Identification of Genetic Markers for Treatment Success in Heart Failure Patients

Living Lab Data of Patient Needs and Expectations for eHealth-Based Cardiac Rehabilitation in Germany and Spain From the TIMELY Study: Cross-Sectional Analysis

BACKGROUND

The use of eHealth technology in cardiac rehabilitation (CR) is a promising approach to enhance patient outcomes since adherence to healthy lifestyles and risk factor management during phase III CR maintenance is often poorly supported. However, patients' needs and expectations have not been extensively analyzed to inform the design of such eHealth solutions.

OBJECTIVE

The goal of this study was to provide a detailed patient perspective on the most important functionalities to include in an eHealth solution to assist them in phase III CR maintenance.

METHODS

A guided survey as part of a Living Lab approach was conducted in Germany (n=49) and Spain (n=30) involving women (16/79, 20%) and men (63/79, 80%) with coronary artery disease (mean age 57 years, SD 9 years) participating in a structured center-based CR program. The survey covered patients' perceived importance of different CR components in general, current usage of technology/technical devices, and helpfulness of the potential features of eHealth in CR. Questionnaires were used to identify personality traits (psychological flexibility, optimism/pessimism, positive/negative affect), potentially predisposing patients to acceptance of an app/monitoring devices.

RESULTS

All the patients in this study owned a smartphone, while 30%-40% used smartwatches and fitness trackers. Patients expressed the need for an eHealth platform that is user-friendly, personalized, and easily accessible, and 71% (56/79) of the patients believed that technology could help them to maintain health goals after CR. Among the offered components, support for regular physical exercise, including updated schedules and progress documentation, was rated the highest. In addition, patients rated the availability of information on diagnosis, current medication, test results, and risk scores as (very) useful. Of note, for each item, except smoking cessation, 35%-50% of the patients indicated a high need for support to achieve their long-term health goals, suggesting the need for individualized care. No major differences were detected between Spanish and German patients (all P>.05) and only younger age (P=.03) but not sex, education level, or personality traits (all P>.05) were associated with the acceptance of eHealth components.

CONCLUSIONS

The patient perspectives collected in this study indicate high acceptance of personalized user-friendly eHealth platforms with remote monitoring to improve adherence to healthy lifestyles among patients with coronary artery disease during phase III CR maintenance. The identified patient needs comprise support in physical exercise, including regular updates on personalized training recommendations. Availability of diagnoses, laboratory results, and medications, as part of a mobile electronic health record were also rated as very useful.

TRIAL REGISTRATION

ClinicalTrials.gov NCT05461729; https://clinicaltrials.gov/study/NCT05461729.

Artificial intelligence models in prediction of response to cardiac resynchronization therapy: a systematic review

The aim of the presented review is to summarize the literature data on the accuracy and clinical applicability of artificial intelligence (AI) models as a valuable alternative to the current guidelines in predicting cardiac resynchronization therapy (CRT) response and phenotyping of patients eligible for CRT implantation. This systematic review was performed according to the PRISMA guidelines. After a search of Scopus, PubMed, Cochrane Library, and Embase databases, 675 records were identified. Twenty supervised (prediction of CRT response) and 9 unsupervised (clustering and phenotyping) AI models were analyzed qualitatively (22 studies, 14,258 patients). Fifty-five percent of AI models were based on retrospective studies. Unsupervised AI models were able to identify clusters of patients with significantly different rates of primary outcome events (death, heart failure event). In comparison to the guideline-based CRT response prediction accuracy of 70%, supervised AI models trained on cohorts with > 100 patients achieved up to 85% accuracy and an AUC of 0.86 in their prediction of response to CRT for echocardiographic and clinical outcomes, respectively. AI models seem to be an accurate and clinically applicable tool in phenotyping of patients eligible for CRT implantation and predicting potential responders. In the future, AI may help to increase CRT response rates to over 80% and improve clinical decision-making and prognosis of the patients, including reduction of mortality rates. However, these findings must be validated in randomized controlled trials.

Diagnostic potential of energy metabolism-related genes in heart failure with preserved ejection fraction

Background

Heart failure with preserved ejection fraction (HFpEF) is associated with changes in cardiac metabolism that affect energy supply in the heart. However, there is limited research on energy metabolism-related genes (EMRGs) in HFpEF.

