The application of big data to cardiovascular disease: paths to precision medicine

Advanced hemodynamic and cluster analysis for identifying novel RV function subphenotypes in patients with pulmonary hypertension

BACKGROUND

Quantifying right ventricular (RV) function is important to describe the pathophysiology of in pulmonary hypertension (PH). Current phenotyping strategies in PH rely on few invasive hemodynamic parameters to quantify RV dysfunction severity. The aim of this study was to identify novel RV phenotypes using unsupervised clustering methods on advanced hemodynamic features of RV function.

METHODS

Participants were identified from the University of Arizona Pulmonary Hypertension Registry (n = 190). RV-pulmonary artery coupling (Ees/Ea), RV systolic (Ees), and diastolic function (Eed) were quantified from stored RV pressure waveforms. Consensus clustering analysis with bootstrapping was used to identify the optimal clustering method. Pearson correlation analysis was used to reduce collinearity between variables. RV cluster subphenotypes were characterized using clinical data and compared to pulmonary vascular resistance (PVR) quintiles.

RESULTS

Five distinct RV clusters (C1-C5) with distinct RV subphenotypes were identified using k-medoids with a Pearson distance matrix. Clusters 1 and 2 both have low diastolic stiffness (Eed) and afterload (Ea) but RV-PA coupling (Ees/Ea) is decreased in C2. Intermediate cluster (C3) has a similar Ees/Ea as C2 but with higher PA pressure and afterload. Clusters C4 and C5 have increased Eed and Ea but C5 has a significant decrease in Ees/Ea. Cardiac output was high in C3 distinct from the other clusters. In the PVR quintiles, contractility increased and stroke volume decreased as a function of increased afterload. World Symposium PH classifications were distributed across clusters and PVR quintiles.

CONCLUSIONS

RV-centric phenotyping offers an opportunity for a more precise-medicine-based management approach.

Back to the basics: The need for an etiological classification of chronic heart failure

The left ventricular (LV) ejection fraction (LVEF), despite its severe limitations, has had an epicentral role in heart failure (HF) classification, management, and risk stratification for decades. The major argument favoring the LVEF based HF classification has been that it defines groups of patients in which treatment is effective. However, this reasoning has recently collapsed, since medical treatment with neurohormonal inhibitors, has proved beneficial in most HF patients regardless of the LVEF. In addition, there has been compelling evidence, that the LVEF provides poor guidance for device treatment of chronic HF (implantation of cardioverter defibrillator, cardiac resynchronization therapy) since sudden cardiac death may occur and cardiac dyssynchronization may be disastrous in all HF patients. The same holds true for LV assist device implantation, in which the LVEF has been used as a surrogate for LV size. In this review article we update the evidence questioning the use of LVEF-based HF classification and argue that guidance of chronic HF treatment should transition to more contemporary concepts. Specifically, we propose an etiologic chronic HF classification predominantly based on epidemiological data, which will be foundational for further higher resolution phenotyping in the emerging era of precision medicine.

Assessing cardiovascular disease risk in women with a history of hypertensive disorders of pregnancy: A guidance paper for studies using administrative data

BACKGROUND

Hypertensive disorders of pregnancy (HDP) are a major cause of maternal morbidity and mortality, and their association with increased cardiovascular disease (CVD) risk represents a major public health concern. However, assessing CVD risk in women with a history of these conditions presents unique challenges, especially when studies are carried out using routinely collected data.

OBJECTIVES

To summarise and describe key challenges related to the design and conduct of administrative studies assessing CVD risk in women with a history of HDP and provide concrete recommendations for addressing them in future research.

METHODS

This is a methodological guidance paper.

RESULTS

Several conceptual and methodological factors related to the data-generating mechanism and study conceptualisation, design/data management and analysis, as well as the interpretation and reporting of study findings should be considered and addressed when designing and carrying out administrative studies on this topic. Researchers should develop an a priori conceptual framework within which the research question is articulated, important study variables are identified and their interrelationships are carefully considered.

CONCLUSIONS

To advance our understanding of CVD risk in women with a history of HDP, future studies should carefully consider and address the conceptual and methodological considerations outlined in this guidance paper. In highlighting these challenges, and providing specific recommendations for how to address them, our goal is to improve the quality of research carried out on this topic.

Feasibility of artificial intelligence its current status, clinical applications, and future direction in cardiovascular disease

In routine clinical practice, the diagnosis and treatment of cardiovascular disease (CVD) rely on data in a variety of formats. These formats comprise invasive angiography, laboratory data, non-invasive imaging diagnostics, and patient history. Artificial intelligence (AI) is a field of computer science that aims to mimic human thought processes, learning capacity, and knowledge storage. In cardiovascular medicine, artificial intelligence (AI) algorithms have been used to discover novel genotypes and phenotypes in established diseases enhance patient care, enable cost effectiveness, and lower readmission and mortality rates. AI will lead to a paradigm change toward precision cardiovascular medicine in the near future. The promise application of AI in cardiovascular medicine is immense; however, failure to recognize and ignorance of the challenges may overshadow its potential clinical impact. AI can facilitate every stage in cardiology in the imaging process, from acquisition and reconstruction, to segmentation, measurement, interpretation, and subsequent clinical pathways. Along with new possibilities, new threats arise, acknowledging and understanding them is as important as understanding the machine learning (ML) methodology itself. Therefore, attention is also paid to the current opinions and guidelines regarding the validation and safety of AI. This paper provides a outline for clinicians on relevant aspects of AI and machine learning, selection of applications and methods in cardiology to date, and identifies how cardiovascular medicine could incorporate AI in the future. With progress continuing in this emerging technology, the impact for cardiovascular medicine is highlighted to provide insight for the practicing clinician and to identify potential patient benefits.

Discovering biomarkers associated and predicting cardiovascular disease with high accuracy using a novel nexus of machine learning techniques for precision medicine

Personalized interventions are deemed vital given the intricate characteristics, advancement, inherent genetic composition, and diversity of cardiovascular diseases (CVDs). The appropriate utilization of artificial intelligence (AI) and machine learning (ML) methodologies can yield novel understandings of CVDs, enabling improved personalized treatments through predictive analysis and deep phenotyping. In this study, we proposed and employed a novel approach combining traditional statistics and a nexus of cutting-edge AI/ML techniques to identify significant biomarkers for our predictive engine by analyzing the complete transcriptome of CVD patients. After robust gene expression data pre-processing, we utilized three statistical tests (Pearson correlation, Chi-square test, and ANOVA) to assess the differences in transcriptomic expression and clinical characteristics between healthy individuals and CVD patients. Next, the recursive feature elimination classifier assigned rankings to transcriptomic features based on their relation to the case-control variable. The top ten percent of commonly observed significant biomarkers were evaluated using four unique ML classifiers (Random Forest, Support Vector Machine, Xtreme Gradient Boosting Decision Trees, and k-Nearest Neighbors). After optimizing hyperparameters, the ensembled models, which were implemented using a soft voting classifier, accurately differentiated between patients and healthy individuals. We have uncovered 18 transcriptomic biomarkers that are highly significant in the CVD population that were used to predict disease with up to 96% accuracy. Additionally, we cross-validated our results with clinical records collected from patients in our cohort. The identified biomarkers served as potential indicators for early detection of CVDs. With its successful implementation, our newly developed predictive engine provides a valuable framework for identifying patients with CVDs based on their biomarker profiles.

