Opportunistic Screening of Chronic Liver Disease with Deep Learning Enhanced Echocardiography.

Importance: Chronic liver disease affects more than 1.5 billion adults worldwide, however the majority of cases are asymptomatic and undiagnosed. Echocardiography is broadly performed and visualizes the liver; but this information is not leveraged. Objective: To develop and evaluate a deep learning algorithm on echocardiography videos to enable opportunistic screening for chronic liver disease. Design: Retrospective observational cohorts. Setting: Two large urban academic medical centers. Participants: Adult patients who received echocardiography and abdominal imaging (either abdominal ultrasound or abdominal magnetic resonance imaging) with ≤30 days between tests, between July 4, 2012, to June 4, 2022. Exposure: Deep learning model predictions from a deep-learning computer vision pipeline that identifies subcostal view echocardiogram videos and detects the presence of cirrhosis or steatotic liver disease (SLD). Main Outcome and Measures: Clinical diagnosis by paired abdominal ultrasound or magnetic resonance imaging (MRI). Results: A total of 1,596,640 echocardiogram videos (66,922 studies from 24,276 patients) from Cedars-Sinai Medical Center (CSMC) were used to develop EchoNet-Liver, an automated pipeline that identifies high quality subcostal images from echocardiogram studies and detects the presence of cirrhosis or SLD. In the held-out CSMC test cohort, EchoNet-Liver was able to detect the presence of cirrhosis with an AUC of 0.837 (0.789 - 0.880) and SLD with an AUC of 0.799 (0.758 - 0.837). In a separate test cohort with paired abdominal MRIs, cirrhosis was detected with an AUC of 0.704 (0.689-0.718) and SLD was detected with an AUC of 0.726 (0.659-0.790). In an external test cohort of 106 patients (n = 5,280 videos), the model detected cirrhosis with an AUC of 0.830 (0.738 - 0.909) and SLD with an AUC of 0.768 (0.652 - 0.875). Conclusions and Relevance: Deep learning assessment of clinical echocardiography enables opportunistic screening of SLD and cirrhosis. Application of this algorithm may identify patients who may benefit from further diagnostic testing and treatment for chronic liver disease. KEY POINTS: Question: Can a deep learning algorithm applied to echocardiography videos effectively identify chronic liver diseases including cirrhosis and steatotic liver disease (SLD)?Findings: This retrospective observational cohort study utilized 1,596,640 echocardiography videos from 66,922 studies of 24,276 patients. The deep learning model with a computer vision pipeline (EchoNet-Liver) demonstrated strong performance to detect cirrhosis and SLD. External validation at a geographically distinct site demonstrated similar discriminative ability.Meaning: The application of EchoNet-Liver to echocardiography could aid opportunistic screening of chronic liver diseases, providing a unique cost-effective angle to improve patient management.

The significance of non-sustained ventricular tachycardia on life-threatening ventricular arrhythmia events in patients with non-ischemic cardiomyopathy in the contemporary era: A systematic review and meta-analysis.

BACKGROUND: Risk stratification for patients with non-ischemic cardiomyopathy (NICM) remains challenging as previous studies predicting life-threatening ventricular arrhythmia (LTVA) events were conducted before the establishment of the current standard treatment. We investigated the prognostic value of non-sustained ventricular tachycardia (NSVT) in NICM patients among recent studies. METHODS: MEDLINE, Embase were searched from January 2000 to October 2023. The risk of NSVT on LTVA and mortality was assessed using a random-effects model for patients with NICM. A meta-regression analysis was employed to identify sources of heterogeneity. The systematic review and meta-analysis were carried out according to the PRISMA guidelines. RESULTS: A total of 18 studies were identified, including 5238 pooled participants. Meta-analysis demonstrated that the presence of NSVT was considered a significant prognostic indicator for LTVA events [hazard ratio (HR): 2.90; 95 % CI; 2.31-3.64] with low heterogeneity (I2: 19 %) and for mortality (HR; 2.28; 95%CI; 1.26-4.13) with high heterogeneity (I2: 69 %). The prognostic value of NSVT for LTVA was not affected by either ejection fraction or medications at baseline. CONCLUSION: NSVT remained an important predictor of LTVA events even in patients receiving healthcare in contemporary eras. Detection of NSVT helps us to identify the high-risk patients with NICM.

