A new approach to the clinical subclassification of heart failure with preserved ejection fraction

Clinical characteristics and prognostic impact of atrial fibrillation among older patients with heart failure with preserved ejection fraction hospitalized for acute heart failure

Heart failure with preserved ejection fraction (HFpEF) and atrial fibrillation (AF) are often coexisting conditions, but their interrelationship has not yet been clarified. This study investigated the clinical characteristics and prognostic impact of AF among older patients with HFpEF hospitalized for acute HF (AHF). The study included patients 65 years of age and older who were admitted to the Emergency Department due to AHF from 1 January 2016 to 31 December 2019. Patients were divided into two groups according to the presence of AF. The primary endpoint was all-cause, in-hospital mortality. Overall, 770 patients with HFpEF were included, mean age 82 years, 53% were females. Nearly, a third (30%) of these patients had a concomitant AF and they were significantly older and had higher N-Terminal pro-B-type natriuretic peptide (NT-proBNP) values. Overall, the in-hospital mortality rate was much higher among HFpEF patients with AF compared to those without AF (11.4% vs 6.9%, respectively; p = 0.037). At multivariate analysis, AF emerged as an independent risk factor for death (OR 1.73 [1.03-2.92]; p = 0.038). Among older patients with HFpEF admitted for AHF, the coexistence of AF was associated with a nearly twofold increased risk of all-cause in-hospital mortality. Patients with HFpEF and AF describe a phenotype of older and more symptomatic patients, with higher NT-proBNP, left atrial enlargement, right ventricular dysfunction, and higher CV mortality.

Eicosapentaenoic Acid (EPA) and Docosahexaenoic Acid (DHA) Ameliorate Heart Failure through Reductions in Oxidative Stress: A Systematic Review and Meta-Analysis

The objectives of this study were to explore the role that eicosapentaenoic acid (EPA) and/or docosahexaenoic acid (DHA) plays in heart failure (HF), highlighting the potential connection to oxidative stress pathways. Following PRISMA guidelines, we conducted electronic searches of the literature in MEDLINE and EMBASE focusing on serum EPA and/or DHA and EPA and/or DHA supplementation in adult patients with heart failure or who had heart failure as an outcome of this study. We screened 254 studies, encompassing RCTs, observational studies, and cohort studies that examined HF outcomes in relation to either serum concentrations or dietary supplementation of EPA and/or DHA. The exclusion criteria were pediatric patients, non-HF studies, abstracts, editorials, case reports, and reviews. Eleven studies met our criteria. In meta-analyses, high serum concentrations of DHA were associated with a lower rate of heart failure with a hazard ratio of 0.74 (CI = 0.59-0.94). High serum concentrations of EPA also were associated with an overall reduction in major adverse cardiovascular events with a hazard ratio of 0.60 (CI = 0.46-0.77). EPA and DHA, or n3-PUFA administration, were associated with an increased LVEF with a mean difference of 1.55 (CI = 0.07-3.03)%. A potential explanation for these findings is the ability of EPA and DHA to inhibit pathways by which oxidative stress damages the heart or impairs cardiac systolic or diastolic function producing heart failure. Specifically, EPA may lower oxidative stress within the heart by reducing the concentration of reactive oxygen species (ROS) within cardiac tissue by (i) upregulating nuclear factor erythroid 2-related factor 2 (Nrf2), which increases the expression of antioxidant enzyme activity, including heme oxygenase-1, thioredoxin reductase 1, ferritin light chain, ferritin heavy chain, and manganese superoxide dismutase (SOD), (ii) increasing the expression of copper-zinc superoxide dismutase (MnSOD) and glutathione peroxidase, (iii) targeting Free Fatty Acid Receptor 4 (Ffar4), (iv) upregulating expression of heme-oxygenase-1, (v) lowering arachidonic acid levels, and (vi) inhibiting the RhoA/ROCK signaling pathway. DHA may lower oxidative stress within the heart by (i) reducing levels of mitochondrial-fission-related protein DRP-1(ser-63), (ii) promoting the incorporation of cardiolipin within the mitochondrial membrane, (iii) reducing myocardial fibrosis, which leads to diastolic heart failure, (iv) reducing the expression of genes such as Appa, Myh7, and Agtr1α, and (v) reducing inflammatory cytokines such as IL-6, TNF-α. In conclusion, EPA and/or DHA have the potential to improve heart failure, perhaps mediated by their ability to modulate oxidative stress.

