WSWeixuan Sheng

Weixuan Sheng

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Weixuan Sheng has a total of 29 co-authors. Here are the top co-authors by number of shared publications:

  • Xianshi Tang

    Key Laboratory of National Health Commission on Parasitic Disease Control and Prevention, Key Laboratory of Jiangsu Province on Parasite and Vector Control Technology, Jiangsu Institute of Parasitic Diseases, Wuxi, China

    3 shared publications
  • Aizhu Liu

    Department of Otolaryngology Head and Neck Surgery, Capital Medical University Affiliated Beijing Shijitan Hospital, Beijing, China

    2 shared publications
  • Aizhu Liu

    Department of Otolaryngology Head and Neck Surgery, Capital Medical University Affiliated Beijing Shijitan Hospital

    1 shared publication
  • Dong-Xin Wang

    Peking University First Hospital

    1 shared publication
  • Guang Yang

    Department of Anesthesiology, Beijing Shijitan Hospital, Capital Medical University, Beijing, China

    1 shared publication
  • Haijing Zhang

    Education Department of Capital Medical University Affiliated Beijing Shijitan Hospital

    1 shared publication

Latest Publications

  • Open Access

    Development and Validation of Machine-Learning-Based Prediction Models for Thyroid Diseases During Pregnancy

    by Guang Yang, Yi Gao, Pengfei Liu, Jingwen Jiang, Hui Qiao, Weixuan Sheng

    Development and Validation of Machine-Learning-Based Prediction Models for Thyroid Diseases During Pregnancy - Article abstract #953235

  • Open Access

    Time-series analysis of pollen concentration effects on allergic conjunctivitis healthcare visits in Beijing, 2023–2024

    by Aizhu Liu, Lei Cheng, Haijing Zhang, Rui Zhang, Xianshi Tang, Weixuan Sheng

    Objective: To analyze the lagged effects of pollen concentration on allergic conjunctivitis (AC) healthcare visits and investigate the influence of environmental factors and pathogen infections on AC risk. Methods: Daily AC outpatient and emergency cases from Beijing Shijitan Hospital, along with concurrent meteorological and pollen concentration data from March 1 to October 31 in 2023–2024, were collected. Spearman rank correlation analysis, generalized additive models (GAM), and distributed lag non-linear models (DLNM) were employed to plot lag-response curves for specific cumulative effects and incremental cumulative effects of relative risks. Results: AC visits significantly increased during spring and autumn, closely aligning with peak pollen concentrations (April in spring, September in autumn). Spearman correlation analysis revealed a strong positive association between pollen concentration and AC visits (2023: r = 0.599; 2024: r = 0.637), while meteorological factors (including temperature, air pressure, etc.) showed weaker correlations. Lagged effect analysis demonstrated that the AC lag effect associated with pollen exposure in 2024 was significantly stronger than in 2023, displaying a strict dose-response relationship with pollen concentration levels. The peak value increase from baseline in relative risk (RR) for specific cumulative effects was 2.6 times higher (0.0018 in 2024 vs. 0.0007 in 2023), with a 1.9-fold longer lag duration (28 days vs. 15 days). For incremental cumulative effects, the time to peak doubled (day 28 in 2024 vs. day 15 in 2023), and the lag duration exceeded 50 days in 2024 (vs. 27 days in 2023). The lag-response curve exhibited biphasic peaks in 2024, contrasting with the unimodal pattern in 2023. Conclusion: This study confirms that pollen concentration is the dominant factor affecting the lagged effects of AC visits, with a clear dose-response relationship. The findings provide a scientific basis for AC prevention strategies and public health early-warning systems.

  • Open Access

    Development of a machine learning algorithm model to predict intraoperative hypotension in elderly patients undergoing thoracic and abdominal surgeries

    by Yifan An, Pengfei Liu, Lei Liu, Xiaoyun Hu, Hui Qiao, Weixuan Sheng

    Objectives: To develop and validate machine learning (ML) models for identifying key predictors and estimating the risk of intraoperative hypotension (IOH) in elderly patients undergoing general anesthesia. Methods: This secondary analysis included 1,720 elderly surgical patients from a randomized controlled trial. Data were split chronologically into training sets. Feature selection was performed using univariate analysis and the Boruta algorithm. Eight ML models – logistic regression, Bayesian model, K-nearest neighbor, support vector machine, neural network, classification and regression tree, extreme gradient boosting, and random forest – were developed with cross-validation, hyperparameter tuning, and random oversampling. Model performance was evaluated using ROC, PRC, calibration, and decision curve analyses, and interpretability was enhanced using SHapley Additive exPlanations (SHAP). Results: Key predictors included anesthesia protocol, Charlson comorbidity index, preoperative sodium, creatinine, BUN/creatinine ratio, intraoperative drug use (e.g., sevoflurane, lidocaine, morphine), preoperative MAP and MHR, surgical and anesthesia duration, and surgical site. The random forest model achieved the best performance (accuracy=0.9917; MCC=0.9832; AUC-ROC=0.9998; AUC-PRC=0.9998). Conclusions: A robust ML-based model was established to accurately predict IOH in elderly patients. These findings may support individualized anesthesia management and targeted preventive strategies to reduce IOH incidence.