Seasonal variations of the prevalence of metabolic syndrome and its markers using big-data of health check-ups

BACKGROUND

It is crucial to understand the seasonal variation of Metabolic Syndrome (MetS) for the detection and management of MetS. Previous studies have demonstrated the seasonal variations in MetS prevalence and its markers, but their methods are not robust. To clarify the concrete seasonal variations in the MetS prevalence and its markers, we utilized a powerful method called Seasonal Trend Decomposition Procedure based on LOESS (STL) and a big dataset of health checkups.

METHODS

A total of 1,819,214 records of health checkups (759,839 records for men and 1,059,375 records for women) between April 2012 and December 2017 were included in this study. We examined the seasonal variations in the MetS prevalence and its markers using 5 years and 9 months health checkup data and STL analysis. MetS markers consisted of waist circumference (WC), systolic blood pressure (SBP), diastolic blood pressure (DBP), triglycerides (TG), high-density lipoprotein cholesterol (HDL-C), fasting plasma glucose (FPG).

RESULTS

We found that the MetS prevalence was high in winter and somewhat high in August. Among men, MetS prevalence was 2.64 ± 0.42 (mean ± SD) % higher in the highest month (January) than in the lowest month (June). Among women, MetS prevalence was 0.53 ± 0.24% higher in the highest month (January) than in the lowest month (June). Additionally, SBP, DBP, and HDL-C exhibited simple variations, being higher in winter and lower in summer, while WC, TG, and FPG displayed more complex variations.

CONCLUSIONS

This finding, complex seasonal variations of MetS prevalence, WC, TG, and FPG, could not be derived from previous studies using just the mean values in spring, summer, autumn and winter or the cosinor analysis. More attention should be paid to factors affecting seasonal variations of central obesity, dyslipidemia and insulin resistance.

A machine learning based approach to identify carotid subclinical atherosclerosis endotypes

AIMS

To define endotypes of carotid subclinical atherosclerosis.

METHODS AND RESULTS

We integrated demographic, clinical, and molecular data (n = 124) with ultrasonographic carotid measurements from study participants in the IMPROVE cohort (n = 3340). We applied a neural network algorithm and hierarchical clustering to identify carotid atherosclerosis endotypes. A measure of carotid subclinical atherosclerosis, the c-IMTmean-max, was used to extract atherosclerosis-related features and SHapley Additive exPlanations (SHAP) to reveal endotypes. The association of endotypes with carotid ultrasonographic measurements at baseline, after 30 months, and with the 3-year atherosclerotic cardiovascular disease (ASCVD) risk was estimated by linear (β, SE) and Cox [hazard ratio (HR), 95% confidence interval (CI)] regression models. Crude estimates were adjusted by common cardiovascular risk factors, and baseline ultrasonographic measures. Improvement in ASCVD risk prediction was evaluated by C-statistic and by net reclassification improvement with reference to SCORE2, c-IMTmean-max, and presence of carotid plaques. An ensemble stacking model was used to predict endotypes in an independent validation cohort, the PIVUS (n = 1061). We identified four endotypes able to differentiate carotid atherosclerosis risk profiles from mild (endotype 1) to severe (endotype 4). SHAP identified endotype-shared variables (age, biological sex, and systolic blood pressure) and endotype-specific biomarkers. In the IMPROVE, as compared to endotype 1, endotype 4 associated with the thickest c-IMT at baseline (β, SE) 0.36 (0.014), the highest number of plaques 1.65 (0.075), the fastest c-IMT progression 0.06 (0.013), and the highest ASCVD risk (HR, 95% CI) (1.95, 1.18-3.23). Baseline and progression measures of carotid subclinical atherosclerosis and ASCVD risk were associated with the predicted endotypes in the PIVUS. Endotypes consistently improved measures of ASCVD risk discrimination and reclassification in both study populations.

CONCLUSIONS

We report four replicable subclinical carotid atherosclerosis-endotypes associated with progression of atherosclerosis and ASCVD risk in two independent populations. Our approach based on endotypes can be applied for precision medicine in ASCVD prevention.

Comment on: Smart Technologies Used as Smart Tools in the Management of Cardiovascular Disease and Their Future Perspective

With keen interest and seriousness, we have read the article "Smart Technologies used as Smart Tools in the Management of Cardiovascular Disease and their Future Perspective" by Muneeb Ullah et al. and writing to provide a critique. For its clarity and conciseness, we applaud the author for his extensive research on this delicate topic. The authors have concisely written several scenarios of using smart technologies used as smart tools in the management of cardiovascular disease, such as wearable devices, mobile applications,3D printing technologies, artificial intelligence, remote monitoring systems, and electronic health records. Nonetheless, While the study addresses an important topic in the field of cardiology, we believe there are certain aspects that require further consideration and exploration.

Functional mutation, splice, distribution, and divergence analysis of impactful genes associated with heart failure and other cardiovascular diseases

Cardiovascular disease (CVD) is caused by a multitude of complex and largely heritable conditions. Identifying key genes and understanding their susceptibility to CVD in the human genome can assist in early diagnosis and personalized treatment of the relevant patients. Heart failure (HF) is among those CVD phenotypes that has a high rate of mortality. In this study, we investigated genes primarily associated with HF and other CVDs. Achieving the goals of this study, we built a cohort of thirty-five consented patients, and sequenced their serum-based samples. We have generated and processed whole genome sequence (WGS) data, and performed functional mutation, splice, variant distribution, and divergence analysis to understand the relationships between each mutation type and its impact. Our variant and prevalence analysis found FLNA, CST3, LGALS3, and HBA1 linked to many enrichment pathways. Functional mutation analysis uncovered ACE, MME, LGALS3, NR3C2, PIK3C2A, CALD1, TEK, and TRPV1 to be notable and potentially significant genes. We discovered intron, 5' Flank, 3' UTR, and 3' Flank mutations to be the most common among HF and other CVD genes. Missense mutations were less common among HF and other CVD genes but had more of a functional impact. We reported HBA1, FADD, NPPC, ADRB2, ADBR1, MYH6, and PLN to be consequential based on our divergence analysis.

Multiomics Network Medicine Approaches to Precision Medicine and Therapeutics in Cardiovascular Diseases

Cardiovascular diseases (CVD) are the leading cause of death worldwide and display complex phenotypic heterogeneity caused by many convergent processes, including interactions between genetic variation and environmental factors. Despite the identification of a large number of associated genes and genetic loci, the precise mechanisms by which these genes systematically influence the phenotypic heterogeneity of CVD are not well understood. In addition to DNA sequence, understanding the molecular mechanisms of CVD requires data from other omics levels, including the epigenome, the transcriptome, the proteome, as well as the metabolome. Recent advances in multiomics technologies have opened new precision medicine opportunities beyond genomics that can guide precise diagnosis and personalized treatment. At the same time, network medicine has emerged as an interdisciplinary field that integrates systems biology and network science to focus on the interactions among biological components in health and disease, providing an unbiased framework through which to integrate systematically these multiomics data. In this review, we briefly present such multiomics technologies, including bulk omics and single-cell omics technologies, and discuss how they can contribute to precision medicine. We then highlight network medicine-based integration of multiomics data for precision medicine and therapeutics in CVD. We also include a discussion of current challenges, potential limitations, and future directions in the study of CVD using multiomics network medicine approaches.

Lacking mechanistic disease definitions and corresponding association data hamper progress in network medicine and beyond

A long-term objective of network medicine is to replace our current, mainly phenotype-based disease definitions by subtypes of health conditions corresponding to distinct pathomechanisms. For this, molecular and health data are modeled as networks and are mined for pathomechanisms. However, many such studies rely on large-scale disease association data where diseases are annotated using the very phenotype-based disease definitions the network medicine field aims to overcome. This raises the question to which extent the biases mechanistically inadequate disease annotations introduce in disease association data distort the results of studies which use such data for pathomechanism mining. We address this question using global- and local-scale analyses of networks constructed from disease association data of various types. Our results indicate that large-scale disease association data should be used with care for pathomechanism mining and that analyses of such data should be accompanied by close-up analyses of molecular data for well-characterized patient cohorts.

