Insuficiencia cardiaca de novo tras un síndrome coronario agudo en pacientes sin insuficiencia cardiaca ni disfunción ventricular izquierda

Classification tree obtained by artificial intelligence for the prediction of heart failure after acute coronary syndromes

BACKGROUND

Coronary heart disease is the leading cause of heart failure (HF), and tools are needed to identify patients with a higher probability of developing HF after an acute coronary syndrome (ACS). Artificial intelligence (AI) has proven to be useful in identifying variables related to the development of cardiovascular complications.

METHODS

We included all consecutive patients discharged after ACS in two Spanish centers between 2006 and 2017. Clinical data were collected and patients were followed up for a median of 53months. Decision tree models were created by the model-based recursive partitioning algorithm.

RESULTS

The cohort consisted of 7,097 patients with a median follow-up of 53months (interquartile range: 18-77). The readmission rate for HF was 13.6% (964 patients). Eight relevant variables were identified to predict HF hospitalization time: HF at index hospitalization, diabetes, atrial fibrillation, glomerular filtration rate, age, Charlson index, hemoglobin, and left ventricular ejection fraction. The decision tree model provided 15 clinical risk patterns with significantly different HF readmission rates.

CONCLUSIONS

The decision tree model, obtained by AI, identified 8 leading variables capable of predicting HF and generated 15 differentiated clinical patterns with respect to the probability of being hospitalized for HF. An electronic application was created and made available for free.

Applicability of the Zwolle score for selection of very high-risk ST-elevation myocardial infarction patients treated with primary angioplasty

The Zwolle risk score was designed to stratify in-hospital mortality risk of ST-elevation myocardial infarction (STEMI) patients treated with primary percutaneous coronary intervention (pPCI) and for decision-making in the unit where patients are admitted. We assessed the accuracy of Zwolle risk score for in-hospital mortality estimation compared with the GRACE score in all patients (n = 4446) admitted for STEMI in 3 university hospitals. Only one fourth of the patients were classified as high-risk by the Zwolle risk score vs 60% by the GRACE score. In-hospital mortality was 10.6%. A statistically significant increase in in-hospital mortality, adjusted by age, gender, and revascularization, was observed with both scores. The assessment of the optimal cut-off points verified the accuracy of Zwolle score ≥4 as optimal threshold for high-risk categorization. In contrast, GRACE score ≥140 had very low specificity as well as percentage of patients correctly classified; GRACE score ≥175 was fairly better. The reclassification index of the Zwolle score after applying the GRACE score was 35.5%. Selection of high-risk STEMI patients treated with pPCI based on the Zwolle risk score has higher specificity than the GRACE score and might be useful in clinical practice.

A Real-World Analysis of New-Onset Heart Failure After Anterior Wall ST-Elevation Acute Myocardial Infarction in the United States

The 1-year incidence of heart failure (HF) after anterior wall ST-elevation acute myocardial infarction (STEMI) remains difficult to determine because of inconsistencies in reporting, definitions, and adjudication. The objective of this study was to evaluate the 1-year incidence of HF after anterior wall STEMI in a real-world data set using a variety of potential criteria and composite definitions. In a retrospective cohort study, anonymized patient data was accessed through a federated health research network (TriNetX Limited Liability Company (LLC)) of 56 US healthcare organizations (US Collaborative Network). Patients were identified based on the International Classification of Diseases, Tenth Revision criteria for anterior wall STEMI during the 10-year period from 2013 to 2022 and the absence of prespecified signs or symptoms of HF. Values for 1-year incidence were calculated as 1 minus Kaplan-Meier survival at 12 months after anterior wall STEMI. Univariate Cox proportional hazard ratio was calculated to compare risk associated with potential risk factors. The analysis utilized 5 different types of definition criteria for HF: Diagnosis codes, Signs and symptoms, Laboratory/imaging, Medications, and Composites. A total of 34,395 patients from the US Collaborative Network met eligibility criteria and were included in the analysis. The 1-year incidence of HF varied from 2% to 30% depending upon the definition criteria. Although no single criteria exceeded a 1-year incidence of 20%, a simple composite of HF diagnosis (International Classification of Diseases, Tenth Revision-I50) or use of loop diuretic produced a 1-year incidence 26.1% that was used as the benchmark outcome for evaluation of risk factors. Age ≥65 years, Black race, low-density lipoprotein ≥100 mg/100 ml, elevated hemoglobin A1c (7% to 9% and >9%), and body mass index≥35 kg/m2 were also associated with increased risk of HF. In conclusion, patients with anterior wall STEMI continue to be at high risk for new-onset HF. In the absence of structured, prospective, systematically adjudicated diagnostic criteria, composite definitions are more likely to yield accurate estimates of HF incidence.

Differential prognosis of patients that are candidates for standard, short or prolonged dual antiplatelet treatment discharged after an acute coronary syndrome

BACKGROUND

Current evidence supports the efficacy of prolonged dual antiplatelet treatment (DAPT) for patients at high-ischemic risk and low bleeding risk as well as the efficacy and safety of short DAPT in high-bleeding risk (HBR) patients.

