Background::Acute pulmonary embolism (APE) is a fatal cardiovascular disease, yet missed diagnosis and misdiagnosis often occur due to non-specific symptoms and signs. A simple, objective technique will help clinicians make a quick and precise diagnosis. In population studies, machine learning (ML) plays a critical role in characterizing cardiovascular risks, predicting outcomes, and identifying biomarkers. This work sought to develop an ML model for helping APE diagnosis and compare it against current clinical probability assessment models.Methods::This is a single-center retrospective study. Patients with suspected APE were continuously enrolled and randomly divided into two groups including training and testing sets. A total of 8 ML models, including random forest (RF), Na?ve Bayes, decision tree, K-nearest neighbors, logistic regression, multi-layer perceptron, support vector machine, and gradient boosting decision tree were developed based on the training set to diagnose APE. Thereafter, the model with the best diagnostic performance was selected and evaluated against the current clinical assessment strategies, including the Wells score, revised Geneva score, and Years algorithm. Eventually, the ML model was internally validated to assess the diagnostic performance using receiver operating characteristic (ROC) analysis.Results::The ML models were constructed using eight clinical features, including D-dimer, cardiac troponin T (cTNT), arterial oxygen saturation, heart rate, chest pain, lower limb pain, hemoptysis, and chronic heart failure. Among eight ML models, the RF model achieved the best performance with the highest area under the curve (AUC) (AUC = 0.774). Compared to the current clinical assessment strategies, the RF model outperformed the Wells score ( P = 0.030) and was not inferior to any other clinical probability assessment strategy. The AUC of the RF model for diagnosing APE onset in internal validation set was 0.726. Conclusions::Based on RF algorithm, a novel prediction model was finally constructed for APE diagnosis. When compared to the current clinical assessment strategies, the RF model achieved better diagnostic efficacy and accuracy. Therefore, the ML algorithm can be a useful tool in assisting with the diagnosis of APE.

Objective To evaluate the effect of parasternal intercostal plane block(PIB)on postopera-tive fatigue in elderly patients undergoing off-pump coronary artery bypass grafting(CABG).Methods A to-tal of 111 elderly patients undergoing elective off-pump CABG in Xuzhou Municipal Central Hospital from May 2021 to January 2023 were selected as the study subjects.The patients were divided into the control group(group C,n=55)and PIB group(group P,n=56)by adopting the random number table method.After induction of anesthesia,the patients in the group P received the ultrasound-guided bilateral PIB,and the group C received the equal volume of normal saline at the same site.The incidence rate of postoperative fatigue syn-drome(POFS)on postoperative 1,3,5,7 d and postoperative 8 weeks,NRS scores immediately after extuba-tion and at postoperative 12,24,48 h,postoperative opioid drugs consumption,ICU stay duration,hospitaliza-tion duration and adverse events occurrence were compared between the two groups.Results Compared with the group C,the incidence rates of POFS on postoperative 1,3,5,7 d and postoperative 8 weeks in the group P were significantly decreased,the NRS scores immediately after extubation and at postoperative 12,24 h in the group P were lower,the postoperative opioid drugs consumption were smaller,the ICU stay duration was shorter,and the differences were statistically significant(P＜0.05).The NRS score at postoperative 48 h and hospitalization duration had no statistical differences between the two groups(P＞0.05).No nerve block re-lated adverse events in the patients appeared during the study period.Conclusion The ultrasound guided PIB could effectively reduce the incidence rate of POFS in elderly patients undergoing off-pump CABG,promote the patients'prognosis and improve the recovery quality of the patients.

