MSMu Sun

Mu Sun

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Mu Sun has a total of 5 co-authors. Here are the top co-authors by number of shared publications:

  • Site Xu

    Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, China

    5 shared publications
  • Si-Te Xu

    Department of Statistics, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, China

    1 shared publication
  • Site Xu

    Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, China

    1 shared publication
  • Yu Xiang

    Key Laboratory of Public Health Safety of Ministry of Education, Department of Epidemiology, School of Public Health, Fudan University, Shanghai 200032, China

    1 shared publication
  • Yu Xiang

    Department of Endocrine and Metabolic Diseases, Shanghai Institute of Endocrine and Metabolic Diseases, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, China

    1 shared publication

Latest Publications

  • Open Access

    Burden and risk factors of depression in seniors from 1990 to 2021: a multi-database study based on EMR mining methods

    by Site Xu, Mu Sun, Yu Xiang

    Depression in seniors is a growing public health concern worldwide. Despite the rising prevalence of depression in this demographic, comprehensive data on its burden and trends over an extended period remain limited. This study aims to assess the trends in the burden of depression among seniors from 1990 to 2021, utilizing the Global Burden of Diseases, Injuries, and Risk Factors Study (GBD) database, and to further explore the risk factors using China Health and Retirement Longitudinal Study (CHARLS) database and National Health and Nutrition Examination Survey (NHANES) database. We utilized data from the GBD 2021, reporting incidence and disability-adjusted life years (DALYs) per 100,000 population, average annual percentage change (AAPC), and risk factors at global, and regional levels. Trends were analyzed by age, sex, and social development index. Joinpoint regression identified significant changes in global trends. We established an interpretable machine learning (ML) model with high efficiency and robustness that identifies depression based on CHARLS (2015, 2018, &2020) and NHANES (2013-2020.3). We chose a best-performing eXtreme Gradient Boosting (XGB) with Genetic Algorithm (GA) for identification, and used SHapley Additive exPlanation (SHAP) to illustrate the potential risk factors. From 1990 to 2021, the overall global incidence of depression among seniors remained broadly stable (AAPC 0.01, 95% CI −0.07 to 0.08), although marked changes emerged in specific regions and population subgroups. The incidence of depressive disorders increased globally for males (AAPC 0.06 [95% CI −0.02 to 0.15]) while it decreased for females (AAPC −0.01 [95% CI −0.09 to 0.07]). Regional analysis showed the highest incidence rates in low-SDI countries, while middle-SDI countries experienced the most significant increases in the burden of depression (AAPC 0.25 [95% CI 0.17 to 0.34]). Risk factor analysis using machine learning models identified key predictors of depression in elderly populations in both China and the United States. The burden of depression among seniors has significantly shifted globally, with marked regional and demographic variations. These findings underscore the urgent need for targeted interventions, policy modifications, and early screening programs to address the rising burden of depression in this vulnerable age group. The use of advanced machine learning models provides valuable insights into the risk factors, facilitating the development of more effective and tailored intervention strategies.


  • Open Access

    The interpretable machine learning model for depression associated with heavy metals via EMR mining method

    by Site Xu, Mu Sun

    Limited research exists on the association between depression and heavy metal exposure. This study aims to develop an interpretable and efficient machine learning (ML) model with robust performance to identify depression linked to heavy metal exposure. Data were derived from the US National Health and Nutrition Examination Survey (NHANES) spanning from 2013 to March 2020. We constructed 5 ML models to detect depression based on heavy metal exposure and assessed their performance using 10 discrimination metrics. The optimal model was selected after parameter tuning with a Genetic Algorithm (GA). To enhance the interpretability of the model’s predictions, we applied SHapley Additive exPlanation (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) algorithms. The study included 19,368 participants. The highest-performing model, an eXtreme Gradient Boosting (XGB) algorithm optimized with GA, identified depression using 16 heavy metal indicators (AUC: 0.686; 95% CI: 0.68–0.69; accuracy: 97.1%). SHAP analysis revealed that elevated blood cadmium levels had a positive influence on the model’s prediction of depression, while urine concentrations of barium, thallium, tin, manganese, antimony, lead, and tungsten, along with blood levels of lead, cadmium, mercury, selenium, and manganese, showed a negative influence. In conclusion, the study successfully utilized an efficient and robust GA-XGB model to identify depression linked to heavy metal exposure, supported by SHAP and LIME explanations. Blood cadmium was positively correlated with depression, whereas barium, thallium, tin, manganese, antimony, lead, and tungsten in urine, along with lead, cadmium, mercury, selenium, and manganese in blood, were negatively correlated with depression.


