B-Lines by Lung Ultrasound Can Predict Worsening Heart Failure in Acute Myocardial Infarction During Hospitalization and Short-Term Follow-Up

The Importance of Lung Ultrasound and IGFBP7 (Insulin-like Growth Factor Binding Protein 7) Assessment in Diagnosing Patients with Heart Failure

Background: In daily practice, there are problems with adequately diagnosing the cause of dyspnea in patients with heart failure with preserved and mildly reduced ejection fractions (HFpEF and HFmrEF). This study aimed to assess the usefulness of lung ultrasound in diagnosing HFpEF and HFmrEF and determine its correlation with IGFBP7 (insulin-like growth factor binding protein 7), NTproBNP (N-terminal pro-B-type natriuretic peptide), and echocardiographic markers. Methods: The research was conducted on 143 patients hospitalized between 2018 and 2020, admitted due to dyspnea, and diagnosed with HFpEF and HFmrEF. Venous blood was collected from all participants to obtain basic biochemical parameters, NTproBNP, and IGFBP7. Moreover, all participants underwent echocardiography and transthoracic lung ultrasound. Two years after hospitalization a follow-up telephone visit was performed. Results: The number of B-lines in the LUS ≥ 16 was determined with a sensitivity of-73% and specificity of-62%, indicating exacerbation of heart failure symptoms on admission. The number of B-lines ≥ 14 on admission was determined as a cut-off point, indicating an increased risk of death during the 2-year follow-up period. The factors that significantly impacted mortality in the study patient population were age and the difference between the number of B-lines on ultrasound at admission and at hospital discharge. IGFBP7 levels had no significant effect on the duration of hospitalization, risk of rehospitalization, or mortality during follow-up. Conclusions: Lung ultrasonography provides additional diagnostic value in patients with HFpEF or HFmrEF and exacerbation of heart failure symptoms. The number of B-lines ≥ 14 may indicate an increased risk of death.

Development and comparison of machine learning-based models for predicting heart failure after acute myocardial infarction

AIMS

Heart failure (HF) is one of the common adverse cardiovascular events after acute myocardial infarction (AMI), but the predictive efficacy of numerous machine learning (ML) built models is unclear. This study aimed to build an optimal model to predict the occurrence of HF in AMI patients by comparing seven ML algorithms.

METHODS

Cohort 1 included AMI patients from 2018 to 2019 divided into HF and control groups. All first routine test data of the study subjects were collected as the features to be selected for the model, and seven ML algorithms with screenable features were evaluated. Cohort 2 contains AMI patients from 2020 to 2021 to establish an early warning model with external validation. ROC curve and DCA curve to analyze the diagnostic efficacy and clinical benefit of the model respectively.

RESULTS

The best performer among the seven ML algorithms was XgBoost, and the features of XgBoost algorithm for troponin I, triglycerides, urine red blood cell count, γ-glutamyl transpeptidase, glucose, urine specific gravity, prothrombin time, prealbumin, and urea were ranked high in importance. The AUC of the HF-Lab9 prediction model built by the XgBoost algorithm was 0.966 and had good clinical benefits.

CONCLUSIONS

This study screened the optimal ML algorithm as XgBoost and developed the model HF-Lab9 will improve the accuracy of clinicians in assessing the occurrence of HF after AMI and provide a reference for the selection of subsequent model-building algorithms.

[Prognostic value of periprocedural dynamics of left ventricular ejection fraction and subclinical pulmonary congestion in patients with myocardial infarction]

AIM

To assess the joint prognostic value of periprocedural dynamics of the left ventricular ejection fraction (PPD of LVEF) and subclinical pulmonary congestion during lung stress ultrasound in patients with first acute myocardial infarction (AMI) and percutaneous coronary intervention (PCI) in relation to the development of heart failure (HF) in the postinfarction period.

MATERIALS AND METHODS

Our prospective, single-centre, observational study included 105 patients with a first MI with no HF in the anamnesis and successful PCI. All patients underwent standard clinical and laboratory tests, NT-proBNP level assessment, echocardiography, lung stress ultrasound with a 6-minute walk test. All patients had no clinical signs of heart failure at admission and at discharge. Criteria for PPD of LV EF: improvement in LV EF≥50%; ∆LV EF more than 5%, but LV EF<50%. According to the results of lung stress ultrasound, pulmonary congestion was diagnosed: mild (2-4 B-lines), moderate (5-9 B-lines) and severe (≥10 B-lines). The end point was hospitalization for HF for 2.5 years.

RESULTS

Upon admission, LV EF of 50% or more was registered in 45 patients (42.9%). Positive PPD was registered in 31 (29.5%) patients. After stress ultrasound of the lungs, 20 (19%) patients had mild subclinical pulmonary congestion, 38 (36%) moderate and 47 (45%) severe according to the criteria presented. During the observation period, patients with no PPD of LVEF were significantly more likely to be hospitalized for the development of HF (in 44.4% of cases) compared with patients with positive PPD (in 15.2% of cases) and with initial LV EF≥50% (in 13.4% of cases; p=0.005). When performing logistic regression analysis, the best predictive ability was found in the combination of the absence of PPD of LV EF and the sum of B-lines ≥10 on exercise (relative risk 7.45; 95% confidence interval 2.55-21.79; p<0.000).

CONCLUSION

Evaluation of the combination of PPD of LV EF and the results of stress lung ultrasound at discharge in patients with first AMI and successful PCI with no HF in anamnesis allows us to identify a high-risk group for the development of HF in the postinfarction period.

Trajectory and correlates of pulmonary congestion by lung ultrasound in patients with acute myocardial infarction: insights from PARADISE-MI

AIM

PARADISE-MI examined the efficacy of sacubitril/valsartan in acute myocardial infarction (AMI) complicated by reduced left ventricular ejection fraction (LVEF), pulmonary congestion, or both. We sought to assess the trajectory of pulmonary congestion using lung ultrasound (LUS) and its association with cardiac structure and function in a pre-specified substudy.

METHODS AND RESULTS

Patients without prior heart failure (HF) underwent eight-zone LUS and echocardiography at baseline (±2 days of randomization) and after 8 months. B-lines were quantified offline, blinded to treatment, clinical findings, time point, and outcomes. Among 152 patients (median age 65, 32% women, mean LVEF 41%), B-lines were detectable in 87% at baseline [median B-line count: 4 (interquartile range 2-8)]. Among 115 patients with LUS data at baseline and follow-up, B-lines decreased significantly from baseline (mean ± standard deviation: -1.6 ± 7.3; P = 0.018). The proportion of patients without pulmonary congestion at follow-up was significantly higher in those with fewer B-lines at baseline. Adjusted for baseline, B-lines at follow-up were on average 6 (95% confidence interval: 3-9) higher in patients who experienced an intercurrent HF event vs. those who did not (P = 0.001). A greater number of B-lines at baseline was associated with larger left atrial size, higher E/e' and E/A ratios, greater degree of mitral regurgitation, worse right ventricular systolic function, and higher tricuspid regurgitation velocity (P-trend <0.05 for all).

CONCLUSION

In this AMI cohort, B-lines, indicating pulmonary congestion, were common at baseline and, on average, decreased significantly from baseline to follow-up. Worse pulmonary congestion was associated with prognostically important echocardiographic markers.