Development of a biomarker panel to predict cardiac resynchronization therapy response: Results from the SMART-AV trial

Obstructive sleep apnea alters microRNA levels: Effects of continuous positive airway pressure

Background

Obstructive sleep apnea (OSA) has been linked to cytokine-mediated chronic inflammatory states. Continuous positive airway pressure (CPAP) is an established therapy for OSA, but its effects on inflammation remain unclear. A recent study from our group identified soluble cytokine receptors altered in OSA patients and modified by CPAP adherence. However, the upstream regulatory pathways responsible for these shifts in proinflammatory cascades with OSA and CPAP therapy remained unknown. Accordingly, this study mapped OSA and CPAP-modulated soluble cytokine receptors to specific microRNAs and then tested the hypothesis that OSA and CPAP adherence shift cytokine-related microRNA expression profiles.

Study Design

Plasma samples were collected from patients with OSA (n=50) at baseline and approximately 90 days after CPAP initiation and compared to referent control subjects (n=10). Patients with OSA were further divided into cohorts defined by adherence vs nonadherence to CPAP therapy. The microRNAs that mapped to soluble cytokine receptors of interest were subjected to quantitative polymerase chain reaction.

Results

At baseline, increased hsa-miR-15a-5p, hsa-miR-15b-5p, hsa-miR-16-5p, hsa-miR-195-5p, hsa-miR-424-5p, hsa-miR-223-3p, and hsa-miR-223-5p were observed in patients with OSA compared to controls (p<0.05). In CPAP adherent patients (n=22), hsa-miR233-3p and hsa-miR233-5p decreased at follow-up (p<0.05) whereas there was no change in miR levels from baseline in non-adherent CPAP patients (n=28). The miRs hsa-miR233-3p and hsa-miR233-5p mapped to both proinflammatory and innate immunity activation; the inflammasome.

Conclusion

A specific set of microRNAs, including hsa-miR233-3p and hsa-miR233-5p, may serve as a marker of inflammatory responses in patients with OSA, and be used to assess attenuation of inflammasome activation by CPAP.

The role of fibrosis, inflammation, and congestion biomarkers for outcome prediction in candidates to cardiac resynchronization therapy: is "response" the right answer?

Background

Cardiac resynchronization therapy (CRT) is an established treatment in selected patients suffering from heart failure with reduced ejection fraction (HFrEF). It has been proposed that myocardial fibrosis and inflammation could influence CRT "response" and outcome. Our study investigated the long-term prognostic significance of cardiac biomarkers in HFrEF patients with an indication for CRT.

Methods

Consecutive patients referred for CRT implantation were retrospectively evaluated. The soluble suppression of tumorigenicity 2 (sST2), galectin-3 (Gal-3), N-terminal portion of the B-type natriuretic peptide (NT-proBNP), and estimated glomerular filtration rate (eGFR) were measured at baseline and after 1 year of follow-up. Multivariate analyses were performed to evaluate their correlation with the primary composite outcome of cardiovascular mortality and heart failure hospitalizations at a mean follow-up of 9 ± 2 years.

Results

Among the 86 patients enrolled, 44% experienced the primary outcome. In this group, the mean baseline values of NT-proBNP, Gal-3, and sST2 were significantly higher compared with the patients without cardiovascular events. At the multivariate analyses, baseline Gal-3 [cut-off: 16.6 ng/ml, AUC: 0.91, p < 0.001, HR 8.33 (1.88-33.33), p = 0.005] and sST2 [cut-off: 35.6 ng/ml AUC: 0.91, p < 0.001, HR 333 (250-1,000), p = 0.003] significantly correlated with the composite outcome in the prediction models with high likelihood. Among the parameters evaluated at 1-year follow-up, sST2, eGFR, and the variation from baseline to 1-year of Gal-3 levels showed a strong association with the primary outcome [HR 1.15 (1.08-1.22), p < 0.001; HR: 0.84 (0.74-0.91), p = 0.04; HR: 1.26 (1.10-1.43), p ≤ 0.001, respectively]. Conversely, the echocardiographic definition of CRT response did not correlate with any outcome.

Conclusion

In HFrEF patients with CRT, sST2, Gal-3, and renal function were associated with the combined endpoint of cardiovascular death and HF hospitalizations at long-term follow-up, while the echocardiographic CRT response did not seem to influence the outcome of the patients.

Risk scores in cardiac resynchronization therapy-A review of the literature

Cardiac resynchronization therapy (CRT) for selected heart failure (HF) patients improves symptoms and reduces morbidity and mortality; however, the prognosis of HF is still poor. There is an emerging need for tools that might help in optimal patient selection and provide prognostic information for patients and their families. Several risk scores have been created in recent years; although, no literature review is available that would list the possible scores for the clinicians. We identified forty-eight risk scores in CRT and provided the calculation methods and formulas in a ready-to-use format. The reviewed score systems can predict the prognosis of CRT patients; some of them have even provided an online calculation tool. Significant heterogeneity is present between the various risk scores in terms of the variables incorporated and some variables are not yet used in daily clinical practice. The lack of cross-validation of the risk scores limits their routine use and objective selection. As the number of prognostic markers of CRT is overwhelming, further studies might be required to analyze and cross-validate the data.

