HFHan Feng

Han Feng

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Han Feng has a total of 164 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Reclassifying Single Lead Sinus Rhythm ECGs for Improved AF Recurrence Detection With Deep Learning

    by Yingshuo Liu, Chanho Lim, Ghassan Bidaoui, Christian Massad, Yunsung Chung, Hadi Younes, Mayana Bsoul, Yishi Jia, Abboud Hassan, Cong Zhao, et al.

    BACKGROUND: Atrial fibrillation (AF) remains a common outcome after catheter ablation, with recurrence observed in up to 50% of patients within 5 years. Despite extensive research, challenges remain in optimizing observation and prediction windows for AF recurrence assessment. Therefore, we developed and validated a novel deep learning model that reclassifies sinus rhythm based on past and future AF events using single-lead ECG strips from handheld devices. METHODS: Of the 558 participants, 308 with no documented recurrence during study follow-up contributed Benign Sinus strips, while 250 with documented recurrence contributed sinus rhythm strips recorded within ±3 days of an AF event, defined as Severe Sinus strips. Both clinical feature-based models and a deep learning model were used to classify these ECGs according to their proximity to AF recurrence events. Performance was evaluated using area under the receiver operating characteristic curve, accuracy, sensitivity, specificity, and F1-score. RESULTS: The strip-level pretrained deep learning model achieved an area under the receiver operating characteristic curve of 0.86, with sensitivity of 0.79, and specificity of 0.76. The complementary participant-level clinical feature-based Random Forest benchmark achieved an area under the receiver operating characteristic curve of 0.71, sensitivity of 0.58, and specificity of 0.69. Feature-based analyses identified associations involving heart-rate variability, mean R–R interval, female sex, left atrial volume, and mean P-wave duration. CONCLUSIONS: Our dynamic deep learning model reclassifies 30-second single-lead sinus rhythm ECGs based on AF events within ±3 days, transforming a brief ECG snapshot into a summarized indicator of short-term AF risk.

  • The Effectiveness and Safety of Deep Sedation Protocols for Pulsed Field Ablation of Atrial Fibrillation

    by Yize Zhao, Fadong Li, Jue Wang, Le Zhou, Xiangyi Kong, Shaobin Wei, Mengge Zhou, Han Feng, Zhicong Wang, Yueqing Mu, et al.

    Background: Deep sedation (DS) is increasingly utilized during pulsed field ablation (PFA) for atrial fibrillation (AF), but the optimal electrophysiologist‐led sedation regimen remains unclear. Objective: To compare sedative effectiveness and safety of three electrophysiologist‐led DS protocols. Methods: In this prospective, single‐center study, AF patients undergoing focal‐form PFA received (1) midazolam + fentanyl (Midazolam group), (2) flurbiprofen axetil + midazolam + fentanyl (Flurbiprofen group), or (3) dexmedetomidine + fentanyl (Dexmedetomidine group). The primary endpoint was the achievement of the target sedation level at ablation initiation (Ramsay Sedation Score ≥3). Secondary endpoints included intraoperative pain, sedation difficulty, operator satisfaction, and sedation‐related adverse events. Results: 166 patients (mean age, 62.2 ± 10.8 years; 62.7% male; 48.2% with paroxysmal AF) were enrolled, with 53, 67, and 46 patients included in the Midazolam, Flurbiprofen, and Dexmedetomidine groups, respectively. The primary outcome occurred more frequently in the Flurbiprofen (73.1%) and Dexmedetomidine (82.6%) groups compared to Midazolam (47.2%) (overall p < 0.001); Flurbiprofen and Dexmedetomidine group did not differ significantly. Intraoperative pain scores were lowest with Dexmedetomidine (overall p < 0.001). Both Flurbiprofen and Dexmedetomidine groups showed lower sedation difficulty and higher operator satisfaction than the Midazolam group (both overall p < 0.001). Dexmedetomidine was associated with more intraoperative hypotension (overall p = 0.047). Conclusion: Electrophysiologist‐led DS protocols with Flurbiprofen and Dexmedetomidine were associated with higher target sedation attainment than the specific low‐dose Midazolam regimen during PFA, but Dexmedetomidine is linked to higher hypotension rates, warranting caution.

