Descriptions of Etiology, Clinical Course, and Prognosis of Patients Presenting with Pericardial Effusion.

Pericardial effusion (PE) presentation varies from an incidental finding to a life-threatening situation; thus, its etiology and clinical course remain unknown. The aim of the present study was to retrospectively investigate these factors.We analyzed 171 patients (0.4%) who presented with PE among 34,873 patients who underwent echocardiography between 2011 and 2021 at our hospital. Clinical and prognostic information was retrieved from electronic medical records. The primary endpoints were all-cause death, hospitalization due to heart failure (HF), and other cardiovascular events such as cardiovascular death, acute coronary syndrome, elective percutaneous coronary intervention, and stroke.The etiologies of PE were as follows: idiopathic (32%), HF-related (18%), iatrogenic (11%), cardiac surgery-related (10%), radiation therapy-related (9%), malignancy (8%), pericarditis/myocarditis (8%), myocardial infarction-related (2%), and acute aortic dissection (2%). Patients with idiopathic/HF etiology were more likely to be older than the others.During a mean follow-up period of 2.5 years, all-cause death occurred in 21 patients (12.3%), cardiovascular events in 10 patients (5.8%), and hospitalization for HF in 24 patients (14.0%). All-cause death was frequently observed in patients with malignancy (44% per person-year). Cardiovascular events were mostly observed in patients with radiation therapy-related and malignancy (8.6% and 7.3% per person-year, respectively).The annual incidence of hospitalization for HF was the highest in patients with HF-related (25.1% per person-year), followed by radiation therapy-related (10.4% per person-year).This retrospective study is the first, to the best of our knowledge, to reveal the contemporary prevalence of PE, its cause, and outcome in patients who visited a cardiovascular hospital in an urban area of Japan.

Identifying patients with acute aortic dissection using an electrocardiogram with convolutional neural network.

Background: The potential of utilizing artificial intelligence with electrocardiography (ECG) for initial screening of aortic dissection (AD) is promising. However, achieving a high positive predictive rate (PPR) remains challenging. Methods and results: This retrospective analysis of a single-center, prospective cohort study (Shinken Database 2010-2017, N = 19,170) used digital 12-lead ECGs from initial patient visits. We assessed a convolutional neural network (CNN) model's performance for AD detection with eight-lead (I, II, and V1-6), single-lead, and double-lead (I, II) ECGs via five-fold cross-validation. The mean age was 63.5 ± 12.5 years for the AD group (n = 147) and 58.1 ± 15.7 years for the non-AD group (n = 19,023). The CNN model achieved an area under the curve (AUC) of 0.936 (standard deviation [SD]: 0.023) for AD detection with eight-lead ECGs. In the entire cohort, the PPR was 7 %, with 126 out of 147 AD cases correctly diagnosed (sensitivity 86 %). When applied to patients with D-dimer levels ≥1 µg/dL and a history of hypertension, the PPR increased to 35 %, with 113 AD cases correctly identified (sensitivity 86 %). The single V1 lead displayed the highest diagnostic performance (AUC: 0.933, SD: 0.03), with PPR improvement from 8 % to 38 % within the same population. Conclusions: Our CNN model using ECG data for AD detection achieved an over 30% PPR when applied to patients with elevated D-dimer levels and hypertension history while maintaining sensitivity. A similar level of performance was observed with a single-lead V1 ECG in the CNN model.

Evaluating convolutional neural network-enhanced electrocardiography for hypertrophic cardiomyopathy detection in a specialized cardiovascular setting.

The efficacy of convolutional neural network (CNN)-enhanced electrocardiography (ECG) in detecting hypertrophic cardiomyopathy (HCM) and dilated HCM (dHCM) remains uncertain in real-world applications. This retrospective study analyzed data from 19,170 patients (including 140 HCM or dHCM) in the Shinken Database (2010-2017). We evaluated the sensitivity, positive predictive rate (PPR), and F1 score of CNN-enhanced ECG in a ''basic diagnosis'' model (total disease label) and a ''comprehensive diagnosis'' model (including disease subtypes). Using all-lead ECG in the "basic diagnosis" model, we observed a sensitivity of 76%, PPR of 2.9%, and F1 score of 0.056. These metrics improved in cases with a diagnostic probability of ≥ 0.9 and left ventricular hypertrophy (LVH) on ECG: 100% sensitivity, 8.6% PPR, and 0.158 F1 score. The ''comprehensive diagnosis'' model further enhanced these figures to 100%, 13.0%, and 0.230, respectively. Performance was broadly consistent across CNN models using different lead configurations, particularly when including leads viewing the lateral walls. While the precision of CNN models in detecting HCM or dHCM in real-world settings is initially low, it improves by targeting specific patient groups and integrating disease subtype models. The use of ECGs with fewer leads, especially those involving the lateral walls, appears comparably effective.

