Xiaoyuan Shen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiaoyuan Shen has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
Songsong Luo
Xiaoshan Affiliated Hospital of Wenzhou Medical University Department of Critical Care Medicine, The First People’s Hospital of Xiaoshan District Hangzhou, Zhejiang
3 shared publicationsJiawei Lai
Department of Critical Care Medicine, The First People’s Hospital of Xiaoshan District, Xiaoshan Affiliated Hospital of Wenzhou Medical University, Hangzhou, Zhejiang, China
2 shared publications- Songsong Luo
Department of Critical Care Medicine, The First People's Hospital of Xiaoshan District, Xiaoshan Affiliated Hospital of Wenzhou Medical University, Hangzhou, Zhejiang, China
2 shared publications Hongliang Dong
Department of Critical Care Medicine, The First People’s Hospital of Xiaoshan District, Xiaoshan Affiliated Hospital of Wenzhou Medical University, Hangzhou, Zhejiang, China
1 shared publicationLeyi Ni
Department of Critical Care Medicine, The First People’s Hospital of Xiaoshan District, Xiaoshan Affiliated Hospital of Wenzhou Medical University, Hangzhou, Zhejiang, China
1 shared publication- Lujiao Mm Mo
Department of Critical Care Medicine, The First People’s Hospital of Xiaoshan District, Xiaoshan Affiliated Hospital of Wenzhou Medical University, Hangzhou, Zhejiang, China
1 shared publication
Latest Publications
- Open Access
- 24 July 2026
- Published by Wolters Kluwer Health in Medicine
- Vol. 105 (30) , e49620
Trends in ARDS-related mortality among US adult patients with diabetes, 1999–2023
Acute respiratory distress syndrome (ARDS) and diabetes mellitus (DM) constitute a high-risk comorbidity, with diabetes-related immune dysfunction and metabolic dysregulation exacerbating ARDS severity and worsening outcomes. However, long-term national mortality trends and subgroup disparities for this comorbidity remain inadequately characterized. Using US national mortality data from the CDC WONDER database (1999–2023), we analyzed death records listing both ARDS (ICD-10 J80) and all types of DM (ICD-10 E10-E14) as underlying or contributing causes of death. Age-adjusted mortality rates (AAMR) per 1,00,000 population were standardized to the 2000 US census. Temporal trends were evaluated using Joinpoint regression to compute average annual percent change (AAPC) and identify inflection points, with stratification by sex, race/ethnicity, census region, urbanization level, and age group. From 1999 to 2023, overall AAMR for ARDS–DM comorbidity declined from 0.66 to 0.40 per 1,00,000 (AAPC: −0.12%, 95% CI: −2.75 to 2.58). A triphasic pattern emerged: pre-pandemic relative stability or gradual decline, a sharp mortality surge during the COVID-19 pandemic (2017–2020/21), followed by steep post-pandemic decline (2020/21–2023). Persistent disparities were evident, with higher 2023 mortality among males, non-Hispanic Black and Hispanic populations, and residents of the South and West census regions. While long-term AAMR for ARDS–DM comorbidity showed an overall declining trend, the COVID-19 pandemic induced significant transient disruption. Preexisting socioeconomic and demographic disparities in mortality persisted throughout the 25-year period, most evident in rural areas, the South, and the Midwest, highlighting the continued need for targeted public health strategies to reduce severe respiratory complications in high-risk diabetic populations.