Methods

The HFpEF mouse dataset (GSE180065, containing heart tissues from 10 HFpEF and five control samples) was sourced from the Gene Expression Omnibus database. Gene expression profiles in HFpEF and control groups were compared to identify differentially expressed EMRGs (DE-EMRGs), and the diagnostic biomarkers with diagnostic value were screened using machine learning algorithms. Meanwhile, we constructed a biomarker-based nomogram model for its predictive power, and functionality of diagnostic biomarkers were conducted using single-gene gene set enrichment analysis, drug prediction, and regulatory network analysis. Additionally, consensus clustering analysis based on the expression of diagnostic biomarkers was utilized to identify differential HFpEF-related genes (HFpEF-RGs). Immune microenvironment analysis in HFpEF and subtypes were performed for analyzing correlations between immune cells and diagnostic biomarkers as well as HFpEF-RGs. Finally, qRT-PCR analysis on the HFpEF mouse model was used to validate the expression levels of diagnostic biomarkers.

Results

We selected 5 biomarkers (Chrna2, Gnb3, Gng7, Ddit4l, and Prss55) that showed excellent diagnostic performance. The nomogram model we constructed demonstrated high predictive power. Single-gene gene set enrichment analysis revealed enrichment in aerobic respiration and energy derivation. Further, various miRNAs and TFs were predicted by Gng7, such as Gng7-mmu-miR-6921-5p, ETS1-Gng7. A lot of potential therapeutic targets were predicted as well. Consensus clustering identified two distinct subtypes of HFpEF. Functional enrichment analysis highlighted the involvement of DEGs-cluster in protein amino acid modification and so on. Additionally, we identified five HFpEF-RGs (Kcnt1, Acot1, Kcnc4, Scn3a, and Gpam). Immune analysis revealed correlations between Macrophage M2, T cell CD4+ Th1 and diagnostic biomarkers, as well as an association between Macrophage and HFpEF-RGs. We further validated the expression trends of the selected biomarkers through experimental validation.

Conclusion

Our study identified 5 diagnostic biomarkers and provided insights into the prediction and treatment of HFpEF through drug predictions and network analysis. These findings contribute to a better understanding of HFpEF and may guide future research and therapy development.

Emerging role of artificial intelligence in cardiac electrophysiology

Artificial intelligence (AI) and machine learning (ML) have significantly impacted the field of cardiovascular medicine, especially cardiac electrophysiology (EP), on multiple fronts. The goal of this review is to familiarize readers with the field of AI and ML and their emerging role in EP. The current review is divided into 3 sections. In the first section, we discuss the definitions and basics of AI, ML, and big data. In the second section, we discuss their application to EP in the context of detection, prediction, and management of arrhythmias. Finally, we discuss the regulatory issues, challenges, and future directions of AI in EP.

An Artificial Intelligence Approach to Guiding the Management of Heart Failure Patients Using Predictive Models: A Systematic Review

Heart failure (HF) is one of the leading causes of mortality and hospitalization worldwide. The accurate prediction of mortality and readmission risk provides crucial information for guiding decision making. Unfortunately, traditional predictive models reached modest accuracy in HF populations. We therefore aimed to present predictive models based on machine learning (ML) techniques in HF patients that were externally validated. We searched four databases and the reference lists of the included papers to identify studies in which HF patient data were used to create a predictive model. Literature screening was conducted in Academic Search Ultimate, ERIC, Health Source Nursing/Academic Edition and MEDLINE. The protocol of the current systematic review was registered in the PROSPERO database with the registration number CRD42022344855. We considered all types of outcomes: mortality, rehospitalization, response to treatment and medication adherence. The area under the receiver operating characteristic curve (AUC) was used as the comparator parameter. The literature search yielded 1649 studies, of which 9 were included in the final analysis. The AUCs for the machine learning models ranged from 0.6494 to 0.913 in independent datasets, whereas the AUCs for statistical predictive scores ranged from 0.622 to 0.806. Our study showed an increasing number of ML predictive models concerning HF populations, although external validation remains infrequent. However, our findings revealed that ML approaches can outperform conventional risk scores and may play important role in HF management.