Lead-Specific Performance for Atrial Fibrillation Detection in Convolutional Neural Network Models Using Sinus Rhythm Electrocardiography.

Background: We developed a convolutional neural network (CNN) model to detect atrial fibrillation (AF) using the sinus rhythm ECG (SR-ECG). However, the diagnostic performance of the CNN model based on different ECG leads remains unclear. Methods and Results: In this retrospective analysis of a single-center, prospective cohort study, we identified 616 AF cases and 3,412 SR cases for the modeling dataset among new patients (n=19,170). The modeling dataset included SR-ECGs obtained within 31 days from AF-ECGs in AF cases and SR cases with follow-up ≥1,095 days. We evaluated the CNN model's performance for AF detection using 8-lead (I, II, and V1-6), single-lead, and double-lead ECGs through 5-fold cross-validation. The CNN model achieved an area under the curve (AUC) of 0.872 (95% confidence interval (CI): 0.856-0.888) and an odds ratio of 15.24 (95% CI: 12.42-18.72) for AF detection using the eight-lead ECG. Among the single-lead and double-lead ECGs, the double-lead ECG using leads I and V1 yielded an AUC of 0.871 (95% CI: 0.856-0.886) with an odds ratio of 14.34 (95% CI: 11.64-17.67). Conclusions: We assessed the performance of a CNN model for detecting AF using eight-lead, single-lead, and double-lead SR-ECGs. The model's performance with a double-lead (I, V1) ECG was comparable to that of the 8-lead ECG, suggesting its potential as an alternative for AF screening using SR-ECG.

Identification of patients with dilated phase of hypertrophic cardiomyopathy using a convolutional neural network applied to multiple, dual, and single lead electrocardiograms.

Background: This study sought to develop an artificial intelligence-derived model to detect the dilated phase of hypertrophic cardiomyopathy (dHCM) on digital electrocardiography (ECG) and to evaluate the performance of the model applied to multiple-lead or single-lead ECG. Methods: This is a retrospective analysis using a single-center prospective cohort study (Shinken Database 2010-2017, n = 19,170). After excluding those without a normal P wave on index ECG (n = 1,831) and adding dHCM patients registered before 2009 (n = 39), 17,378 digital ECGs were used. Totally 54 dHCM patients were identified of which 11 diagnosed at baseline, 4 developed during the time course, and 39 registered before 2009. The performance of the convolutional neural network (CNN) model for detecting dHCM was evaluated using eight-lead (I, II, and V1-6), single-lead, and double-lead (I, II) ECGs with the five-fold cross validation method. Results: The area under the curve (AUC) of the CNN model to detect dHCM (n = 54) with eight-lead ECG was 0.929 (standard deviation [SD]: 0.025) and the odds ratio was 38.64 (SD 9.10). Among the single-lead and double-lead ECGs, the AUC was highest with the single lead of V5 (0.953 [SD: 0.038]), with an odds ratio of 58.89 (SD:68.56). Conclusion: Compared with the performance of eight-lead ECG, the most similar performance was achieved with the model with a single V5 lead, suggesting that this single-lead ECG can be an alternative to eight-lead ECG for the screening of dHCM.

Association between serum alkaline phosphatase and cardiovascular events in patients with atrial fibrillation.

