BACKGROUND: Hypertension is a serious chronic disease that can significantly lead to various cardiovascular diseases, affecting vital organs such as the heart, brain, and kidneys. Our goal is to predict the risk of new onset hypertension using machine learning algorithms and identify the characteristics of patients with new onset hypertension. METHODS: We analyzed data from the 2011 China Health and Nutrition Survey cohort of individuals who were not hypertensive at baseline and had follow-up results available for prediction by 2015. We tested and evaluated the performance of four traditional machine learning algorithms commonly used in epidemiological studies: Logistic Regression, Support Vector Machine, XGBoost, LightGBM, and two deep learning algorithms: TabNet and AMFormer model. We modeled using 16 and 29 features, respectively. SHAP values were applied to select key features associated with new onset hypertension. RESULTS: A total of 4,982 participants were included in the analysis, of whom 1,017 developed hypertension during the 4-year follow-up. Among the 16-feature models, Logistic Regression had the highest AUC of 0.784(0.775∼0.806). In the 29-feature prediction models, AMFormer performed the best with an AUC of 0.802(0.795∼0.820), and also scored the highest in MCC (0.417, 95%CI: 0.400∼0.434) and F1 (0.503, 95%CI: 0.484∼0.505) metrics, demonstrating superior overall performance compared to the other models. Additionally, key features selected based on the AMFormer, such as age, province, waist circumference, urban or rural location, education level, employment status, weight, WHR, and BMI, played significant roles. CONCLUSION We used the AMFormer model for the first time in predicting new onset hypertension and achieved the best results among the six algorithms tested. Key features associated with new onset hypertension can be determined through this algorithm. The practice of machine learning algorithms can further enhance the predictive efficacy of diseases and identify risk factors for diseases.
Humans ; China/epidemiology* ; Hypertension/diagnosis* ; Machine Learning ; Male ; Female ; Middle Aged ; Adult ; Nutrition Surveys ; Algorithms ; Aged ; Risk Factors

Objective:At present,the doctor-patient relationship is tense.The prevalence of negative emotions,such as depression and anxiety,among healthcare workers is increasing every year.Negative attitudes of medical workers toward mental problems may aggravate the doctor-patient conflict and psychological problems of medical workers.This study aims to explore the complex network relationships between outpatient medical workers'attitudes toward mental problems,doctor-patient relationships,and their depression/anxiety levels. Methods:A total of 578 outpatient medical staff from the Second Xiangya Hospital of Central South University(167 males,411 females)completed questionnaires on their attitudes toward mental problems,doctor-patient relationships,and depression/anxiety symptoms.Network analysis was conducted separately to construct the"attitude towards mental problems-doctor-patient relationship network"and"depression-anxiety related network". Results:The edge between"M15(insulting words)"and"D8(waste time)"showed the strongest strength in the"attitude towards mental problems-doctor-patient relationship network",and"M15(insulting words)"had the highest bridge strength in the network.For the analysis of emotional variables,"P1(anhedonia)"showed the most obvious association with"D10(communication difficulties)"in the doctor-patient relationship and"M2(poor quality of life)"in the psychiatric attitudes,and"P1(anhedonia)"was the key bridge symptom in the network. Conclusion:The"insulting words"may be an intervention target for medical workers'attitudes toward mental problems.The"anhedonia"in depression is the potential symptom that needs to be treated.Intervention targeting these variables may be beneficial to improve the mental health level of medical workers and the doctor-patient relationship.

Objective:To evaluate the safety and efficacy of rubber band and clip facilitated endoscopic submucosal dissection (RAC-ESD) for colorectal neoplasms.Methods:A retrospective cohort study was performed. Clinical data of 115 patients with colorectal neoplasm receiving ESD from September 2018 to August 2019 were retrospectively analyzed. Thirty-four patients received RAC-ESD treatment (RAC-ESD group) and 81 received conventional ESD treatment (conventional ESD group). The procedure time, the dissected area per minute during ESD, en bloc resection rate, complete resection rate, curative resection rate, complication occurence and recurrence rate were compared between the two groups.Results:The median specimen area of RAC-ESD group was 6.32 (7.53) cm 2, and the median procedure time was 40.0 (55.0) min. The mean dissected area per minute was 0.14 (0.20) cm 2/min. While in conventional ESD group, the median specimen area was 4.71 (5.02) cm 2, the median procedure time was 50.0 (50.0) min and the mean dissected area per minute was 0.09 (0.07) cm 2/min. The median specimen area of RAC-ESD group was slightly larger and the median procedure time was slightly shorter than those of conventional ESD group, but neither was significantly different(both P>0.05). The median dissected area per minute of RAC-ESD group was significantly larger than that of the conventional ESD group ( P=0.008). The en bloc resection rate, complete resection rate and curative resection rate of RAC-ESD group were 100.0% (34/34), 100.0% (34/34) and 97.1% (33/34), while those of the conventional ESD group were 100.0%(81/81), 96.3%(78/81) and 91.4%(74/81), respectively. There was no ESD-related complication in either group. After 10.0±5.5 months of follow-up, there was no local recurrence in both groups. Conclusion:RAC-ESD may increase resection efficacy with safety.