- 24 July 2026
- Published by Wolters Kluwer Health in Medicine
- Vol. 105 (30) , e49620
Open AccessTrends in ARDS-related mortality among US adult patients with diabetes, 1999–2023
Acute respiratory distress syndrome (ARDS) and diabetes mellitus (DM) constitute a high-risk comorbidity, with diabetes-related immune dysfunction and metabolic dysregulation exacerbating ARDS severity and worsening outcomes. However, long-term national mortality trends and subgroup disparities for this comorbidity remain inadequately characterized. Using US national mortality data from the CDC WONDER database (1999–2023), we analyzed death records listing both ARDS (ICD-10 J80) and all types of DM (ICD-10 E10-E14) as underlying or contributing causes of death. Age-adjusted mortality rates (AAMR) per 1,00,000 population were standardized to the 2000 US census. Temporal trends were evaluated using Joinpoint regression to compute average annual percent change (AAPC) and identify inflection points, with stratification by sex, race/ethnicity, census region, urbanization level, and age group. From 1999 to 2023, overall AAMR for ARDS–DM comorbidity declined from 0.66 to 0.40 per 1,00,000 (AAPC: −0.12%, 95% CI: −2.75 to 2.58). A triphasic pattern emerged: pre-pandemic relative stability or gradual decline, a sharp mortality surge during the COVID-19 pandemic (2017–2020/21), followed by steep post-pandemic decline (2020/21–2023). Persistent disparities were evident, with higher 2023 mortality among males, non-Hispanic Black and Hispanic populations, and residents of the South and West census regions. While long-term AAMR for ARDS–DM comorbidity showed an overall declining trend, the COVID-19 pandemic induced significant transient disruption. Preexisting socioeconomic and demographic disparities in mortality persisted throughout the 25-year period, most evident in rural areas, the South, and the Midwest, highlighting the continued need for targeted public health strategies to reduce severe respiratory complications in high-risk diabetic populations.
- Open Access
- 29 November 2025
- Published by Oxford University Press (OUP) in Clinical Kidney Journal
- Vol. 19 (1)
Prediction of hospital mortality in sepsis-associated acute kidney injury using a machine-learning approach: a multicenter study using SHAP interpretability analysis
Background: Sepsis-associated acute kidney injury (S-AKI) represents a critical complication with high mortality rates in intensive care units. Current risk stratification tools lack precision and interpretability for clinical decision-making. This study aimed to develop and validate interpretable machine learning models for predicting hospital mortality in S-AKI patients. Methods: This retrospective cohort study utilized five international critical care databases: Medical Information Mart for Intensive Care (MIMIC)-IV (n = 12 966), MIMIC-III-CareVue (n = 2209), eICU (n = 8210), Northwestern University Intensive Care Unit (NWICU) (n = 2207) and Salzburg Intensive Care database (SICdb) (n = 1893). Adult patients with S-AKI meeting sepsis-3.0 and acute kidney injury criteria were included. Feature selection used the Boruta algorithm on MIMIC-IV, MIMIC-III and eICU databases. Eleven machine learning algorithms were trained using MIMIC-IV data with external validation on all other datasets. Performance was evaluated using receiver operating characteristic (ROC) curve analysis, calibration plots and decision curve analysis. SHapley Additive exPlanations (SHAP) analysis provided model interpretability. Results: Among 27 485 S-AKI patients, hospital mortality was 27.5%. Boruta identified 21 consensus features including severity scores [Simplified Acute Physiology Score II (SAPS II), Sequential Organ Failure Assessment (SOFA), OASIS], vital signs and laboratory parameters. Gradient Boosting Machine emerged as optimal with area under the curve (AUC) values of 0.770 (training), 0.731 (internal validation) and 0.732–0.778 across four external validation cohorts. The model demonstrated excellent calibration and minimal overfitting (3.9% AUC difference). Decision curve analysis revealed superior clinical utility across probability thresholds of 4%–82%. SHAP analysis identified SAPS II as the most important predictor, with scores >60 and SOFA >15 associated with substantially increased mortality risk. Complete case analysis confirmed model robustness (AUC 0.766–0.847). Conclusions: The interpretable machine learning model demonstrated excellent performance and robust generalizability for S-AKI mortality prediction across five international databases. SHAP analysis provided clinically meaningful insights supporting personalized risk stratification and evidence-based clinical decision-making.