High alkaline phosphatase (ALP) levels are reported to be associated with an increased risk of cardiovascular events in patients with chronic kidney disease (CKD). Given the pathological link with CKD, a similar relationship may exist in patients with atrial fibrillation (AF). We retrospectively evaluated 1,719 patients with AF and normal hepatic function who were registered in the Shinken Database between November 2011 and March 2017. Study patients were divided into three groups according to ALP value tertiles with cut-offs of 175 and 227 IU/L (normal range: 95-350 IU/L). Each group's incidence rate was recorded, and the risks of cardiovascular events and each component for patients in the middle and high ALP tertiles were compared with those in the low tertile and evaluated using Cox regression models. The additional predictive value of the high ALP tertile over the existing risk scores for the components of cardiovascular events was evaluated via receiver operating characteristic (ROC) curve analysis. During the median follow-up of 731 days (IQR: 444-1095 days), 137 cardiovascular events occurred, with incidence rates of 2.94%, 3.44%, and 6.19%/person-year for the low, middle, and high ALP tertiles, respectively. Of these cardiovascular events, heart failure had the highest incidence rates (1.34%, 1.89%, and 4.29%/person-year for the low, middle, and high ALP tertiles, respectively) and the incidence rates of the other components of cardiovascular event were similar in each ALP groups. Multivariate Cox regression analysis yielded hazard ratios of 1.22 (95% confidence interval [CI] 0.70-1.96) and 1.62 (95% CI 1.06-2.48) for cardiovascular events and 1.66 (95% CI 0.87-3.15) and 2.50 (95% CI 1.39-4.48) for heart failure admission in the middle and high ALP tertiles, respectively. By ROC curve analysis for heart failure admission showed that the high ALP tertile lacked significant additive predictive value over the existing risk scores. High serum ALP levels, even those in the normal range, were significantly associated with an increased risk of cardiovascular events, especially heart failure admission in patients with AF.

Five-year clinical outcomes of a 2.25 mm sirolimus-eluting stent in Japanese patients with very small coronary artery disease: final results of the CENTURY JSV study.

The aim of this study is to evaluate the long-term safety and efficacy of the 2.25 mm bioresorbable-polymer sirolimus-eluting Ultimaster stent in a Japanese patient population. Treatment of coronary artery disease in very small vessels is associated with an increased risk for cardiac events. The CENTURY JSV study is a prospective, multicenter, single-arm study. Seventy patients with stable and unstable coronary artery disease with a coronary lesion eligible for implantation with a 2.25 mm stent were enrolled in this study. Patients underwent clinical follow-up through 5-year after the PCI procedure. The mean age was 70.4 ± 9.2 years. The prevalence of diabetes mellitus was 37.1%, all not insulin dependent. The incidence of major adverse cardiac events, defined as cardiac death, target vessel myocardial infarction (MI), and clinically driven target lesion revascularization (CD-TLR) at 5 years was 5.7%. A non-Q wave MI was noted in 1.4% and 4.3% underwent a CD-TLR. There was no stent thrombosis during the entire follow-up period. No cardiac events were reported between 2 and 5 years. This is the first study to demonstrate safety and effectiveness for 5 years after treatment of very small coronary disease with 2.25 mm-diameter DES.Clinical trial registration: UMIN000012928.

Blood culture-negative prosthetic valve endocarditis and daptomycin-associated eosinophilic pneumonia: A case report.

Acute eosinophilic pneumonia is a rare but severe side effect of daptomycin, which has been recommended as empirical antimicrobial drug therapy for blood culture-negative prosthetic valve endocarditis. Here, we present a case of an 82-year-old man who developed fever, cough, and shortness of breath after 23-day treatment with daptomycin for prosthetic valve endocarditis. Bilateral ground-glass opacities were observed on computed tomography with peripheral eosinophilia of 640/µL (7%). Cessation of daptomycin and commencement of corticosteroid therapy improved his symptoms. This case highlights the importance of prompt diagnosis of acute eosinophilic pneumonia in endocarditis patients treated with daptomycin. .

CVIT expert consensus document on primary percutaneous coronary intervention (PCI) for acute myocardial infarction (AMI) update 2022.