Using Deep learning to Predict Cardiovascular Magnetic Resonance Findings from Echocardiography Videos.

Background: Echocardiography is the most common modality for assessing cardiac structure and function. While cardiac magnetic resonance (CMR) imaging is less accessible, CMR can provide unique tissue characterization including late gadolinium enhancement (LGE), T1 and T2 mapping, and extracellular volume (ECV) which are associated with tissue fibrosis, infiltration, and inflammation. While deep learning has been shown to uncover findings not recognized by clinicians, it is unknown whether CMR-based tissue characteristics can be derived from echocardiography videos using deep learning. We hypothesized that deep learning applied to echocardiography could predict CMR-based measurements. Methods: In a retrospective single-center study, adult patients with CMRs and echocardiography studies within 30 days were included. A video-based convolutional neural network was trained on echocardiography videos to predict CMR-derived labels including wall motion abnormality (WMA) presence, LGE presence, and abnormal T1, T2 or ECV across echocardiography views. The model performance was evaluated in a held-out test dataset not used for training. Results: The study population included 1,453 adult patients (mean age 56±18 years, 42% female) with 2,556 paired echocardiography studies occurring on average 2 days after CMR (interquartile range 2 days prior to 6 days after). The model had high predictive capability for presence of WMA (AUC 0.873 [95%CI 0.816-0.922]), however, the model was unable to reliably detect the presence of LGE (AUC 0.699 [0.613-0.780]), native T1 (AUC 0.614 [0.500-0.715]), T2 0.553 [0.420-0.692], or ECV 0.564 [0.455-0.691]). Conclusions: Deep learning applied to echocardiography accurately identified CMR-based WMA, but was unable to predict tissue characteristics, suggesting that signal for these tissue characteristics may not be present within ultrasound videos, and that the use of CMR for tissue characterization remains essential within cardiology. Clinical Perspective: Tissue characterization of the heart muscle is useful for clinical diagnosis and prognosis by identifying myocardial fibrosis, inflammation, and infiltration, and can be measured using cardiac MRI. While echocardiography is highly accessible and provides excellent functional information, its ability to provide tissue characterization information is limited at this time. Our study using a deep learning approach to predict cardiac MRI-based tissue characteristics from echocardiography showed limited ability to do so, suggesting that alternative approaches, including non-deep learning methods should be considered in future research.

Comparative Evaluation of Alcohol Septal Ablation: Left Anterior Descending Versus Non-left Anterior Descending Artery Approaches.

Alcohol septal ablation (ASA) is performed for symptomatic drug-refractory hypertrophic obstructive cardiomyopathy to reduce the left ventricular outflow tract pressure gradient (LVOTPG) by injecting ethanol into a septal branch that perforates the septal bulge. The target septal branches usually arise directly from the left anterior descending (LAD) artery; however, vessels from a non-LAD artery can be selected in some cases. This study aimed to compare the effectiveness and safety between ASA performed using a septal branch arising from a non-LAD artery and a branch arising from the LAD artery. This single-center, retrospective, observational cohort study comprised patients with hypertrophic obstructive cardiomyopathy who underwent ASA at the Gifu Heart Centre between 2011 and 2022. The effectiveness and safety of ASA using the 2 artery types were compared. The primary end points were LVOTPG and procedure success, determined as LVOTPG <30 mm Hg after 1 year. Of 33 patients (mean age 66.4 ± 13.0 years, 13 men), 18 patients who underwent ASA using only LAD branches and 15 patients who underwent ASA using only non-LAD branches demonstrated no significant difference in the decrease in LVOTPG during the follow-up period (-99.1 ± 47.4 mm Hg/year vs -75.7 ± 39.2 mm Hg/year, respectively, p = 0.19). The procedure success at 1 year was not significantly different between the 2 groups (93.3% and 84.6%, respectively, p = 0.58). ASA performed using septal branches from non-LAD arteries could be an alternative treatment approach when appropriate septal branches are missing or desirable effects cannot be obtained from ASA using LAD branches.