  • Open Access

    Application of XGBoost in the prediction of acute postoperative pain after major noncardiac surgery in older patients

    by Yang Sun, Kang Yu, Leyao Du, Xiaoyun Hu, Weixuan Sheng, Dongxin Wang, Huihui Miao

    Background: Acute postoperative pain (APP) are key factors in the recovery of surgical patients after surgery. This study used the machine learning eXtreme Gradient Boosting (XGBoost) algorithm for the prediction of acute postoperative pain after major noncardiac surgery in older patients. Methods: This was a secondary analysis of data from a randomized controlled trial containing 1720 older patients undergoing general anesthesia. The training and test sets were divided according to the timeline. The Boruta function was made to screen for relevant characteristic variables. The XGBoost model was built on the training set using 10-fold cross-validation and hyperparameter optimization, and the tuned optimal model plotted the importance ranking diagram of feature variables, partial dependence profile (PDP) and Break down profile (BDP). The optimal model was used to calculate the confusion matrices and their parameters for the training and validation sets, and to plot the receiver operating characteristic curve (ROC), precision recall curve (PRC), calibration curve and Clinical decision curve (CDC) on the validation set. Results: The Boruta function was used to screen the relevant characteristic variables, and the screened postoperative acute pain characteristic variables were CHARLSON score, Mini-Mental State Examination (MMSE), duration of surgery, preoperative depression score, smoking or not, duration of anesthesia, intraoperative mean heart rate, lidocaine dosage, age, intraoperative morphine dosage, grouping, preoperative anxiety score, loperamide dosage, intraoperative colloid amount, APACHE -II score, postoperative ICU or not, surgical site and postoperative tracheal intubation or not. Test set and validation set accuracy (ACC) for acute postoperative pain: 0.921 and 0.871; AUC-ROC: 0.964 and 0.920; AUC-PRC: 0.983 and 0.959; Brier: 0.067 and 0.098; Matthews Correlation Coefficient (MCC): 0.847 and 0.746. Conclusions: A high-performance algorithm was developed and validated to predict the degree of change in postoperative pain; controlling important characterizing variables may be helpful for postoperative analgesia.


  • Open Access

    Knowledge, attitude, and practice of medical staffs in the operating room towards unintentional perioperative hypothermia prevention: A multicenter cross-sectional study

    by Wei Guo, Weixuan Sheng, Yang Han, Ying Zhang, Xun Zhao

    This study aimed to investigate the knowledge, attitudes, and practices of medical staff regarding the prevention of unintentional perioperative hypothermia. This multicenter cross-sectional study enrolled medical staffs in northern China between September and November 2022. A total of 213 valid questionnaires were collected. The mean scores for knowledge, attitudes, and practices were 5.36 ± 2.06 (total score of 12), 47.54 ± 5.44 (total score of 55), and 31.57 ± 4.37 (total score of 40), respectively. The participant demographics included 14 surgeons (6.57%), 29 anesthesiologists (13.62%), and 170 operating room nurses (79.81%). Significant differences were observed in the knowledge (P = 0.046) and practices (P = 0.023) related to perioperative hypothermia among surgeons, anesthesiologists, and operating room nurses. Pearson correlation analysis revealed positive correlations between knowledge and attitudes (r = 0.21, P = 0.002), knowledge and practices (r = 0.23, P = 0.001), as well as attitudes and practices (r = 0.57, P < 0.001). Structural equation modeling indicated that knowledge had a direct effect on attitudes (β = 0.56, P = 0.002) and an indirect effect on practices (β = 0.25, P = 0.003). Additionally, attitudes had a direct effect on practices (β = 0.45, P < 0.001). This study concluded that knowledge regarding the prevention of unintentional perioperative hypothermia was inadequate; however, most participants exhibited a positive attitude and acceptable practices. Targeted interventions are necessary to enhance understanding and implementation in clinical settings.