Proline and glucose metabolic reprogramming supports vascular endothelial and medial biomass in pulmonary arterial hypertension

In pulmonary arterial hypertension (PAH), inflammation promotes a fibroproliferative pulmonary vasculopathy. Reductionist studies emphasizing single biochemical reactions suggest a shift toward glycolytic metabolism in PAH; however, key questions remain regarding the metabolic profile of specific cell types within PAH vascular lesions in vivo. We used RNA-Seq to profile the transcriptome of pulmonary artery endothelial cells (PAECs) freshly isolated from an inflammatory vascular injury model of PAH ex vivo, and these data were integrated with information from human gene ontology pathways. Network medicine was then used to map all aa and glucose pathways to the consolidated human interactome, which includes data on 233,957 physical protein-protein interactions. Glucose and proline pathways were significantly close to the human PAH disease module, suggesting that these pathways are functionally relevant to PAH pathobiology. To test this observation in vivo, we used multi-isotope imaging mass spectrometry to map and quantify utilization of glucose and proline in the PAH pulmonary vasculature at subcellular resolution. Our findings suggest that elevated glucose and proline avidity underlie increased biomass in PAECs and the media of fibrosed PAH pulmonary arterioles. Overall, these data show that anabolic utilization of glucose and proline are fundamental to the vascular pathology of PAH.

Targeting mitochondrial impairment for the treatment of cardiovascular diseases: From hypertension to ischemia-reperfusion injury, searching for new pharmacological targets

Mitochondria and mitochondrial proteins represent a group of promising pharmacological target candidates in the search of new molecular targets and drugs to counteract the onset of hypertension and more in general cardiovascular diseases (CVDs). Indeed, several mitochondrial pathways result impaired in CVDs, showing ATP depletion and ROS production as common traits of cardiac tissue degeneration. Thus, targeting mitochondrial dysfunction in cardiomyocytes can represent a successful strategy to prevent heart failure. In this context, the identification of new pharmacological targets among mitochondrial proteins paves the way for the design of new selective drugs. Thanks to the advances in omics approaches, to a greater availability of mitochondrial crystallized protein structures and to the development of new computational approaches for protein 3D-modelling and drug design, it is now possible to investigate in detail impaired mitochondrial pathways in CVDs. Furthermore, it is possible to design new powerful drugs able to hit the selected pharmacological targets in a highly selective way to rescue mitochondrial dysfunction and prevent cardiac tissue degeneration. The role of mitochondrial dysfunction in the onset of CVDs appears increasingly evident, as reflected by the impairment of proteins involved in lipid peroxidation, mitochondrial dynamics, respiratory chain complexes, and membrane polarization maintenance in CVD patients. Conversely, little is known about proteins responsible for the cross-talk between mitochondria and cytoplasm in cardiomyocytes. Mitochondrial transporters of the SLC25A family, in particular, are responsible for the translocation of nucleotides (e.g., ATP), amino acids (e.g., aspartate, glutamate, ornithine), organic acids (e.g. malate and 2-oxoglutarate), and other cofactors (e.g., inorganic phosphate, NAD⁺, FAD, carnitine, CoA derivatives) between the mitochondrial and cytosolic compartments. Thus, mitochondrial transporters play a key role in the mitochondria-cytosol cross-talk by leading metabolic pathways such as the malate/aspartate shuttle, the carnitine shuttle, the ATP export from mitochondria, and the regulation of permeability transition pore opening. Since all these pathways are crucial for maintaining healthy cardiomyocytes, mitochondrial carriers emerge as an interesting class of new possible pharmacological targets for CVD treatments.

Tensions in Taxonomies: Current Understanding and Future Directions in the Pathobiologic Basis and Treatment of Group 1 and Group 3 Pulmonary Hypertension

In the over 100 years since the recognition of pulmonary hypertension (PH), immense progress and significant achievements have been made with regard to understanding the pathophysiology of the disease and its treatment. These advances have been mostly in idiopathic pulmonary arterial hypertension (IPAH), which was classified as Group 1 Pulmonary Hypertension (PH) at the Second World Symposia on PH in 1998. However, the pathobiology of PH due to chronic lung disease, classified as Group 3 PH, remains poorly understood and its treatments thus remain limited. We review the history of the classification of the five groups of PH and aim to provide a state-of-the-art review of the understanding of the pathogenesis of Group 1 PH and Group 3 PH including insights gained from novel high-throughput omics technologies that have revealed heterogeneities within these categories as well as similarities between them. Leveraging the substantial gains made in understanding the genomics, epigenomics, proteomics, and metabolomics of PAH to understand the full spectrum of the complex, heterogeneous disease of PH is needed. Multimodal omics data as well as supervised and unbiased machine learning approaches after careful consideration of the powerful advantages as well as of the limitations and pitfalls of these technologies could lead to earlier diagnosis, more precise risk stratification, better predictions of disease response, new sub-phenotype groupings within types of PH, and identification of shared pathways between PAH and other types of PH that could lead to new treatment targets. © 2023 American Physiological Society. Compr Physiol 13:4295-4319, 2023.

Uncovering common pathobiological processes between COVID-19 and pulmonary arterial hypertension by integrating Omics data

Coronavirus disease 2019 (COVID-19) is an infectious disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), which led to the current pandemic. Many factors, including age and comorbidities, influence the severity and mortality of COVID-19. SARS-CoV-2 infection can cause pulmonary vascular dysfunction. The COVID-19 case-fatality rate in patients with pulmonary arterial hypertension (PAH) is higher in comparison with the general population. In this study, we aimed to identify pathobiological processes common to COVID-19 and PAH by utilizing the human protein-protein interactome and whole-genome transcription data from peripheral blood mononuclear cells (PBMCs) and from lung tissue. We found that there are significantly more interactions between SARS-CoV-2 targets and PAH disease proteins than expected by chance, suggesting that the PAH disease module is in the neighborhood of SARS-CoV-2 targets in the human interactome. In addition, SARS-CoV-2 infection-induced changes in gene expression significantly overlap with PAH-induced gene expression changes in both tissues, indicating SARS-CoV-2 and PAH may share common transcriptional regulators. We identified many upregulated genes and downregulated genes common to COVID-19 and PAH. Interestingly, we observed different co-regulation patterns and dysfunctional signaling pathways in PBMCs versus lung tissue. Endophenotype enrichment analysis revealed that genes regulating fibrosis, inflammation, hypoxia, oxidative stress, immune response, and thromboembolism are significantly enriched in the COVID-19-PAH co-expression modules. We examined the network proximity of the targets of repositioned drugs for COVID-19 to the co-expression modules in PBMCs and lung tissue, and identified 42 drugs that can be potentially used for COVID-19 patients with PAH as a comorbidity. The uncovered common pathobiological pathways are crucial for discovering therapeutic targets and designing tailored treatments for COVID-19 patients who also have PAH.

Subtyping based on immune cell fractions reveal heterogeneity of cardiac fibrosis in end-stage heart failure

Background

A central issue hindering the development of effective anti-fibrosis drugs for heart failure is the unclear interrelationship between fibrosis and the immune cells. This study aims at providing precise subtyping of heart failure based on immune cell fractions, elaborating their differences in fibrotic mechanisms, and proposing a biomarker panel for evaluating intrinsic features of patients' physiological statuses through subtype classification, thereby promoting the precision medicine for cardiac fibrosis.