- 29 November 2025
- Published by Oxford University Press (OUP) in Clinical Kidney Journal
- Vol. 19 (1)
Open AccessPrediction of hospital mortality in sepsis-associated acute kidney injury using a machine-learning approach: a multicenter study using SHAP interpretability analysis
Background: Sepsis-associated acute kidney injury (S-AKI) represents a critical complication with high mortality rates in intensive care units. Current risk stratification tools lack precision and interpretability for clinical decision-making. This study aimed to develop and validate interpretable machine learning models for predicting hospital mortality in S-AKI patients. Methods: This retrospective cohort study utilized five international critical care databases: Medical Information Mart for Intensive Care (MIMIC)-IV (n = 12 966), MIMIC-III-CareVue (n = 2209), eICU (n = 8210), Northwestern University Intensive Care Unit (NWICU) (n = 2207) and Salzburg Intensive Care database (SICdb) (n = 1893). Adult patients with S-AKI meeting sepsis-3.0 and acute kidney injury criteria were included. Feature selection used the Boruta algorithm on MIMIC-IV, MIMIC-III and eICU databases. Eleven machine learning algorithms were trained using MIMIC-IV data with external validation on all other datasets. Performance was evaluated using receiver operating characteristic (ROC) curve analysis, calibration plots and decision curve analysis. SHapley Additive exPlanations (SHAP) analysis provided model interpretability. Results: Among 27 485 S-AKI patients, hospital mortality was 27.5%. Boruta identified 21 consensus features including severity scores [Simplified Acute Physiology Score II (SAPS II), Sequential Organ Failure Assessment (SOFA), OASIS], vital signs and laboratory parameters. Gradient Boosting Machine emerged as optimal with area under the curve (AUC) values of 0.770 (training), 0.731 (internal validation) and 0.732–0.778 across four external validation cohorts. The model demonstrated excellent calibration and minimal overfitting (3.9% AUC difference). Decision curve analysis revealed superior clinical utility across probability thresholds of 4%–82%. SHAP analysis identified SAPS II as the most important predictor, with scores >60 and SOFA >15 associated with substantially increased mortality risk. Complete case analysis confirmed model robustness (AUC 0.766–0.847). Conclusions: The interpretable machine learning model demonstrated excellent performance and robust generalizability for S-AKI mortality prediction across five international databases. SHAP analysis provided clinically meaningful insights supporting personalized risk stratification and evidence-based clinical decision-making.
- Open Access
- 5 November 2025
- Published by Elsevier in Preventive Medicine Reports
- Vol. 60, 103303
Comment on “Association between the dietary index for gut microbiota and osteoporosis among middle-aged and older adults in the United States”
- 5 November 2025
- Published by Elsevier in Preventive Medicine Reports
- Vol. 60, 103303
Open AccessComment on “Association between the dietary index for gut microbiota and osteoporosis among middle-aged and older adults in the United States”
- 7 October 2025
- Published by Elsevier in Journal of Critical Care
- Vol. 91, 155300
Letter to the editor: Portable handheld ultrasound for VExUS assessment in critical care: Reliability and time efficiency in resident-led examinations
- 7 October 2025
- Published by Elsevier in Journal of Critical Care
- Vol. 91, 155300
Letter to the editor: Portable handheld ultrasound for VExUS assessment in critical care: Reliability and time efficiency in resident-led examinations
- 8 September 2025
- Published by Springer Nature in Neurocritical Care
- Vol. 43 (3) , 1097-1098
Comment on “Dynamic Impact of Leptomeningeal Collateral Status for Hemorrhagic Transformation in Patients with Acute Ischemic Stroke with Endovascular Treatment”
- 8 September 2025
- Published by Springer Nature in Neurocritical Care
- Vol. 43 (3) , 1097-1098
Comment on “Dynamic Impact of Leptomeningeal Collateral Status for Hemorrhagic Transformation in Patients with Acute Ischemic Stroke with Endovascular Treatment”