The Role of AI in Characterizing the DCM Phenotype

Dilated Cardiomyopathy is conventionally defined by left ventricular dilatation and dysfunction in the absence of coronary disease. Emerging evidence suggests many patients remain vulnerable to major adverse outcomes despite clear therapeutic success of modern evidence-based heart failure therapy. In this era of personalized medical care, the conventional assessment of left ventricular ejection fraction falls short in fully predicting evolution and risk of outcomes in this heterogenous group of heart muscle disease, as such, a more refined means of phenotyping this disease appears essential. Cardiac MRI (CMR) is well-placed in this respect, not only for its diagnostic utility, but the wealth of information captured in global and regional function assessment with the addition of unique tissue characterization across different disease states and patient cohorts. Advanced tools are needed to leverage these sensitive metrics and integrate with clinical, genetic and biochemical information for personalized, and more clinically useful characterization of the dilated cardiomyopathy phenotype. Recent advances in artificial intelligence offers the unique opportunity to impact clinical decision making through enhanced precision image-analysis tasks, multi-source extraction of relevant features and seamless integration to enhance understanding, improve diagnosis, and subsequently clinical outcomes. Focusing particularly on deep learning, a subfield of artificial intelligence, that has garnered significant interest in the imaging community, this paper reviews the main developments that could offer more robust disease characterization and risk stratification in the Dilated Cardiomyopathy phenotype. Given its promising utility in the non-invasive assessment of cardiac diseases, we firstly highlight the key applications in CMR, set to enable comprehensive quantitative measures of function beyond the standard of care assessment. Concurrently, we revisit the added value of tissue characterization techniques for risk stratification, showcasing the deep learning platforms that overcome limitations in current clinical workflows and discuss how they could be utilized to better differentiate at-risk subgroups of this phenotype. The final section of this paper is dedicated to the allied clinical applications to imaging, that incorporate artificial intelligence and have harnessed the comprehensive abundance of data from genetics and relevant clinical variables to facilitate better classification and enable enhanced risk prediction for relevant outcomes.

Using ensemble of ensemble machine learning methods to predict outcomes of cardiac resynchronization

INTRODUCTION

The efficacy of cardiac resynchronization therapy (CRT) has been widely studied in the medical literature; however, about 30% of candidates fail to respond to this treatment strategy. Smart computational approaches based on clinical data can help expose hidden patterns useful for identifying CRT responders.

METHODS

We retrospectively analyzed the electronic health records of 1664 patients who underwent CRT procedures from January 1, 2002 to December 31, 2017. An ensemble of ensemble (EoE) machine learning (ML) system composed of a supervised and an unsupervised ML layers was developed to generate a prediction model for CRT response.

RESULTS

We compared the performance of EoE against traditional ML methods and the state-of-the-art convolutional neural network (CNN) model trained on raw electrocardiographic (ECG) waveforms. We observed that the models exhibited improvement in performance as more features were incrementally used for training. Using the most comprehensive set of predictors, the performance of the EoE model in terms of the area under the receiver operating characteristic curve and F1-score were 0.76 and 0.73, respectively. Direct application of the CNN model on the raw ECG waveforms did not generate promising results.

CONCLUSION

The proposed CRT risk calculator effectively discriminates which heart failure (HF) patient is likely to respond to CRT significantly better than using clinical guidelines and traditional ML methods, thus suggesting that the tool can enhanced care management of HF patients by helping to identify high-risk patients.

Association of RANK and RANKL gene polymorphism with survival and calcium levels in multiple myeloma

Multiple myeloma (MM) is a heterogeneous bone marrow cancer characterized by proliferation of malignant plasma cells in the bone marrow. One of its major symptoms are hypercalcaemia and bone lesions, which may result in pathologic bone fractures. Receptor activator for nuclear factor κB (RANK) and its ligand, RANKL, are part of an activation pathway for osteoclasts and are thus responsible for bone resorption. Furthermore, RANKL expression is increased in multiple myeloma. In the present study, we investigated the role of single nucleotide polymorphisms (SNPs) in the genes coding for RANK (rs1805034, rs8086340), RANKL (rs7325635, rs7988338), and TACI (rs34562254), a receptor for osteoclast-derived pro-survival factors. The study involved 222 patients and 222 healthy individuals, and the analysis included disease susceptibility, survival, bone lesions, calcium levels, and vascular endothelial growth factor levels. Patients with allele RANK rs1805034 C had higher survival (p = .003). This relationship was especially evident in women (p = .006). Furthermore, allele rs1805034 C was associated with slightly lower median age at diagnosis (64.0 vs. 65.5, p = .008). Allele RANKL rs7325635 A correlated with lower progression-free survival (p = .027), and with lack of early progression (p = .023). Additionally, women with allele rs7325635 G were found to have higher calcium blood concentration (p = .040). Allele TACI rs34562254 A was more common in MM patients in more advanced stages (II and III stage International Staging System) at diagnosis (p = .017), and the SNP showed a slight trend towards association in a multivariate analysis (p = .084). Taken together, our results suggest that RANK rs1805034 and RANKL rs7325635 may have a role in MM development and progression.

