred image frames. After conversion and deduplication, there were 3369 frame images with a resolution of 1,920×1,080 PPI. LabelMe was used for instance segmentation of the images into the following 23 categories: veins, arteries, sutures, needle holders, ultrasonic knives, suction devices, bleeding, colon, forceps, gallbladder, small gauze, Hem-o-lok, Hem-o-lok appliers, electrocautery hooks, small intestine, hepatogastric ligaments, liver, omentum, pancreas, spleen, surgical staplers, stomach, and trocars. The frame images were randomly allocated to training and validation sets in a 9:1 ratio. The YOLOv8 deep learning framework was used for model training and validation. Precision, recall, average precision (AP), and mean average precision (mAP) were used to evaluate detection and recognition accuracy.Results:The training set contained 3032 frame images comprising 30 895 instance segmentation counts across 23 categories. The validation set contained 337 frame images comprising 3407 instance segmentation counts. The YOLOv8m model was used for training. The loss curve of the training set showed a smooth gradual decrease in loss value as the number of iteration calculations increased. In the training set, the AP values of all 23 categories were above 0.90, with a mAP of 0.99, whereas in the validation set, the mAP of the 23 categories was 0.82. As to individual categories, the AP values for ultrasonic knives, needle holders, forceps, gallbladders, small pieces of gauze, and surgical staplers were 0.96, 0.94, 0.91, 0.91, 0.91, and 0.91, respectively. The model successfully inferred and applied to a 5-minutes video segment of laparoscopic gastroenterostomy suturing.Conclusion:The primary finding of this multicenter study is that computer vision can efficiently, accurately, and in real-time detect organs and instruments in various scenarios of radical laparoscopic gastrectomy for gastric cancer.