Methods

We inferred immune cell type abundance of the ventricular samples by a computational method (CIBERSORTx) based on ventricular tissue samples from 103 patients with heart failure, and applied K-means clustering to divide patients into two subtypes based on their immune cell type abundance. We also designed a novel analytic strategy: Large-Scale Functional Score and Association Analysis (LAFSAA), to study fibrotic mechanisms in the two subtypes.

Results

Two subtypes of immune cell fractions: pro-inflammatory and pro-remodeling subtypes, were identified. LAFSAA identified 11 subtype-specific pro-fibrotic functional gene sets as the basis for personalised targeted treatments. Based on feature selection, a 30-gene biomarker panel (ImmunCard30) established for diagnosing patient subtypes achieved high classification performance, with the area under the receiver operator characteristic curve corresponding to 0.954 and 0.803 for the discovery and validation sets, respectively.

Conclusion

Patients with the two subtypes of cardiac immune cell fractions were likely having different fibrotic mechanisms. Patients' subtypes can be predicted based on the ImmunCard30 biomarker panel. We envision that our unique stratification strategy revealed in this study will unravel advance diagnostic techniques for personalised anti-fibrotic therapy.

Artificial Intelligence and Precision Medicine: A New Frontier for the Treatment of Brain Tumors

Brain tumors are a widespread and serious neurological phenomenon that can be life- threatening. The computing field has allowed for the development of artificial intelligence (AI), which can mimic the neural network of the human brain. One use of this technology has been to help researchers capture hidden, high-dimensional images of brain tumors. These images can provide new insights into the nature of brain tumors and help to improve treatment options. AI and precision medicine (PM) are converging to revolutionize healthcare. AI has the potential to improve cancer imaging interpretation in several ways, including more accurate tumor genotyping, more precise delineation of tumor volume, and better prediction of clinical outcomes. AI-assisted brain surgery can be an effective and safe option for treating brain tumors. This review discusses various AI and PM techniques that can be used in brain tumor treatment. These new techniques for the treatment of brain tumors, i.e., genomic profiling, microRNA panels, quantitative imaging, and radiomics, hold great promise for the future. However, there are challenges that must be overcome for these technologies to reach their full potential and improve healthcare.

Personalized prediction of incident hospitalization for cardiovascular disease in patients with hypertension using machine learning

BACKGROUND

Prognostic information for patients with hypertension is largely based on population averages. The purpose of this study was to compare the performance of four machine learning approaches for personalized prediction of incident hospitalization for cardiovascular disease among newly diagnosed hypertensive patients.

METHODS

Using province-wide linked administrative health data in Alberta, we analyzed a cohort of 259,873 newly-diagnosed hypertensive patients from 2009 to 2015 who collectively had 11,863 incident hospitalizations for heart failure, myocardial infarction, and stroke. Linear multi-task logistic regression, neural multi-task logistic regression, random survival forest and Cox proportional hazard models were used to determine the number of event-free survivors at each time-point and to construct individual event-free survival probability curves. The predictive performance was evaluated by root mean squared error, mean absolute error, concordance index, and the Brier score.

RESULTS

The random survival forest model has the lowest root mean squared error value at 33.94 and lowest mean absolute error value at 28.37. Machine learning methods provide similar discrimination and calibration in the personalized survival prediction of hospitalizations for cardiovascular events in patients with hypertension. Neural multi-task logistic regression model has the highest concordance index at 0.8149 and lowest Brier score at 0.0242 for the personalized survival prediction.

CONCLUSIONS

This is the first personalized survival prediction for cardiovascular diseases among hypertensive patients using administrative data. The four models tested in this analysis exhibited a similar discrimination and calibration ability in predicting personalized survival prediction of hypertension patients.

Development and evaluation of a radiomics model of resting 13N-ammonia positron emission tomography myocardial perfusion imaging to predict coronary artery stenosis in patients with suspected coronary heart disease

BACKGROUND

Coronary angiography (CAG) is usually performed in patients with coronary heart disease (CHD) to evaluate the coronary artery stenosis. However, patients with iodine allergy and renal dysfunction are not suitable for CAG. We try to develop a radiomics machine learning model based on rest 13N-ammonia (13N-NH3) positron emission tomography (PET) myocardial perfusion imaging (MPI) to predict coronary stenosis.

METHODS

Eighty-four patients were included with the inclusion criteria: adult patients; suspected CHD; resting MPI and CAG were performed; and complete data. Coronary artery stenosis >75% were considered to be significant stenosis. Patients were randomly divided into a training group and a testing group with a ratio of 1:1. Myocardial blood flow (MBF), perfusion defect extent (EXT), total perfusion deficit (TPD), and summed rest score (SRS) were obtained. Myocardial static images of the left ventricular (LV) coronary segments were segmented, and radiomics features were extracted. In the training set, the conventional parameter (MPI model) and radiomics (Rad model) models were constructed using the machine learning method and were combined to construct a nomogram. The models' performance was evaluated by area under the curve (AUC), accuracy, sensitivity, specificity, decision analysis curve (DCA), and calibration curves. Testing and subgroup analysis were performed.

RESULTS

MPI model was composed of MBF and EXT, and Rad model was composed of 12 radiomics features. In the training set, the AUC/accuracy/sensitivity/specificity of the MPI model, Rad model, and the nomogram were 0.795/0.778/0.937/0.511, 0.912/0.825/0.760/0.936 and 0.911/0.865/0.924/0.766 respectively. In the testing set, the AUC/accuracy/sensitivity/specificity of the MPI model, Rad model, and the nomogram were 0.798/0.722/0.659/0.841, 0.887/0.810/0.744/0.932 and 0.900/0.849/0.854/0.841 respectively. The AUC of Rad model and nomogram were significantly higher than that of MPI model. The DCA curve also showed that the clinical net benefit of the Rad model and nomogram was similar but greater than that of MPI model. The calibration curve showed good agreement between the observed and predicted values of the Rad model. In the subgroup analysis of Rad model, there was no significant difference in AUC between subgroups.

CONCLUSIONS

The Rad model is more accurate than the MPI model in predicting coronary stenosis. This noninvasive technique could help improve risk stratification and had good generalization ability.

Improving the prognostic value of multimorbidity through the integration of selected biomarkers to the comprehensive geriatric assessment: An observational retrospective monocentric study

Background

Multimorbidity (MM) burdens individuals and healthcare systems, since it increases polypharmacy, dependency, hospital admissions, healthcare costs, and mortality. Several attempts have been made to determine an operational definition of MM and to quantify its severity. However, the lack of knowledge regarding its pathophysiology prevented the estimation of its severity in terms of outcomes. Polypharmacy and functional impairment are associated with MM. However, it is unclear how inappropriate drug decision-making could affect both conditions. In this context, promising circulating biomarkers and DNA methylation tools have been proposed as potential mortality predictors for multiple age-related diseases. We hypothesize that a comprehensive characterization of patients with MM that includes the measure of epigenetic and selected circulating biomarkers in the medical history, in addition to the functional capacity, could improve the prognosis of their long-term mortality.

Methods

This monocentric retrospective observational study was conducted as part of a project funded by the Italian Ministry of Health titled “imProving the pROgnostic value of MultimOrbidity through the inTegration of selected biomarkErs to the comprehensive geRiatric Assessment (PROMOTERA).” This study will examine the methylation levels of thousands of CpG sites and the levels of selected circulating biomarkers in the blood and plasma samples of older hospitalized patients with MM (n = 1,070, age ≥ 65 years) recruited by the Reportage Project between 2011 and 2019. Multiple statistical approaches will be utilized to integrate newly measured biomarkers into clinical, demographic, and functional data, thus improving the prediction of mortality for up to 10 years.

