Aims: Available predictive models for sudden cardiac death (SCD) in heart failure (HF) patients remain suboptimal. We assessed whether the electrocardiography (ECG)-based artificial intelligence (AI) could better predict SCD, and also whether the combination of the ECG-AI index and conventional predictors of SCD would improve the SCD stratification among HF patients.Methods and results: In a prospective observational study, 4 tertiary care hospitals in Tokyo enrolled 2559 patients hospitalized for HF who were successfully discharged after acute decompensation. The ECG data during the index hospitalization were extracted from the hospitals’ electronic medical record systems. The association of the ECG-AI index and SCD was evaluated with adjustment for left ventricular ejection fraction (LVEF), New York Heart Association (NYHA) class, and competing risk of non-SCD. The ECG-AI index plus classical predictive guidelines (i.e. LVEF ≤35%, NYHA Class II and III) significantly improved the discriminative value of SCD [receiver operating characteristic area under the curve (ROC-AUC), 0.66 vs. 0.59; P = 0.017; Delong’s test] with good calibration (P = 0.11; Hosmer–Lemeshow test) and improved net reclassification [36%; 95% confidence interval (CI), 9–64%; P = 0.009]. The Fine–Gray model considering the competing risk of non-SCD demonstrated that the ECG-AI index was independently associated with SCD (adjusted sub-distributional hazard ratio, 1.25; 95% CI, 1.04–1.49; P = 0.015). An increased proportional risk of SCD vs. non-SCD with an increasing ECG-AI index was also observed (low, 16.7%; intermediate, 18.5%; high, 28.7%; P for trend = 0.023). Similar findings were observed in patients aged ≤75 years with a non-ischaemic aetiology and an LVEF of >35%.Conclusion: To improve risk stratification of SCD, ECG-based AI may provide additional values in the management of patients with HF.

Background: Although 30‐day readmission is thought to be an important quality indicator in patients with hospitalized heart failure, its prognostic impact and comparison of patients who were readmitted beyond 30 days has not been investigated. We assessed early (0–30 days) versus midrange (31–90 days) readmission in terms of incidence and distribution, and elucidated whether the timing of readmission could have a different prognostic significance. Methods and Results: We examined patients with hospitalized heart failure registered in the WET ‐ HF (West Tokyo Heart Failure) registry. The primary outcomes analyzed were all‐cause death and HF readmission. Data of 3592 consecutive patients with hospitalized heart failure (median follow‐up, 2.0 years [interquartile range, 0.8–3.1 years]; 39.6% women, mean age 73.9±13.3 years) were analyzed. Within 90 days after discharge, HF readmissions occurred in 11.1% patients. Of them, patients readmitted within 30 and 31 to 90 days after discharge accounted for 43.1% and 56.9%, respectively. Independent predictors of 30‐ and 90‐day readmission were almost identical, and after adjustment, readmission for HF within 90 days (including both early and midrange readmission) was an independent predictor of subsequent all‐cause death (hazard ratio, 2.36; P <0.001). Among 90‐day readmitted patients, the time interval from discharge to readmission was not significantly associated with subsequent all‐cause death. Conclusions: Among patients readmitted within 90 days after index hospitalization discharge, ≈60% of readmission events occurred beyond 30 days. Patients readmitted within 90 days had a higher risk of long‐term mortality, regardless of the temporal proximity of readmission to the index hospitalization.

Background: The natural course of heart failure (HF) is typically associated with repeated hospitalizations, and subsequently, patient prognosis deteriorates. However, the precise relationship between repeated admissions for HF and long-term prognosis remains unknown. Methods and Results: We analyzed data from 1,730 consecutive acute HF patients registered in the West Tokyo Heart Failure (WET-HF) registry between June 2005 and April 2014 (median age, 76 years). Patients were divided into 3 groups according to the number of previous HF admissions at the time of the index admission (0, n=876 [55.4%]; 1, n=425 [26.9%]; ≥2, n=279 [17.7%] previous admissions). A history of multiple previous admissions was an independent predictor for all-cause death and HF readmission in reference to a history of a single previous admission (hazard ratio (HR), 1.53; 95% confidence interval (CI) 1.10–2.13; HR, 1.90 95% CI, 1.47–2.44, respectively) or no previous admissions (HR, 1.37, 95% CI, 1.01–1.85; HR, 2.83, 95% CI, 2.19–3.65, respectively). On the other hand, a history of a single previous admission was an independent predictor for HF readmission in reference to a history of no previous admissions (HR, 1.51, 95% CI, 1.18–1.92), but not for all-cause death (HR, 0.89, 95% CI, 0.66–1.20). Conclusions: Based on a contemporary multicenter HF registry, a history of multiple previous HF admissions was revealed as an independent, strong risk factor of adverse events following the index admission. The number of hospitalizations could be a simple and important surrogate indicating subsequent adverse events in patients with HF.

Aims: Multimorbidity is common among heart failure (HF) patients and may attenuate guideline-directed medical therapy (GDMT). Multimorbid patients are under-represented in clinical trials; therefore, the effect of multimorbidity clustering on the prognosis of HF patients remains unknown. We evaluated the prevalence of multimorbidity clusters among consecutively registered hospitalized HF patients and assessed whether GDMT attenuated outcomes. Methods and results: We examined 1924 hospitalized HF patients with reduced left ventricular ejection fraction (<50%) in a multicentre registry (West Tokyo HF Registry: WET-HF). Ten comorbid conditions in the WET-HF were abstracted: coronary artery disease, atrial fibrillation, stroke, anaemia, chronic obstructive pulmonary disease, renal dysfunction, obesity, hypertension, dyslipidaemia, and diabetes. Patients were divided into three groups (0–2: n = 451; 3–4: n = 787; and ≥5: n = 686) based on the number of comorbid conditions. The primary composite endpoint was all-cause mortality and HF rehospitalization. The most prevalent comorbidities were renal dysfunction (67.9%), hypertension (66.0%), and anaemia (53.8%). Increased comorbidity was associated with increased adverse outcomes [3–4: hazard ratio (HR) 1.42, 95% confidence interval (CI) 1.13–1.77, P = 0.003; ≥5: HR 2.12, 95%CI 1.69–2.65, P < 0.001; and reference: 0–2] and lower GDMT prescription rate (0–2: 69.2%; 3–4: 57.7%; and ≥5: 57.6%). GDMT was associated with decreased adverse outcomes; this association was maintained even as the comorbidity burden increased but tended to weaken (0–2: HR 0.53, 95%CI 0.35–0.78; P = 0.001; 3–4: HR 0.82, 95%CI 0.65–1.04, P = 0.095; and ≥5: HR 0.81, 95%CI 0.65–1.00, P = 0.053; P for interaction = 0.156). Conclusions: Comorbidity clusters were prevalent and associated with poorer outcomes. GDMT remained beneficial regardless of the comorbidity burden but tended to weaken with increasing comorbidity burden. Further research is required to optimize medical care in these patients.