Objective:To observe the expression of S100A8 in plasma exosomes, microvesicles (MV), plasma and vitreous in patients with diabetic retinopathy (DR), and verify it in a diabetic rat model, and to preliminarily explore its role in the occurrence and development of DR.Methods:A case-control study. From September 2018 to December 2019, a total of 73 patients with type 2 diabetes, hospitalized patients undergoing vitrectomy, and healthy physical examinations in the Tianjin Medical University Eye Hospital were included in the study. Among them, plasma were collected from 32 patients and vitreous fluid were collected from 41 patients, which were divided into plasma sample research cohort and vitreous sample research cohort. The subjects were divided into simple diabetes group (DM group), non-proliferative DR group (NPDR group) and proliferative DR group (PDR group) without fundus changes; healthy subjects were regarded as normal control group (NC group). In the study cohort of vitreous samples, the control group was the vitreous humor of patients with epimacular membrane or macular hole. Plasma exosomes and microvesicles (MVs) were separated using ultracentrifugation. Transmission electron microscopy, nanometer particle size analyzer and Western blot (WB) were used to characterize exosomes and MVs. The mass concentration of S100A8 was determined by enzymelinked immunosorbent assay. Eighteen healthy male Brown Norway rats were divided into normal control group and diabetic group with 9 rats in each group by random number table method. The rats of diabetes group were induced by streptozotocin to establish diabetic model. Five months after modeling, immunohistochemical staining and WB were used to detect the expression of S100A8 in the retina of rats in the normal control group and the diabetes group. t test was used for the comparison of measurement data between the two groups. Single-factor analysis of variance were used for the comparison of multiple groups of measurement data.parison of measurement data between the two groups. Single-factor analysis of variance were used for the comparison of multiple groups of measurement data. Results:Exosomes and MVs with their own characteristics were successfully separated from plasma. The concentrations of plasma exosomes and vitreous S100A8 in the PDR group were higher than those in the NPDR group, DM group, NC group, and the difference was statistically significant ( P=0.039, 0.020, 0.002, 0.002, P<0.000,<0.000). In the plasma sample cohort study, It was not statistically significant that the overall comparison of the S100A8 mass concentrations of plasma and plasma MV in the four groups of subjects ( F=0.283, 0.015; P=0.836, 0.996). Immunohistochemical staining showed that retinal ganglion cells, bipolar cells, cone rod cells and vascular endothelial cells in the diabetic group all expressed S100A8 protein. Compared with the normal control group, the expression level of S100A8 in the retina of the diabetic group increased, and the difference was statistically significant ( t=8.028, P=0.001). Conclusions:The level of S100A8 protein in circulating exosomes increases significantly with the severity of DR in patients with type 2 diabetes. S100A8 may be an influential factor in the inflammatory environment of DR and a potential anti-inflammatory therapeutic target.

Objective:To investigate the risk factors for anastomotic leakage after laparo-scopic lower anterior resection (LAR) of rectal cancer, and the application value of its risk assess-ment scoring model.Methods:The retrospective case-control study was conducted. The clinico-pathological data of 539 patients who underwent laparoscopic LAR of rectal cancer in 13 medical centers, including 248 cases in Renji Hospital of Shanghai Jiaotong University School of Medicine, 35 cases in Ningbo First Hospital, 35 cases in Changzhou Second People's Hospital, 32 cases in the First People's Hospital of Nantong, 32 cases in Linyi People's Hospital, 31 cases in Changzhou Wujin People's Hospital, 28 cases in Jiading District Hospital of Traditional Chinese Medicine, 27 cases in the First Hospital of Taizhou, 26 cases in Shanghai Pudong Gongli Hospital, 21 cases in the People's Hospital of Rugao, 11 cases in Central Hospital of Fengxian District, 7 cases in Ningbo Hangzhou Bay Hospital and 6 cases in Jiangsu jianhu People's Hospital, from January 2016 to November 2020 were collected. There were 157 males and 382 females, aged (62.7±0.5)years. Observation indicators: (1) follow-up; (2) risk factors for anastomotic leakage after laparoscopic LAR; (3) establishment of risk assessment scoring model for anastomotic leakage after laparoscopic LAR. Follow-up was conducted by outpatient examination or telephone interview. Patients were followed up at 1 week after discharge or 1 month after the operation to detect the anastomotic leakage. Measurement data with normal distribution were represented as Mean± SD, and measurement data with skewed distribution were represented as M(range). Count data were represented as absolute numbers or percentages, and comparison between groups was analyzed using the chi-square test. Univariate analysis was conducted using the chi-square test and multivariate analysis was conducted usong the Logistic regression model. The area under curve of receiver operating characteristic curve was used to estimate the efficiency of detecton methods. The maximum value of the Youden index was defined as the best cut-off value. Results:(1) Follow-up: 539 patients were followed up at postoperative 1 week and 1 month. During the follow-up, 79 patient had anastomotic leakage, with an incidence of 14.66%(79/539). Of the 79 patients, 39 cases were cured after conservative treatment, 40 cases were cured after reoperation (ileostomy or colostomy). (2) Risk factors for anastomotic leakage after laparoscopic LAR. Results of univariate analysis showed that sex, age, body mass index, smoking and/or drinking, tumor diameter, diabetes mellitus, hemoglobin, albumin, grade of American Society of Anesthesio-logists (ASA), neoadjuvant chemoradiotherapy, distance from anastomotic level to dentate line, the number of pelvic stapler, reinforced anastomosis, volume of intraoperative blood loss, placement of decompression tube, preservation of left colic artery, operation time and professional doctors were related factors for anastomotic leakage after laparoscopic LAR ( χ2=14.060, 4.387, 5.039, 4.094, 17.488, 33.485, 25.066, 28.959, 34.973, 34.207, 22.076, 13.208, 16.440, 17.708, 17.260, 4.573, 5.919, 5.389, P<0.05). Results of multivariate analysis showed that male, tumor diameter ≥3.5 cm, diabetes mellitus, hemoglobin <90 g/L, albumin <30 g/L, grade of ASA ≥Ⅲ, neoadjuvant chemoradiotherapy, distance from anastomotic level to dentate line <1 cm, the number of pelvic stapler ≥3, non-reinforced anastomosis, volume of intraoperative blood loss ≥100 mL and no placement of decom-pression tube were independent risk factors for anastomotic leakage after laparoscopic LAR ( odds ratio=2.864,3.043,12.556,7.178,8.425,12.895,8.987,4.002,3.084,4.393,3.266,3.224,95% confidence interval as 1.279?6.411, 1.404?6.594, 4.469?35.274, 2.648?19.459, 2.471?28.733, 4.027?41.289, 3.702?21.777, 1.746?9.171, 1.365?6.966, 1.914?10.083, 1.434?7.441, 1.321?7.867, P<0.05). (3) Establishment of risk assessment scoring model for anastomotic leakage after laparoscopic LAR. based on the results of univariate analysis, clinicopathological factors with χ2>20, χ2>10 and ≤20 or χ2≤10 were defined as scoring of 3, 2, 1, respectively. The cumulative clinicopatho-logical factors scoring ≥6 was defined as an effective evaluating indicator for postoperative anastomotic leakage. The risk assessment scoring model (6-321) for anastomotic leakage after laparoscopic LAR was established. The cumulative value ≥6 indicated high incidence of anastomotic leakage, and the cumulative value <6 indicated low incidence of anastomotic leakage. Conclusions:Male, tumor diameter ≥3.5 cm, diabetes mellitus, hemoglobin <90 g/L, albumin <30 g/L, grade of ASA ≥Ⅲ, neo-adjuvant chemoradiotherapy, distance from anastomotic level to dentate line <1 cm, the number of pelvic stapler ≥3, non-reinforced anastomosis, volume of intraoperative blood loss ≥100 mL and no placement of decompression tube are independent risk factors for anastomotic leakage after laparoscopic LAR. The risk assessment scoring model (6-321) is established according to the above results.The cumulative value ≥6 indicates high incidence of anastomotic leakage and the cumulative value <6 indicates low incidence of anastomotic leakage.

