Shen Wang

Dr. Shen Wang


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 May 2025 in Journal of Medical Internet Research
Verified
Journal Article
Open access
BSBoqun Shi
Boqun Shi
LCLiangguo Chen
Liangguo Chen
SPShuo Pang
Shuo Pang
YWYue Wang
Yue Wang
SWShen Wang
Shen Wang
XWXiaofan Wu
Xiaofan Wu
Background: Accurate mortality risk prediction is crucial for effective cardiovascular risk management. Recent advancements in artificial intelligence (AI) have demonstrated potential in this specific medical field. Qwen-2 and Llama-3 are high-performance, open-source large language models (LLMs) available online. An artificial neural network (ANN) algorithm derived from the SWEDEHEART (Swedish Web System for Enhancement and Development of Evidence-Based Care in Heart Disease Evaluated According to Recommended Therapies) registry, termed SWEDEHEART-AI, can predict patient prognosis following acute myocardial infarction (AMI). Objective: This study aims to evaluate the 3 models mentioned above in predicting 1-year all-cause mortality in critically ill patients with AMI. Methods: The Medical Information Mart for Intensive Care IV (MIMIC-IV) database is a publicly available data set in critical care medicine. We included 2758 patients who were first admitted for AMI and discharged alive. SWEDEHEART-AI calculated the mortality rate based on each patient’s 21 clinical variables. Qwen-2 and Llama-3 analyzed the content of patients’ discharge records and directly provided a 1-decimal value between 0 and 1 to represent 1-year death risk probabilities. The patients’ actual mortality was verified using follow-up data. The predictive performance of the 3 models was assessed and compared using the Harrell C-statistic (C-index), the area under the receiver operating characteristic curve (AUROC), calibration plots, Kaplan-Meier curves, and decision curve analysis. Results: SWEDEHEART-AI demonstrated strong discrimination in predicting 1-year all-cause mortality in patients with AMI, with a higher C-index than Qwen-2 and Llama-3 (C-index 0.72, 95% CI 0.69-0.74 vs C-index 0.65, 0.62-0.67 vs C-index 0.56, 95% CI 0.53-0.58, respectively; all P<.001 for both comparisons). SWEDEHEART-AI also showed high and consistent AUROC in the time-dependent ROC curve. The death rates calculated by SWEDEHEART-AI were positively correlated with actual mortality, and the 3 risk classes derived from this model showed clear differentiation in the Kaplan-Meier curve (P<.001). Calibration plots indicated that SWEDEHEART-AI tended to overestimate mortality risk, with an observed-to-expected ratio of 0.478. Compared with the LLMs, SWEDEHEART-AI demonstrated positive and greater net benefits at risk thresholds below 19%. Conclusions: SWEDEHEART-AI, a trained ANN model, demonstrated the best performance, with strong discrimination and clinical utility in predicting 1-year all-cause mortality in patients with AMI from an intensive care cohort. Among the LLMs, Qwen-2 outperformed Llama-3 and showed moderate predictive value. Qwen-2 and SWEDEHEART-AI exhibited comparable classification effectiveness. The future integration of LLMs into clinical decision support systems holds promise for accurate risk stratification in patients with AMI; however, further research is needed to optimize LLM performance and address calibration issues across diverse patient populations.

3 September 2023 in Clinical Cardiology
Verified
Journal Article
Open access
FLFadong Li
Fadong Li
SWShen Wang
Shen Wang
YWYue Wang
Yue Wang
CWCan Wei
Can Wei
XLXinyan Liu
Xinyan Liu
XWXiaofan Wu
Xiaofan Wu
Background: Because of the advancement of bioabsorbable polymers and thinner struts, bioabsorbable‐polymer sirolimus‐eluting stents (BP‐SES) with ultrathin struts may be related to superior performance when compared to durable‐polymer drug‐eluting stents (DP‐DES) with thin struts. Nonetheless, the long‐term safety of ultrathin BP‐SES in acute coronary syndrome (ACS) remains unknown.Methods: We sought to assess the long‐term safety of ultrathin BP‐SES in ACS patients, conducting a thorough meta‐analysis of all relevant trials drawing a comparison between ultrathin BP‐SES and contemporary thin DP‐DES. Target lesion failure (TLF), which includes cardiac death (CD), target‐vessel myocardial infarction (TV‐MI), and clinically driven target lesion revascularization (CD‐TLR) was considered the primary endpoint. Multiple databases comprising Embase, MEDLINE, Cochrane Library, and Pubmed were all thoroughly searched.Results: There were seven randomized controlled trials included in our study with 7522 randomized patients with ACS (BP‐SES = 3888, DP‐DES = 3634). TLF occurred in 371 (9.5% in BP‐SES) and 393 (10.8% in DP‐DES) patients, respectively, across a 40.7‐month weighted mean follow‐up, with no statistically significant group differences (risk ratio [RR]: 0.87; 95% confidence interval [CI]: 0.73–1.04; p = .12). Furthermore, no significant differences in cardiac death (RR: 0.96; 95% CI: 0.68–1.35; p = .81), TV‐MI (RR: 0.63; 95% CI: 0.36–1.10; p = .10) and CD‐TLR (RR: 0.77; 95% CI: 0.46–1.29; p = .32) were detected between two groups.Conclusion: During a follow‐up of 40.7 months, ultrathin BP‐SES and thin DP‐DES had a comparable risk of TLF and its individual components (CD, TV‐MI, and CD‐TLR), indicating that ultrathin BP‐SES held at least the same safety and efficiency as thin DP‐DES presented in patients with ACS.