Objective:To assess the effectiveness and safety of endoscopic submucosal dissection (ESD) in the treatment of early esophagogastric junction (EGJ) cancer and precancerous lesion.Methods:Clinical data of 67 patients with Siewert type Ⅱ early EGJ cancer or precancerous lesion who underwent ESD at Endoscopy Center of Peking University First Hospital from July 2012 to June 2019 were retrospectively analyzed. Clinical and pathological features, technical data and complication rate were reviewed. The factors that may affect the curative resection were analyzed.Results:Among the 67 cases, 5 were protruding type, 59 flat type, and 3 depressed type. The median lesion diameter was 1.6 ( QR: 1.8) cm, the median operation time was 60.0 ( QR: 56.0) min. The en bloc resection rate was 97.0% (65/67), the complete resection rate was 91.0% (61/67), and the curative resection rate was 82.1% (55/67). Factors related to non-curative resection were tumor size ( OR=8.457, 95% CI: 1.227-58.302, P=0.030) and pathological type ( OR=15.133, 95% CI: 1.518-150.870, P=0.021). ESD-related complications occurred in 3 cases (4.5%), including 1 case of delayed hemorrhage who received endoscopic hemostasis therapy, and 2 cases of post-operative cicatricial stricture who then received endoscopic dilation. Fifty-eight patients were followed up, and recurrence was found in 1 patient during follow-up with positive vertical margin who refused subsequent therapy.Metachronous early gastric cancer was found in another patient during follow-up, who was treated with a second ESD. Conclusion:ESD is a safe, effective and less invasive technique for early EGJ cancer and precancerous lesion. Tumor size, boundary and infiltration depth of the lesion should be accurately evaluated before operation to formulate appropriate treatment strategies.

Objective:To assess rapid on-line evaluation (ROLE) of endoscopic ultrasound-guided fine needle aspiration (EUS-FNA) for pancreatic masses.Methods:Data of patients with solid pancreatic masses who underwent EUS-FNA in Peking University First Hospital from October 2017 to October 2019 were retrospectively analyzed. Patients were divided into the ROLE group and the control group. The number of FNA passes in ROLE group was decided by the cytopathologist based on the number of pancreatic tissue cells or heteromorphic cells obtained, while that in the control group was decided by the endoscopy physician according to the visual observation of tissue strips. The cytological and histological diagnosis of EUS-FNA specimen were made by another cytopathologist. The gold standard for final diagnosis was based on the histological diagnosis of surgically resected specimens. For patients who did not undergo surgical treatment, the final diagnosis was made based on the clinical course, imaging, tumor markers and feedback on treatment. The diagnostic yield, the accuracy, the sensitivity, the specificity, FNA passes, puncture time and adverse events were compared between the two groups.Results:A total of 87 patients were enrolled, 51 in the ROLE group and 36 in the control group. The diagnostic yield of the ROLE group was higher than that of the control group without significant difference [98.0% (50/51) VS 86.1%(31/36), P=0.078]. The number of FNA passes in the ROLE group was significantly less than that in the control group (median 2 VS 3, P<0.001). No significant difference in mean FNA puncture time was found between the ROLE group and the control group (19.4 min VS 18.5 min, P=0.089). There were no significant differences between the two groups with regard to the diagnostic yield, the sensitivity, the specificity, the positive predictive value, the negative predictive value or the incidence of adverse events. Conclusion:ROLE of EUS-FNA for pancreatic solid tumor may improve tissue acquisition for puncture, reduce the number of FNA passes, and may not significantly increase the procedure time and risk of puncture.