Discussion

This study's results are expected to: (i) identify the clinical, biological, demographic, and functional factors associated with distinct patterns of MM; (ii) improve the prognostic accuracy of MM patterns in relation to death, hospitalization-related outcomes, and onset of new comorbidities; (iii) define the epigenetic signatures of MM; (iv) construct multidimensional algorithms to predict negative health outcomes in both the overall population and specific disease and functional patterns; and (v) expand our understanding of the mechanisms underlying the pathophysiology of MM.

Integrated proteomic and metabolomic profile analyses of cardiac valves revealed molecular mechanisms and targets in calcific aortic valve disease

Background

This study aimed to define changes in the metabolic and protein profiles of patients with calcific aortic valve disease (CAVD).

Methods and results

We analyzed cardiac valve samples of patients with and without (control) CAVD (n = 24 per group) using untargeted metabolomics and tandem mass tag-based quantitative proteomics. Significantly different metabolites and proteins between the CAVD and control groups were screened; then, functional enrichment was analyzed. We analyzed co-expressed differential metabolites and proteins, and constructed a metabolite-protein-pathway network. The expression of key proteins was validated using western blotting. Differential analysis identified 229 metabolites in CAVD among which, 2-aminophenol, hydroxykynurenine, erythritol, carnosine, and choline were the top five. Proteomic analysis identified 549 differentially expressed proteins in CAVD, most of which were localized in the nuclear, cytoplasmic, extracellular, and plasma membranes. Levels of selenium binding protein 1 (SELENBP1) positively correlated with multiple metabolites. Adenosine triphosphate-binding cassette transporters, starch and sucrose metabolism, hypoxia-inducible factor 1 (HIF-1) signaling, and purine metabolism were key pathways in the network. Ectonucleotide pyrophosphatase/phosphodiesterase 1 (ENPP1), calcium²⁺/calmodulin-dependent protein kinase II delta (CAMK2D), and ATP binding cassette subfamily a member 8 (ABCA8) were identified as hub proteins in the metabolite-protein-pathway network as they interacted with ADP, glucose 6-phosphate, choline, and other proteins. Western blotting confirmed that ENPP1 was upregulated, whereas ABCA8 and CAMK2D were downregulated in CAVD samples.

Conclusion

The metabolic and protein profiles of cardiac valves from patients with CAVD significantly changed. The present findings provide a holistic view of the molecular mechanisms underlying CAVD that may lead to the development of novel diagnostic biomarkers and therapeutic targets to treat CAVD.

Meeting the Challenges of Myocarditis: New Opportunities for Prevention, Detection, and Intervention—A Report from the 2021 National Heart, Lung, and Blood Institute Workshop

The National Heart, Lung, and Blood Institute (NHLBI) convened a workshop of international experts to discuss new research opportunities for the prevention, detection, and intervention of myocarditis in May 2021. These experts reviewed the current state of science and identified key gaps and opportunities in basic, diagnostic, translational, and therapeutic frontiers to guide future research in myocarditis. In addition to addressing community-acquired myocarditis, the workshop also focused on emerging causes of myocarditis including immune checkpoint inhibitors and SARS-CoV-2 related myocardial injuries and considered the use of systems biology and artificial intelligence methodologies to define workflows to identify novel mechanisms of disease and new therapeutic targets. A new priority is the investigation of the relationship between social determinants of health (SDoH), including race and economic status, and inflammatory response and outcomes in myocarditis. The result is a proposal for the reclassification of myocarditis that integrates the latest knowledge of immunological pathogenesis to refine estimates of prognosis and target pathway-specific treatments.

What Causes Hypertrophic Cardiomyopathy?

Hypertrophic cardiomyopathy (HCM) is a global and relatively common cause of patient morbidity and mortality and is among the first reported monogenic cardiac diseases. For 30 years, the basic etiology of HCM has been attributed largely to variants in individual genes encoding cardiac sarcomere proteins, with the implication that HCM is fundamentally a genetic disease. However, data from clinical and network medicine analyses, as well as contemporary genetic studies show that single gene variants do not fully explain the broad and diverse HCM clinical spectrum. These transformative advances place a new focus on possible novel interactions between acquired disease determinants and genetic context to produce complex HCM phenotypes, also offering a measure of caution against overemphasizing monogenics as the principal cause of this disease. These new perspectives in which HCM is not a uniformly genetic disease but likely explained by multifactorial etiology will also unavoidably impact how HCM is viewed by patients and families in the clinical practicing community going forward, including relevance to genetic counseling and access to healthcare insurance and psychosocial wellness.

Clinical Characteristics and Transplant-Free Survival Across the Spectrum of Pulmonary Vascular Disease

BACKGROUND

PVDOMICS (Pulmonary Vascular Disease Phenomics) is a precision medicine initiative to characterize pulmonary vascular disease (PVD) using deep phenotyping. PVDOMICS tests the hypothesis that integration of clinical metrics with omic measures will enhance understanding of PVD and facilitate an updated PVD classification.

OBJECTIVES

The purpose of this study was to describe clinical characteristics and transplant-free survival in the PVDOMICS cohort.

METHODS

Subjects with World Symposium Pulmonary Hypertension (WSPH) group 1-5 PH, disease comparators with similar underlying diseases and mild or no PH and healthy control subjects enrolled in a cross-sectional study. PH groups, comparators were compared using standard statistical tests including log-rank tests for comparing time to transplant or death.

RESULTS

A total of 1,193 subjects were included. Multiple WSPH groups were identified in 38.9% of PH subjects. Nocturnal desaturation was more frequently observed in groups 1, 3, and 4 PH vs comparators. A total of 50.2% of group 1 PH subjects had ground glass opacities on chest computed tomography. Diffusing capacity for carbon monoxide was significantly lower in groups 1-3 PH than their respective comparators. Right atrial volume index was higher in WSPH groups 1-4 than comparators. A total of 110 participants had a mean pulmonary artery pressure of 21-24 mm Hg. Transplant-free survival was poorest in group 3 PH.

CONCLUSIONS

PVDOMICS enrolled subjects across the spectrum of PVD, including mild and mixed etiology PH. Novel findings include low diffusing capacity for carbon monoxide and enlarged right atrial volume index as shared features of groups 1-3 and 1-4 PH, respectively; unexpected, frequent presence of ground glass opacities on computed tomography; and sleep alterations in group 1 PH, and poorest survival in group 3 PH. PVDOMICS will facilitate a new understanding of PVD and refine the current PVD classification. (Pulmonary Vascular Disease Phenomics Program PVDOMICS [PVDOMICS]; NCT02980887).

Connections for Matters of the Heart: Network Medicine in Cardiovascular Diseases

Cardiovascular diseases (CVD) are diverse disorders affecting the heart and vasculature in millions of people worldwide. Like other fields, CVD research has benefitted from the deluge of multiomics biomedical data. Current CVD research focuses on disease etiologies and mechanisms, identifying disease biomarkers, developing appropriate therapies and drugs, and stratifying patients into correct disease endotypes. Systems biology offers an alternative to traditional reductionist approaches and provides impetus for a comprehensive outlook toward diseases. As a focus area, network medicine specifically aids the translational aspect of in silico research. This review discusses the approach of network medicine and its application to CVD research.