As a promising method in artificial intelligence, deep learning has been proven successful in several domains ranging from acoustics and images to natural language processing. With medical imaging becoming an important part of disease screening and diagnosis, deep learning-based approaches have emerged as powerful techniques in medical image areas. In this process, feature representations are learned directly and automatically from data, leading to remarkable breakthroughs in the medical field. Deep learning has been widely applied in medical imaging for improved image analysis. This paper reviews the major deep learning techniques in this time of rapid evolution and summarizes some of its key contributions and state-of-the-art outcomes. The topics include classification, detection, and segmentation tasks on medical image analysis with respect to pulmonary medical images, datasets, and benchmarks. A comprehensive overview of these methods implemented on various lung diseases consisting of pulmonary nodule diseases, pulmonary embolism, pneumonia, and interstitial lung disease is also provided. Lastly, the application of deep learning techniques to the medical image and an analysis of their future challenges and potential directions are discussed.

Objective: To evaluate the performance of a convolutional neural network (CNN) model that can automatically detect and classify rib fractures, and output structured reports from computed tomography (CT) images. Materials and Methods: This study included 1079 patients (median age, 55 years; men, 718) from three hospitals, between January 2011 and January 2019, who were divided into a monocentric training set (n = 876; median age, 55 years; men, 582), five multicenter/multiparameter validation sets (n = 173; median age, 59 years; men, 118) with different slice thicknesses and image pixels, and a normal control set (n = 30; median age, 53 years; men, 18). Three classifications (fresh, healing, and old fracture) combined with fracture location (corresponding CT layers) were detected automatically and delivered in a structured report. Precision, recall, and F1-score were selected as metrics to measure the optimum CNN model. Detection/diagnosis time, precision, and sensitivity were employed to compare the diagnostic efficiency of the structured report and that of experienced radiologists. Results: A total of 25054 annotations (fresh fracture, 10089; healing fracture, 10922; old fracture, 4043) were labelled for training (18584) and validation (6470). The detection efficiency was higher for fresh fractures and healing fractures than for old fractures (F1-scores, 0.849, 0.856, 0.770, respectively, p = 0.023 for each), and the robustness of the model was good in the five multicenter/multiparameter validation sets (all mean F1-scores > 0.8 except validation set 5 [512 x 512 pixels; F1-score = 0.757]). The precision of the five radiologists improved from 80.3% to 91.1%, and the sensitivity increased from 62.4% to 86.3% with artificial intelligence-assisted diagnosis. On average, the diagnosis time of the radiologists was reduced by 73.9 seconds. Conclusion Our CNN model for automatic rib fracture detection could assist radiologists in improving diagnostic efficiency, reducing diagnosis time and radiologists’ workload.