Objective: To evaluate the short-term and long-term efficacy of endoscopic submucosal dissection (ESD) in the treatment of early low rectal cancer and precancerous lesions. Methods: Inclusion criteria: (1) Distance from the lower margin of tumor to the anal was ≤ 5 cm. (2) Early low rectal cancers were any size rectal epithelial tumors with infiltration depth limited to the mucosa and submucosa, which were diagnosed by postoperative pathology as high-grade intraepithelial neoplasia or adenocarcinoma of the rectum with infiltration depth of intramucosal or submucosal cancer (M or SM stage). (3) Precancerous lesions included adenoma and low-grade intraepithelial neoplasia of the rectum. (4) Patients received ESD treatment. Patients with tumor invasion depth over submucosa by pathology were excluded. From January 2008 to January 2018, 63 patients meeting the above criteria in Peking University First Hospital were enrolled in this descriptive cohort study. The disease characteristics, clinical manifestations, pathological types, treatment time, hospitalization time, en bloc resection rate (resection of the whole lesion), complete resection rate (both the horizontal and vertical incision margins were negative), postoperative complications and follow-up results were analyzed. Cummulative survival rate was calculated by Kaplan-Meier. Results: The diameter of the lesion was (29.0±23.4) mm and the distance from the lesion to the anus was (2.7±1.8) cm. The median operation time was 45.0 (range, 10.0 to 360.0) minutes, the median hospitalization time was 3.0 (range, 2.0 to 12.0) days, en bloc resection rate was 100%, complete resection rate was 96.8% (61/63), and 1 case (1.6%) had postoperative bleeding. The follow-up rate was 87.3% (55/63) and the median follow-up time was 57.9 (range, 15.6 to 121.1) months. No local recurrence was found during the follow-up period and the 5-year survival rate was 100%. Conclusion Short- and long-term efficacy of ESD are quite good in the treatment of patients with early low rectal cancer and precancerous lesions.

Objective To evaluate the short?term and long?term efficacy of endoscopic submucosal dissection (ESD) in the treatment of early low rectal cancer and precancerous lesions. Methods Inclusion criteria: (1) Distance from the lower margin of tumor to the anal was ≤5 cm. (2) Early low rectal cancers were any size rectal epithelial tumors with infiltration depth limited to the mucosa and submucosa, which were diagnosed by postoperative pathology as high?grade intraepithelial neoplasia or adenocarcinoma of the rectum with infiltration depth of intramucosal or submucosal cancer (M or SM stage). (3) Precancerous lesions included adenoma and low?grade intraepithelial neoplasia of the rectum. (4) Patients received ESD treatment. Patients with tumor invasion depth over submucosa by pathology were excluded. From January 2008 to January 2018, 63 patients meeting the above criteria in Peking University First Hospital were enrolled in this descriptive cohort study. The disease characteristics, clinical manifestations, pathological types, treatment time, hospitalization time, en bloc resection rate (resection of the whole lesion), complete resection rate (both the horizontal and vertical incision margins were negative), postoperative complications and follow?up results were analyzed. Cummulative survival rate was calculated by Kaplan?Meier. Results The diameter of the lesion was (29.0 ± 23.4) mm and the distance from the lesion to the anus was (2.7±1.8) cm. The median operation time was 45.0 (range, 10.0 to 360.0) minutes, the median hospitalization time was 3.0 (range, 2.0 to 12.0) days, en bloc resection rate was 100%, complete resection rate was 96.8% (61/63), and 1 case (1.6%) had postoperative bleeding. The follow?up rate was 87.3% (55/63) and the median follow?up time was 57.9 (range, 15.6 to 121.1) months. No local recurrence was found during the follow?up period and the 5?year survival rate was 100%. Conclusion Short?and long?term efficacy of ESD are quite good in the treatment of patients with early low rectal cancer and precancerous lesions.