METHODS

We evaluated patterns of DAPT candidates in all patients discharged in 2 hospitals after an acute coronary syndrome (ACS). Patients categorized in 3 groups: 1) short-DAPT candidates if they met 1 major o 2 minor criteria for HBR, by the 2019 ARC-HBR criteria; 2) prolonged-DAPT candidates if were not HBR and had recurrent ACS, complex percutaneous coronary interventions or diabetes; 3) standard 12 months DAPT if were not include in the previous 2 groups. Major bleeding (MB) was registered according to 3 or 5 of the BARC consortium definitions.

RESULTS

We included 8252 patients and 3215 (39 %) were candidates for abbreviated DAPT, 3119 (37.8 %) for prolonged DAPT, and 1918 (23.2 %) for 12 m DAPT. Relevant differences were observed between the 3 categories beyond the bleeding risk. Median follow-up was 57 months. Multivariate analysis identified higher risk of all-cause mortality (HR: 1.96 95 % CI 1.45-2.67; p < 0.001), cardiovascular mortality (HR: 2.10 95 % CI 1.39-3.19; p < 0.011), MACE (HR: 1.69 95 % 1.50-2.02; p < 0.001) and MB (sHR: 3.41 95 % CI 1.45-8.02; p = 0.005) in candidates to short DAPT. Candidates to prolonged DAPT had higher risk of MACE (HR: 1.17 95 % CI 1.02-1.35; p = 0.027).

CONCLUSIONS

Almost two thirds of patients discharged after an ACS would be candidates for short or prolonged DAPT and these patients are at higher risk of MACE and mortality.

Remnant cholesterol in patients admitted for acute coronary syndromes

BACKGROUND

Remnant cholesterol has been identified as one of leading lipid values associated with the incidence of coronary heart disease. There is scarce evidence on its distribution and prognostic value in acute coronary syndrome (ACS) patients.

METHODS AND RESULTS

We included all consecutive patients admitted for ACS in two different centres. Remnant cholesterol was calculated by the equation: total cholesterol minus LDL cholesterol minus HDL cholesterol, and values ≥30 were considered high. Among the 7479 patients, median remnant cholesterol level was 28 mg/dL (21-39), and 3429 (45.85%) patients had levels ≥30 mg/dL. Age (r: -0.29) and body mass index (r: 0.44) were the variables more strongly correlated. At any given age, patients with overweigh or obesity had higher levels. In-hospital mortality was 3.75% (280 patients). Remnant cholesterol was not associated to higher in-hospital mortality risk (odds ratio: 0.89; P = 0.21). After discharge (median follow-up of 57 months), an independent and linear risk of all-cause mortality and heart failure (HF) associated to cholesterol remnant levels was observed. Remnant cholesterol levels >60 mg/dL were associated to higher risk of mortality [hazard ratio (HR): 1.49 95% CI 1.08-2.06; P = 0.016], cardiovascular mortality (HR: 1.49 95% CI 1.08-2.06; P = 0.016), and HF re-admission (sub-HR: 1.55 95% CI 1.14-2.11; P = 0.005).

CONCLUSIONS

Elevated remnant cholesterol is highly prevalent in patients admitted for ACS and is inversely correlated with age and positively with body mass index. Remnant cholesterol levels were not associated to higher in-hospital mortality risk, but they were associated with higher long-term risk of mortality and HF.

Predicting Acute Onset of Heart Failure Complicating Acute Coronary Syndrome: An Explainable Machine Learning Approach

Patients with acute coronary syndrome (ACS) are at high risk of heart failure (HF). Early prediction and management of HF among ACS patients are essential to provide timely and cost-effective care. The aim of this study is to train and evaluate a machine learning model to predict the acute onset of HF subsequent to ACS. A total of 1,028 patients with ACS admitted to Guangdong Second Provincial General Hospital between October 2019 and May 2022 were included in this study. 128 clinical features were ranked using Shapley additive exPlanations (SHAP) values and the top 20% of features were selected for building a balanced random forest (BRF) model. We compared the discriminatory capability of BRF with linear logistic regression (LLR). In the hold-out test set, the BRF model predicted subsequent HF with areas under the curve (AUC) of 0.76 (95% CI: 0.75-0.77), sensitivity of 0.97 (95% CI: 0.96-0.97), positive predictive value (PPV) of 0.73 (95% CI: 0.72-0.74), negative predictive value (NPV) of 0.63 (95% CI: 0.60-0.66), and accuracy of 0.73 (95% CI: 0.72-0.73), respectively. BRF outperforms linear logistic regression by 15.6% in AUC, 3.0% in sensitivity, and 60.8% in NPV. End-to-end machine learning approaches can predict the acute onset of HF following ACS with high prediction accuracy. This proof-of-concept study has the potential to substantially advance the management of ACS patients by utilizing the machine learning model as a triage tool to automatically identify clinically significant patients allowing for prioritization of interventions.

Prognostic value of liver fibrosis assessed by the FIB-4 index in patients with acute coronary syndrome

INTRODUCTION AND OBJECTIVES

Liver fibrosis is present in nonalcoholic liver disease (NAFLD) and both precede liver failure. Subclinical forms of liver fibrosis might increase the risk of cardiovascular events. The objective of this study was to describe the prognostic value of the FIB-4 index on in-hospital mortality and postdischarge outcomes in patients with acute coronary syndrome (ACS).