Interpretable machine learning predicts cardiac resynchronization therapy responses from personalized biochemical and biomechanical features

BACKGROUND

Cardiac Resynchronization Therapy (CRT) is a widely used, device-based therapy for patients with left ventricle (LV) failure. Unfortunately, many patients do not benefit from CRT, so there is potential value in identifying this group of non-responders before CRT implementation. Past studies suggest that predicting CRT response will require diverse variables, including demographic, biomarker, and LV function data. Accordingly, the objective of this study was to integrate diverse variable types into a machine learning algorithm for predicting individual patient responses to CRT.

METHODS

We built an ensemble classification algorithm using previously acquired data from the SMART-AV CRT clinical trial (n = 794 patients). We used five-fold stratified cross-validation on 80% of the patients (n = 635) to train the model with variables collected at 0 months (before initiating CRT), and the remaining 20% of the patients (n = 159) were used as a hold-out test set for model validation. To improve model interpretability, we quantified feature importance values using SHapley Additive exPlanations (SHAP) analysis and used Local Interpretable Model-agnostic Explanations (LIME) to explain patient-specific predictions.

RESULTS

Our classification algorithm incorporated 26 patient demographic and medical history variables, 12 biomarker variables, and 18 LV functional variables, which yielded correct prediction of CRT response in 71% of patients. Additional patient stratification to identify the subgroups with the highest or lowest likelihood of response showed 96% accuracy with 22 correct predictions out of 23 patients in the highest and lowest responder groups.

CONCLUSION

Computationally integrating general patient characteristics, comorbidities, therapy history, circulating biomarkers, and LV function data available before CRT intervention can improve the prediction of individual patient responses.

The Translation and Commercialisation of Biomarkers for Cardiovascular Disease—A Review

As a leading cause of mortality and morbidity worldwide, cardiovascular disease and its diagnosis, quantification, and stratification remain significant health issues. Increasingly, patients present with cardiovascular disease in the absence of known risk factors, suggesting the presence of yet unrecognized pathological processes and disease predispositions. Fortunately, a host of emerging cardiovascular biomarkers characterizing and quantifying ischaemic heart disease have shown great promise in both laboratory settings and clinical trials. These have demonstrated improved predictive value additional to widely accepted biomarkers as well as providing insight into molecular phenotypes beneath the broad umbrella of cardiovascular disease that may allow for further personalized treatment regimens. However, the process of translation into clinical practice – particularly navigating the legal and commercial landscape – poses a number of challenges. Practical and legal barriers to the biomarker translational pipeline must be further considered to develop strategies to bring novel biomarkers into the clinical sphere and apply these advances at the patient bedside. Here we review the progress of emerging biomarkers in the cardiovascular space, with particular focus on those relevant to the unmet needs in ischaemic heart disease.

Prediction of response after cardiac resynchronization therapy with machine learning

AIMS

Nearly one third of patients receiving cardiac resynchronization therapy (CRT) suffer non-response. We intend to develop predictive models using machine learning (ML) approaches and easily attainable features before CRT implantation.

METHODS AND RESULTS

The baseline characteristics of 752 CRT recipients from two hospitals were retrospectively collected. Nine ML predictive models were established, including logistic regression (LR), elastic network (EN), lasso regression (Lasso), ridge regression (Ridge), neural network (NN), support vector machine (SVM), random forest (RF), XGBoost and k-nearest neighbour (k-NN). Sensitivity, specificity, precision, accuracy, F1, log-loss, area under the receiver operating characteristic (AU-ROC), and average precision (AP) of each model were evaluated. AU-ROC was compared between models and the latest guidelines. Six models had an AU-ROC value above 0.75. The LR, EN and Ridge models showed the highest overall predictive power compared with other models with AU-ROC at 0.77. The XGBoost model reached the highest sensitivity at 0.72, while the highest specificity was achieved by Ridge model at 0.92. All ML models achieved higher AU-ROCs that those derived from the latest guidelines (all P < 0.05). The effect size analysis identified left bundle branch block, left ventricular end-systolic diameter, and history of percutaneous coronary intervention as the most crucial predictors of CRT response. An online tool to facilitate the prediction of CRT response is freely available at http://www.crt-response.com/.

CONCLUSIONS

ML algorithms produced efficient predictive models for evaluation of CRT response with features before implantation. Tools developed accordingly could improve the selection of CRT candidates and reduce the incidence of non-response.