Clustering of Cardiovascular Risk Factors and Heart Failure in Older Adults from the Brazilian Far North

Given the aging global population, identifying heart failure (HF) phenotypes has become crucial, as distinct disease characteristics can influence treatment and prognosis in older adults. This study aimed to analyze the association between clustering of cardiovascular risk factors and HF in older adults. A cross-sectional epidemiological study was conducted with 1322 older adults (55% women, mean age 70.4) seen in primary health care. Diagnosis of HF was performed by a cardiologist based on diagnostic tests and medical history. Cardiovascular risk factors included hypertension, diabetes, hypercholesterolemia, and smoking. Using logistic regression, potential associations were tested. Individual risk factor analysis showed that older adults with hypertension, diabetes, or hypercholesterolemia had up to 7.6 times higher odds to have HF. The cluster where older adults had only one risk factor instead of none increased the odds of HF by 53.0%. Additionally, the odds of older patients having HF ranged from 3.59 times for the two-risk factor cluster to 20.61 times for the simultaneous presence of all four factors. The analysis of clusters substantially increasing HF risk in older adults revealed the importance of individualizing subgroups with distinct HF pathophysiologies. The clinical significance of these clusters can be beneficial in guiding a more personalized therapeutic approach.

Myeloperoxidase, carnitine, and derivatives of reactive oxidative metabolites in heart failure with preserved versus reduced ejection fraction: A meta-analysis

BACKGROUND

Understanding the pathophysiology of heart failure (HF) with preserved ejection fraction (HFpEF) continues to be challenging. Several inflammatory and metabolic biomarkers have recently been suggested to be involved in HFpEF.

OBJECTIVES

The purpose of this review was to synthesize the evidence on non-traditional biomarkers from metabolomic studies that may distinguish HFpEF from heart failure with reduced ejection fraction (HFrEF) and controls without HF.

METHODS

A systematic search was conducted using Medline and PubMed with search terms such as "HFpEF" and "metabolomics", and a meta-analysis was conducted.

RESULTS

Myeloperoxidase (MPO) levels were significantly (p < 0.001) higher in HFpEF than controls without HF, but comparable (p = 0.838) between HFpEF and HFrEF. Carnitine levels were significantly (p < 0.0001) higher in HFrEF than HFpEF, but comparable (p = 0.443) between HFpEF and controls without HF. Derivatives of reactive oxidative metabolites (DROMs) were not significantly (p = 0.575) higher in HFpEF than controls without HF.

CONCLUSION

These data suggest that MPO is operative in HFpEF and HFrEF and may be a biomarker for HF. Furthermore, circulating carnitine levels may distinguish HFrEF from HFpEF.

Discovering Distinct Phenotypical Clusters in Heart Failure Across the Ejection Fraction Spectrum: a Systematic Review

REVIEW PURPOSE

This systematic review aims to summarise clustering studies in heart failure (HF) and guide future clinical trial design and implementation in routine clinical practice.

FINDINGS

34 studies were identified (n = 19 in HF with preserved ejection fraction (HFpEF)). There was significant heterogeneity invariables and techniques used. However, 149/165 described clusters could be assigned to one of nine phenotypes: 1) young, low comorbidity burden; 2) metabolic; 3) cardio-renal; 4) atrial fibrillation (AF); 5) elderly female AF; 6) hypertensive-comorbidity; 7) ischaemic-male; 8) valvular disease; and 9) devices. There was room for improvement on important methodological topics for all clustering studies such as external validation and transparency of the modelling process. The large overlap between the phenotypes of the clustering studies shows that clustering is a robust approach for discovering clinically distinct phenotypes. However, future studies should invest in a phenotype model that can be implemented in routine clinical practice and future clinical trial design. HF = heart failure, EF = ejection fraction, HFpEF = heart failure with preserved ejection fraction, HFrEF = heart failure with reduced ejection fraction, CKD = chronic kidney disease, AF = atrial fibrillation, IHD = ischaemic heart disease, CAD = coronary artery disease, ICD = implantable cardioverter-defibrillator, CRT = cardiac resynchronization therapy, NT-proBNP = N-terminal pro b-type natriuretic peptide, BMI = Body Mass Index, COPD = Chronic obstructive pulmonary disease.

Identifying Premature Ventricular Complexes from Outflow Tracts Based on PVC Configuration: A Machine Learning Approach

BACKGROUND

Current inferences about the site of origin (SOO) of premature ventricular complexes (PVC) from the surface ECG have not been subjected to newer data analytic techniques that identify signals that are not recognized by visual inspection.