METHODS

Retrospective study including all consecutive patients admitted for ACS between 2009 and 2019. According to the FIB-4 index, patients were categorized as <1.30, 1.30-2.67 or> 2.67. Heart failure (HF) and major bleeding (MB) were assessed taking all-cause mortality as a competing event and subhazard ratios (sHR) are presented. Recurrent events were evaluated by the incidence rate ratio (IRR).

RESULTS

We included 3106 patients and 6.66% had a FIB-4 index ≥ 1.3. A multivariate analysis verified a higher risk of in-hospital mortality associated with the FIB-4 index (OR, 1.24; P=.016). Patients with a FIB-4 index> 2.67 had a 2-fold higher in-hospital mortality risk (OR, 2.35; P=.038). After discharge (median follow-up 1112 days), the FIB-4 index had no prognostic value for mortality. In contrast, patients with FIB-4 index ≥ 1.3 had a higher risk of first (sHR, 1.61; P=.04) or recurrent (IRR, 1.70; P=.001) HF readmission. Similarly, FIB-4 index ≥ 1.30 was associated with a higher MB risk (sHR, 1.62; P=.030).

CONCLUSIONS

The assessment of liver fibrosis by the FIB-4 index identifies ACS patients not only at higher risk of in-hospital mortality but also at higher risk of HF and MB after discharge.

Prevalence, Characteristics, Management and Outcomes of Patients with Heart Failure with Preserved, Mildly Reduced, and Reduced Ejection Fraction in Spain

Objective: To estimate the prevalence, incidence, and describe the characteristics and management of patients with heart failure with preserved (HFpEF), mildly reduced (HFmrEF), and reduced ejection fraction (HFrEF) in Spain. Methods: Adults with ≥1 inpatient or outpatient HF diagnosis between 1 January 2013 and 30 September 2019 were identified through the BIG-PAC database. Annual incidence and prevalence by EF phenotype were estimated. Characteristics by EF phenotype were described in the 2016 and 2019 HF prevalent cohorts and outcomes in the 2016 HF prevalent cohort. Results: Overall, HF incidence and prevalence were 0.32/100 person-years and 2.34%, respectively, but increased every year. In 2019, 49.3% had HFrEF, 38.1% had HFpEF, and 4.3% had HFmrEF (in 8.3%, EF was not available). Compared with HFrEF, patients with HFpEF were largely female, older, and had more atrial fibrillation but less atherosclerotic cardiovascular disease. Among patients with HFrEF, 76.3% were taking renin-angiotensin system inhibitors, 69.5% beta-blockers, 36.8% aldosterone antagonists, 12.5% sacubitril/valsartan and 6.7% SGLT2 inhibitors. Patients with HFpEF and HFmrEF took fewer HF drugs compared to HFrEF. Overall, the event rates of HF hospitalization were 231.6/1000 person-years, which is more common in HFrEF patients. No clinically relevant differences were found in patients with HFpEF, regardless EF (50- < 60% vs. ≥60%). Conclusions: >2% of patients have HF, of which around 50% have HFrEF and 40% have HFpEF. The prevalence of HF is increasing over time. Clinical characteristics by EF phenotype are consistent with previous studies. The risk of outcomes, particularly HF hospitalization, remains high, likely related to insufficient HF treatment.

Predictive Value of Pro-BNP for Heart Failure Readmission after an Acute Coronary Syndrome

BACKGROUND

N-terminal pro-brain natural peptide (NT-pro-BNP) is a well-established biomarker of tissue congestion and has prognostic value in patients with heart failure (HF). Nonetheless, there is scarce evidence on its predictive capacity for HF re-admission after an acute coronary syndrome (ACS). We performed a prospective, single-center study in all patients discharged after an ACS. HF re-admission was analyzed by competing risk regression, taking all-cause mortality as a competing event. Results are presented as sub-hazard ratios (sHR). Recurrent hospitalizations were tested by negative binomial regression, and results are presented as incidence risk ratio (IRR).

RESULTS

Of the 2133 included patients, 528 (24.8%) had HF during the ACS hospitalization, and their pro-BNP levels were higher (3220 pg/mL vs. 684.2 pg/mL; p < 0.001). In-hospital mortality was 2.9%, and pro-BNP was similarly higher in these patients. Increased pro-BNP levels were correlated to increased risk of HF or death during the hospitalization. Over follow-up (median 38 months) 243 (11.7%) patients had at least one hospital readmission for HF and 151 (7.1%) had more than one. Complete revascularization had a preventive effect on HF readmission, whereas several other variables were associated with higher risk. Pro-BNP was independently associated with HF admission (sHR: 1.47) and readmission (IRR: 1.45) at any age. Significant interactions were found for the predictive value of pro-BNP in women, diabetes, renal dysfunction, STEMI and patients without troponin elevation.

CONCLUSIONS

In-hospital determination of pro-BNP is an independent predictor of HF readmission after an ACS.