  • Open Access

    Pulmonary Vein Isolation Alone Versus Adjunctive Ablation for Paroxysmal Atrial Fibrillation

    by Michel Abou Khalil, Christian M. Massad, Eli Tsakiris, William Herbst, Maximilian Moersdorf, Mohammad Montaser Atasi, Yara Menassa, Alex El Darzi, Carlo El Khoury, Ghassan Bidaoui, et al.

    Background: Pulmonary vein isolation (PVI) is the standard ablation strategy for paroxysmal atrial fibrillation (PAF). Despite guideline recommendations favoring PVI alone in PAF, some operators routinely perform extra pulmonary vein ablation (PVI+) during initial procedures. Objective: To determine frequency of PVI+ strategy for treatment of PAF in the real world and examine its impact on arrhythmic recurrence and progression compared to PVI alone. Methods: Using the TriNetX research network, we identified adults with PAF who underwent catheter ablation between January 2020 and January 2024. Recurrence was defined as repeat ablation, cardioversion, or antiarrhythmic drug (AAD) use beyond a 3‐month blanking period. Progression to persistent AF and atypical atrial flutter were also assessed. Kaplan‐Meier analysis was performed with 3‐year follow‐up. Results: Before matching, 5134 of 18,891 patients (27.2%) underwent PVI+. In the propensity matched analysis ( n = 5020 per group), recurrence was significantly higher in the PVI+ group (HR 1.28, 95% CI 1.16–1.42; p < 0.001). Repeat ablation, cardioversion and AAD use were more common with PVI+ (HR 1.99, 95% CI 1.60–2.46; p < 0.0001, HR 1.37, 95% CI 1.13–1.66; p = 0.001, and HR 1.41, 95% CI 1.05–1.87; p = 0.020, respectively). Progression to persistent AF was higher with PVI+ (HR 1.37, 95% CI 1.23–1.53, p < 0.001), as was atypical atrial flutter (HR 2.63, 95% CI 1.97–3.50; p < 0.0001). Conclusion: Extra‐pulmonary vein ablation during first‐time PAF ablation remains common in real‐world practice but is associated with worse outcomes including repeat ablation, cardioversion, AAD use, atrial flutter, and progression to persistent AF.

  • Open Access

    Repeat catheter ablation vs. direct current cardioversion for recurrent atrial fibrillation after prior ablation: a propensity-matched analysis

    by Michel Abou Khalil, Mohammad Montaser Atasi, Yara Menassa, Maximilian Moersdorf, Christian M Massad, Alex El Darzi, Carlo El Khoury, Yishi Jia, Ghassan Bidaoui, Hadi Younes, et al.

  • Open Access

    Health Electronic Assessment of Risks and Trends using Biometric Equipment and Technology (HEARTBEAT): study design and rationale

    by Nassir Marrouche, Christian Massad, Han Feng, Ala Assaf, Mayana Bsoul, Yara Menassa, Ghassan Bidaoui, Qussay Marashly, Chanho Lim

    Aims: Cardiovascular disease remains the leading driver of morbidity and mortality worldwide. As consumer smartwatches become ubiquitous, they offer a practical platform for continuous, real-world phenotyping, capturing passive and active biometrics that may detect occult disease and anticipate adverse cardiovascular events. Scaled deployment of these devices could enable remote screening, longitudinal monitoring, and earlier risk mitigation beyond traditional episodic care. Methods and results: The Health Electronic Assessment of Risks and Trends using Biometric Equipment and Technology (HEARTBEAT) study is a prospective, single-arm wearable study that has enrolled 897 participants since 10 October 2024. The primary objectives are to: (1) define associations between smartwatch-derived biometrics and incident cardiovascular events; (2) derive biometric profiles that support identification of underlying cardiometabolic and cardiovascular conditions; and (3) apply artificial intelligence to improve prediction of cardiovascular events. Participants are screened, consented, and enrolled in person or remotely. Data are captured through electronic medical record (EMR) extraction and a companion smartphone application. Participants are followed for 12 months, with outcomes adjudicated on an ongoing basis using EMR review and app-based surveys. Conclusion: The HEARTBEAT study will test whether scalable, consumer-grade wearables can move from wellness tracking to clinically meaningful signal, identifying comorbidities and predicting adverse cardiovascular outcomes in routine care settings. If successful, the study will help establish an evidence base for smartwatches as validated digital health tools for remote screening and continuous cardiovascular monitoring.