AIMS

The objective of this study was to apply data analytics to PVC characteristics.

METHODS

PVCs from 12-lead ECGs of a consecutive series of 338 individuals were examined by unsupervised machine learning cluster analysis, and indexes were compared to a composite criterion for SOO.

RESULTS

Data analytics found that V1S plus V2S ≤ 9.25 of the PVC had a LVOT origin (sensitivity 95.4%; specificity 97.5%). V1R + V2R + V3R > 15.0 (a RBBB configuration) likely had a LVOT origin. PVCs with V1S plus V2S > 12.75 (LBBB configuration) likely had a RVOT origin. PVC with V1S plus V2S > 14.25 (LBBB configuration) and all inferior leads positive likely had a RVOT origin.

CONCLUSION

Newer data analytic techniques provide a non-invasive approach to identifying PVC SOO, which should be useful for the clinician evaluating a 12-lead ECG.

WATCH-DM risk score predicts the prognosis of diabetic phenotype patients with heart failure and preserved ejection fraction

BACKGROUND

Heart failure with preserved ejection fraction (HFpEF) is a heterogeneous syndrome. Diabetes may identify an essential phenotype that significantly affects the prognosis of these patients. The WATCH-DM risk score has been validated for predicting the risk of heart failure in outpatients with type 2 diabetes mellitus (T2DM), but its ability to predict clinical outcomes in HFpEF patients with T2DM is unknown. We aimed to assess whether this risk score could predict the prognosis of diabetic phenotype patients with heart failure and preserved ejection fraction.

METHODS

We enrolled retrospectively 414 patients with HFpEF (70.03 ± 8.654 years, 58.70% female), including 203 (49.03%) type 2 diabetics. Diabetic HFpEF patients were stratified by baseline WATCH-DM risk score.

RESULTS

Diabetic HFpEF patients exhibited a trend toward more concentric remodeling/hypertrophy than nondiabetic HFpEF patients. When analyzed as a continuous variable, per 1-point increase in the WATCH-DM risk score was associated with increased risks of all-cause death (HR 1.181), cardiovascular death (HR 1.239), any hospitalization (HR 1.082), and HF hospitalization (HR 1.097). The AUC for the WATCH-DM risk score in predicting incident cardiovascular death (0.7061, 95% CI 0.6329-0.7792) was higher than that of all-cause death, any hospitalization, or HF hospitalization.

CONCLUSIONS

As a high-risk phenotype for heart failure, diabetic HFpEF necessitates early risk stratification and specific treatment. To the best of our knowledge, the current study is the first to demonstrate that the WATCH-DM score predicts poor outcomes in diabetic HFpEF patients. Its convenience may allow for quick risk assessments in busy clinical settings.

Phenomapping in heart failure with preserved ejection fraction: insights, limitations, and future directions

Heart failure with preserved ejection fraction (HFpEF) is a heterogeneous entity with complex pathophysiology and manifestations. Phenomapping is the process of applying statistical learning techniques to patient data to identify distinct subgroups based on patterns in the data. Phenomapping has emerged as a technique with potential to improve the understanding of different HFpEF phenotypes. Phenomapping efforts have been increasing in HFpEF over the past several years using a variety of data sources, clinical variables, and statistical techniques. This review summarizes methodologies and key takeaways from these studies, including consistent discriminating factors and conserved HFpEF phenotypes. We argue that phenomapping results to date have had limited implications for clinical care and clinical trials, given that the phenotypes, as currently described, are not reliably identified in each study population and may have significant overlap. We review the inherent limitations of aggregating and utilizing phenomapping results. Lastly, we discuss potential future directions, including using phenomapping to optimize the likelihood of clinical trial success or to drive discovery in mechanisms of the disease process of HFpEF.

C-Reactive Protein, Interleukin-6, Trimethylamine-N-Oxide, Syndecan-1, Nitric Oxide, and Tumor Necrosis Factor Receptor-1 in Heart Failure with Preserved Versus Reduced Ejection Fraction: a Meta-Analysis

PURPOSE OF REVIEW

The purpose of this review was to synthesize the evidence on non-traditional biomarkers from proteomic and metabolomic studies that may distinguish heart failure (HF) with preserved ejection fraction (HFpEF) from heart failure with reduced ejection fraction (HFrEF) and non-HF.

