Deep learning analysis of electrocardiography (ECG) may predict cardiovascular outcomes. We present a novel multi-task deep learning model, the ECG-MACE, which predicts the one-year first-ever major adverse cardiovascular events (MACE) using 2,821,889 standard 12-lead ECGs, including training (n = 984,895), validation (n = 422,061), and test (n = 1,414,933) sets, from Chang Gung Memorial Hospital database in Taiwan. Data from another independent medical center (n = 113,224) was retrieved for external validation. The model’s performance achieves AUROCs of 0.90 for heart failure (HF), 0.85 for myocardial infarction (MI), 0.76 for ischemic stroke (IS), and 0.89 for mortality. Furthermore, it outperforms the Framingham risk score at 5-year MACEs and 10-year mortality prediction. Over 10-year follow-ups, the model-predicted-positive group exhibits significantly higher MACE incidences than the model-predicted-negative group (relative incidence ratio: HF: 15.28; MI: 7.87; IS: 4.74; mortality: 13.18). Using solely ECGs, ECG-MACE effectively predicts one-year events and exhibits long-term anticipation. It provides potential applications in preventive medicine.

Objective: To compare the real‐world effectiveness and tolerability of calcitonin gene‐related peptide (CGRP) monoclonal antibodies (mAbs) and onabotulinumtoxinA in chronic migraine (CM) patients.Methods: This multicenter study involved retrospective analysis of prospectively collected data of CM patients treated with CGRP mAbs or onabotulinumtoxinA, including difficult‐to‐treat (DTT) patients (i.e., ≥3 preventive failures). Treatment outcomes were determined at 6 months based on prospective headache diaries and Migraine Disability Assessment (MIDAS).Results: The study included 316 (55 M/261F, mean age 44.4 ± 13.5 years) and 333 (61 M/272F, mean age 47.9 ± 13.4 years) CM patients treated with CGRP mAbs or onabotulinbumtoxinA, respectively. At 6 months, CGRP mAb treatment was associated with a greater decrease in monthly migraine days (MMDs) (−13.0 vs. −8.7 days/month, p < 0.001) and a higher ≥50% responder rate (RR) (74.7% vs. 50.7%, p < 0.001) compared with onabotulinumtoxinA injections. The findings were consistent in DTT patients (−13.0 vs. −9.1 MMDs, p < 0.001; ≥50% RR: 73.9% vs. 50.3%, p < 0.001) or those with medication‐overuse headache (MOH) (−13.3 vs. −9.0 MMDs, p < 0.001; ≥50% RR: 79.0% vs. 51.6%, p < 0.001). Besides, patients receiving CGRP mAbs had greater improvement (−42.2 vs. −11.8, p < 0.001) and a higher ≥50% RR (62.0% vs. 40.0%, p = 0.001) in MIDAS scores and a lower rate of adverse events (AEs) (6.0% vs. 21.0%, p < 0.001). However, none of the patients discontinued treatment due to AEs.Conclusions: In this multicenter, real‐world study, CGRP mAbs were more effective than onabotulinumtoxinA in CM patients, even in DTT or MOH patients. All of these injectables were well tolerated. Further prospective studies are needed to verify these findings.

Background: Statins are frequently prescribed with direct oral anticoagulants (DOACs), and previous studies have raised concerns about the increased risk of intracerebral hemorrhage or other major bleeding in concurrent statins and DOACs use. The objective of this study is to evaluate the risk of major bleeding in non-valvular atrial fibrillation patients taking DOACs with or without statins.Methods: This nationwide, retrospective cohort study used data from the Taiwan National Health Insurance Research Database, enrolled a total of 90,731 non-valvular atrial fibrillation patients receiving rivaroxaban, dabigatran, apixaban or edoxaban from January 1st, 2012 to December 31st, 2017. Major bleeding was defined as a hospitalization or emergency department visit with a primary diagnosis of intracerebral hemorrhage, gastrointestinal tract bleeding, urogenital tract bleeding, or other sites of bleeding. Adjusted incidence rate ratios (IRR) and differences of major bleeding between person-quarters of DOACs with or without statins were estimated using a Poisson regression and inverse probability of treatment weighting using the propensity score.Results: 50,854 (56.0%) of them were male with a mean age of 74.9 (SD, 10.4) years. Using DOACs without statins as a reference, the adjusted IRR for all major bleedings in concurrent use of DOACs and statins was 0.8 (95% CI 0.72–0.81). Lower major bleeding risk was seen in both low-to-moderate-intensity statins (IRR: 0.8, 95% CI 0.74–0.84) and high-intensity statins (IRR: 0.8, 95% CI 0.74–0.88). Concurrent use of DOACs and statins decreased the risk for intracerebral hemorrhage with an IRR of 0.8 (95% CI 0.66–0.93), and gastrointestinal tract bleeding with an IRR of 0.7 (95% CI 0.69–0.79). The protective effect of statins on intracerebral hemorrhage was observed only in female patients (IRR 0.67, 95% CI 0.51–0.89), but not in male patients (IRR 0.87, 95% CI 0.70–1.08).Conclusions: Among non-valvular atrial fibrillation patients who were taking DOACs, concurrent use of statins decreased major bleeding risk, including intracerebral hemorrhage and gastrointestinal tract bleeding. Considering this and other cardioprotective effects, statins should be considered in all eligible patients prescribed with DOACs.