Objective: To identify predictors of pulmonary fibrosis development by combining follow-up thin-section CT findings and clinical features in patients discharged after treatment for COVID-19. Materials and Methods: This retrospective study involved 32 confirmed COVID-19 patients who were divided into two groups according to the evidence of fibrosis on their latest follow-up CT imaging. Clinical data and CT imaging features of all the patients in different stages were collected and analyzed for comparison. Results: The latest follow-up CT imaging showed fibrosis in 14 patients (male, 12; female, 2) and no fibrosis in 18 patients (male, 10; female, 8). Compared with the non-fibrosis group, the fibrosis group was older (median age: 54.0 years vs. 37.0 years, p = 0.008), and the median levels of C-reactive protein (53.4 mg/L vs. 10.0 mg/L, p = 0.002) and interleukin-6 (79.7 pg/L vs. 11.2 pg/L, p = 0.04) were also higher. The fibrosis group had a longer-term of hospitalization (19.5 days vs. 10.0 days, p = 0.001), pulsed steroid therapy (11.0 days vs. 5.0 days, p < 0.001), and antiviral therapy (12.0 days vs. 6.5 days, p = 0.012). More patients on the worst-state CT scan had an irregular interface (59.4% vs. 34.4%, p = 0.045) and a parenchymal band (71.9% vs. 28.1%, p < 0.001). On initial CT imaging, the irregular interface (57.1%) and parenchymal band (50.0%) were more common in the fibrosis group. On the worst-state CT imaging, interstitial thickening (78.6%), air bronchogram (57.1%), irregular interface (85.7%), coarse reticular pattern (28.6%), parenchymal band (92.9%), and pleural effusion (42.9%) were more common in the fibrosis group. Conclusion Fibrosis was more likely to develop in patients with severe clinical conditions, especially in patients with highinflammatory indicators. Interstitial thickening, irregular interface, coarse reticular pattern, and parenchymal band manifested in the process of the disease may be predictors of pulmonary fibrosis. Irregular interface and parenchymal band could predict the formation of pulmonary fibrosis early.

Objective:To explore the significance of multimodal monitoring in the monitoring and treatment of neurocritical care patients.Methods:104 neurocritical care patients admitted to the department of Critical Care Medicine of Fujian Provincial Hospital from March 2019 to January 2020 were enrolled. Patients were randomly assigned into two groups, with 52 in each group. In the routine monitoring treatment group, heart rate, blood pressure, respiratory rate and the changes in consciousness and pupils were monitored after operation. The patients were treated with routine medicine to reduce intracranial pressure (ICP), maintain proper cerebral perfusion pressure (CPP), balance fluid intake and output, and maintain the airway clear. Patients in the multimodal monitoring treatment group were treated with invasive ICP monitoring, ultrasound to assess brain structure, ultrasound to measure optic nerve sheath diameter (ONSD), transcranial color doppler (TCCD), internal jugular venous blood oxygen saturation monitoring, near-infrared spectroscopy (NIRS), non-invasive cerebral blood oxygen saturation monitoring and quantitative electroencephalogram monitoring. According to the monitoring results, the patients were given targeted treatment with the goal of controlling ICP and improving brain metabolism. The length of intensive care unit (ICU) stay, the incidences of neurological complications (secondary cerebral infarction, cerebral hemorrhage, high intracranial pressure, etc.), and the incidences of poor prognosis [6 months after the onset of Glasgow outcome score (GOS) 1 to 3] were compared between the two groups. Spearman rank correlation analysis of the correlation between invasive ICP and the ICP value which was calculated by TCCD. The receiver operating characteristic (ROC) curve of invasive ICP and pulsatility index of middle cerebral artery (PI MCA) were used to predict poor prognosis. Results:The length of ICU stay in the multimodal monitoring treatment group was significantly shorter than that of the routine monitoring treatment group (days: 6.27±3.81 vs. 9.61±5.09, P < 0.01), and the incidence of neurological complications was significantly lower than that in the routine monitoring treatment group (9.62% vs. 25.00%, P < 0.05). In the multimodal monitoring treatment group, 37 cases had a good prognosis and 15 cases had a poor prognosis, while the routine monitoring treatment group had a good prognosis in 27 cases and a poor prognosis in 25 cases. The incidence of poor prognosis in the multimodal monitoring treatment group was lower than that of the routine monitoring treatment group (28.85% vs. 48.08%, P < 0.05). In the multimodal monitoring treatment group, the invasive ICP and PI MCA of patients with good prognosis were significantly lower than those of patients with poor prognosis [invasive ICP (mmHg, 1 mmHg = 0.133 kPa): 16 (12, 17) vs. 22 (20, 24), PI MCA: 0.90±0.33 vs. 1.39±0.58, both P < 0.01]. There was no significant difference in resistance index of the middle cerebral artery (RI MCA) between the good prognosis group and the poor prognosis group (0.63±0.12 vs. 0.66±0.15, P > 0.05). There was a positive correlation between the invasive ICP and the ICP value which was calculated by TCCD ( r = 0.767, P < 0.001). ROC curve analysis showed that the area under ROC curve (AUC) of invasive ICP for poor prognosis prediction was 0.906, the best cut-off value was ≥ 18 mmHg, the sensitivity was 86.49%, and the specificity was 86.67%. The AUC of PI MCA for poor prognosis prediction was 0.759, the best cut-off value was ≥ 1.12, the sensitivity was 81.08%, and the specificity was 60.00%. The AUC of invasive ICP was greater than PI MCA ( Z = 2.279, P = 0.023). Conclusion:Comprehensive analysis of multimodal monitoring indicators for neurocritical care patients to guide clinical treatment can reduce the length of hospital stay, and reduce the risk of neurosurgery complications and disability; invasive ICP can predict poor prognosis of neurocritical care patients.