RECENT FINDINGS

Understanding the pathophysiology of HFpEF continues to be challenging. A number of inflammatory and metabolic biomarkers that have recently been suggested to be involved include C-reactive protein (CRP), interleukin-6 (IL-6), trimethylamine-N-oxide (TMAO), syndecan-1 (SDC-1), nitric oxide (NO), and tumor necrosis factor receptor-1 (TNFR-1). A systematic search was conducted using Medline, EMBASE, and Web of Science with search terms such as "HFpEF," "metabolomics," and "proteomics," and a meta-analysis was conducted. The results demonstrate significantly higher levels of TMAO, CRP, SDC-1, and IL-6 in HFpEF compared to controls without HF and significantly higher levels of TMAO and CRP in HFrEF compared to controls. The results further suggest that HFpEF might be distinguishable from HFrEF based on higher levels of IL-6 and lower levels of SDC-1 and NO. These data may reflect pathophysiological differences between HFpEF and HFrEF.

Chronotropic index and long-term outcomes in heart failure with preserved ejection fraction

INTRODUCTION AND OBJECTIVES

Little is known about the usefulness of heart rate (HR) response to exercise for risk stratification in heart failure with preserved ejection fraction (HFpEF). Therefore, this study aimed to assess the association between HR response to exercise and the risk of total episodes of worsening heart failure (WHF) in symptomatic stable patients with HFpEF.

METHODS

This single-center study included 133 patients with HFpEF (NYHA II-III) who performed maximal cardiopulmonary exercise testing. HR response to exercise was evaluated using the chronotropic index (CI_x) formula. A negative binomial regression method was used.

RESULTS

The mean age of the sample was 73.2± 10.5 years; 56.4% were female, and 51.1% were in atrial fibrillation. The median for CI_x was 0.4 [0.3-0.55]. At a median follow-up of 2.4 [1.6-5.3] years, a total of 146 WHF events in 58 patients and 41 (30.8%) deaths were registered. In the whole sample, CI_x was not associated with adverse outcomes (death, P=.319, and WHF events, P=.573). However, we found a differential effect across electrocardiographic rhythms for WHF events (P for interaction=.002). CI_x was inversely and linearly associated with the risk of WHF events in patients with sinus rhythm and was positively and linearly associated with those with atrial fibrillation.

CONCLUSIONS

In patients with HFpEF, CI_x was differentially associated with the risk of total WHF events across rhythm status. Lower CI_x emerged as a risk factor for predicting higher risk in patients with sinus rhythm. In contrast, higher CI_x identified a higher risk in those with atrial fibrillation.

Identifying novel subgroups in heart failure patients with unsupervised machine learning: A scoping review

Background

Heart failure is currently divided into three main forms, HFrEF, HFpEF, and HFmrEF, but its etiology is diverse and highly heterogeneous. Many studies reported a variety of novel subgroups in heart failure patients, with unsupervised machine learning methods. The aim of this scoping review is to provide insights into how these techniques can diagnose and manage HF faster and better, thus providing direction for future research and facilitating its routine use in clinical practice.

Methods

The review was performed following PRISMA-SCR guideline. We searched the PubMed database for eligible publications. Studies were included if they defined new subgroups in HF patients using clustering analysis methods, and excluded if they are (1) Reviews, commentary, or editorials, (2) Studies not about defining new sub-types, or (3) Studies not using unsupervised algorithms. All study screening and data extraction were conducted independently by two investigators and narrative integration of data extracted from included studies was performed.

Results

Of the 498 studies identified, 47 were included in the analysis. Most studies (61.7%) were published in 2020 and later. The largest number of studies (46.8%) coming from the United States, and most of the studies were authored and included in the same country. The most commonly used machine learning method was hierarchical cluster analysis (46.8%), the most commonly used cluster variable type was comorbidity (61.7%), and the least used cluster variable type was genomics (12.8%). Most of the studies used data sets of less than 500 patients (48.9%), and the sample size had negative correlation with the number of clustering variables. The majority of studies (85.1%) assessed the association between cluster grouping and at least one outcomes, with death and hospitalization being the most commonly used outcome measures.

Conclusion

This scoping review provides an overview of recent studies proposing novel HF subgroups based on clustering analysis. Differences were found in study design, study population, clustering methods and variables, and outcomes of interests, and we provided insights into how these studies were conducted and identify the knowledge gaps to guide future research.