Primary Percutaneous Coronary Intervention (PCI) has significantly contributed to reducing the mortality of patients with ST-segment elevation myocardial infarction (STEMI) even in cardiogenic shock and is now the standard of care in most of Japanese institutions. The Task Force on Primary PCI of the Japanese Association of Cardiovascular Interventional and Therapeutics (CVIT) society proposed an expert consensus document for the management of acute myocardial infarction (AMI) focusing on procedural aspects of primary PCI in 2018. Updated guidelines for the management of AMI were published by the European Society of Cardiology (ESC) in 2017 and 2020. Major changes in the guidelines for STEMI patients included: (1) radial access and drug-eluting stents (DES) over bare-metal stents (BMS) were recommended as a Class I indication, (2) complete revascularization before hospital discharge (either immediate or staged) is now considered as Class IIa recommendation. In 2020, updated guidelines for Non-ST-Elevation Myocardial Infarction (NSTEMI) patients, the followings were changed: (1) an early invasive strategy within 24 h is recommended in patients with NSTEMI as a Class I indication, (2) complete revascularization in NSTEMI patients without cardiogenic shock is considered as Class IIa recommendation, and (3) in patients with atrial fibrillation following a short period of triple antithrombotic therapy, dual antithrombotic therapy (e.g., DOAC and single oral antiplatelet agent preferably clopidogrel) is recommended, with discontinuation of the antiplatelet agent after 6 to 12 months. Furthermore, an aspirin-free strategy after PCI has been investigated in several trials those have started to show the safety and efficacy. The Task Force on Primary PCI of the CVIT group has now proposed the updated expert consensus document for the management of AMI focusing on procedural aspects of primary PCI in 2022 version.

Glasgow prognostic score can be a prognostic indicator after percutaneous coronary intervention: a two-center study in Japan.

Glasgow prognostic score (GPS) has been used to evaluate inflammatory response and nutritional status. This study aimed to investigate the impact of nutritional status on cardiac prognosis by using GPS in patients after undergoing percutaneous coronary intervention (PCI). We included 862 patients who underwent PCI for stable angina pectoris between 2015 and 2018. We used the original cutoff values, which were an albumin (Alb) level of 3.5 g/dl and a C-reactive protein (CRP) level of 0.3 mg/dl. We categorized them into the three groups: originally defined GPS (od-GPS) 0 (high Alb and low CRP), 1 (low Alb or high CRP), and 2 (low Alb and high CRP). Major adverse clinical events (MACEs) included all-cause death, nonfatal myocardial infarction, revascularization, and hospitalization for heart failure. The median follow-up period was 398.5 days. During the follow-up, MACEs occurred in 136 patients. Od-GPS 2 had higher prevalence rates in terms of chronic kidney disease (CKD; 31.7% [229/722] vs. 44.9% [53/118] vs. 63.6% [14/22], p < 0.001), hemodialysis (6.4% [46/722] vs. 14.4% [17/118] vs. 31.8% [7/22], p < 0.001), and heart failure cases (HF; 9.1% [66/722] vs. 14.4% [17/118] vs. 27.3% [6/22], p = 0.007), with higher creatinine (1.17 ± 1.37 mg/dl vs. 1.89 ± 2.60 mg/dl vs. 3.49 ± 4.01 mg/dl, p < 0.001) and brain natriuretic peptide levels (104.1 ± 304.6 pg/ml vs. 242.4 ± 565.9 pg/ml vs. 668.1 ± 872.2 pg/ml, p < 0.001) and lower low-density lipoprotein cholesterol (101.5 ± 32.9 mg/dl vs. 98.2 ± 28.8 mg/dl vs. 77.1 ± 24.3 mg/dl, p = 0.002) than od-GPS 0 and 1.Od-GPS 2 (HR 2.42; 95% CI 1.16-5.02; p = 0.018), od-GPS 1 (HR 2.09; 95% CI 1.40-3.13; p < 0.001), diabetes (HR 1.41; 95% CI 1.00-1.99; p = 0.048), CKD (HR 2.10; 95% CI 1.49-2.96; p < 0.001), and HF (HR 1.64; 95% CI 1.05-2.56; p = 0.029) were independent predictors of MACEs. A scoring system using CRP and Alb levels with a milder definition than GPS suitably predicted the risk of MACEs in the patients who underwent PCI.

Identifying risk patterns in older adults with atrial fibrillation by hierarchical cluster analysis: A retrospective approach based on the risk probability for clinical events.

