Wenhui Li

Wenhui Li

Auto-generated profile, based on publicly available information

Wenhui Li

Institute of Life Course and Medical Sciences, University of Liverpool , William Henry Duncan Building, 6 West Derby Street, Liverpool L7 8TX

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
10 November 2025 in EP Europace
Verified
Journal Article
Open access
YCYang Chen
Yang Chen
ESEva Soler-Espejo
Eva Soler-Espejo
MZManlin Zhao
Manlin Zhao
WLWenhui Li
Wenhui Li
HLHongyu Liu
Hongyu Liu
Gregory LipGregory Lip
Gregory Lip
Aims: Multimorbidity frequently coexists with atrial fibrillation (AF) and complicates treatment decisions. While current guidelines offer selective recommendations for catheter ablation in this group, evidence remains limited. This study aimed to evaluate whether comorbidity burden modifies the effectiveness of catheter ablation vs. antiarrhythmic drug therapy. Methods and results: In this post hoc analysis of the CABANA trial, patients were stratified by overall comorbidity burden using a data-driven threshold based on the distribution of 15 pre-specified conditions. The primary outcome was a composite of all-cause mortality, disabling stroke, serious bleeding, or cardiac arrest. Secondary outcomes included cardiovascular hospitalization and a composite of all-cause mortality or cardiovascular hospitalization. Additional outcomes included AF recurrence and AF-related quality of life in a sub-cohort. Of 2204 patients, 736 had high comorbidity burden {≥4 conditions, based on a data-driven threshold; median age 68.0 [interquartile range (IQR): 63.0–73.0], 67.1% male} and 1468 had low burden [median age 67.0 (IQR: 61.0–71.0), 60.7% male]. Over a median follow-up of 3.9 years (IQR: 2.4–5.1), for the primary outcome, the adjusted hazard ratio for catheter ablation vs. drug therapy was 0.62 [95% confidence interval (CI): 0.42–0.93] in patients with high comorbidity burden and 1.16 (95% CI: 0.76–1.77) in those with low burden (interaction P = 0.038). Secondary outcomes also tended to favour ablation in the high comorbidity burden group. Moreover, catheter ablation significantly reduced AF recurrence, with relative risk reductions of 49% and 40% in the low- and high-burden groups, respectively. Furthermore, catheter ablation improved AF-related quality of life in both comorbidity groups, with more sustained and pronounced benefits over time in patients with high comorbidity burden. Conclusion: Catheter ablation was associated with more favourable clinical outcomes in AF patients with high comorbidity burden, which support broader consideration of ablation in this population, though prospective trials are needed to confirm and guide clinical decision-making in personalized rhythm management. Pre-registered clinical trial number: NCT00911508

28 January 2026 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
QYQinkai Yu
Qinkai Yu
CZChong Zhang
Chong Zhang
GJGaojie Jin
Gaojie Jin
THTianjin Huang
Tianjin Huang
WZWei Zhou
Wei Zhou
YMYanda Meng
Yanda Meng
Annotating medical data for training AI models is often costly and limited due to the shortage of specialists with relevant clinical expertise. This challenge is further compounded by privacy and ethical concerns associated with sensitive patient information. As a result, well-trained medical segmentation models on private datasets constitute valuable intellectual property requiring robust protection mechanisms. Existing model protection techniques primarily focus on classification and generative tasks, while segmentation models—crucial to medical image analysis— remain largely underexplored. In this paper, we propose a novel, stealthy, and harmless method, StealthMark, for verifying the ownership of medical segmentation models under black-box conditions. Our approach subtly modulates model uncertainty without altering the final segmentation outputs, thereby preserving the model's performance. To enable ownership verification, we incorporate model-agnostic explanation methods, e.g. LIME, to extract feature attributions from the model outputs. Under specific triggering conditions, these explanations reveal a distinct and verifiable watermark. We further design the watermark as a QR code to facilitate robust and recognizable ownership claims. We conducted extensive experiments across four medical imaging datasets (CMR dataset from UK Biobank, the SEG fundus dataset, the EchoNet echocardiography dataset, and the PraNet colonoscopy dataset) and five mainstream segmentation models. The results demonstrate the effectiveness, stealthiness, and harmlessness of our method on the original model's segmentation performance. For example, when applied to the SAM model, Stealth-Mark consistently achieved attack success rates (ASR) above 95% across various datasets while maintaining less than a 1% drop in Dice and AUC scores—significantly outperforming backdoor-based watermarking methods and highlighting its strong potential for practical deployment. Our implementation code is made available at https://github.com/Qinkaiyu/StealthMark.