28 October 2025 in Catheterization and Cardiovascular Interventions
Verified
Journal Article
Closed access
CFChu Fan
Chu Fan
YZYi Zou
Yi Zou
LCLiangguo Chen
Liangguo Chen
YWYue Wang
Yue Wang
SPShuo Pang
Shuo Pang
XWXiaofan Wu
Xiaofan Wu

11 November 2023 in Research Square
Verified
Preprint
Open access
PDF file
SWShen Wang
Shen Wang
SSShuaifeng Sun
Shuaifeng Sun
YWYue Wang
Yue Wang
FLFadong Li
Fadong Li
XWXiaofan Wu
Xiaofan Wu
Objective Some observational studies and a few meta-analyses have shown a similarity of optical coherence tomography (OCT) in guiding drug-eluting stent (DES) implantation compared with intravascular ultrasound (IVUS). However, a comparison of long-term outcomes between guidance OCT or IVUS from randomized controlled trials (RCTs) is lacking. This study aimed to compare the prognosis of IVUS vs. OCT in guiding stent implantation. Methods Randomized controlled trials (RCTs) related to compare long outcomes of IVUS versus OCT in guiding stent implantation from inception to 15 October 2023 were identified using PubMed, Cochrane Library, Medline, Web of Science and EMBASE databases. Two researchers independently screened articles, extracted data, and assessed the quality of each study according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Data were aggregated for the primary outcome measure using the random-effects model as pooled risk ratio (RR). The primary clinical prognosis including major adverse cardiac events (MACEs), all-cause mortality, all-cause myocardial infarction, all revascularization, and stent thrombosis. Results Five RCTs (3,339 patients) were included (OCT guidance = 1,680; IVUS guidance = 1,659). There were similar results for all long-term outcomes between OCT and IVUS-guided DES implantation: major adverse cardiac events (relative risk (RR) = 0.96; 95% confidence interval (CI), 0.68–1.36; P = 0.82), all-cause mortality (RR = 1.00; 95% CI, 0.52–1.91; P = 1.00), all-cause myocardial infarction (RR = 0.81; 95% CI, 0.44–1.49; P = 0.50), all revascularization (RR = 1.02; 95% CI, 0.74–1.42; P = 0.88), and stent thrombosis (RR = 0.44; 95% CI, 0.10–1.97; P = 0.28). Conclusions This meta-analysis suggested no significant difference in prognosis between OCT-guided vs. IVUS-guided coronary stent implantation.

6 October 2024 in JMIR Preprints
Verified
Preprint
Open access
BSBoqun Shi
Boqun Shi
LCLiangguo Chen
Liangguo Chen
SPShuo Pang
Shuo Pang
YWYue Wang
Yue Wang
SWShen Wang
Shen Wang
XWXiaofan Wu
Xiaofan Wu
BACKGROUND Accurate mortality risk prediction is crucial for effective cardiovascular risk management. Recent advancements in artificial intelligence (AI) have demonstrated potential in this specific medical field. Qwen-2 and Llama-3 are high-performance, open-source large language models (LLMs) available online. An artificial neural network (ANN) algorithm derived from the SWEDEHEART (Swedish Web System for Enhancement and Development of Evidence-Based Care in Heart Disease Evaluated According to Recommended Therapies) registry, termed SWEDEHEART-AI, can predict patient prognosis following acute myocardial infarction (AMI). OBJECTIVE This study aims to evaluate the 3 models mentioned above in predicting 1-year all-cause mortality in critically ill patients with AMI. METHODS The Medical Information Mart for Intensive Care IV (MIMIC-IV) database is a publicly available data set in critical care medicine. We included 2758 patients who were first admitted for AMI and discharged alive. SWEDEHEART-AI calculated the mortality rate based on each patient’s 21 clinical variables. Qwen-2 and Llama-3 analyzed the content of patients’ discharge records and directly provided a 1-decimal value between 0 and 1 to represent 1-year death risk probabilities. The patients’ actual mortality was verified using follow-up data. The predictive performance of the 3 models was assessed and compared using the Harrell C-statistic (C-index), the area under the receiver operating characteristic curve (AUROC), calibration plots, Kaplan-Meier curves, and decision curve analysis. RESULTS SWEDEHEART-AI demonstrated strong discrimination in predicting 1-year all-cause mortality in patients with AMI, with a higher C-index than Qwen-2 and Llama-3 (C-index 0.72, 95% CI 0.69-0.74 vs C-index 0.65, 0.62-0.67 vs C-index 0.56, 95% CI 0.53-0.58, respectively; all P<.001 for both comparisons). SWEDEHEART-AI also showed high and consistent AUROC in the time-dependent ROC curve. The death rates calculated by SWEDEHEART-AI were positively correlated with actual mortality, and the 3 risk classes derived from this model showed clear differentiation in the Kaplan-Meier curve (P<.001). Calibration plots indicated that SWEDEHEART-AI tended to overestimate mortality risk, with an observed-to-expected ratio of 0.478. Compared with the LLMs, SWEDEHEART-AI demonstrated positive and greater net benefits at risk thresholds below 19%. CONCLUSIONS SWEDEHEART-AI, a trained ANN model, demonstrated the best performance, with strong discrimination and clinical utility in predicting 1-year all-cause mortality in patients with AMI from an intensive care cohort. Among the LLMs, Qwen-2 outperformed Llama-3 and showed moderate predictive value. Qwen-2 and SWEDEHEART-AI exhibited comparable classification effectiveness. The future integration of LLMs into clinical decision support systems holds promise for accurate risk stratification in patients with AMI; however, further research is needed to optimize LLM performance and address calibration issues across diverse patient populations.