BACKGROUND:Neural stem cel s have multi-directional differentiation potential, self-sustaining and self-renewal capacity as wel as have strong migration ability. Bushen Huoxue Recipe can reduce neuronal damage and promote nerve cel regeneration, to achieve neural function reconstruction. Underlying mechanisms of Bushen Huoxue Recipe combined with neural stem cel transplantation in rats with tinnitus induced by sodium salicylate are yet unclear. OBJECTIVE:To investigate the effects of Bushen Huoxue Recipe combined with neural stem cel transplantation in rats with tinnitus induced by sodium salicylate. METHODS:Sixty Sprague-Dawley rats were randomized into five groups (n=12):normal control group, tinnitus model group, Bushen Huoxue Recipe group, stem cel group and combined treatment group (Bushen Huoxue Recipe combined with neural stem cel transplantation). Animal models of tinnitus induced by sodium salicylate were made in al the groups except for the normal control group. Fifteen days after modeling, rats were given intragastric administration of Bushen Huoxue Recipe water decoction (3 mL, 2.592 g/mL) for consecutive 7 days in the Bushen Huoxue Recipe group, intravenous injection of neural stem cel s (1 mL, 1.0×109/L) in the stem cel group, or their combined treatment in the combined treatment group. RESULTS AND CONCLUSION:Bushen Huoxue Recipe, neural stem cel transplantation and their combination al could effectively promote the recovery of drinking water inhibitory rate that was ranked as fol ows:combined treatment group

Objective To investigate the effects of recombinant human erythropoietin βinjection on levels of superoxide dismutase ( SOD ) , glutathione peroxidase ( GSH-PX ) , malondialdehyde ( MDA ) and homocysteine ( Hcy ) in patients with diabetic peritoneal dialysis.Methods 92 patients of parallel peritoneal dialysis in diabetic nephropathy who received therapy from September 2014 to September 2016 in our hospital were selected and randomly divided into the observation group and the control group with 46 cases in each group.The control group was treated with peritoneal dialysis routine treatment, while the observation group was treated with recombinant human erythropoietin βinjection on this basis.The levels of hemoglobin (Hb), hematocrit (Hct), renal function, SOD, GSH-PX, MDA and Hcy were compared.Results After treatment, the levels of Hb and Hct in the observation group were higher than the control group, the difference was statistically significant (P<0.05), the urinary albumin excretion rate (UAER) and serum creatinine (SCr) in the observation group were lower than the control group, the difference was statistically significant (P<0.05), the levels of SOD and GSH-PX in the observation group were higher than the control group, the levels of MDA and Hcy were lower the control group, the difference was statistically significant (P<0.05).Conclusion The effect of recombinant human erythropoietin βinjection on diabetic nephropathy patients with peritoneal dialysis was significant, which could improve the levels of SOD, GSH-PX, MDA and Hcy.