Development of artificial intelligence-based slow-motion echocardiography and clinical usefulness for evaluating regional wall motion abnormalities.

The diagnostic accuracy of exercise stress echocardiography (ESE) for myocardial ischemia requires improvement, given that it currently depends on the physicians' experience and image quality. To address this issue, we aimed to develop artificial intelligence (AI)-based slow-motion echocardiography using inter-image interpolation. The clinical usefulness of this method was evaluated for detecting regional wall-motion abnormalities (RWMAs). In this study, an AI-based echocardiographic image-interpolation pipeline was developed using optical flow calculation and prediction for in-between images. The accuracy for detecting RWMAs and image readability among 25 patients with RWMA and 25 healthy volunteers was compared between four cardiologists using slow-motion and conventional ESE. Slow-motion echocardiography was successfully developed for arbitrary time-steps (e.g., 0.125×, and 0.5×) using 1,334 videos. The RWMA detection accuracy showed a numerical improvement, but it was not statistically significant (87.5% in slow-motion echocardiography vs. 81.0% in conventional ESE; odds ratio: 1.43 [95% CI: 0.78-2.62], p = 0.25). Interreader agreement analysis (Fleiss's Kappa) for detecting RWMAs among the four cardiologists were 0.66 (95%CI: 0.55-0.77) for slow-motion ESE and 0.53 (95%CI: 0.42-0.65) for conventional ESE. Additionally, subjective evaluations of image readability using a four-point scale showed a significant improvement for slow-motion echocardiography (2.11 ± 0.73 vs. 1.70 ± 0.78, p < 0.001).In conclusion, we successfully developed slow-motion echocardiography using in-between echocardiographic image interpolation. Although the accuracy for detecting RWMAs did not show a significant improvement with this method, we observed enhanced image readability and interreader agreement. This AI-based approach holds promise in supporting physicians' evaluations.

Inappropriate shock incidence in patients with subcutaneous implantable cardioverter-defibrillators with concomitant cardiac implantable electronic devices: A single-center cohort study.

BACKGROUND: Subcutaneous implantable cardioverter defibrillators (S-ICDs) are occasionally used in combination with other cardiac implantable electronic devices (CIEDs). However, whether the incidence of inappropriate shock increases in patients with S-ICDs and concomitant CIEDs remains unclear. This study aimed to investigate the association between the concomitant use of CIEDs and the incidence of inappropriate shock in patients with current-generation S-ICDs. METHODS: A total of 127 consecutive patients received an S-ICD. Patients were assigned to two groups depending on concomitant use of CIEDs at the time of S-ICD implantation: patients without other CIEDs (non-combined group, 106 patients) and patients with other CIEDs (combined group, 21 patients). CIEDs included pacemakers, implantable cardioverter defibrillators, cardiac resynchronization therapy pacemakers, and cardiac resynchronization therapy defibrillators. The primary outcome was inappropriate shock, defined as a shock other than ventricular arrhythmia. Hazard ratios and 95% confidence intervals were calculated using a time-varying Cox proportional hazards model which was adjusted for age because age differed between the groups and could be a confounder. RESULTS: During a median follow-up period of 2.2 years (interquartile range, 1.0-3.4 years), inappropriate shock events occurred in 17 (16%) and five (19%) patients of the non-combined and combined groups, respectively. While the age-adjusted hazard ratio for inappropriate shock was 24% higher in the combined than in the non-combined group (hazard ratio = 1.24, 95% confidence interval, 0.39-3.97), this difference was insignificant (p = .71). CONCLUSION: The incidence of inappropriate shock did not differ between patients with and without concomitant use of CIEDs, suggesting that S-ICDs could potentially be combined with other CIEDs without increasing the number of inappropriate shocks. Further studies are warranted to confirm the safety and feasibility of concomitant use of S-ICDs and CIEDs.

Impact of Tweet Content on the Number of Retweets　- "Tweet the Meeting 2022".

