Aims Heart failure (HF) involves complex remodelling leading to electrical and mechanical dysfunction. We hypothesized that machine learning approaches incorporating data obtained from different investigative modalities including atrial and ventricular measurements from electrocardiography and echocardiography, blood inflammatory marker [neutrophil-to-lymphocyte ratio (NLR)], and prognostic nutritional index (PNI) will improve risk stratification for adverse outcomes in HF compared to logistic regression. Methods and results Consecutive Chinese patients referred to our centre for transthoracic echocardiography and subsequently diagnosed with HF, between 1 January 2010 and 31 December 2016, were included in this study. Two machine learning techniques, multilayer perceptron and multi-task learning, were compared with logistic regression for their ability to predict incident atrial fibrillation (AF), transient ischaemic attack (TIA)/stroke, and all-cause mortality. This study included 312 HF patients [mean age: 64 (55-73) years, 75% male]. There were 76 cases of new-onset AF, 62 cases of incident TIA/stroke, and 117 deaths during follow-up. Univariate analysis revealed that age, left atrial reservoir strain (LARS) and contractile strain (LACS) were significant predictors of new-onset AF. Age and smoking predicted incident stroke. Age, hypertension, type 2 diabetes mellitus, chronic kidney disease, mitral or aortic regurgitation, P-wave terminal force in V1, the presence of partial inter-atrial block, left atrial diameter, ejection fraction, global longitudinal strain, serum creatinine and albumin, high NLR, low PNI, and LARS and LACS predicted all-cause mortality. Machine learning techniques achieved better prediction performance than logistic regression. Conclusions Multi-modality assessment is important for risk stratification in HF. A machine learning approach provides additional value for improving outcome prediction.

Heart failure (HF) is a major epidemic with rising morbidity and mortality rates that encumber global healthcare systems. While some studies have demonstrated the value of CRP in predicting (i) the development of HFpEF and (ii) long-term clinical outcomes in HFpEF patients, others have shown no such correlation. As a result, we conducted the following systematic review and meta-analysis to assess both the diagnostic and prognostic role of CRP in HFpEF. PubMed and Embase were searched for studies that assess the relationship between CRP and HFpEF using the following search terms: (((C-reactive protein) AND ((preserved ejection fraction) OR (diastolic heart failure))). The search period was from the start of database to August 6, 2019, with no language restrictions. A total of 312 and 233 studies were obtained from PubMed and Embase respectively, from which 19 studies were included. Our meta-analysis demonstrated the value of a high CRP in predicting the development of not only new onset HFpEF (HR: 1.08; 95% CI: 1.00-1.16; P = 0.04; I 2 = 22%), but also an increased risk of cardiovascular mortality when used as a categorical (HR: 2.52; 95% CI: 1.61-3.96; P < 0.0001; I 2 = 19%) or a continuous variable (HR: 1.24; 95% CI: 1.04-1.47; P = 0.01; I 2 = 28%), as well as all-cause mortality when used as a categorical (HR: 1.78; 95% CI: 1.53-2.06; P < 0.00001; I 2 = 0%) or a continuous variable: (HR: 1.06; 95% CI: 1.02-1.06; P = 0.003; I 2 = 61%) in HFpEF patients. CRP can be used as a biomarker to predict the development of HFpEF and long-term clinical outcomes in HFpEF patients, in turn justifying its use as a simple, accessible parameter to guide clinical management in this patient population. However, more prospective studies are still required to not only explore the utility and dynamicity of CRP in HFpEF but also to determine whether risk stratification algorithms incorporating CRP actually provide a material benefit in improving patient prognosis.

ObjectivesBrugada syndrome (BrS) is an ion channelopathy that predisposes affected patients to spontaneous ventricular tachycardia/fibrillation (VT/VF) and sudden cardiac death. The aim of this study is to examine the predictive factors of spontaneous VT/VF.MethodsThis was a territory-wide retrospective cohort study of patients diagnosed with BrS between 1997 and 2019. The primary outcome was spontaneous VT/VF. Cox regression was used to identify significant risk predictors. Non-linear interactions between variables (latent patterns) were extracted using non-negative matrix factorisation (NMF) and used as inputs into the random survival forest (RSF) model.ResultsThis study included 516 consecutive BrS patients (mean age of initial presentation=50±16 years, male=92%) with a median follow-up of 86 (IQR: 45–118) months. The cohort was divided into subgroups based on initial disease manifestation: asymptomatic (n=314), syncope (n=159) or VT/VF (n=41). Annualised event rates per person-year were 1.70%, 0.05% and 0.01% for the VT/VF, syncope and asymptomatic subgroups, respectively. Multivariate Cox regression analysis revealed initial presentation of VT/VF (HR=24.0, 95% CI=1.21 to 479, p=0.037) and SD of P-wave duration (HR=1.07, 95% CI=1.00 to 1.13, p=0.044) were significant predictors. The NMF-RSF showed the best predictive performance compared with RSF and Cox regression models (precision: 0.87 vs 0.83 vs. 0.76, recall: 0.89 vs. 0.85 vs 0.73, F1-score: 0.88 vs 0.84 vs 0.74).ConclusionsClinical history, electrocardiographic markers and investigation results provide important information for risk stratification. Machine learning techniques using NMF and RSF significantly improves overall risk stratification performance.

No abstract

Background: Risk stratification in acute myocardial infarction (AMI) is important for guiding clinical management. Current risk scores are mostly derived from clinical trials with stringent patient selection. We aimed to establish and evaluate a composite scoring system to improve short-term mortality classification after index episodes of AMI, independent of electrocardiography (ECG) pattern, in a large realworld cohort.Methods: Using electronic health records, patients admitted to our regional teaching hospital (derivation cohort, n=1747) and an independent tertiary care center (validation cohort, n=1276) with index acute myocardial infarction between January 2013 and December 2017 as confirmed by principal diagnosis and laboratory findings, were identified retrospectively.Results: Univariate logistic regression was used as the primary model to identify potential contributors to mortality. Stepwise forward likelihood ratio logistic regression revealed that neutrophil-to-lymphocyte ratio, peripheral vascular disease, age, and serum creatinine (NPAC) were significant for 90-day mortality (Hosmer-Lemeshow test, P=0.21). Each component of the NPAC score was weighted by betacoefficients in multivariate analysis. The C-statistic of the NPAC score was 0.75, which was higher than the conventional Charlson's score (C-statistic=0.63). Judicious application of a deep learning model to our dataset improved the accuracy of classification with a C-statistic of 0.81. Conclusions:The NPAC score comprised of four items from routine laboratory parameters and basic clinical information and can facilitate early identification of cases at risk of short-term mortality following index myocardial infarction. Deep learning model can serve as a gate-keeper to facilitate clinical decision making.