Mimicking Metabolic Disturbance in Establishing Animal Models of Heart Failure With Preserved Ejection Fraction

Heart failure (HF), the terminal state of different heart diseases, imposed a significant health care burden worldwide. It is the last battlefield in dealing with cardiovascular diseases. HF with preserved ejection fraction (HFpEF) is a type of HF in which the symptoms and signs of HF are mainly ascribed to diastolic dysfunction of left ventricle, whereas systolic function is normal or near-normal. Compared to HF with reduced ejection fraction (HFrEF), the diagnosis and treatment of HFpEF have made limited progress, partly due to the lack of suitable animal models for translational studies in the past. Given metabolic disturbance and inflammatory burden contribute to HFpEF pathogenesis, recent years have witnessed emerging studies focusing on construction of animal models with HFpEF phenotype by mimicking metabolic disorders. These models prefer to recapitulate the metabolic disorders and endothelial dysfunction, leading to the more detailed understanding of the entity. In this review, we summarize the currently available animal models of HFpEF with metabolic disorders, as well as their advantages and disadvantages as tools for translational studies.

Comparison of Unsupervised Machine Learning Approaches for Cluster Analysis to Define Subgroups of Heart Failure with Preserved Ejection Fraction with Different Outcomes

Heart failure with preserved ejection (HFpEF) is a heterogenous condition affecting nearly half of all patients with heart failure (HF). Artificial intelligence methodologies can be useful to identify patient subclassifications with important clinical implications. We sought a comparison of different machine learning (ML) techniques and clustering capabilities in defining meaningful subsets of patients with HFpEF. Three unsupervised clustering strategies, hierarchical clustering, K-prototype, and partitioning around medoids (PAM), were used to identify distinct clusters in patients with HFpEF, based on a wide range of demographic, laboratory, and clinical parameters. The study population had a median age of 77 years, with a female majority, and moderate diastolic dysfunction. Hierarchical clustering produced six groups but two were too small (two and seven cases) to be clinically meaningful. The K-prototype methods produced clusters in which several clinical and biochemical features did not show statistically significant differences and there was significant overlap between the clusters. The PAM methodology provided the best group separations and identified six mutually exclusive groups (HFpEF1-6) with statistically significant differences in patient characteristics and outcomes. Comparison of three different unsupervised ML clustering strategies, hierarchical clustering, K-prototype, and partitioning around medoids (PAM), was performed on a mixed dataset of patients with HFpEF containing clinical and numerical data. The PAM method identified six distinct subsets of patients with HFpEF with different long-term outcomes or mortality. By comparison, the two other clustering algorithms, the hierarchical clustering and K-prototype, were less optimal.

What can machines learn about heart failure? A systematic literature review

This paper presents a systematic literature review with respect to application of data science and machine learning (ML) to heart failure (HF) datasets with the intention of generating both a synthesis of relevant findings and a critical evaluation of approaches, applicability and accuracy in order to inform future work within this field. This paper has a particular intention to consider ways in which the low uptake of ML techniques within clinical practice could be resolved. Literature searches were performed on Scopus (2014-2021), ProQuest and Ovid MEDLINE databases (2014-2021). Search terms included ‘heart failure’ or ‘cardiomyopathy’ and ‘machine learning’, ‘data analytics’, ‘data mining’ or ‘data science’. 81 out of 1688 articles were included in the review. The majority of studies were retrospective cohort studies. The median size of the patient cohort across all studies was 1944 (min 46, max 93260). The largest patient samples were used in readmission prediction models with the median sample size of 5676 (min. 380, max. 93260). Machine learning methods focused on common HF problems: detection of HF from available dataset, prediction of hospital readmission following index hospitalization, mortality prediction, classification and clustering of HF cohorts into subgroups with distinctive features and response to HF treatment. The most common ML methods used were logistic regression, decision trees, random forest and support vector machines. Information on validation of models was scarce. Based on the authors’ affiliations, there was a median 3:1 ratio between IT specialists and clinicians. Over half of studies were co-authored by a collaboration of medical and IT specialists. Approximately 25% of papers were authored solely by IT specialists who did not seek clinical input in data interpretation. The application of ML to datasets, in particular clustering methods, enabled the development of classification models assisting in testing the outcomes of patients with HF. There is, however, a tendency to over-claim the potential usefulness of ML models for clinical practice. The next body of work that is required for this research discipline is the design of randomised controlled trials (RCTs) with the use of ML in an intervention arm in order to prospectively validate these algorithms for real-world clinical utility.