  • Open Access

    A Dual‐Modal Wearable PPG Smartwatch with AI‐Enhanced Correction for High‐Accuracy and Continuous AF Burden Assessment

    by Song Zuo, Jinglei Wang, Xin Wang, Han Feng, Yize Zhao, Fadong Li, Shaobin Wei, Le Zhou, Zixu Zhao, Songjie Chen, et al.

    Atrial fibrillation (AF) increases the risk of stroke and heart failure, yet accurate quantification of AF burden in daily life remains difficult. Although smartwatch photoplethysmography (PPG) supports continuous monitoring, complex rhythms and signal noise can impair burden estimation. We developed an AI‐enhanced dual‐modal framework that combines continuous watch‐based PPG (W‐PPG) with intermittent single‐lead watch‐based ECG (W‐ECG). A hybrid convolutional neural network–long short‐term memory model uses high‐fidelity W‐ECG segments as dynamic anchors to correct long‐term W‐PPG classifications. In this prospective validation study, 1,054 patients with AF undergoing catheter ablation (mean age, 62.1 years) were evaluated against patch‐based ECG as the reference standard. After ECG‐based correction, the system achieved 98.60% sensitivity and 99.27% specificity. The mean absolute percentage error of AF burden decreased by 23.4%, from 1.11% to 0.85%, while the Pearson correlation remained 0.9988. This dual‐modal approach offers a scalable and clinically practical solution for long‐term AF monitoring, improving burden estimation beyond PPG‐only devices without requiring continuous multi‐lead ECG. It may support personalized AF management and large‐scale cardiovascular screening in real‐world settings. (NCT06552468)


  • Open Access

    Gastrointestinal Bleeding Risk Associated With Pulse Pressure in Patients With Atrial Fibrillation: A Retrospective Cohort Study (Preprint)

    by Michel Abou Khalil, Carlo El Khoury, Maximilian Moersdorf, Christian Massad, Alex El Darzi, Yara Menassa, Mohammad Montaser Atasi, Ghassan Bidaoui, Hadi Younes, Ala Assaf, et al.

    Background: Patients with atrial fibrillation (AF) face significant bleeding risks, particularly those receiving oral anticoagulation; however, existing risk scores such as HAS-BLED and ORBIT demonstrate limited predictive accuracy. Pulse pressure (PP), calculated as the difference between systolic blood pressure (SBP) and diastolic blood pressure, is a noninvasive marker of arterial stiffness that has been associated with cardiovascular outcomes. However, PP has not been evaluated as a predictor of bleeding in this population. Objective: This study evaluated whether elevated PP independently predicts major bleeding events, overall and by subtype, in patients with AF after adjusting for established clinical risk factors. Methods: We conducted a retrospective cohort study using electronic health records from REACHnet, a PCORnet-affiliated clinical data network in Louisiana. A total of 4935 adults (mean age 63.7, SD 11.0 y; n=1606, 32.5% female) with AF between 2010 and 2019 were included via consecutive sampling of all eligible patients. PP was derived from outpatient blood pressure measurements closest to AF diagnosis and analyzed in tertiles (low: 62 mm Hg) and continuously per 10 mm Hg. The primary outcome was time to the first bleeding event, a composite of gastrointestinal bleeding, intracranial hemorrhage, and other clinically significant bleeding, identified using ICD-9 / ICD-10 codes. Kaplan-Meier survival curves with log-rank testing were used for univariable analysis. Multivariable Cox proportional hazards regression was adjusted for age, sex, race, comorbidities, medications, and the ORBIT score. A sensitivity analysis applied multivariable logistic regression additionally incorporating SBP. Statistical significance was set at P <.05. Results: Over a 5-year follow-up, 677 out of 4935 (13.7%) patients experienced a bleeding event (intracranial hemorrhage: n=60, 1.2%; gastrointestinal bleeding: n=195, 4.0%; and other bleeding: n=149, 3.0%). Gastrointestinal bleeding differed significantly across PP tertiles ( P= .007). Kaplan-Meier analysis confirmed lower gastrointestinal bleeding-free survival in the highest tertile (log-rank P= .004). No significant differences were observed for intracranial ( P= .08), other ( P =.58), or composite bleeding ( P =.22). In multivariable Cox regression, each 1 mm Hg increase in PP was independently associated with a 1.4% higher gastrointestinal bleeding risk (hazard ratio 1.014, 95% CI 1.001‐1.028; P= .04), approximately 15% per 10 mm Hg. This remained significant after adjusting for SBP and ORBIT score (odds ratio 1.013/mm Hg, 95% CI 1.001‐1.025; P =.03), while SBP was not independently significant ( P =.13). Conclusions: PP independently predicts gastrointestinal bleeding risk in patients with AF beyond established clinical risk factors and validated bleeding risk scores. Unlike prior investigations that examined SBP or diastolic blood pressure components in isolation, this is the first study to identify PP as a predictor of gastrointestinal bleeding in this population. As a readily available, low-cost hemodynamic parameter derived from routine clinical measurements, PP could enhance existing risk stratification tools and inform more personalized bleeding risk management strategies in patients with AF.