Background: The objective is to study whether the cardiovascular protective effects of colchicines could be applied to non-cardiogenic ischemic stroke (IS) patients. Patients and Methods: Non-cardiogenic IS patients were identified from the National Health Insurance Research Database. Eligible patients were divided into chronic and non-chronic use categories based on their long-term status of colchicine use. The non-chronic use category was subdivided into (1) non-user and (2) new user groups while the chronic use category was divided into (3) former user and (4) long-term user groups according to the patient’s recent status of colchicine use. Inverse probability of treatment weights for propensity scores was used to balance the baseline characteristics. The primary outcome was recurrent IS, which was compared within the non-chronic use and chronic use categories. Results: In the non-chronic use category, the number of patients was 355,498 and 912 in the non-user and new user groups, respectively. In the chronic use category, the number of patients was 4737 and 4354 in the former user and long-term user groups, respectively. In the non-chronic use category, patients in the new user group had a marginally lower risk of recurrent IS at 6-months (subdistribution hazard ratio [SHR], 0.95; 95% confidence interval [CI], 0.94–0.97) and 2-years (SHR, 0.92; 95% CI, 0.91–0.93) follow up. In the chronic use category, patients in the long-term user group also had a marginally lower risk of recurrent IS at 6-months (SHR, 0.87; 95% CI, 0.86–0.88) and 2-years (SHR, 0.87; 95% CI, 0.86–0.88) follow up. The effect of colchicine on the reduced risk of recurrent IS was more favorable in patients who also used statins. Conclusions: Recent colchicine use in acute non-cardiogenic IS patients is associated with marginal fewer incidences of recurrent IS. Patients with concurrent statin use may have more profound protective effects.

Background and purpose: to investigate the frequency of cervical–cranial vascular complications soon after radiation therapy (RT) and identify differences among patients with various types of head and neck cancer (HNC). Methods: We enrolled 496 patients with HNC who had received their final RT dose in our hospital. These patients underwent carotid duplex ultrasound (CDU) for monitoring significant carotid artery stenosis (CAS). Brain imaging were reviewed to detect vertebral, intracranial artery stenosis, or preexisted CAS before RT. Primary outcome was significant CAS at the internal or common carotid artery within first 5 years after RT. We categorized the patients into nasopharyngeal carcinoma (NPC) and non-NPC groups and compared the cumulative occurrence of significant CAS between the groups using Kaplan–Meier and Cox-regression analyses. Results: Compared to the NPC group, the non-NPC group had a higher frequency of significant CAS (12.7% vs. 2.0%) and were more commonly associated with significant CAS after adjusting the covariates (Adjusted hazard ratio: 0.17, 95% confident interval: 0.05–0.57) during the follow-up period. All the non-NPC subtypes (oral cancer/oropharyngeal, hypopharyngeal, and laryngeal cancers) were associated with higher risks of significant CAS than the NPC group (p < 0.001 respectively). Conclusion: Significant CAS was more frequently noted within 5 years of RT among the patients with non-NPC HNC than among the patients with NPC. Scheduled carotid artery surveillance and vascular risk monitoring should be commenced earlier for patients with non-NPC HNC. By contrast, vascular surveillance could be deferred to 5 years after RT completion in NPC patients.

Carotid blowout syndrome (CBS) is a rare yet life-threatening complication that occurs after radiation therapy (RT). This study aimed to determine the incidence of CBS in patients with head and neck cancer (HNC) undergoing contemporary RT and to explore potential discrepancies in the risk of CBS between nasopharyngeal cancer (NPC) and non-NPC patients. A total of 1084 patients with HNC who underwent RT between 2013 and 2023 were included in the study. All patients were under regular follow-ups at the radio-oncology department, and underwent annual contrast-enhanced computed tomography and/or magnetic resonance imaging for cancer recurrence surveillance. Experienced neuroradiologists and vascular neurologists reviewed the recruited patients’ images. Patients were further referred to the neurology department for radiation vasculopathy evaluation. The primary outcome of this study was CBS. Patients were categorized into NPC and non-NPC groups and survival analysis was employed to compare the CBS risk between the two groups. A review of the literature on CBS incidence was also conducted. Among the enrolled patients, the incidence of CBS in the HNC, NPC, and non-NPC groups was 0.8%, 0.9%, and 0.7%, respectively. Kaplan–Meier analysis revealed no significant difference between the NPC and non-NPC groups (p = 0.34). Combining the findings for our cohort with those of previous studies revealed that the cumulative incidence of CBS in patients with HNC is 5% (95% CI = 3–7%) after both surgery and RT, 4% (95% CI = 2–6%) after surgery alone, and 5% (95% CI = 3–7%) after RT alone. Our findings indicate a low incidence of CBS in patients with HNC undergoing contemporary RT. Patients with NPC may have a CBS risk close to that of non-NPC patients. However, the low incidence of CBS could be a potentially cause of selection bias and underestimation bias.