Background: With the prevalence of cardiovascular diseases increasing worldwide, early prediction and accurate assessment of heart failure (HF) risk are crucial to meet the clinical demand. Objective: Our study objective was to develop machine learning (ML) models based on real-world electronic health records to predict 1-year in-hospital mortality, use of positive inotropic agents, and 1-year all-cause readmission rate. Methods: For this single-center study, we recruited patients with newly diagnosed HF hospitalized between December 2010 and August 2018 at the First Affiliated Hospital of Dalian Medical University (Liaoning Province, China). The models were constructed for a population set (90:10 split of data set into training and test sets) using 79 variables during the first hospitalization. Logistic regression, support vector machine, artificial neural network, random forest, and extreme gradient boosting models were investigated for outcome predictions. Results: Of the 13,602 patients with HF enrolled in the study, 537 (3.95%) died within 1 year and 2779 patients (20.43%) had a history of use of positive inotropic agents. ML algorithms improved the performance of predictive models for 1-year in-hospital mortality (areas under the curve [AUCs] 0.92-1.00), use of positive inotropic medication (AUCs 0.85-0.96), and 1-year readmission rates (AUCs 0.63-0.96). A decision tree of mortality risk was created and stratified by single variables at levels of high-sensitivity cardiac troponin I (<0.068 μg/L), followed by percentage of lymphocytes (<14.688%) and neutrophil count (4.870×109/L). Conclusions: ML techniques based on a large scale of clinical variables can improve outcome predictions for patients with HF. The mortality decision tree may contribute to guiding better clinical risk assessment and decision making.

The proportion of the elderly in the total population of the world is growing, and the number of elderly patients with coronary chronic total occlusions (CTO) is huge. The elderly patients often have more extensive coronary artery disease, more severe ischemic burden and higher risk of cardiovascular events, as compared to younger patients, and thereby they might greatly benefit from coronary revascularization, even though they may have higher risk of operative complications. Most interventional cardiologists are more likely to be reluctant to operate complex percutaneous coronary intervention (PCI) in elderly patients. The latest refinements in dedicated CTO-PCI equipment and techniques have led to high rates of success and low complications rates and have made the CTO-PCI procedures safe and effective among the elderly patients. However, up to now, there is no widely recognized consensus or guideline on treatment strategy of elderly CTO patients, and the prognosis in this population is unknown. In this review, we aim to provide an overview of the current evidence and future perspectives on PCI in elderly patients with CTOs.

Objective: This study aimed to investigate the prognostic value of systemic immune inflammation index (SII) concerning long-term outcomes in patients with the three-vessel disease (TVD) after revascularization in a large cohort. Methods: In total, 3561 TVD patients who had undergone revascularization between 2013 and 2018 were included in the study. Patients were divided into the low SII (< 694.3 × 10⁹/L) (n = 2556, 71.8%) and the high SII (≥ 694.3 × 10⁹/L) group (n = 1005, 28.2%). The C-index, net reclassification improvement (NRI), and integrated discrimination improvement (IDI) were calculated to assess whether the addition of SII to a baseline model with traditional risk factors improved the accuracy of cardiac event prediction. The primary outcome was the frequency of major adverse and cerebrovascular events (MACCE). The secondary outcome was the incidence of all-cause death. Results: After 2.4 years of follow-up, the Cox proportional hazard regression model analysis displayed that high SII was independently associated with an increased risk of developing future MACCE (hazard ratio [HR] 1.65, 95% confidence interval [CI] 1.23– 2.21, p = 0.001) and all-cause death (HR: 2.96; 95% CI: 1.19– 7.32, p = 0.019). The addition of SII significantly improved the reclassification beyond the baseline model with traditional risk factors (MACCE: NRI, 0.115; p = 0.0001; all-cause death: NRI, 0.369; p = 0.0001). Reclassification with the addition of SII also demonstrated an IDI of 0.0022 (p = 0.006) in MACCE and 0.0033 (p = 0.014) in all-cause death. Conclusion: In TVD patients after revascularization, increased SII is an independent prognostic factor for long-term outcomes of MACCE and death. Compared to traditional risk factors, SII improved the risk prediction of major cardiovascular events in TVD patients who underwent revascularization.