Background: Previous research has investigated the effectiveness of the "Tweet the Meeting" campaign, but the relationship between tweet content and the number of retweets has not been fully evaluated. Methods and Results: We analyzed the number of tweets and retweets during the Japanese Circulation Society's 2022 annual meeting. The ambassador group had significantly more session- and symposium-related tweets than the non-ambassador group (P<0.001), associated with the nubmer of retweets. Symposium-related tweets with figures generated more retweets than those without figures (mean [±SD] 3.47±3.31 vs. 2.48±1.94 retweets per tweet, respectively; P=0.001). Conclusions: The study revealed that official meeting-designated Twitter ambassadors disseminate more educational content than non-ambassadors, and generated more retweets.

Comparison of Unguided De-Escalation Versus Guided Selection of Dual Antiplatelet Therapy After Acute Coronary Syndrome: A Systematic Review and Network Meta-Analysis.

BACKGROUND: The benefit of dual antiplatelet therapy (DAPT) for reducing ischemic events is greatest in the early period of acute coronary syndrome, and recent randomized controlled trials have investigated the unguided de-escalation strategy of changing potent P2Y12 inhibitors to less potent or reduced-dose P2Y12 inhibitors 1 month after acute coronary syndrome. However, it remains unclear which strategy is more effective and safer: the uniform unguided de-escalation strategy versus the personalized guided selection of DAPT with genotype or platelet function tests. METHODS: PubMed, EMBASE, and Cochrane Central were searched for articles published from database inception to September 10, 2021. Randomized controlled trials investigating DAPT using clopidogrel, low-dose prasugrel, standard-dose prasugrel, ticagrelor, unguided de-escalation strategy, and guided selection strategy for patients with acute coronary syndrome were included. Hazard ratios and relative risk estimates were extracted from each study. The estimates were pooled using a random-effects network meta-analysis. The primary efficacy outcome was major adverse cardiovascular events, defined as a composite of cardiovascular death, myocardial infarction, or stroke. The primary safety outcome was major or minor bleeding. Secondary outcomes were all-cause death, cardiovascular death, myocardial infarction, stroke, stent thrombosis, and major bleeding. RESULTS: This study included 19 randomized controlled trials with 69 746 patients. Compared with guided selection of DAPT, unguided de-escalation of DAPT was associated with a decreased risk of the primary safety outcome (hazard ratio, 0.48 [95% CI, 0.33-0.72]) without increased risks of major adverse cardiovascular events (hazard ratio, 0.82 [95% CI, 0.53-1.28]) or any secondary outcomes. The results were similar when the guided selection strategy was divided into platelet function-guided and genotype-guided strategies. CONCLUSIONS: Compared with guided selection of DAPT, unguided de-escalation of DAPT decreased bleeding without increasing ischemic events in patients after acute coronary syndrome. If a strategy of de-escalation is chosen, these findings do not support the routine use of personalized guiding tests. REGISTRATION: URL: https://www.crd.york.ac.uk/PROSPERO/; Unique identifier: CRD42021273082.

Thirty-day readmission rate of same-day discharge protocol after left atrial appendage occlusion: A propensity score-matched analysis from the National Readmission Database.

BACKGROUND: Given the reduction in periprocedural complication rates, same-day discharge (SDD) after percutaneous left atrial appendage closure (LAAC) could be beneficial. To date, little data exist comparing the standard overnight stay (ONS) vs SDD after LAAC. OBJECTIVE: The purpose of this study was to investigate the safety and efficacy of SDD compared with ONS. METHODS: A retrospective cohort study of LAAC procedures performed in the United States from 2015 to 2019 was conducted using the US Nationwide Readmission Database. The primary outcome was all-cause 30-day readmission after discharge in patients who underwent LAAC, and a secondary outcome was requiring total health care cost. A 1:1 propensity score matching was conducted for adjustment. Multivariate Cox proportional hazards regression was also performed to estimate the hazard ratio for all-cause readmission within 30 days of LAAC. RESULTS: Of 48,953 patients (mean age 76.0 ± 7.9 years), 972 patients (1.99%) were discharged on the same day after LAAC (SDD group) and the remaining 47,981 patients stayed at least 1 night (ONS group). A propensity score-matched analysis generated 961 matched pairs in each group. The 30-day readmission rate after discharge was similar between the groups (SDD vs ONS: 8.5% vs 9.8%; P = .31; hazard ratio 1.13; 95% confidence interval 0.78-1.63; P = .53). The total required health care cost was significantly lower in the SDD group ($23,720 [$18,075-$29,416] vs $25,877 [$19,906-$32,748]; P < .01). Gastrointestinal bleeding was the major cause for readmission (SDD vs ONS: 14.7% vs 15.1%; P = .95), but stroke and pericardial effusion were rare. CONCLUSION: In patients without procedure-related complications, SDD is a safe and cost-effective protocol.