  • Open Access

    Natural Language Processing (NLP): Identifying Linguistic Gender Bias in Electronic Medical Records (EMRs)

    by Site Xu, Mu Sun

    With the rise of feminism, women report experiencing doubt or discrimination in medical settings. This study aims to explore the linguistic mechanisms by which physicians express disbelief toward patients and to investigate gender differences in the use of negative medical descriptions. A content analysis of 285 electronic medical records was conducted to identify 4 linguistic bias features: judging, reporting, quoting, and fudging. Sentiment classification and knowledge graph with ICD-11 were used to determine the prevalence of these features in the medical records, and logistic regression was applied to test gender differences. A total of 2354 descriptions were analyzed, with 64.7% of the patients identified as male. Descriptions of female patients contained fewer judgmental linguistic features but more fudging-related linguistic features compared to male patients (judging: OR 0.69, 95% CI 0.54-0.88, p < 0.01; fudging: OR 1.38, 95% CI 1.09-1.75, p < 0.01). No significant differences were found in the use of reporting (OR 0.95, 95% CI 0.61-1.47, p = 0.81) and quoting (OR 0.99, 95% CI 0.72-1.36, p = 0.96) between male and female patients. This study highlights how physicians may express disbelief toward patients through linguistic biases, particularly through the use of judging and fudging language. Both male and female patients may face different types of systematic bias from physicians, with female patients experiencing more fudging-related language and less judgmental language compared to male patients. These differences point to a potential mechanism through which gender disparities in healthcare quality may arise, underscoring the need for further investigation and action to address these biases.


  • Open Access

    Global, regional, and national trends in type 2 diabetes mellitus burden among adolescents and young adults aged 10–24 years from 1990 to 2021: a trend analysis from the Global Burden of Disease Study 2021

    by Si-Te Xu, Mu Sun, Yu Xiang

    Background: Type 2 diabetes mellitus (T2DM) poses an escalating public health challenge among adolescents and young adults worldwide. Despite the rising incidence, comprehensive data on the burden and trends of T2DM in this demographic remain scarce. This study aims to evaluate the burden of T2DM among individuals aged 10–24 years globally, regionally, and nationally from 1990 to 2021. Methods: Utilizing data from the Global Burden of Diseases, Injuries, and Risk Factors Study (GBD) 2021, we assessed incidence rates, disability-adjusted life-years (DALYs), and average annual percentage changes (AAPCs) for T2DM in the specified age group. Analyses accounted for variations by age, sex, and socio-demographic index (SDI). Joinpoint regression analysis identified years of significant trend shifts. Results: The global incidence of T2DM among adolescents and young adults rose from 56.02 per 100,000 (95% UI 43.03–72.32) in 1990 to 123.86 per 100,000 (95% UI 100.43–149.79) in 2021, reflecting an AAPC of 3.01 (95% CI 2.78–3.23). Notable increases were recorded in 1995, 2002, and 2009, with joinpoints indicating significant trend stabilization post-2010 for prevalence and DALYs. The largest relative incidence increase was observed in the 15–19 age group [AAPC 2.97 (95% CI 2.71–3.24)]. Although T2DM mortality was 2.4 times higher in the 15–19 age group compared to the 20–24 age group, the latter exhibited a significantly higher overall mortality rate. Regionally, Oceania recorded the highest incidence rates in 2021, while North Africa and the Middle East showed the greatest AAPCs. High-SDI countries experienced the most substantial increase in T2DM burden, with males comprising 54.8% of cases. Conclusions: From 1990 to 2021, the global burden of T2DM among adolescents and young adults has markedly increased, underscoring the necessity for targeted, region-specific interventions to address this issue. The observed demographic disparities in mortality rates necessitate the implementation of age-specific strategies. Furthermore, the emergent trends in T2DM indicators warrant urgent attention to mitigate the rising burden in this vulnerable population. Graphical


  • Open Access

    Assessment of EMR ML Mining Methods for Measuring Association between Metal Mixture and Mortality for Hypertension