Harnessing Big Data to Advance Treatment and Understanding of Pulmonary Hypertension

Pulmonary hypertension is a complex disease with multiple causes, corresponding to phenotypic heterogeneity and variable therapeutic responses. Advancing understanding of pulmonary hypertension pathogenesis is likely to hinge on integrated methods that leverage data from health records, imaging, novel molecular -omics profiling, and other modalities. In this review, we summarize key data sets generated thus far in the field and describe analytical methods that hold promise for deciphering the molecular mechanisms that underpin pulmonary vascular remodeling, including machine learning, network medicine, and functional genetics. We also detail how genetic and subphenotyping approaches enable earlier diagnosis, refined prognostication, and optimized treatment prediction. We propose strategies that identify functionally important molecular pathways, bolstered by findings across multi-omics platforms, which are well-positioned to individualize drug therapy selection and advance precision medicine in this highly morbid disease.

The Future of Precision Medicine to Predict Outcomes and Control Tissue Remodeling in Inflammatory Bowel Disease

Inflammatory bowel disease is characterized by significant interindividual heterogeneity. With a wider selection of pharmacologic and nonpharmacologic interventions available and in advanced developmental stages, a priority for the coming decade is to determine accurate methods of predicting treatment response and disease course. Precision medicine strategies will allow tailoring of preventative and therapeutic decisions to individual patient needs. In this review, we consider the future of precision medicine in inflammatory bowel disease. We discuss the critical need to extend from research focused on short-term symptomatic response to integrative multi-omic systems biology strategies to identify and validate biomarkers that underpin precision approaches. Crucially, the international community has collective responsibility to provide well-phenotyped and -curated longitudinal datasets for scientific discovery and validation. Research must also study broader aspects of the immune response, including components of the extracellular matrix, to better understand biological pathways initiating and perpetuating tissue fibrosis and longer-term disease complications.

A Collaborative Approach for the Development and Application of Machine Learning Solutions for CMR-Based Cardiac Disease Classification

The quality and acceptance of machine learning (ML) approaches in cardiovascular data interpretation depends strongly on model design and training and the interaction with the clinical experts. We hypothesize that a software infrastructure for the training and application of ML models can support the improvement of the model training and provide relevant information for understanding the classification-relevant data features. The presented solution supports an iterative training, evaluation, and exploration of machine-learning-based multimodal data interpretation methods considering cardiac MRI data. Correction, annotation, and exploration of clinical data and interpretation of results are supported through dedicated interactive visual analytics tools. We test the presented concept with two use cases from the ACDC and EMIDEC cardiac MRI image analysis challenges. In both applications, pre-trained 2D U-Nets are used for segmentation, and classifiers are trained for diagnostic tasks using radiomics features of the segmented anatomical structures. The solution was successfully used to identify outliers in automatic segmentation and image acquisition. The targeted curation and addition of expert annotations improved the performance of the machine learning models. Clinical experts were supported in understanding specific anatomical and functional characteristics of the assigned disease classes.

Artificial Intelligence in Cardiovascular Medicine: Historical Overview, Current Status, and Future Directions

Artificial intelligence and machine learning are rapidly gaining popularity in every aspect of our daily lives, and cardiovascular medicine is no exception. Here, we provide physicians with an overview of the past, present, and future of artificial intelligence applications in cardiovascular medicine. We describe essential and powerful examples of machine-learning applications in industry and elsewhere. Finally, we discuss the latest technologic advances, as well as the benefits and limitations of artificial intelligence and machine learning in cardiovascular medicine.

Personalizing treatments for patients based on cardiovascular phenotyping

Introduction

Cardiovascular disease persists as the leading cause of death worldwide despite continued advances in diagnostics and therapeutics. Our current approach to patients with cardiovascular disease is rooted in reductionism, which presupposes that all patients share a similar phenotype and will respond the same to therapy; however, this is unlikely as cardiovascular diseases exhibit complex heterogeneous phenotypes.

Areas covered

With the advent of high-throughput platforms for omics testing, phenotyping cardiovascular diseases has advanced to incorporate large-scale molecular data with classical history, physical examination, and laboratory results. Findings from genomics, proteomics, and metabolomics profiling have been used to define more precise cardiovascular phenotypes and predict adverse outcomes in population-based and disease-specific patient cohorts. These molecular data have also been utilized to inform drug efficacy based on a patient's unique phenotype.

Expert opinion

Multiscale phenotyping of cardiovascular disease has revealed diversity among patients that can be used to personalize pharmacotherapies and predict outcomes. Nonetheless, precision phenotyping for cardiovascular disease remains a nascent field that has not yet translated into widespread clinical practice despite its many potential advantages for patient care. Future endeavors that demonstrate improved pharmacotherapeutic responses and associated reduction in adverse events will facilitate mainstream adoption of precision cardiovascular phenotyping.

Artificial Intelligence-Based Echocardiographic Left Atrial Volume Measurement with Pulmonary Vein Comparison

This paper combines echocardiographic signal processing and artificial intelligence technology to propose a deep neural network model adapted to echocardiographic signals to achieve left atrial volume measurement and automatic assessment of pulmonary veins efficiently and quickly. Based on the echocardiographic signal generation mechanism and detection method, an experimental scheme for the echocardiographic signal acquisition was designed. The echocardiographic signal data of healthy subjects were measured in four different experimental states, and a database of left atrial volume measurements and pulmonary veins was constructed. Combining the correspondence between ECG signals and echocardiographic signals in the time domain, a series of preprocessing such as denoising, feature point localization, and segmentation of the cardiac cycle was realized by wavelet transform and threshold method to complete the data collection. This paper proposes a comparative model based on artificial intelligence, adapts to the characteristics of one-dimensional time-series echocardiographic signals, automatically extracts the deep features of echocardiographic signals, effectively reduces the subjective influence of manual feature selection, and realizes the automatic classification and evaluation of human left atrial volume measurement and pulmonary veins under different states. The experimental results show that the proposed BP neural network model has good adaptability and classification performance in the tasks of LV volume measurement and pulmonary vein automatic classification evaluation and achieves an average test accuracy of over 96.58%. The average root-mean-square error percentage of signal compression is only 0.65% by extracting the coding features of the original echocardiographic signal through the convolutional autoencoder, which completes the signal compression with low loss. Comparing the training time and classification accuracy of the LSTM network with the original signal and encoded features, the experimental results show that the AI model can greatly reduce the model training time cost and achieve an average accuracy of 97.97% in the test set and increase the real-time performance of the left atrial volume measurement and pulmonary vein evaluation as well as the security of the data transmission process, which is very important for the comparison of left atrial volume measurement and pulmonary vein. It is of great practical importance to compare left atrial volume measurements with pulmonary veins.

Preliminary Analysis of the Risk Factor Identification Embedding Model for Cardiovascular Disease

Cardiovascular Disease (CVD) is responsible for a large part of healthcare costs every year, but susceptibility to it is affected by complex biological and physiological variables including patients' genetics and lifestyles. There has not been much work to develop a framework that incorporates these important and clinically relevant risk factors into a comprehensive model for CVD research. Moreover, the data labeling required to do so, such as annotating gene functions, is an extremely challenging, tedious, and time-consuming process. In this work, our goal was to develop and validate a risk factor embedding model, which incorporates genotype, phenotype without pre-labeled information to identify various risk factors of CVD. We hypothesize that (1) the knowledge background that does not require data labeling could be gathered from published abstract data, (2) the phenotype, genotype risk factors could be represented in an embedding vector space. We collected 1,363,682 published abstracts from PubMed using the keyword "heart" and 19,264 human gene names, then trained our model using the collected abstracts. We evaluated our CVD risk factor identification model using both intrinsic and extrinsic evaluations: for the intrinsic evaluation, we examined whether or not the captured top-10 words and genes have references related to the input query "myocardial infarction", as one of CVDs, and our model correctly identified them. For the extrinsic evaluation, we used our model to the dimensionality reduction task for classifications, and our method outperformed other popular methods. These results show the feasibility of our approach for disease-associated risk factors of CVD which incorporates genotype, phenotype.Clinical Relevance-Our model provides a comprehensive tool to incorporate various risk factors without any a priori data labeling knowledge for CVD. Our approach shows a potential to provide discovered knowledge that contributes to better understanding and treatment of CVD.