Inverse Association between Fruit and Vegetable Intake and All-Cause Mortality: Japan Public Health Center-Based Prospective Study.

BACKGROUND: A dose-response and nonlinear association between fruit and vegetable intake and mortality has been reported in Europe and the United States, but little is known about this association in Asia. OBJECTIVES: This study aimed to evaluate the association of fruit and vegetable intake with all-cause, cancer, cardiovascular, and respiratory disease mortality in a Japanese cohort. METHODS: In the Japan Public Health Center-based prospective study, we included 94,658 participants (mean age: 56.4; 46.0% male) without cancer and cardiovascular disease at baseline. Information on fruit and vegetable intake was collected using a validated FFQ. The Cox proportional hazard model was used to estimate HRs and 95% CIs of each quintile of fruit and vegetable intake, separately, in relation to all-cause and cause-specific mortality using the first quintile as a reference. Nonlinear associations were evaluated using a likelihood ratio test, comparing a linear model with a restricted cubic spline model. RESULTS: During a median of 20.9 follow-up years (IQR: 19.6-23.8 y), 23,687 all-cause deaths were documented. After adjusting for age, sex, and potential confounding factors, fruit and vegetable intake was nonlinearly and significantly associated with lower all-cause mortality, with the fourth and fifth quintiles having comparable HRs (fruit: fourth quintile HR: 0.91; 95% CI: 0.87, 0.95 and fifth quintile HR: 0.92; 95% CI: 0.88, 0.96; P-nonlinearity < 0.001; vegetable: fourth quintile HR: 0.92; 95% CI: 0.88, 0.97 and fifth quintile HR: 0.93; 95% CI: 0.89, 0.98; P-nonlinearity = 0.002). Fruit intake was significantly associated with lower cardiovascular mortality (HR in the fifth quintile: 0.91; 95% CI: 0.83, 0.99; P-nonlinearity = 0.01). CONCLUSIONS: In the Japanese population, higher intake of fruits and vegetables was nonlinearly associated with decreased all-cause mortality. These findings may contribute to the establishment of dietary recommendations for enhancing life expectancy in Asia.

QRS and cycle length alternans in a patient with idiopathic left ventricular tachycardia: Postulated mechanism and clinical implications.

Idiopathic left ventricular tachycardia is macro-reentrant tachycardia involving the fascicles in the left ventricle as a part of its reentrant circuit. The detailed circuit mechanisms somewhat remain unclear. We reported QRS and cycle length alternans confirmed after the first application of radiofrequency delivery for the distal site of left posterior fascicle potential (P2) in a patient with idiopathic left ventricular tachycardia.

Development of 60 MHz integrated backscatter intravascular ultrasound and tissue characterization of attenuated signal coronary plaques that cause myocardial injury after percutaneous coronary intervention.

The purpose of the present study was to develop a 60 MHz integrated backscatter intravascular ultrasound (IB-IVUS) and to evaluate its usefulness for the detection of lipid area with backward attenuation of ultrasound signal (AT) that for the prediction of post-procedural myocardial injury (PMI) after percutaneous coronary intervention (PCI). In a pathological study, images were acquired from 221 cross-sections of 18 coronary arteries from 13 cadavers obtained at autopsy. In the clinical training study, we compared non-targeted plaques in 38 patients by a previous IB-IVUS system (38 MHz) and a new IB-IVUS system (60 MHz). In the clinical testing study, we included 70 consecutive patients who underwent PCI. Serum troponin-I was measured just before and 24 h after PCI to evaluate PMI. As the % microcalcification + % cholesterol cleft area increased, the attenuation of IB values increased (r = 0.56, p < 0.001). The slopes of regression lines of the area of each tissue component between 38 and 60 MHz IB-IVUS were excellent. The lipid pool area with AT tended to be more useful than that of the conventional lipid pool area for the prediction of PMI (p = 0.11). We developed a 60 MHz IB-IVUS imaging system for tissue characterization of coronary plaques. Cutoff value of purple color was the most reliable value for the prediction of PMI.