  • Open Access

    Prediction of Stroke Risk in Patients with Atrial Fibrillation: Comorbidities vs Temporal AF Behavior

    by Eli Tsakiris, Mario Mekhael, Yuxuan Gu, Christian Massad, Ghassan Bidaoui, Yishi Jia, Yingshuo Liu, Mohammad Montaser Atasi, Yara Menassa, Michel Abou Khalil, et al.

    Background: There are controversies about whether atrial fibrillation (AF) type, paroxysmal (PaAF) vs persistent (PeAF), affects stroke risk. The type of AF is still not included in most risk stratification tools. Objective: We aim to assess differences in stroke outcomes between PaAF and PeAF patients in both low- and high-CHA 2 DS 2 -VASc groups. Methods: We conducted an epidemiological study of all patients admitted to Tulane Medical Center with the diagnosis of AF from January 2010 to March 2020. Data were extracted from the regional US electronic medical records database, Research Action for Health Network (REACHnet), for all patients aged 18 years or older with a diagnosis of AF. Patients were divided into four groups: a low CHA 2 DS 2 -VASc score was defined as CHA 2 DS 2 -VASc < 2 in women and CHA 2 DS 2 -VASc < 1 in men. PeAF was defined as a patient with at least one episode of AF lasting 7 days or more. PaAF was defined as a patient with AF with no episode lasting more than 7 days. The outcome of the study was an ischemic stroke event or a transient ischemic attack that occurred after the diagnosis of AF. Kaplan-Meier curves and the log-rank test were used to compare the study outcomes across all four groups. Multivariable Cox regression was performed to adjust for the use of anticoagulants. Results: A total of 1,079 patients were included in the study. 576 patients had PaAF and high CHA 2 DS 2 -VASc, 215 had PaAF and low CHA 2 DS 2 -VASc, 214 had PeAF and high CHA 2 DS 2 -VASc, and 74 patients were PeAF, and low CHA 2 DS 2 -VASc. Patients were followed up over 5 years. Based on the Log-rank test, there were significant differences among the four groups (p < 0.001). After adjusting for anticoagulants, patients with high CHA 2 DS 2 -VASc appeared to have more strokes on follow-up than patients with low CHA 2 DS 2 -VASc, independent of AF type and anticoagulation prescription. For the Cox model, when the PaAF High CHA 2 DS 2 -VASc group was used as the reference, both low CHA 2 DS 2 -VASc groups, PaAF (0.032 [0.012–0.081], p < 0.001) and PeAF (0.032 [0.008–0.135], p < 0.001), had a lower risk of stroke. However, there was no difference in stroke when the reference group was compared to high CHA 2 DS 2 -VASc, PeAF (1.169 [0.866 – 1.576], p=0.308). Conclusion: In our database, the CHA 2 DS 2 -VASc score remained superior to the type of AF when predicting stroke outcome. Type of AF did not affect stroke outcome even after adjusting for CHA 2 DS 2 -VASc and for anticoagulation prescription.