Difficulty in knowledge validation is a significant hindrance to knowledge discovery via data mining, especially automatic validation without artificial participation. In the field of medical research, medical knowledge discovery from electronic medical records is a common medical data mining method, but it is difficult to validate the discovered medical knowledge without the participation of medical experts. In this article, we propose a data-driven medical knowledge discovery closed-loop pipeline based on interpretable machine learning and deep learning; the components of the pipeline include Data Generator, Medical Knowledge Mining, Medical Knowledge Evaluation, and Medical Knowledge Application. In addition to completing the discovery of medical knowledge, the pipeline can also automatically validate the knowledge. We apply our pipeline's discovered medical knowledge to a traditional prognostic predictive model of heart failure in a real-world study, demonstrating that the incorporation of medical knowledge can effectively improve the performance of the traditional model. We also construct a scale model based on the discovered medical knowledge and demonstrate that it achieves good performance. To guarantee its medical effectiveness, every process of our pipeline involves the participation of medical experts.

Background: The number of coronary chronic total occlusion (CTO) patients with left ventricular (LV) systolic dysfunction is significant, but the clinical outcomes of these patients are rarely reported. The present retrospective cohort study aimed to investigate the long-term outcomes of successful recanalization vs. optimal medical therapy (MT) for CTOs in patients with preserved and impaired LV systolic function.Methods: A total of 1,895 patients with CTOs were stratified according to LV function. Of these, 1,420 patients (74.9%) with LV ejection fraction (LVEF) >45% and 475 patients (25.1%) with LVEF ≤45% were treated with optimal MT or successful CTO percutaneous coronary intervention (PCI). A 1:1 propensity score matching (PSM) was conducted to reduce the impact of potential confounding on the outcomes. The primary outcome was the frequency of major adverse cardiac events (MACEs).Results: Throughout a 2.6-year follow-up and after adjusting for confounders, among patients with preserved LV function, successful CTO PCI was associated with reduced incidence of MACE (14.2 vs. 23.9%, adjusted HR 0.63, 95% CI 0.48–0.83, p = 0.001) compared to MT. There was no significant difference in MACE occurrence (29.6 vs. 28.9%, adjusted HR 1.05, 95% CI: 0.71–1.56, p = 0.792) between successful recanalization and MT in patients with LV systolic dysfunction. The primary outcome among patients with impaired and preserved LV systolic function after PSM was similar to that from earlier findings before PSM was conducted. A significant interaction between LV function and therapeutic strategy for MACE was observed (interaction p = 0.038).Conclusions: Compared to MT alone for management of patients with CTOs, successful CTO PCI may reduce the risk of MACE in patients with preserved LV systolic function, but not in patients with LV dysfunction.

Objective: Limited data are available on the predictors of major adverse cardiac events (MACE) after a successful coronary chronic total occlusion (CTO) percutaneous coronary intervention (PCI) and medical therapy. This study aimed to identify predictors of MACE in CTO patients undergoing successful recanalization and medical therapy. Methods: A total of 2015 patients with CTOs were enrolled. About 718 patients underwent successful CTO recanalization, and 1297 patients received medical therapy. The primary outcome was the frequency of MACE, defined as a composite of cardiac death, myocardial infarction, and target-vessel revascularization. Multivariate models were used to determine predictors of MACE. Results: In successful CTO recanalization group, MACE occurred in 123 (17.1%) patients. In multivariate analysis, heart failure (hazard ratio [HR] 1.77, 95% confidence interval [CI]: 1.04– 3.04, p = 0.036) was identified as independent predictors for MACE in successful CTO recanalization. Additionally, in medical therapy group, the significant predictors of MACE were male gender (HR 1.53, 95% CI: 1.13– 2.05, p = 0.005), diabetes mellitus (HR 1.39, 95% CI: 1.11– 1.74, p = 0.003), heart failure (HR 1.44, 95% CI: 1.10– 1.87, p = 0.007), J-CTO score (HR 1.17, 95% CI: 1.07– 1.28, p = 0.001) and multivessel disease (HR 2.20, 95% CI: 1.42– 3.39, p < 0.001). Conclusion: Heart failure was predictor for composite cardiovascular events in patients with CTO after successful recanalization. Male gender, diabetes mellitus, heart failure, J-CTO score and multivessel disease were predictors of MACE in CTO patients with medical therapy.