29 August 2026 in European Journal of Preventive Cardiology
Verified
Journal Article
Open access
Yifan XieYifan Xie
Yifan Xie
WLWenhui Li
Wenhui Li
YMYanda Meng
Yanda Meng
THTianjin Huang
Tianjin Huang
YZYalin Zheng
Yalin Zheng
Gregory LipGregory Lip
Gregory Lip
Aims: Major bleeding remains a major barrier to optimal anticoagulation in patients with atrial fibrillation (AF). We aimed to develop and externally validate a weighted score that balances clinical usability and predictive performance for 1-year major bleeding prediction. Methods and results: Using prospective multinational Global Registry on Long-Term Oral Antithrombotic Treatment in Patients With Atrial Fibrillation (GLORIA-AF) Phase II/III data, we developed the GLORIA-AF Bleeding Weighted Risk Score using least absolute shrinkage and selection operator-penalized regression with stability selection, coefficient rescaling, and internal validation. The score was externally evaluated in EURObservational Research Programme Atrial Fibrillation and EURObservational Research Programme Atrial Fibrillation registries. Discrimination, calibration, and clinical benefit were assessed using concordance index (C-index), observed-to-expected ratio, calibration plot, and decision-curve analysis and compared with HAS-BLED, the unweighted GLORIA-AF score, and the full multivariable Cox model. Among 20 250 eligible derivation cohort patients [69.9 (10.3) years; 9092 female (44.9%)], 317 (1.6%) had major bleeding during 1-year follow-up. The derived score ranges from 0 to 22, with the highest weight (5) assigned to age >65 years, followed by abnormal kidney function (3). The derived score achieved a C-index of 0.688 (95% CI, 0.660–0.717), outperforming HAS-BLED (C-index, 0.631; 95% CI, 0.604–0.658; P < 0.001), while preserving discrimination comparable to full multivariable regression (C-index, 0.690; 95% CI, 0.661–0.719; P = 0.084). Calibration was good (observed-to-expected ratio, 0.996) and DCA showed a greater net benefit than HAS-BLED across 1–3% thresholds. Among 9752 external validation patients, 148 (1.5%) had major bleeding. The derived score achieved a C-index of 0.674 (95% CI, 0.643–0.705; P < 0.001), with better discrimination, calibration, and clinical benefit than HAS-BLED. Conclusion: The GLORIA-AF Bleeding Score showed modestly higher discrimination than HAS-BLED for 1-year major bleeding prediction while retaining clinical interpretability and usability. External validation in independent European and Asia-Pacific registries further supports its transportability beyond the derivation population.

29 August 2026 in EP Europace
Verified
Journal Article
Open access
Yifan XieYifan Xie
Yifan Xie
WLWenhui Li
Wenhui Li
YMYanda Meng
Yanda Meng
THTianjin Huang
Tianjin Huang
Yalin ZhengYalin Zheng
Yalin Zheng
Gregory LipGregory Lip
Gregory Lip
Aims: Accurate stroke risk stratification is central to anticoagulation decision-making in patients with atrial fibrillation (AF), but conventional scores may not fully capture risk heterogeneity. We aimed to develop and externally validate an interpretable weighted score using a time-to-event framework. Methods and results: GLORIA-AF Phase II/III data were used to evaluate 17 baseline predictors using LASSO-penalized Cox regression with stability selection; coefficients were converted into integer weights. Performance was assessed using discrimination, calibration, integrated discrimination improvement (IDI), continuous net reclassification improvement (NRI), and decision curve analysis. External validation was performed in EORP-AF and APHRS-AF registries. Among 20 517 patients included in the derivation cohort [mean (SD) age, 69.9 (10.3) years; 9196 women (44.8%)], 487 (2.4%) had stroke, and 17 397 (84.8%) were receiving anticoagulation at baseline. Ten selected predictors formed a 0–23-point score. The derived score achieved a C-index of 0.661 (95% CI, 0.636–0.685), higher than CHA2DS2-VA (0.626; P < 0.001), CHA2DS2-VASc (0.615; P < 0.001), and the unweighted score (P = 0.016), with no significant difference from the full Cox or machine learning models. In external validation (8309 patients; 147 strokes), the C-index was 0.652 (95% CI, 0.614–0.690) vs. 0.616 for CHA2DS2-VA (95% CI, 0.598–0.634; P < 0.001). IDI/NRI, calibration, and decision curve analyses supported improved risk differentiation, close calibration, and generally greater net benefit than CHA2DS2-VA. The score retained higher discrimination than CHA2DS2-VA among patients without baseline anticoagulation (P < 0.001). Conclusion: The GLORIA-AF Stroke Weighted Risk Score provides risk refinement beyond CHA2DS2-VA while retaining discrimination consistent with more complex models. External validation supports its transportability and potential adjunctive role in guideline-directed thromboembolic risk assessment.