Personalized Medicine for Pulmonary Hypertension:: The Future Management of Pulmonary Hypertension Requires a New Taxonomy

Pulmonary hypertension is a convergent phenotype that presents late in the natural history of the condition. The current clinical classification of patients lacks granularity, and this impacts on the development and deployment of treatment. Deep molecular phenotyping using platform 'omic' technologies is beginning to reveal the genetic and molecular architecture that underlies the phenotype, promising better targeting of patients with new treatments. The future treatment of pulmonary hypertension depends on the integration of clinical and molecular information to create a new taxonomy that defines patient groups coupled to druggable targets.

Multiple-ancestry genome-wide association study identifies 27 loci associated with measures of hemolysis following blood storage

BackgroundThe evolutionary pressure of endemic malaria and other erythrocytic pathogens has shaped variation in genes encoding erythrocyte structural and functional proteins, influencing responses to hemolytic stress during transfusion and disease.MethodsWe sought to identify such genetic variants in blood donors by conducting a genome-wide association study (GWAS) of 12,353 volunteer donors, including 1,406 African Americans, 1,306 Asians, and 945 Hispanics, whose stored erythrocytes were characterized by quantitative assays of in vitro osmotic, oxidative, and cold-storage hemolysis.ResultsGWAS revealed 27 significant loci (P < 5 × 10-8), many in candidate genes known to modulate erythrocyte structure, metabolism, and ion channels, including SPTA1, ALDH2, ANK1, HK1, MAPKAPK5, AQP1, PIEZO1, and SLC4A1/band 3. GWAS of oxidative hemolysis identified variants in genes encoding antioxidant enzymes, including GLRX, GPX4, G6PD, and SEC14L4 (Golgi-transport protein). Genome-wide significant loci were also tested for association with the severity of steady-state (baseline) in vivo hemolytic anemia in patients with sickle cell disease, with confirmation of identified SNPs in HBA2, G6PD, PIEZO1, AQP1, and SEC14L4.ConclusionsMany of the identified variants, such as those in G6PD, have previously been shown to impair erythrocyte recovery after transfusion, associate with anemia, or cause rare Mendelian human hemolytic diseases. Candidate SNPs in these genes, especially in polygenic combinations, may affect RBC recovery after transfusion and modulate disease severity in hemolytic diseases, such as sickle cell disease and malaria.

Epigenetics and pulmonary diseases in the horizon of precision medicine: a review

Epigenetic mechanisms represent potential molecular routes which could bridge the gap between genetic background and environmental risk factors contributing to the pathogenesis of pulmonary diseases. In patients with COPD, asthma and pulmonary arterial hypertension (PAH), there is emerging evidence of aberrant epigenetic marks, mainly including DNA methylation and histone modifications which directly mediate reversible modifications to the DNA without affecting the genomic sequence. Post-translational events and microRNAs can be also regulated epigenetically and potentially participate in disease pathogenesis. Thus, novel pathogenic mechanisms and putative biomarkers may be detectable in peripheral blood, sputum, nasal and buccal swabs or lung tissue. Besides, DNA methylation plays an important role during the early phases of fetal development and may be impacted by environmental exposures, ultimately influencing an individual's susceptibility to COPD, asthma and PAH later in life. With the advances in omics platforms and the application of computational biology tools, modelling the epigenetic variability in a network framework, rather than as single molecular defects, provides insights into the possible molecular pathways underlying the pathogenesis of COPD, asthma and PAH. Epigenetic modifications may have clinical applications as noninvasive biomarkers of pulmonary diseases. Moreover, combining molecular assays with network analysis of epigenomic data may aid in clarifying the multistage transition from a "pre-disease" to "disease" state, with the goal of improving primary prevention of lung diseases and its subsequent clinical management.We describe epigenetic mechanisms known to be associated with pulmonary diseases and discuss how network analysis could improve our understanding of lung diseases.

Big data and predictive analytics in healthcare in Bangladesh: regulatory challenges

Big data analytics and artificial intelligence are revolutionizing the global healthcare industry. As the world accumulates unfathomable volumes of data and health technology grows more and more critical to the advancement of medicine, policymakers and regulators are faced with tough challenges around data security and data privacy. This paper reviews existing regulatory frameworks for artificial intelligence-based medical devices and health data privacy in Bangladesh. The study is legal research employing a comparative approach where data is collected from primary and secondary legal materials and filtered based on policies relating to medical data privacy and medical device regulation of Bangladesh. Such policies are then compared with benchmark policies of the European Union and the USA to test the adequacy of the present regulatory framework of Bangladesh and identify the gaps in the current regulation. The study highlights the gaps in policy and regulation in Bangladesh that are hampering the widespread adoption of big data analytics and artificial intelligence in the industry. Despite the vast benefits that big data would bring to Bangladesh's healthcare industry, it lacks the proper data governance and legal framework necessary to gain consumer trust and move forward. Policymakers and regulators must work collaboratively with clinicians, patients and industry to adopt a new regulatory framework that harnesses the potential of big data but ensures adequate privacy and security of personal data. The article opens valuable insight to regulators, academicians, researchers and legal practitioners regarding the present regulatory loopholes in Bangladesh involving exploiting the promise of big data in the medical field. The study concludes with the recommendation for future research into the area of privacy as it relates to artificial intelligence-based medical devices should consult the patients' perspective by employing quantitative analysis research methodology.

IBD Systems Biology Is Here to Stay

BACKGROUND

Systems biology is a rapidly advancing field of science that allows us to look into disease mechanisms, patient diagnosis and stratification, and drug development in a completely new light. It is based on the utilization of unbiased computational systems free of the traditional experimental approaches based on personal choices of what is important and what select experiments should be performed to obtain the expected results.

METHODS

Systems biology can be applied to inflammatory bowel disease (IBD) by learning basic concepts of omes and omics and how omics-derived "big data" can be integrated to discover the biological networks underlying highly complex diseases like IBD. Once these biological networks (interactomes) are identified, then the molecules controlling the disease network can be singled out and specific blockers developed.

RESULTS

The field of systems biology in IBD is just emerging, and there is still limited information on how to best utilize its power to advance our understanding of Crohn disease and ulcerative colitis to develop novel therapeutic strategies. Few centers have embraced systems biology in IBD, but the creation of international consortia and large biobanks will make biosamples available to basic and clinical IBD investigators for further research studies.

CONCLUSIONS

The implementation of systems biology is indispensable and unavoidable, and the patient and medical communities will both benefit immensely from what it will offer in the near future.

Risk Stratification Towards Precision Medicine in Heart Failure - Current Progress and Future Perspectives

Clinical risk stratification is a key strategy used to identify low- and high-risk subjects to optimize the management, ranging from pharmacological treatment to palliative care, of patients with heart failure (HF). Using statistical modeling techniques, many HF risk prediction models that combine predictors to assess the risk of specific endpoints, including death or worsening HF, have been developed. However, most risk prediction models have not been well-integrated into the clinical setting because of their inadequacy and diverse predictive performance. To improve the performance of such models, several factors, including optimal sampling and biomarkers, need to be considered when deriving the models; however, given the large heterogeneity of HF, the currently advocated one-size-fits-all approach is not appropriate for every patient. Recent advances in techniques to analyze biological "omics" information could allow for the development of a personalized medicine platform, and there is growing awareness that an integrated approach based on the concept of system biology may be an excessively naïve view of the multiple contributors and complexity of an individual's HF phenotype. This review article describes the progress in risk stratification strategies and perspectives of emerging precision medicine in the field of HF management.