  • Open Access

    Atmospheric pollen concentrations and chronic obstructive pulmonary disease (COPD) patients visits in Beijing: time series analysis using a generalized additive model

    by Aizhu Liu, Weixuan Sheng, Xianshi Tang

    To investigate the correlation between the daily visits of chronic obstructive pulmonary disease (COPD) patients in hospital clinic and pollen concentrations in Beijing. We collected daily visits of COPD patients of Beijing Shijitan Hospital from April 1st, 2019 to September 30th, 2019. The relationship between pollen concentrations and COPD patient number was analyzed with meteorological factors, time trend, day of the week effect and holiday effect being controlled by the generalized additive model of time series analysis. R4.1.2 software was applied to generate Spearman correlation coefficient, specific and incremental cumulative effect curves of relative risks as well as the response and three-dimensional diagrams for the exposure lag effect prediction. The fitting models were used to predict the lag relative risk and 95% confidence intervals for specific and incremental cumulative effects of specific pollen concentrations. The number of COPD patients was positively correlated with pollen concentration. When pollen concentration increased by 10 grains/1000 mm2, the peak value of the specific cumulative effect appeared on day0, with the effect gone on day4 and a lag time of 4 days observed, whereas the incremental cumulative effect’s peak value was shown on day17, and the effect disappeared on day18, with a lag time of 18 days. The results showed that pollen concentration was not only positively correlated with the number of COPD patients, but also had a bimodal lag effect on COPD visits in the hospital at Beijing.


  • Effect of atmospheric pollen concentration on daily visits of allergic rhinitis in Beijing: a distributed lag nonlinear model analysis

    by Aizhu Liu, Weixuan Sheng, Xianshi Tang, Jinshu Yin

    To investigate the influence and lag effect of atmospheric pollen concentration on daily visits of patients with allergic rhinitis (AR), we collected the AR data during the pollen seasons from 2018 to 2019 from the outpatient and emergency department of Beijing Shijitan Hospital. The distributed lag non-linear model (DLNM) was used to analyze the correlation and the lag effect between pollen concentration and the incidence of AR. R4.1.2 was used to generate the Spearman correlation coefficients and plot the lag response curves of relative risk specific and incremental cumulative effects. In 2018 and 2019, the number of AR visits was moderately positively correlated with pollen concentration. The peak value of the overall specific cumulative effect for every 10 grains/1000 mm2 increase in atmospheric pollen concentration occurred on day 0 (2018, 2019), and the lag disappearance time was day 6 (2018) and day 7 (2019), and the specific cumulative effect duration was respectively 6 days (2018) and 7 days (2019), with the curve showing a downward trend with time increase. In 2018, the peak value of the overall incremental cumulative effect was on day 7, the lag disappearance time was day 13, and the duration of the incremental cumulative effect was 13 days, forming a curve pattern of rising first and then falling. In 2019, the peak value time of the overall incremental cumulative effect was on day 8, and the curve went down afterwards until it showed the trend of ascending again after day26.


  • Air pollution and coronary heart disease–related hospital visits in Beijing, China: time-series analysis using a generalized additive model

    by Yuan Gao, Weixuan Sheng, Yongtao Yang

    To investigate correlations between environmental and meteorological factors and frequency of presentation for coronary heart disease (CHD) in Beijing. Daily measurements of levels of six atmospheric pollutants were made, data relating to meteorological conditions collected, and CHD-related outpatient visits recorded from January 2015 to December 2019 in Beijing. A time-series analysis was made, using a generalized additive model with Poisson distribution, and R 3.6.3 software was used to estimate relationships among levels of atmospheric pollutants, ambient temperature, and visits occasioned by CHD. Results were controlled for time-dependent trend, other weather variables, day of the week, and holiday effects. Lag-response curves were plotted for specific and incremental cumulative effects of relative risk (RR). The aim was to correlate meteorological-environmental factors and the daily number of CHD-related hospital visits and to quantify the degree of correlation to identify any pathological associations. Response diagrams and three-dimensional diagrams of predicted exposure lag effects were constructed in order to evaluate relationships among the parameters of air pollution, temperature, and daily CHD visits. The fitted model was employed to predict the lag RR and 95% confidence interval (95% CI) for specific and incremental cumulative effects of random air pollutants at random concentrations. This model may then be used to predict effects on the outcome variable at any concentration of any defined pollutant, giving flexibility for public health purposes. The overall lag-response RR curves for the specific cumulative effects of the pollutants, particulate matter (PM)2.5, PM10, SO2, CO, and NO2, were statistically significant and for PM2.5, PM10, CO, and NO2, the overall lag-response RR curves for the incremental cumulative effect were statistically significant. When PM2.5, PM10, SO2, CO, and NO2 concentrations were above threshold values and the temperature was below 45 °F (reference value 70 °F), the number of CHD-related hospital visits increased with a time lag effect. The outpatient volume of CHD was predicted by the model to guide the flexible distribution of medical resources. Elevated PM2.5, PM10, SO2, CO, and NO2 concentrations in the atmosphere combined and low ambient temperature increased the risk of CHD with a time lag effect.