BACKGROUND: Older adults with atrial fibrillation (AF) have highly diverse risk levels for mortality, heart failure (HF), thromboembolism (TE), and major bleeding (MB), thus an integrated risk-pattern algorithm is warranted. METHODS: We analyzed 573 AF patients aged ≥ 75 years from our single-center cohort (Shinken Database 2010-2018). The 3-year risk scores (risk probability) for mortality (M-score), HF (HF-score), TE (TE-score), and MB (MB-score) were estimated for each patient by logistic regression analysis. Using the four risk scores, cluster analysis was performed with Ward's linkage hierarchical algorithm. RESULTS: Three clusters were identified: Clusters 1 (n = 429, 74%), 2 (n = 24, 5%), and 3 (n = 120, 21%). The clusters were characterized as standard risk (Cluster 1), high TE- and MB-risk (Cluster 2), and high M- and HF-risk (Cluster 3). Oral anticoagulants were prescribed for over 80% of the patients in each cluster. Catheter ablation for AF was performed only in Cluster 1 (8.9%). Compared with Cluster 1, Cluster 2 was more closely associated with males, asymptomatic AF, history of cerebral infarction or transient ischemic attack, history of intracranial hemorrhage, high HAS-BLED score (≥3), and low body mass index (<18.0 kg/m2). Cluster 3 was more closely associated with old age, heart failure, and low estimated creatinine clearance (<30 mL/min). CONCLUSION: The cluster analysis identified those at a high risk for all-cause death and HF or a high risk for TE and MB and could support decision making in older adults with AF.

Association between number of medications and mortality among older adult patients in a specialized cardiology hospital.

AIM: Although polypharmacy has been associated with poor clinical outcomes, whether taking an increased number of medications is harmful or beneficial for older adult patients treated for cardiovascular diseases might require further discussion. METHODS: We analyzed data of 2089 patients aged ≥75 years in a single hospital-based cohort. The study population was divided into three groups according to the tertiles of the number of medications at baseline: <3 (n = 647), 3-7 (n = 707) and ≥8 (n = 735). RESULTS: The cumulative incidences of all-cause death at 3 years among patients taking less than three, three to seven and eight or more medications were 3.7%, 4.1% and 7.8%, respectively (log-rank test P = 0.015). In a Cox regression analysis, taking eight or more total medications (vs 0-2) was independently associated with all-cause death (hazard ratio 1.67, 95% CI 1.01-2.78). For predicting mortality using the number of medications, the maximum Youden Index was 7. In subgroups with certain heart diseases, no regular tendency of an increase in the risk of all-cause death was observed with an increase in the number of medications. CONCLUSIONS: The number of medications taken was independently associated with mortality among older adult patients, with a relatively high cut-off point. This association was not observed in patients with certain heart diseases, possibly indicating the merit - rather than the harm - of medical treatment in the cardiovascular field. Geriatr Gerontol Int 2021; 21: 985-995.

Relationship between number of medications and incidence of falls or bone fracture in elderly patients with non-valvular atrial fibrillation: Shinken database analysis.

AIM: Polypharmacy is known to be a risk factor for falls or bone fracture (F/F) in elderly patients. However, this relationship is not fully described in patients with non-valvular atrial fibrillation (NVAF), for which F/F may lead to serious clinical outcomes, including major bleeding. METHODS: We analyzed 509 elderly (aged ≥75 years) patients with NVAF who had recently visited a hospital specializing in cardiology, of which 272 patients had paroxysmal atrial fibrillation (PAF) and 237 had persistent/permanent atrial fibrillation (PeAF). Patients were divided into four groups according to the number of medications: ≤3, 4-6, 7-9, and ≥10. The relationship between the number of medications and incidence rate of F/F in AF patients was analyzed. In addition, this relationship was analyzed in patients with each AF type. RESULTS: Cumulative incidence of F/F at 3 years in the respective categories was 3.7%, 5.4%, 4.3% and 5.7% for PAF, and 5.2%, 7.5%, 7.8% and 25.0% for PeAF (log-rank test, P = 0.930 and 0.003, respectively). In a multivariable model, patients with ≥10 medications showed a significantly higher risk for F/F compared with those with ≤3 medications as reference only in PeAF (adjusted hazard ratio 4.82, 95%CI 1.42-16.33), without significant interaction (P = 0.081). CONCLUSIONS: Elderly NVAF patients using ≥10 medications showed a higher risk for F/F. In subgroup analysis, this association was observed only in patients with PeAF, although there was no significant interaction between number of medications and AF type. Geriatr Gerontol Int 2021; 21: 802-809.