Clinical epigenetics settings for cancer and cardiovascular diseases: real-life applications of network medicine at the bedside

Despite impressive efforts invested in epigenetic research in the last 50 years, clinical applications are still lacking. Only a few university hospital centers currently use epigenetic biomarkers at the bedside. Moreover, the overall concept of precision medicine is not widely recognized in routine medical practice and the reductionist approach remains predominant in treating patients affected by major diseases such as cancer and cardiovascular diseases. By its' very nature, epigenetics is integrative of genetic networks. The study of epigenetic biomarkers has led to the identification of numerous drugs with an increasingly significant role in clinical therapy especially of cancer patients. Here, we provide an overview of clinical epigenetics within the context of network analysis. We illustrate achievements to date and discuss how we can move from traditional medicine into the era of network medicine (NM), where pathway-informed molecular diagnostics will allow treatment selection following the paradigm of precision medicine.

Application of Big data scientific research analysis platform in clinical medical research

With the rapid development of evidence-based medicine, translational medicine, and pharmacoeconomics in China, as well as the country’s strong commitment to clinical research, the demand for physicians’ research continues to increase. In recent years, real-world studies are attracting more and more attention in the field of health care, as a method of post-marketing re-evaluation of drugs, RWS can better reflect the effects of drugs in real clinical settings. In the past, it was difficult to ensure data quality and efficiency of research implementation because of the large sample size required and the large amount of medical data involved. However, due to the large sample size required and the large amount of medical data involved, it is not only time-consuming and labor-intensive, but also prone to human error, making it difficult to ensure data quality and efficiency of research implementation. This paper analyzes and summarizes the existing application systems of big data analytics platforms, and concludes that big data research analytics platforms using natural language processing, machine learning and other artificial intelligence technologies can help RWS to quickly complete the collection, integration, processing, statistics and analysis of large amounts of medical data, and deeply mine the intrinsic value of the data, real-world research in new drug development, drug discovery, drug discovery, drug discovery, and drug discovery. It has a broad application prospect for multi-level and multi-angle needs such as economics, medical insurance cost control, indications/contraindications evaluation, and clinical guidance.

Cardiovascular Informatics: building a bridge to data harmony

The search for new strategies for better understanding cardiovascular disease is a constant one, spanning multitudinous types of observations and studies. A comprehensive characterization of each disease state and its biomolecular underpinnings relies upon insights gleaned from extensive information collection of various types of data. Researchers and clinicians in cardiovascular biomedicine repeatedly face questions regarding which types of data may best answer their questions, how to integrate information from multiple datasets of various types, and how to adapt emerging advances in machine learning and/or artificial intelligence to their needs in data processing. Frequently lauded as a field with great practical and translational potential, the interface between biomedical informatics and cardiovascular medicine is challenged with staggeringly massive datasets. Successful application of computational approaches to decode these complex and gigantic amounts of information becomes an essential step toward realizing the desired benefits. In this review, we examine recent efforts to adapt informatics strategies to cardiovascular biomedical research: automated information extraction and unification of multifaceted -omics data. We discuss how and why this interdisciplinary space of Cardiovascular Informatics is particularly relevant to and supportive of current experimental and clinical research. We describe in detail how open data sources and methods can drive discovery while demanding few initial resources, an advantage afforded by widespread availability of cloud computing-driven platforms. Subsequently, we provide examples of how interoperable computational systems facilitate exploration of data from multiple sources, including both consistently-formatted structured data and unstructured data. Taken together, these approaches for achieving data harmony enable molecular phenotyping of cardiovascular (CV) diseases and unification of cardiovascular knowledge.

Individualized interactomes for network-based precision medicine in hypertrophic cardiomyopathy with implications for other clinical pathophenotypes

Progress in precision medicine is limited by insufficient knowledge of transcriptomic or proteomic features in involved tissues that define pathobiological differences between patients. Here, myectomy tissue from patients with obstructive hypertrophic cardiomyopathy and heart failure is analyzed using RNA-Seq, and the results are used to develop individualized protein-protein interaction networks. From this approach, hypertrophic cardiomyopathy is distinguished from dilated cardiomyopathy based on the protein-protein interaction network pattern. Within the hypertrophic cardiomyopathy cohort, the patient-specific networks are variable in complexity, and enriched for 30 endophenotypes. The cardiac Janus kinase 2-Signal Transducer and Activator of Transcription 3-collagen 4A2 (JAK2-STAT3-COL4A2) expression profile informed by the networks was able to discriminate two hypertrophic cardiomyopathy patients with extreme fibrosis phenotypes. Patient-specific network features also associate with other important hypertrophic cardiomyopathy clinical phenotypes. These proof-of-concept findings introduce personalized protein-protein interaction networks (reticulotypes) for characterizing patient-specific pathobiology, thereby offering a direct strategy for advancing precision medicine.

Integrative Omics to Characterize and Classify Pulmonary Vascular Disease

Advances in high-throughput biotechnologies have facilitated omics profiling, a key component of precision phenotyping, in patients with pulmonary vascular disease. Omics provides comprehensive information pertaining to genes, transcripts, proteins, and metabolites. The resulting omics big datasets may be integrated for more robust results and are amenable to analysis using machine learning or newer analytical methodologies, such as network analysis. Results from fully integrated multi-omics datasets combined with clinical data are poised to provide novel insight into pulmonary vascular disease as well as diagnose the presence of disease and prognosticate outcomes.

Exploring the Interdisciplinary Nature of Precision Medicine：Network Analysis and Visualization

Background

Interdisciplinary research is an important feature of precision medicine. However, the accurate cross-disciplinary status of precision medicine is still unclear.

Objective

The aim of this study is to present the nature of interdisciplinary collaboration in precision medicine based on co-occurrences and social network analysis.

Methods

A total of 7544 studies about precision medicine, published between 2010 and 2019, were collected from the Web of Science database. We analyzed interdisciplinarity with descriptive statistics, co-occurrence analysis, and social network analysis. An evolutionary graph and strategic diagram were created to clarify the development of streams and trends in disciplinary communities.

Results

The results indicate that 105 disciplines are involved in precision medicine research and cover a wide range. However, the disciplinary distribution is unbalanced. Current cross-disciplinary collaboration in precision medicine mainly focuses on clinical application and technology-associated disciplines. The characteristics of the disciplinary collaboration network are as follows: (1) disciplinary cooperation in precision medicine is not mature or centralized; (2) the leading disciplines are absent; (3) the pattern of disciplinary cooperation is mostly indirect rather than direct. There are 7 interdisciplinary communities in the precision medicine collaboration network; however, their positions in the network differ. Community 4, with disciplines such as genetics and heredity in the core position, is the most central and cooperative discipline in the interdisciplinary network. This indicates that Community 4 represents a relatively mature direction in interdisciplinary cooperation in precision medicine. Finally, according to the evolution graph, we clearly present the development streams of disciplinary collaborations in precision medicine. We describe the scale and the time frame for development trends and distributions in detail. Importantly, we use evolution graphs to accurately estimate the developmental trend of precision medicine, such as biological big data processing, molecular imaging, and widespread clinical applications.

Conclusions

This study can help researchers, clinicians, and policymakers comprehensively understand the overall network of interdisciplinary cooperation in precision medicine. More importantly, we quantitatively and precisely present the history of interdisciplinary cooperation and accurately predict the developing trends of interdisciplinary cooperation in precision medicine.