Effect of diabetes mellitus on the development of left ventricular contractile dysfunction in women with heart failure and preserved ejection fraction

Background

Heart failure with preserved ejection fraction (HFpEF) is a heterogeneous syndrome with sex-specific pathophysiology. Estrogen deficiency is believed to be responsible for the development of HFpEF in women. However, estrogen deficiency does not seem to be completely responsible for the differences in HFpEF prevalence between sexes. While diabetes mellitus (DM) frequently coexists with HFpEF in women and is associated with worse outcomes, the changes in myocardial contractility among women with HFpEF and the DM phenotype is yet unknown. Therefore, we aimed to investigate sex-related differences in left ventricular (LV) contractility dysfunction in HFpEF comorbid with DM.

Methods

A total of 224 patients who underwent cardiac cine MRI were included in this study. Sex-specific differences in LV structure and function in the context of DM were determined. LV systolic strains (global longitudinal strain [GLS], circumferential strain [GCS] and radial strain [GRS]) were measured using cine MRI. The determinants of impaired myocardial strain for women and men were assessed.

Results

The prevalence of DM did not differ between sexes (p > 0.05). Despite a similar LV ejection fraction, women with DM demonstrated a greater LV mass index than women without DM (p = 0.023). The prevalence of LV geometry patterns by sex did not differ in the non-DM subgroup, but there was a trend toward a more abnormal LV geometry in women with DM (p = 0.072). The magnitudes of systolic strains were similar between sexes in the non-DM group (p > 0.05). Nevertheless, in the DM subgroup, there was significant impairment in women in systolic strains compared with men (p < 0.05). In the multivariable analysis, DM was associated with impaired systolic strains in women (GLS [β = 0.26; p = 0.007], GCS [β = 0.31; p < 0.001], and GRS [β = −0.24; p = 0.016]), whereas obesity and coronary artery disease were associated with impaired systolic strains in men (p < 0.05).

Conclusions

Women with DM demonstrated greater LV contractile dysfunction, which indicates that women with HFpEF comorbid with DM have a high-risk phenotype of cardiac failure that may require more aggressive and personalized medical treatment.

Endotyping in Heart Failure - Identifying Mechanistically Meaningful Subtypes of Disease

Endotyping is an emerging concept in which diseases are classified into distinct subtypes based on underlying molecular mechanisms. Heart failure (HF) is a complex clinical syndrome that encompasses multiple endotypes with differential risks of adverse events, and varying responses to treatment. Identifying these distinct endotypes requires molecular-level investigation involving multi-"omics" approaches, including genomics, transcriptomics, proteomics, and metabolomics. The derivation of these HF endotypes has important implications in promoting individualized treatment and facilitating more targeted selection of patients for clinical trials, as well as in potentially revealing new pathways of disease that may serve as therapeutic targets. One challenge in the integrated analysis of high-throughput omics and detailed clinical data is that it requires the ability to handle "big data", a task for which machine learning is well suited. In particular, unsupervised machine learning has the ability to uncover novel endotypes of disease in an unbiased approach. In this review, we will discuss recent efforts to identify HF endotypes and cover approaches involving proteomics, transcriptomics, and genomics, with a focus on machine-learning methods.

Machine Learning Augmented Echocardiography for Diastolic Function Assessment

Cardiac diastolic dysfunction is prevalent and is a diagnostic criterion for heart failure with preserved ejection fraction—a burgeoning global health issue. As gold-standard invasive haemodynamic assessment of diastolic function is not routinely performed, clinical guidelines advise using echocardiography measures to determine the grade of diastolic function. However, the current process has suboptimal accuracy, regular indeterminate classifications and is susceptible to confounding from comorbidities. Advances in artificial intelligence in recent years have created revolutionary ways to evaluate and integrate large quantities of cardiology data. Imaging is an area of particular strength for the sub-field of machine-learning, with evidence that trained algorithms can accurately discern cardiac structures, reliably estimate chamber volumes, and output systolic function metrics from echocardiographic images. In this review, we present the emerging field of machine-learning based echocardiographic diastolic function assessment. We summarise how machine-learning has made use of diastolic parameters to accurately differentiate pathology, to identify novel phenotypes within diastolic disease, and to grade diastolic function. Perspectives are given about how these innovations could be used to augment clinical practice, whilst areas for future investigation are identified.