Biomarkers to predict the response to cardiac resynchronization therapy

Cardiac resynchronization therapy (CRT) is an established non-pharmacological treatment for selected heart failure patients with wide QRS duration. However, there is a persistent number of non-responders throughout. The prediction of the CRT response is paramount to adequately select the correct patients for CRT. One of the expanding fields of research is the development of biomarkers that predict the response to CRT. A review of the available literature on biomarkers in CRT patients has been performed to formulate a critical appraisal of the available data. The main conclusion of our review is that biomarker research in this patient population is very fragmented and broad. This results in the use of non-uniform endpoints to define the CRT response, which precludes an in-depth comparison of the available data. To improve research development in this field, a uniform definition of the CRT response and relevant endpoints is necessary to better predict the CRT response.

Polymorphisms within the RANK and RANKL Encoding Genes in Patients with Rheumatoid Arthritis: Association with Disease Progression and Effectiveness of the Biological Treatment

Inconsistency of the results regarding the genetic variability within genes coding for receptor activator of nuclear factor κB (RANK) and its ligand (RANKL) in rheumatoid arthritis (RA) prompted us to study the RANK and RANKL polymorphisms as potential biomarkers associated with disease predisposition and response to anti-TNF treatment in a group of Polish patients with RA. This study enrolled 318 RA patients and 163 controls. RANK (rs8086340, C > G; rs1805034, C > T) and RANKL (rs7325635, G > A; rs7988338 G > A) alleles were determined by real-time PCR with melting curve analysis and related with clinical parameters. In addition, RANKL serum levels were measured by ELISA. The RANK rs8086340-G allele was overrepresented among patients as compared to controls (OD = 1.777, p = 0.038). C-reactive protein (CRP) levels were significantly (p < 0.05) associated with RANK rs8086340 polymorphism and were higher in the CC-homozygotes at the baseline while lower in the GG-carriers at the 12th week of the treatment. At the latter time point RANKL rs7325635-GG-positive patients also showed significantly lower CRP concentrations. Higher alkaline phosphatase levels before induction of anti-TNF therapy were observed in RANK rs8086340 and RANK rs1805034 CC homozygotes (p = 0.057 and p = 0.035, respectively). The GG homozygosity of both RANKL single nucleotide polymorphisms was significantly associated with the number of swollen joints (rs7988338 and rs7325635, before and at the 12th week of therapy, respectively, p < 0.05 in both cases). These results imply that polymorphisms within the RANK and RANKL genes affect RA susceptibility and anti-TNF treatment outcome.

Artificial Intelligence in Pharmacoepidemiology: A Systematic Review. Part 1-Overview of Knowledge Discovery Techniques in Artificial Intelligence

Aim

To perform a systematic review on the application of artificial intelligence (AI) based knowledge discovery techniques in pharmacoepidemiology.

Study Eligibility Criteria

Clinical trials, meta-analyses, narrative/systematic review, and observational studies using (or mentioning articles using) artificial intelligence techniques were eligible. Articles without a full text available in the English language were excluded.

Data Sources

Articles recorded from 1950/01/01 to 2019/05/06 in Ovid MEDLINE were screened.

Participants

Studies including humans (real or simulated) exposed to a drug.

Results

In total, 72 original articles and 5 reviews were identified via Ovid MEDLINE. Twenty different knowledge discovery methods were identified, mainly from the area of machine learning (66/72; 91.7%). Classification/regression (44/72; 61.1%), classification/regression + model optimization (13/72; 18.0%), and classification/regression + features selection (12/72; 16.7%) were the three most frequent tasks in reviewed literature that machine learning methods has been applied to solve. The top three used techniques were artificial neural networks, random forest, and support vector machines models.

Conclusions

The use of knowledge discovery techniques of artificial intelligence techniques has increased exponentially over the years covering numerous sub-topics of pharmacoepidemiology.

Systematic Review Registration

Systematic review registration number in PROSPERO: CRD42019136552.

Artificial Intelligence for Cardiac Imaging-Genetics Research

Cardiovascular conditions remain the leading cause of mortality and morbidity worldwide, with genotype being a significant influence on disease risk. Cardiac imaging-genetics aims to identify and characterize the genetic variants that influence functional, physiological, and anatomical phenotypes derived from cardiovascular imaging. High-throughput DNA sequencing and genotyping have greatly accelerated genetic discovery, making variant interpretation one of the key challenges in contemporary clinical genetics. Heterogeneous, low-fidelity phenotyping and difficulties integrating and then analyzing large-scale genetic, imaging and clinical datasets using traditional statistical approaches have impeded process. Artificial intelligence (AI) methods, such as deep learning, are particularly suited to tackle the challenges of scalability and high dimensionality of data and show promise in the field of cardiac imaging-genetics. Here we review the current state of AI as applied to imaging-genetics research and discuss outstanding methodological challenges, as the field moves from pilot studies to mainstream applications, from one dimensional global descriptors to high-resolution models of whole-organ shape and function, from univariate to multivariate analysis and from candidate gene to genome-wide approaches. Finally, we consider the future directions and prospects of AI imaging-genetics for ultimately helping understand the genetic and environmental underpinnings of cardiovascular health and disease.