Cytokine Signaling and Matrix Remodeling Pathways Associated with Cardiac Sarcoidosis Disease Activity Defined Using FDG PET Imaging

While cardiac imaging has improved the diagnosis and risk assessment for cardiac sarcoidosis (CS), treatment regimens have consisted of generalized heart failure therapies and non-specific anti-inflammatory regimens. The overall goal of this study was to perform high-sensitivity plasma profiling of specific inflammatory pathways in patients with sarcoidosis and with CS.Specific inflammatory/proteolytic cascades were upregulated in sarcoidosis patients, and certain profiles emerged for CS patients.Plasma samples were collected from patients with biopsy-confirmed sarcoidosis undergoing F-18 fluorodeoxyglucose positron emission tomography (n = 47) and compared to those of referent control subjects (n = 6). Using a high-sensitivity, automated multiplex array, cytokines, soluble cytokine receptor profiles (an index of cytokine activation), as well as matrix metalloproteinase (MMP), and endogenous MMP inhibitors (TIMPs) were examined.The plasma tumor necrosis factor (TNF) and soluble TNF receptors sCD30 and sTNFRI were increased using sarcoidosis, and sTNFRII increased in CS patients (n = 18). The soluble interleukin sIL-2R and vascular endothelial growth factor receptors (sVEGFR2 and sVEGFR3) increased to the greatest degree in CS patients. When computed as a function of referent control values, the majority of soluble cytokine receptors increased in both sarcoidosis and CS groups. Plasma MMP-9 levels increased in sarcoidosis but not in the CS subset. Plasma TIMP levels declined in both groups.The findings from this study were the identification of increased activation of a cluster of soluble cytokine receptors, which augment not only inflammatory cell maturation but also transmigration in patients with sarcoidosis and patients with cardiac involvement.

Using Machine-Learning for Prediction of the Response to Cardiac Resynchronization Therapy: The SMART-AV Study

OBJECTIVES

This study aimed to apply machine learning (ML) to develop a prediction model for short-term cardiac resynchronization therapy (CRT) response to identifying CRT candidates for early multidisciplinary CRT heart failure (HF) care.

BACKGROUND

Multidisciplinary optimization of cardiac resynchronization therapy (CRT) delivery can improve long-term CRT outcomes but requires substantial staff resources.

METHODS

Participants from the SMART-AV (SmartDelay-Determined AV Optimization: Comparison of AV Optimization Methods Used in Cardiac Resynchronization Therapy [CRT]) trial (n = 741; age: 66 ± 11 years; 33% female; 100% New York Heart Association HF class III-IV; 100% ejection fraction ≤35%) were randomly split into training/testing (80%; n = 593) and validation (20%; n = 148) samples. Baseline clinical, electrocardiographic, echocardiographic, and biomarker characteristics, and left ventricular (LV) lead position (43 variables) were included in 8 ML models (random forests, convolutional neural network, lasso, adaptive lasso, plugin lasso, elastic net, ridge, and logistic regression). A composite of freedom from death and HF hospitalization and a >15% reduction in LV end-systolic volume index at 6 months after CRT was the end point.

RESULTS

The primary end point was met by 337 patients (45.5%). The adaptive lasso model was the most more accurate (area under the receiver operating characteristic curve: 0.759; 95% confidence interval [CI]: 0.678-0.840), well calibrated, and parsimonious (19 predictors; nearly half potentially modifiable). Participants in the 5th quintile compared with those in the 1st quintile of the prediction model had 14-fold higher odds of composite CRT response (odds ratio: 14.0; 95% CI: 8.0-14.4). The model predicted CRT response with 70% accuracy, 70% sensitivity, and 70% specificity, and should be further validated in prospective studies.

CONCLUSIONS

ML predicts short-term CRT response and thus may help with CRT procedure and early post-CRT care planning. (SmartDelay-Determined AV Optimization: A Comparison of AV Optimization Methods Used in Cardiac Resynchronization Therapy [CRT] [SMART-AV]; NCT00677014).

The relationship between ECG predictors of cardiac resynchronization therapy benefit

INTRODUCTION

Cardiac resynchronization therapy (CRT) is an effective treatment that reduces mortality and improves cardiac function in patients with left bundle branch block (LBBB). However, about 30% of patients passing the current criteria do not benefit or benefit only a little from CRT. Three predictors of benefit based on different ECG properties were compared: 1) "strict" left bundle branch block classification (SLBBB); 2) QRS area; 3) ventricular electrical delay (VED) which defines the septal-lateral conduction delay. These predictors have never been analyzed concurrently. We analyzed the relationship between them on a subset of 602 records from the MADIT-CRT trial.

METHODS & RESULTS

SLBBB classification was performed by two experts; QRS area and VED were computed fully automatically. High-frequency QRS (HFQRS) maps were used to inspect conduction abnormalities. The correlation between SLBBB and other predictors was R = 0.613, 0.523 and 0.390 for VED, QRS area in Z lead, and QRS duration, respectively. Scatter plots were used to pick up disagreement between the predictors. The majority of SLBBB subjects- 295 of 330 (89%)-are supposed to respond positively to CRT according to the VED and QRS area, though 93 of 272 (34%) non-SLBBB should also benefit from CRT according to the VED and QRS area.

CONCLUSION

SLBBB classification is limited by the proper setting of cut-off values. In addition, it is too "strict" and excludes patients that may benefit from CRT therapy. QRS area and VED are clearly defined parameters. They may be used to optimize biventricular stimulation. Detailed analysis of conduction irregularities with CRT optimization should be based on HFQRS maps.