Left atrial dimension and ischemic stroke in patients with and without atrial fibrillation.

The incidence of ischemic stroke (IS) increases in patients with enlarged left atrium (LA) irrespective of whether or not the existence of atrial fibrillation (AF). In such situation, it is unclear whether the impact of LA on incidence of IS still significant in young, non-AF patients with enlarged LA who are primarily unconcerned on anticoagulation therapy. The study population consisted of 18,511 consecutive patients not receiving oral anticoagulants and undergoing echocardiography with measurement of LAD at baseline. The incidence rate of ischemic stroke was calculated in 3 groups according to left atrial dimension (LAD; < 30, 30-45 and ≥ 45 mm) in AF and non-AF patients. Further subgroup analysis was performed in stratification by elderly and young (aged ≥ 65 and < 65 years, respectively). The incidences of IS (per 100 patient-years) were 0.11 and 0.71 in non-AF and AF patients with LAD < 30 mm, respectively, which increased to 0.58 and 1.35 in LAD ≥ 45 mm (adjusted hazard ratios [HRs]; 1.95 [95% confidence intervals, CIs: 0.76-5.01] and 1.22 [95% CIs: 0.27-5.58], interaction P was 0.246). In non-AF patients, the incidences of IS were 0.30 and 0.04 in elderly and young patients with LAD < 30 mm, which increased to 0.67 and 0.48 in LAD ≥ 45 mm (adjusted HRs; 1.34 [95% CIs: 0.43-4.15] and 4.21 [95% CIs: 0.77-23.12], interaction P was 0.158). The incidence of IS significantly increased with increase of LAD in non-AF, especially in non-AF and young patients, although the difference was not independent of other clinical factors. The impact of LAD on IS was numerically larger in non-AF than in AF, and larger in young and non-AF than in elderly counterpart, although a significant interaction was not observed in this small population. Further studies with large population are necessary to judge whether these population with enlarged LA need antithrombotic therapy.

Relationship between resting 12-lead electrocardiogram and all-cause death in patients without structural heart disease: Shinken Database analysis.

BACKGROUND: Resting 12-lead electrocardiography is widely used for the detection of cardiac diseases. Electrocardiogram readings have been reported to be affected by aging and, therefore, can predict patient mortality. METHODS: A total of 12,837 patients without structural heart disease who underwent electrocardiography at baseline were identified in the Shinken Database among those registered between 2010 and 2017 (n = 19,170). Using 438 electrocardiography parameters, predictive models for all-cause death and cardiovascular (CV) death were developed by a support vector machine (SVM) algorithm. RESULTS: During the observation period of 320.4 days, 55 all-cause deaths and 23 CV deaths were observed. In the SVM prediction model, the mean c-statistics of 10 cross-validation models with training and testing datasets were 0.881 ± 0.027 and 0.927 ± 0.101, respectively, for all-cause death and 0.862 ± 0.029 and 0.897 ± 0.069, respectively for CV death. For both all-cause and CV death, high values of permutation importance in the ECG parameters were concentrated in the QRS complex and ST-T segment. CONCLUSIONS: Parameters acquired from 12-lead resting electrocardiography could be applied to predict the all-cause and CV deaths of patients without structural heart disease. The ECG parameters that greatly contributed to the prediction were concentrated in the QRS complex and ST-T segment.

Decline in eGFR over time and incidence of cardiovascular events: Shinken database analysis.