Machine Learning Algorithm Predicts Cardiac Resynchronization Therapy Outcomes: Lessons From the COMPANION Trial

BACKGROUND

Cardiac resynchronization therapy (CRT) reduces morbidity and mortality in heart failure patients with reduced left ventricular function and intraventricular conduction delay. However, individual outcomes vary significantly. This study sought to use a machine learning algorithm to develop a model to predict outcomes after CRT.

METHODS AND RESULTS

Models were developed with machine learning algorithms to predict all-cause mortality or heart failure hospitalization at 12 months post-CRT in the COMPANION trial (Comparison of Medical Therapy, Pacing, and Defibrillation in Heart Failure). The best performing model was developed with the random forest algorithm. The ability of this model to predict all-cause mortality or heart failure hospitalization and all-cause mortality alone was compared with discrimination obtained using a combination of bundle branch block morphology and QRS duration. In the 595 patients with CRT-defibrillator in the COMPANION trial, 105 deaths occurred (median follow-up, 15.7 months). The survival difference across subgroups differentiated by bundle branch block morphology and QRS duration did not reach significance (P=0.08). The random forest model produced quartiles of patients with an 8-fold difference in survival between those with the highest and lowest predicted probability for events (hazard ratio, 7.96; P<0.0001). The model also discriminated the risk of the composite end point of all-cause mortality or heart failure hospitalization better than subgroups based on bundle branch block morphology and QRS duration.

CONCLUSIONS

In the COMPANION trial, a machine learning algorithm produced a model that predicted clinical outcomes after CRT. Applied before device implant, this model may better differentiate outcomes over current clinical discriminators and improve shared decision-making with patients.

GNB3 C825T Polymorphism and Myocardial Recovery in Peripartum Cardiomyopathy: Results of the Multicenter Investigations of Pregnancy-Associated Cardiomyopathy Study

BACKGROUND

Black women are at greater risk for peripartum cardiomyopathy (PPCM). The guanine nucleotide-binding proteins β-3 subunit (GNB3) has a polymorphism C825T. The GNB3 TT genotype more prevalent in blacks is associated with poorer outcomes. We evaluated GNB3 genotype and myocardial recovery in PPCM.

METHODS AND RESULTS

A total of 97 women with PPCM were enrolled and genotyped for the GNB3 T/C polymorphism. Left ventricular ejection fraction (LVEF) was assessed by echocardiography at entry, 6 and 12 months postpartum. LVEF over time in subjects with the GNB3 TT genotype was compared with those with the C allele overall and in black and white subsets. The cohort was 30% black, age 30+6, LVEF 0.34+0.10 at entry 31+25 days postpartum. The % GNB3 genotype for TT/CT/CC=23/41/36 and differed markedly by race (blacks=52/38/10 versus whites=10/44/46, P<0.001). In subjects with the TT genotype, LVEF at entry was lower (TT=0.31+0.09; CT+CC=0.35+0.09, P=0.054) and this difference increased at 6 (TT=0.45+0.15; CT+CC=0.53+0.08, P=0.002) and 12 months (TT=0.45+0.15; CT+CC=0.56+0.07, P<0.001.). The difference in LVEF at 12 months by genotype was most pronounced in blacks (12 months LVEF for GNB3 TT=0.39+0.16; versus CT+CC=0.53+0.09, P=0.02) but evident in whites (TT=0.50++0.11; CT+CC=0.56+0.06, P=0.04).

CONCLUSIONS

The GNB3 TT genotype was associated with lower LVEF at 6 and 12 months in women with PPCM, and this was particularly evident in blacks. Racial differences in the prevalence and impact of GNB3 TT may contribute to poorer outcomes in black women with PPCM.

Cardiac dyssynchrony and response to cardiac resynchronisation therapy in heart failure: can genetic predisposition play a role?

Cardiac resynchronisation therapy (CRT) is an accepted treatment for heart failure patients with depressed left ventricular (LV) function and dyssynchrony. However, despite better clinical outcome and improved cardiac function after CRT in the majority of eligible heart failure patients, a large proportion of implanted patients do not seem to benefit clinically from this therapy. In this review we consider whether genetic factors may play a role in modulating response to CRT and summarise the few genetic studies that have investigated the role of genetic variation in candidate genes.