    by Site Xu, Mu Sun

    Introduction There are limited data available regarding the connection between heavy metal exposure and mortality among hypertension patients. Aim We intend to establish an interpretable machine learning (ML) model with high efficiency and robustness that monitors mortality based on heavy metal exposure among hypertension patients. Methods Our datasets were obtained from the US National Health and Nutrition Examination Survey (NHANES, 2013–2018). We developed 5 ML models for mortality prediction among hypertension patients by heavy metal exposure, and tested them by 10 discrimination characteristics. Further, we chose the optimally performing model after parameter adjustment by genetic algorithm (GA) for prediction. Finally, in order to visualize the model’s ability to make decisions, we used SHapley Additive exPlanation (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) algorithm to illustrate the features. The study included 2347 participants in total. Results A best-performing eXtreme Gradient Boosting (XGB) with GA for mortality prediction among hypertension patients by 13 heavy metals was selected (AUC 0.959; 95% CI 0.953–0.965; accuracy 96.8%). According to sum of SHAP values, cadmium (0.094), cobalt (2.048), lead (1.12), tungsten (0.129) in urine, and lead (2.026), mercury (1.703) in blood positively influenced the model, while barium (− 0.001), molybdenum (− 2.066), antimony (− 0.398), tin (− 0.498), thallium (− 2.297) in urine, and selenium (− 0.842), manganese (− 1.193) in blood negatively influenced the model. Conclusions Hypertension patients’ mortality associated with heavy metal exposure was predicted by an efficient, robust, and interpretable GA-XGB model with SHAP and LIME. Cadmium, cobalt, lead, tungsten in urine, and mercury in blood are positively correlated with mortality, while barium, molybdenum, antimony, tin, thallium in urine, and lead, selenium, manganese in blood is negatively correlated with mortality.


  • Open Access

    The interpretable machine learning model associated with metal mixtures to identify hypertension via EMR mining method

    by Site Xu, Mu Sun

    There are limited data available regarding the connection between hypertension and heavy metal exposure. The authors intend to establish an interpretable machine learning (ML) model with high efficiency and robustness that identifies hypertension based on heavy metal exposure. Our datasets were obtained from the US National Health and Nutrition Examination Survey (NHANES, 2013–2020.3). The authors developed 5 ML models for hypertension identification by heavy metal exposure, and tested them by 10 discrimination characteristics. Further, the authors chose the optimally performing model after parameter adjustment by Genetic Algorithm (GA) for identification. Finally, in order to visualize the model's ability to make decisions, the authors used SHapley Additive exPlanation (SHAP) and Local Interpretable Model‐Agnostic Explanations (LIME) algorithm to illustrate the features. The study included 19 368 participants in total. A best‐performing eXtreme Gradient Boosting (XGB) with GA for hypertension identification by 16 heavy metals was selected (AUC: 0.774; 95% CI: 0.772–0.776; accuracy: 87.7%). According to SHAP values, Barium (0.02), Cadmium (0.017), Lead (0.017), Antimony (0.008), Tin (0.007), Manganese (0.006), Thallium (0.004), Tungsten (0.004) in urine, and Lead (0.048), Mercury (0.035), Selenium (0.05), Manganese (0.007) in blood positively influenced the model, while Cadmium (−0.001) in urine negatively influenced the model. Study participants' hypertension associated with heavy metal exposure was identified by an efficient, robust, and interpretable GA‐XGB model with SHAP and LIME. Barium, Cadmium, Lead, Antimony, Tin, Manganese, Thallium, Tungsten in urine, and Lead, Mercury, Selenium, Manganese in blood are positively correlated with hypertension, while Cadmium in blood is negatively correlated with hypertension.


  • Open Access

    Covid-19 vaccine effectiveness during Omicron BA.2 pandemic in Shanghai: A cross-sectional study based on EMR

    by Site Master Degree Xu, Mu Master Degree Sun

    Large-scale vaccination against the spread and mutation of COVID-19 is being implemented in many countries. We aimed to assess the effectiveness of certain vaccines (87.35% inactivated), mainly Sinovac – CoronaVac and Sinopharm (Beijing) – BBIBP-CorV, during the Omicron BA.2 pandemic by cross-sectional study. The study was conducted in a cabin hospital of Shanghai, China. A total of 1194 Covid-19 patients infected with Omicron BA.2 were enrolled and epidemiological survey information was collected from the subjects through electronic medical records and questionnaires, from March 23th to April 1st in 2022. Vaccine effectiveness was reflected by the occurrence of multi-dimensional symptoms while adjusting for confounding variables. In the unstandardized vaccinated group, the Covid-19 vaccine effectiveness of Omicron BA.2 in the male group was higher than in the female group (P = .0171). In the standardized vaccinated group, vaccine effectiveness in [20, 40) age group was higher than in other age groups (P = .0002). Adjusting for gender and age, Covid-19 vaccine effectiveness of Omicron BA.2 at the specific level was 87.42% (95% confidence interval [CI], 72.35–94.28, P < .0001), and 62.65% (95% CI, 1.47–85.84, P = .047) in the unstandardized vaccinated and the standardized vaccinated group, respectively. Covid-19 vaccine effectiveness of Omicron BA.2 was not apparent at the general level but remained effective for the specific symptom. Further development for the Covid-19 vaccine is necessary.