Impact of Tweeting Summaries by the Japanese Circulation Society Official Account on Article Viewership　- Pilot Trial.

BACKGROUND: The impact of promotional tweets from the official journal account (forCirculation JournalandCirculation Reports) on article viewership has not been thoroughly evaluated.Methods and Results:We retrospectively collected journal viewership data forCirculation JournalandCirculation Reportsfrom March 2021 to August 2021. We compared viewership between articles with (n=15) and without (n=250) tweets. After 1 : 4 propensity score matching (15 tweeted articles and 60 non-tweeted matched controls), journal viewership metrics within 7 days of the tweeting date (and the hypothetical tweeting date), was larger in tweeted articles than non-tweeted articles (median [interquartile range] Abstract page views 89 [60-104] vs. 18 [8-41]). CONCLUSIONS: This pilot study suggests a positive relationship between journal-posted promotional tweets and article viewership.

Machine learning prediction model of acute kidney injury after percutaneous coronary intervention.

Acute kidney injury (AKI) after percutaneous coronary intervention (PCI) is associated with a significant risk of morbidity and mortality. The traditional risk model provided by the National Cardiovascular Data Registry (NCDR) is useful for predicting the preprocedural risk of AKI, although the scoring system requires a number of clinical contents. We sought to examine whether machine learning (ML) techniques could predict AKI with fewer NCDR-AKI risk model variables within a comparable PCI database in Japan. We evaluated 19,222 consecutive patients undergoing PCI between 2008 and 2019 in a Japanese multicenter registry. AKI was defined as an absolute or a relative increase in serum creatinine of 0.3 mg/dL or 50%. The data were split into training (N = 16,644; 2008-2017) and testing datasets (N = 2578; 2017-2019). The area under the curve (AUC) was calculated using the light gradient boosting model (GBM) with selected variables by Lasso and SHapley Additive exPlanations (SHAP) methods among 12 traditional variables, excluding the use of an intra-aortic balloon pump, since its use was considered operator-dependent. The incidence of AKI was 9.4% in the cohort. Lasso and SHAP methods demonstrated that seven variables (age, eGFR, preprocedural hemoglobin, ST-elevation myocardial infarction, non-ST-elevation myocardial infarction/unstable angina, heart failure symptoms, and cardiogenic shock) were pertinent. AUC calculated by the light GBM with seven variables had a performance similar to that of the conventional logistic regression prediction model that included 12 variables (light GBM, AUC [training/testing datasets]: 0.779/0.772; logistic regression, AUC [training/testing datasets]: 0.797/0.755). The AKI risk model after PCI using ML enabled adequate risk quantification with fewer variables. ML techniques may aid in enhancing the international use of validated risk models.

Safety and feasibility of same-day discharge in patients receiving pulmonary vein isolation-systematic review and a meta-analysis.

PURPOSE: The purpose of this systematic review and meta-analysis was to evaluate the feasibility and safety of a same-day discharge protocol following pulmonary vein isolation (PVI). METHODS: PubMed and Embase were systematically investigated from the inception to 20 July 2020. Studies on safety and feasibility of PVI for atrial fibrillation (AF) were included. Study-specific estimates were combined using one-group meta-analysis with a random-effects model. RESULTS: Seven observational studies investigating the safety and feasibility of same-day discharge protocols were identified. Of a total of 3656 patients who have undergone PVI for AF, the overall complication rate was 0.80% (95% confidence interval [CI], 0.20-1.40%). The readmission within 30-day following same-day discharge protocol occurred at a pooled rate of 3.6% (95% CI, 0.0-8.4%). Frequent complications following the procedure were complications related to vascular access (0.38%; 95% CI, 0.18-0.58%), and phrenic nerve injury (0.19%; 95% CI, 0.05-0.33%). The reported complications in SDD group were mainly based on results among patients without perioperative complications. CONCLUSIONS: The introduction of same-day discharge strategies might be safe and feasible in selected patients given the reported complication and re-admission rates in the current practice. Further prospective studies are needed to confirm these findings.