Objective To evaluate the short?term and long?term efficacy of endoscopic submucosal dissection (ESD) in the treatment of early low rectal cancer and precancerous lesions. Methods Inclusion criteria: (1) Distance from the lower margin of tumor to the anal was ≤5 cm. (2) Early low rectal cancers were any size rectal epithelial tumors with infiltration depth limited to the mucosa and submucosa, which were diagnosed by postoperative pathology as high?grade intraepithelial neoplasia or adenocarcinoma of the rectum with infiltration depth of intramucosal or submucosal cancer (M or SM stage). (3) Precancerous lesions included adenoma and low?grade intraepithelial neoplasia of the rectum. (4) Patients received ESD treatment. Patients with tumor invasion depth over submucosa by pathology were excluded. From January 2008 to January 2018, 63 patients meeting the above criteria in Peking University First Hospital were enrolled in this descriptive cohort study. The disease characteristics, clinical manifestations, pathological types, treatment time, hospitalization time, en bloc resection rate (resection of the whole lesion), complete resection rate (both the horizontal and vertical incision margins were negative), postoperative complications and follow?up results were analyzed. Cummulative survival rate was calculated by Kaplan?Meier. Results The diameter of the lesion was (29.0 ± 23.4) mm and the distance from the lesion to the anus was (2.7±1.8) cm. The median operation time was 45.0 (range, 10.0 to 360.0) minutes, the median hospitalization time was 3.0 (range, 2.0 to 12.0) days, en bloc resection rate was 100%, complete resection rate was 96.8% (61/63), and 1 case (1.6%) had postoperative bleeding. The follow?up rate was 87.3% (55/63) and the median follow?up time was 57.9 (range, 15.6 to 121.1) months. No local recurrence was found during the follow?up period and the 5?year survival rate was 100%. Conclusion Short?and long?term efficacy of ESD are quite good in the treatment of patients with early low rectal cancer and precancerous lesions.

Objective To evaluate the accuracy in placement of cervical anterior transpedicular screws (ATPS) under the guidance of our modified drilling template.Methods Eight wet cadaveric specimens of adult cervical spine,4 male and 4 female ones,were used for this experiment.Data of CT thin layer scanning of the cervical specimens in DICOM format were imported into software Mimics 17.0.After 3D models of the cervical vertebrae were reconstructed,the optimal trajectory was designed for ATPS placement in the transparent mode of the 3D models.Normal and our modified drilling templates for ATPS placement were designed and manufactured by 3D printing.The 2 kinds of drilling templates were used to assist ATPS placement onto one cervical vertebra,with laterality randomized.Altogether 64 pieces of ATPS were placed,with 32 ones for each drilling template.Postoperative CT scanning was conducted to evaluate the accuracy in ATPS placement.The 2 kinds of ATPS template were compared in terms of the deviations between actual and ideal trajectories in direction (caudal-angle and extroversive-angle) and position (X and Y axes) of the entry point.Results Our modified drilling template led to one screw penetrating the pedicle cortical bone while the normal drilling template led to 4 screws penetrating the pedicle cortical bone,yielding an accuracy rate of 96.9％ and of 87.5％ respectively.The extroversive-angle deviation (0.72°±0.69°),caudal-angle deviation (0.91°±0.70°),X axis shift (0.53 ±0.40 mm) and Y axis shift (0.54 ±0.42 mm) related to the modified template were all significantly smaller than those related to the normal template (1.16° ± 0.70°,1.49°±0.68°,0.88±0.40mm,1.22±0.42mm,respectively) (P ＜0.05).Conclusion Compared with a normal ATPS template,our modified drilling template for ATPS may be advantageous in better fitness,greater stability,increased accuracy in screw placement,and protection of adjacent discs.

OBJECTIVETo analyze the clinical efficacy of endoscopic therapy for early colorectal cancer.

METHODSClinical data of 113 early colorectal mucosal carcinoma or submucosal carcinoma receiving endoscopic therapy were retrospectively analyzed and compared with 39 early colorectal cancer cases receiving surgery during the same time.

RESULTSAll the cases were well-moderately differentiated adenocarcinoma. Size of tumors in endoscopic group was (26.2±21.5) mm, and that was (30.9±24.3) mm in surgery group (P=0.257). Baseline data between the two groups were not significantly different (all P>0.05). Significantly shorter median operating time [15.0 minutes vs. 203.0 minutes, χ=69.322, P=0.000] and median hospital stay [3.0 days vs. 17.0 days, χ=76.180, P=0.000] were observed in endoscopic group compared with surgery group. The en bloc resection rate, curative resection rate, lymph node metastatic rate and complication rate were not significantly different between two groups (all P>0.05). Ten patients in endoscopic group were referred to additional surgery for deep invasion and/or incomplete resection, of whom 7 received radical surgery, and the other 3 cases without radical surgery did not develop recurrence during follow-up of (20.5±0.9) months. After follow-up for (17.5±15.8) months, the local recurrence rate was 5.3% (6/113) in endoscopic group and 0 (0/39) in surgery group without significant difference (χ=0.983, P=0.321). There was no significant difference in 5-year tumor-free survival rate between two groups (91.8% vs. 97.0%, χ=1.533, P=0.216).

CONCLUSIONEndoscopic therapy possesses shorter operating time, shorter hospital stay and similar efficacy as compared to surgery in the treatment of early colorectal cancer.