9 July 2026 in Heart Rhythm
Verified
Journal Article
Open access
WLWenhui Li
Wenhui Li
MSMaria Sudell
Maria Sudell
YCYang Chen
Yang Chen
MZManlin Zhao
Manlin Zhao
MKMark Kelson
Mark Kelson
Gregory LipGregory Lip
Gregory Lip
The risk profile of patients with atrial fibrillation (AF) is heterogeneous, and treatment responses to catheter ablation versus drug therapy may vary across clinical phenotypes. Latent class analysis (LCA) identifies unobserved subgroups from baseline characteristics. To apply LCA to CABANA data to define AF phenotypes and assess whether treatment effects differed across latent classes. This secondary analysis of the CABANA trial included 2,204 patients randomized to catheter ablation or drug therapy. Twenty baseline variables covering demographics, comorbidities, AF history, symptom burden, and echocardiographic measures were used for LCA. The primary outcome was a composite of all-cause death, disabling stroke, serious bleeding, or cardiac arrest. Treatment effects across latent classes were evaluated under intention-to-treat (ITT) and per-protocol (PP) frameworks using Cox models with a treatment-by-class interaction term. Three latent classes were identified: Class 1 (n = 558), an older multimorbid symptomatic phenotype; Class 2 (n = 739), an older preserved-function lower-comorbidity phenotype; and Class 3 (n = 905), a younger male metabolic-risk phenotype. In ITT, treatment-effect estimates for catheter ablation versus drug therapy were most favorable in Class 2 (adjusted hazard ratio 0.56, 95% CI 0.34-0.92), whereas estimates in other classes were less distinct; interaction p = 0.070. PP analysis showed similar patterns, with the most favorable estimates observed in Class 2; interaction p = 0.047. LCA identified three AF phenotypes with differential responses to catheter ablation versus drug therapy. These findings suggest treatment heterogeneity across AF phenotypes and support further evaluation of phenotype-guided rhythm-control strategies. URL: https://clinicaltrials.gov/; Unique Identifier: NCT00911508.

3 July 2026 in EP Europace
Verified
Journal Article
Open access
HLHongyu Liu
Hongyu Liu
RHRunhui Hu
Runhui Hu
WLWenhui Li
Wenhui Li
ESEva Soler-Espejo
Eva Soler-Espejo
TBTommaso Bucci
Tommaso Bucci
Gregory LipGregory Lip
Gregory Lip
Aims: Early recurrence of atrial tachyarrhythmia (ERAT) after catheter ablation for atrial fibrillation (AF) is common, yet its prognostic significance and implications for the duration of the blanking period remain uncertain. We aimed to evaluate the association between ERAT and post-ablation clinical outcomes, late arrhythmia recurrence, and AF burden, and to explore the optimal duration of the blanking period. Methods and results: This post hoc analysis included 811 patients from the CABANA trial who underwent catheter ablation and had trial-specific electrocardiographic monitoring data available. ERAT was defined as any episode of AF, atrial flutter, or atrial tachycardia lasting >30 s within the 90-day blanking period. The primary outcome was a composite of all-cause mortality, disabling stroke, serious bleeding, or cardiac arrest. Secondary outcomes included cardiovascular hospitalization and late atrial tachyarrhythmia recurrence. During a median 4 years (IQR 2.5–5.2) follow-up, ERAT occurred in 567 patients (69.9%). Patients with ERAT had higher risks of cardiovascular hospitalization [adjusted hazard ratio (aHR) 1.35, 95% confidence interval (CI) 1.07–1.71] and of the composite outcome of all-cause mortality or cardiovascular hospitalization (aHR 1.33, 95% CI 1.07–1.66), but no increased risk of the primary composite outcome. ERAT was independently associated with late atrial tachyarrhythmia recurrence (aHR 1.35, 95% CI 1.07–1.71). Prognostic relevance varied by timing, with the strongest association observed for ERAT occurring between 60 and 90 days after ablation (aHR 1.80, 95% CI 1.16–2.79). Receiver operating characteristic analysis identified 58 days as the optimal threshold for predicting late arrhythmia recurrence (AUC 0.727). Conclusion: ERAT was associated with higher risks of cardiovascular hospitalization and late atrial tachyarrhythmia recurrence in a time-dependent manner, supporting a shorter blanking period to better identify patients at risk of adverse rhythm outcomes.