Prediction of in-hospital mortality with machine learning for COVID-19 patients treated with steroid and remdesivir.

We aimed to create the prediction model of in-hospital mortality using machine learning methods for patients with coronavirus disease 2019 (COVID-19) treated with steroid and remdesivir. We reviewed 1571 hospitalized patients with laboratory confirmed COVID-19 from the Mount Sinai Health System treated with both steroids and remdesivir. The important variables associated with in-hospital mortality were identified using LASSO (least absolute shrinkage and selection operator) and SHAP (SHapley Additive exPlanations) through the light gradient boosting model (GBM). The data before February 17th, 2021 (N = 769) was randomly split into training and testing datasets; 80% versus 20%, respectively. Light GBM models were created with train data and area under the curves (AUCs) were calculated. Additionally, we calculated AUC with the data between February 17th, 2021 and March 30th, 2021 (N = 802). Of the 1571 patients admitted due to COVID-19, 331 (21.1%) died during hospitalization. Through LASSO and SHAP, we selected six important variables; age, hypertension, oxygen saturation, blood urea nitrogen, intensive care unit admission, and endotracheal intubation. AUCs using training and testing datasets derived from the data before February 17th, 2021 were 0.871/0.911. Additionally, the light GBM model has high predictability for the latest data (AUC: 0.881) (https://risk-model.herokuapp.com/covid). A high-value prediction model was created to estimate in-hospital mortality for COVID-19 patients treated with steroid and remdesivir.

The 30-day readmission rate of same-day discharge protocol following catheter ablation for atrial fibrillation: a propensity score-matched analysis from National Readmission Database.

AIMS: The effectiveness and safety of same-day discharge (SDD) for catheter ablation (CA) for atrial fibrillation (AF) has not been fully elucidated using a large nationwide database. This study aimed to evaluate the all-cause readmission rates within 30-days among patients receiving CA for AF with an SDD protocol compared with a conventional overnight stay (ONS). METHODS AND RESULTS: We performed a retrospective cohort study using the US Nationwide Readmission Database. The primary outcome was all-cause 30-day readmission following discharge in patients receiving CA and a secondary outcome was requiring total healthcare cost. A 1 : 3 propensity score matching was conducted to compare the safety and efficacy within both SDD and ONS group. Among 30 776 patients [mean 67.2 ± 11.4 years, 12 590 female (41.5%)] who received CA from 2016 through 2018, 440 (1.42%) patients were discharged on the same-day following CA (SDD group), and the remaining 30 336 patients stayed at least one night in the hospital (ONS group). A propensity score analysis generated 1751 matched pairs (440 in the SDD group; 1311 in the ONS group). The 30-day readmission following discharge was not significantly higher in the SDD group than the ONS group (SDD vs. ONS: 12.7% vs. 9.7%; hazard ratio: 1.17, 95% confidence interval: 0.76-1.81, P = 0.47). Healthcare cost was significantly higher in the ONS group ($25 237 ± 14 036 vs. $30 749 ± 16 383; P < 0.01). CONCLUSION: In this nationwide database study, there was no significant difference in the all-cause 30-day readmission following SDD for CA compared with ONS.

Relationship Between Official Twitter Ambassadors and the Number of Retweets in the Annual Congress　- "Tweet the Meeting".

Background: The relationship between Twitter ambassadors and retweets has not been fully evaluated for "tweet the meeting" activity. Methods and Results: We collected data on the number of tweets and retweets during the Japanese Circulation Society's (JCS) annual meetings in 2019, 2020, and 2021. After adjustment, JCS Twitter Ambassadors, selected by the JCS to increase the meeting's visibility, increased the total number of retweets by 9%. Conclusions: This is the first report on the numerical relationship between JCS Twitter Ambassadors and the total number of retweets during an annual congress. Original tweets by JCS Twitter Ambassadors increased the number of retweets, but retweets by influencers were more effective at stimulating social media engagement.