BACKGROUND: It has been reported that a large decline in estimated glomerular filtration rate (eGFR) over time is associated with increased incidence of cardiovascular disease. We investigated whether this association differs according to the baseline eGFR. METHODS: A total of 4666 patients (male 71%) with measurements of eGFR at both baseline and 1 year and that had no cardiovascular events at 1-year follow-up were retrieved from the Shinken Database between June 2004 and March 2015. The study population was divided into three groups by baseline eGFR (mL/min/1.73 m2): high (≥60, n = 1650), intermediate (45-59, n = 1947), and low (<45, n = 1069) eGFR groups. Each eGFR group was further divided into two groups by eGFR slope (change at 1 year, <-10 and ≥-10 mL/min/1.73 m2). The patient characteristics and the incidences of cardiovascular events within 3 years (after 1-year follow-up) were compared between the negatively large eGFR slope (<-10) and others (≥-10) in each eGFR group. RESULTS: A total of 187 cardiovascular events occurred during the mean follow-up of 2.8 ±â€…0.6 years. The adjusted hazard ratios of eGFR slope (<-10 with reference to ≥-10) were 2.37 (95% CI, 1.28-4.40), 3.10 (95% CI, 1.78-5.40), and 2.66 (95% CI, 1.15-6.13) in the high, middle, and low eGFR groups, respectively. Similar results were found in patients with structural heart disease, but not in those without. CONCLUSIONS: Decline in eGFR was associated with an increase in cardiovascular events, and this effect was consistent regardless of the baseline eGFR.

A Phenotyping of Diastolic Function by Machine Learning Improves Prediction of Clinical Outcomes in Heart Failure.

Background: Discriminating between different patterns of diastolic dysfunction in heart failure (HF) is still challenging. We tested the hypothesis that an unsupervised machine learning algorithm would detect heterogeneity in diastolic function and improve risk stratification compared with recommended consensus criteria. Methods: This study included 279 consecutive patients aged 24-97 years old with clinically stable HF referred for echocardiographic assessment, in whom diastolic variables were measured according to the current guidelines. Cluster analysis was undertaken to identify homogeneous groups of patients with similar profiles of the variables. Sequential Cox models were used to compare cluster-based classification with guidelines-based classification for predicting clinical outcomes. The primary endpoint was hospitalization for worsening HF. Results: The analysis identified three clusters with distinct properties of diastolic function that shared similarities with guidelines-based classification. The clusters were associated with brain natriuretic peptide level (p < 0.001), hemoglobin concentration (p = 0.017) and estimated glomerular filtration rate (p = 0.001). During a mean follow-up period of 2.6 ± 2.0 years, 62 patients (22%) experienced the primary endpoint. Cluster-based classification predicted events with a hazard ratio 1.68 (p = 0.019) that was independent from and incremental to the Meta-analysis Global Group in Chronic Heart Failure (MAGGIC) risk score for HF, and from left ventricular end-diastolic volume and global longitudinal strain, whereas guidelines-based classification did not retain its independent prognostic value (hazard ratio = 1.25, p = 0.202). Conclusion: Machine learning can identify patterns of diastolic function that better stratify the risk for decompensation than the current consensus recommendations in HF. Integrating this data-driven phenotyping may help in refining prognostication and optimizing treatment.

Prediction of current and new development of atrial fibrillation on electrocardiogram with sinus rhythm in patients without structural heart disease.

BACKGROUND: Diagnosis of atrial fibrillation (AF) based on electrocardiogram (ECG) with sinus rhythm remains a major challenge. Obtaining a panoramic view with hundreds of automatically measured ECG parameters at sinus rhythm on the predictive capability for AF would be informative. METHODS: We used a single-center database of a specialist cardiovascular hospital (Shinken Database 2010-2017; n = 19,170). We analyzed 12,863 index ECGs with sinus rhythm after excluding those showing AF rhythm, other atrial tachyarrhythmia, pacing beat, or indeterminate axis, and those of patients with structural heart diseases. We used 438 automatically measured ECG parameters in the MUSE data management system. The predictive models were developed using random forest algorithm with the 10-fold cross-validation method. RESULTS: In 12,863 index ECGs with sinus rhythm, a predictive capability for current paroxysmal AF (n = 1131) by c-statistics was 0.99981 ± 0.00037 for training dataset and 0.91337 ± 0.00087 for testing dataset, respectively. Excluding AF at baseline (n = 11,732), a predictive capability for newly developed AF (n = 98) by c-statistics was 0.99973 ± 0.00086 for training dataset and 0.99160 ± 0.00038 for testing dataset, respectively. The distribution of parameter importance was mostly similar among P, QRS, and ST-T segment for both current and newly developed AF. CONCLUSIONS: This study intended to provide panoramic information in relation between ECG parameters and AF. The parameter importance of ECG parameters for predicting AF was mostly similar in P, QRS, and ST-T segment in models for both current and future AF.